Survival prediction landscape: an in-depth systematic literature review on activities, methods, tools, diseases, and databases

Survival prediction integrates patient-specific molecular information and clinical signatures to forecast the anticipated time of an event, such as recurrence, death, or disease progression. Survival prediction proves valuable in guiding treatment decisions, optimizing resource allocation, and interventions of precision medicine. The wide range of diseases, the existence of various variants within the same disease, and the reliance on available data necessitate disease-specific computational survival predictors. The widespread adoption of artificial intelligence (AI) methods in crafting survival predictors has undoubtedly revolutionized this field. However, the ever-increasing demand for more sophisticated and effective prediction models necessitates the continued creation of innovative advancements. To catalyze these advancements, it is crucial to bring existing survival predictors knowledge and insights into a centralized platform. The paper in hand thoroughly examines 23 existing review studies and provides a concise overview of their scope and limitations. Focusing on a comprehensive set of 90 most recent survival predictors across 44 diverse diseases, it delves into insights of diverse types of methods that are used in the development of disease-specific predictors. This exhaustive analysis encompasses the utilized data modalities along with a detailed analysis of subsets of clinical features, feature engineering methods, and the specific statistical, machine or deep learning approaches that have been employed. It also provides insights about survival prediction data sources, open-source predictors, and survival prediction frameworks.

1 Introduction

According to World Health Organization (WHO), around ten thousand diseases have been discovered and each disease has unique characteristics, symptoms, and implications on human health (Haendel et al., 2020). Millions of people died from such diseases in the span of years 2000 to 2019, while cancers, cardiovascular, and infectious diseases persisted as the leading causes of mortality (Jamison, 2018; World Health Organization, 2020). Extensive research on the intersection of life and technology has yielded a wide range of therapies and medications for various well-known diseases [National Research Council (US), 2010]. However, the core idea behind traditional therapies and medications is based on the “one-size-fits-all” (Sellin, 2015). In this paradigm, a single drug is supposed to effectively treat a medical condition across a variety of patient cohorts i.e., children, old and young populations (Al-Lazikani et al., 2012; Sellin, 2015). In-depth exploration and understanding of living organisms' inherent biological processes reveal that high variability in genetics and drug responses make one-size-fits-all medication ineffective (Al-Lazikani et al., 2012; Sellin, 2015).

The groundbreaking discoveries of the factors contributing to the limited effectiveness of generalized medications marked the inception of the era of precision medicine (Ashley, 2016; Kosorok and Laber, 2019). Precision medicine offers customization in tailored medical treatments based on an individual's unique genetic makeup, and optimization in drug selection and dosage based on the individual's lifestyle, and environmental factors (Farrokhi et al., 2023). Precision medicine's adoption and effectiveness have been significantly enhanced by the accurate, cost-effective, and large-scale analysis of molecular information obtained through next-generation sequencing (Kamps et al., 2017).

In the realm of precision medicine, survival prediction plays a pivotal role in tailoring medical treatments to individual needs (Billheimer et al., 2014; Tsimberidou et al., 2019). Survival prediction categorizes patients into distinct risk groups that enhance the efficiency of resource allocation for the patients who are likely to gain the most benefit from specific treatments (Billheimer et al., 2014; Tsimberidou et al., 2019). It also enables counseling of patients and their families by predicting the expected course of the disease and potential challenges (Billheimer et al., 2014). In addition to medical treatments, survival prediction offers multiple advantages in research, particularly in the area of biomarker discovery and disease understanding (Chen et al., 2018; Sarma et al., 2020). Survival prediction models provide useful information about the correlation between different features and clinical outcomes. This correlation information enables the identification of novel biomarkers associated with disease prognosis (Sarma et al., 2020). Moreover, researchers leverage survival prediction to unravel disease heterogeneity which helps to identify distinct subtypes with different survival profiles (Hao et al., 2023). This knowledge not only aids in the stratification of homogeneous patients in clinical trials but also validates therapeutic targets by assessing their relevance in predicting patient outcomes (Glare et al., 2003). Furthermore, it enables the longitudinal monitoring of disease progression that helps to explore critical time points and progression patterns (Carobbio et al., 2020).

To expedite advancements in survival prediction research, researchers are harnessing the capabilities of AI algorithms by utilizing extensive survival-related data from public databases such as the Cancer Genome Atlas Program (TCGA) (Tomczak et al., 2015), and NCI Genomic Data Commons (GDC) (Jensen et al., 2017; Shen et al., 2019; Malik et al., 2021; Mirbabaie et al., 2021; Arjmand et al., 2022; Fan et al., 2023; Pellegrini, 2023). In addition, the diversity and heterogeneity of diseases hinder the development of a universally applicable survival prediction pipeline (Kourou et al., 2015; Hao et al., 2023).

Driven by the necessity for disease-specific predictors, there is a concerted effort to develop more accurate and powerful predictive tools (Baek and Lee, 2020; Jiang et al., 2020; Benkirane et al., 2023). Figure 1 illustrates that for the advancement of survival predictors, public databases provide a spectrum of clinical data (Jung et al., 2023; Qian et al., 2023) and encompass nine diverse omics data modalities, including gene expression (mRNA), micro RNA (miRNA), DNA methylation, copy number variation (CNV), long non-coding RNA (lncRNA), proteomics, metabolic, whole exome sequencing (WES) and mutation (Baek and Lee, 2020; Malik et al., 2021; Han et al., 2022; Jiang et al., 2022). In each data modality, there exists an array of missing values that hinder survival predictors learning. Extensive research is being conducted to impute missing values by using different techniques such as deletion, multiple, K-nearest neighbor (KNN), and median imputation (Van Buuren et al., 1999; Garćıa-Laencina et al., 2015; Chai et al., 2021b). In addition, various normalization methods are also being used to normalize feature space such as quantile (Zhao et al., 2020), variance threshold (Bolstad et al., 2003), and rank normalizations (Ni and Qin, 2021).

Figure 1

Figure 1. An end-to-end survival prediction pipeline.

In the development of survival prediction pipelines, researchers are trying to unlock the potential of various data modalities by assessing predictor performance with individual modalities and combinations of multiple data modalities across diverse types of diseases (Lee et al., 2020; Hao et al., 2023; Pellegrini, 2023). When data from different modalities is combined, survival predictors' input feature space becomes very large which impedes the performance of AI approaches (Feldner-Busztin et al., 2023). Researchers are trying to explore feature engineering approaches such as random forest importance (RFI), and recursive feature elimination (RFI) (Wang et al., 2022), principal component analysis (PCA) (Lv et al., 2020; Jiang et al., 2022), non-negative matrix factorization (NMF) (Tang et al., 2021), and autoencoders (AEs) (Li et al., 2020; Wang et al., 2020; Owens et al., 2021). Moreover, in an end-to-end survival predictive pipeline, apart from the selection of appropriate data and feature engineering strategy, designing appropriate survival prediction models is also an active area of research (Deepa and Gunavathi, 2022).

Under different aforementioned directions, the recent 3 years have witnessed around 74 different survival predictors for different diseases. To further accelerate and expedite the development of more powerful predictors, in the last 10 years, from time to time, researchers have published 22 different review articles. These articles primarily aim to summarize the latest trends and developments in data modalities, feature engineering methods, and AI models specifically related to survival prediction. However, the focus of these reviews is often constrained to either a singular disease or multiple subtypes of cancer, highlighting a limited scope within the broader landscape of survival prediction research (Herrmann et al., 2021; Pobar et al., 2021; Boshier et al., 2022; Deepa and Gunavathi, 2022; Feldner-Busztin et al., 2023; Rahimi et al., 2023). More comprehensive details about the scope of existing review articles in terms of contributions and drawbacks are summarized in Table 2 and Section 3. Following the need for a comprehensive review article for survival prediction, the contributions of this paper are manifold:

• It consolidates a diverse array of 22 survival prediction review papers, bringing together their scopes and limitations under a unified umbrella. This compilation serves as a valuable resource for researchers seeking high-level insights and pertinent information in the field.

• It provides comprehensive insights into 74 survival prediction articles published between 2020 and 2023.

The objective is to delve into diverse aspects of the field, extract and furnish useful information from these articles under the following different research questions (RQs) and objectives: (i) What is the distribution of 74 research articles across 44 different diseases, and how does it vary among cancer subtypes and other diseases? (ii) How do studies address the spectrum of survival prediction, from a broader perspective covering multiple cancer subtypes to individual subtypes? (iii) What are the predominant survival endpoints used in studies, and how are studies distributed across four endpoints overall survival (OS), disease-free survival (DFS), progression-free survival (PFS), and biochemical recurrence (BC)? (iv) What are the most commonly used public and private data sources in existing survival prediction studies and the types of data they encompass? (v) What are the most commonly used omics data modalities and their associations with different diseases and survival endpoints? (vi) Which clinical features are most commonly employed in survival prediction studies? (vii) How have feature engineering techniques evolved across different data modalities, diseases, and survival endpoints in survival prediction studies? (viii) Which specific statistical, machine learning (ML), and deep learning (DL) survival prediction algorithms have been applied to diverse diseases and survival endpoints? (ix) Which survival prediction studies have made their source codes publicly available, and what types of methods are available in open-source survival prediction frameworks? (x) What are the most commonly utilized survival prediction evaluation measures? (xi) Which conferences and journals predominantly publish survival prediction studies?

2 Background

Survival prediction makes use of patient-specific molecular information and clinical signatures to forecast a wide range of events at particular time intervals (Pellegrini, 2023). The most common events include recurrence, metastasis, response, hospitalization, recovery, and progression of a disease. Some of these events represent similar contexts, i.e., metastasis and progression, both contribute to the overall progression of the condition/cancer (Murthy et al., 2004). Survival prediction events are generally categorized into 4 different survival endpoints namely, overall survival (OS) (Driscoll and Rixe, 2009), disease-free survival (DFS) (Sargent et al., 2005), progression-free survival (PFS) (Gyawali et al., 2022), and biochemical recurrence (BC) (Boorjian et al., 2011). Survival endpoints serve as crucial measures for assessing the outcomes of interventions, indicating the duration until specific events occur. Therefore, events are essentially the occurrences that contribute to the survival endpoints (Fiteni et al., 2014). These endpoints are critical to examine the trajectory of a particular disease (Fiteni et al., 2014; Gyawali et al., 2022). These survival endpoints are clearly defined in Table 1.

Table 1

Table 1. Common clinical/survival endpoints in cancer studies.

Survival prediction is time to event approach with two distinct aspects, i.e., survival and hazard function (Kleinbaum and Klein, 1996). Survival function describes the probability that a subject survives longer than some specified time t. Mathematically, it is expressed as:

$\begin{array}{l}S(t)=P(T>t),\end{array}$

where T is the random variable for survival time, t is a specific value of interest for T. For instance, S(10) represents the probability of survival beyond 10 years without experiencing a specific event. As time passes, S(t) decreases, reflecting the reduction in the probability of surviving without the occurrence of event E up to time t.

In comparison, the hazard function illustrates the probability of an event E occurring at a specific time interval (Δt) with a prior assumption that the event has not taken place. The probability that the event E occurs within a very small time interval Δt around time t is given by the conditional probability:

$\begin{array}{l}P(t\le T<t+\Delta t\mid T\ge t)\end{array}$

Dividing this probability by the length of the time interval (Δt) gives the rate of occurrence of the event at time t. The limit as the time interval (Δt) approaches zero gives the instantaneous rate of occurrence at time t. Mathematically, this is represented as:

$\begin{array}{l}h(t)=\underset{(\Delta t\to 0)}{\lim }\frac{Pr(t\le T<t+\Delta t\mid T\ge t)}{\Delta t}\\ =\frac{f(t)}{S(t)}\end{array}$

$\begin{array}{r}\hfill Pr(t\le T<t+\Delta t\mid T\ge t)=\\ \hfill P(\text{individual fails in interval}\mid [t,t+\Delta t]\\ \hfill \text{survivaluptotimet})\end{array}$

where f(t) represents the probability density function of survival time. Thus, survival function S(t) shows that the subject survives beyond a specific time point and hazard function h(t) complements this by providing a risk rate that a patient does not survive in a specific time interval conditioned on having survived thus far. Moreover, S(t) is always monotonic in nature, however h(t) is classically assumed to follow increasing Weibull, decreasing Weibull, or lognormal survival curves (Kleinbaum and Klein, 1996; Murthy et al., 2004).

3 A look-back into existing review studies

In recent years multiple review papers have been published and the objective of each review revolves around summarizing fundamental concepts in survival prediction and identifying trends in statistical, ML, and DL algorithms that have been utilized in the development of survival predictors. Table 2 illustrates a high-level overview of the existing 22 review articles in terms of their review scope and limitations. This comprehensive summary aims to assist researchers in locating specific information within relevant articles more effectively.

Table 2

Table 2. The scope and limitations of current survey papers.

In Table 2, a comprehensive analysis of the scope of review articles indicates that existing studies can be classified into three distinct groups. (I) Nine review papers primarily focus on the application of DL algorithms in survival prediction (Ahmed, 2005; Bakasa and Viriri, 2021; Kvamme and Borgan, 2021; Pobar et al., 2021; Kantidakis et al., 2022; Altuhaifa et al., 2023; Salerno and Li, 2023; Wekesa and Kimwele, 2023; Wiegrebe et al., 2023), (II) seven review papers summarize the application of ML algorithms in survival prediction (Gupta et al., 2018; Lee and Lim, 2019; Boshier et al., 2022; Guan et al., 2022; Mo et al., 2022; Wissel et al., 2022; Feldner-Busztin et al., 2023), andsix review papers summarize survival prediction methods from three different categories namely statistical, ML, and DL methods (Bashiri et al., 2017; Herrmann et al., 2021; Tewarie et al., 2021; Westerlund et al., 2021; Deepa and Gunavathi, 2022; Rahimi et al., 2023).

On the other hand, in the realm of disease specific survival predictors scope of existing review papers is limited. For instance, eight papers only summarize survival predictors on single disease or subtype of cancer, i.e., cervical cancer (Rahimi et al., 2023), glioblastoma (Tewarie et al., 2021), esophageal adenocarcinoma (Boshier et al., 2022), esophageal and gastroesophageal junction cancer (Gupta et al., 2018), head and squamous cell carcinoma (Mo et al., 2022), palliative cancer patients (Pobar et al., 2021), cardiovascular diseases (CVD) (Westerlund et al., 2021; Kresoja et al., 2023), and schizophrenia (Guan et al., 2022). Although four papers cover multiple subtypes of cancer but they cover only handful of eight different subtypes such as, breast, lung, gastric, colon, esophageal, ovarian cancers and so on.

While the scope of survival prediction extends beyond multiple diseases, existing review papers fall short to summarize current trends of data modalities, feature engineering approaches and survival prediction models. For example, Deepa and Gunavathi (2022) specifically address the primary categories of data modalities used for survival prediction, namely multiomics and clinical data. However, the review does not extensively explore trends and patterns related to the nine different omics types i.e., gene expression (mRNA), micro RNA (miRNA), methylation, copy number variation (CNV), whole exome sequencing (WES), long noncoding RNA (lncRNA), mutation, metabolic, and proteomics, or clinical features associated with distinct cancer subtypes. Similarly, Westerlund et al. (2021) do not explore the potential of multiomics data in terms of cardiovascular diseases. In addition, various review papers completely neglect to address feature engineering in survival prediction (Ahmed, 2005; Bashiri et al., 2017; Gupta et al., 2018; Pobar et al., 2021; Kantidakis et al., 2022; Rahimi et al., 2023). For instance, Feldner-Busztin et al. (2023) despite their focus on dimensionality reduction, fall short in providing a comprehensive summary of current trends in feature engineering approaches with respect to diseases and data modalities. Furthermore, a small portion of these review papers cover details of few state of the art survival prediction models (Ahmed, 2005; Kantidakis et al., 2022; Wiegrebe et al., 2023). While current review papers summarize survival prediction pipelines partially, there is a necessity to bring diverse information into a unified platform which offers comprehensive insights into patterns and trends associated with survival prediction pipelines.

4 Methodology

This section explains different steps or stages of preferred reporting items for systematic review and meta-analyses (PRISMA) strategy (Moher et al., 2010), which is used to gather relevant papers on survival analysis. Figure 2 provides a visual representation of various stages form PRISMA that are summarized in the following subsections.

Figure 2

Figure 2. PRISMA flow diagram: a step-by-step process for articles search and their inclusion or exclusion criteria to generate a set of studies for further in-depth trends analysis. The included papers are collected from Jan 2020 to Jul 2023.

4.1 Search strategy

In Figure 2, the identification stage illustrates combinations of different keywords that are used to search research articles. The keywords block has two different types of operators “∧” and “∨” operators. On the basis of these operators one keyword from each block is selected and various search queries are formulated such as, “SURVIVAL PREDICTION AND AI AND OMICS”, “SURVIVAL PREDICTION AND AI AND Multiomics”, “SURVIVAL Machine Learning AND OMICS”, and so on. These queries are utilized in literature search engines like lens (https://www.lens.org/), and Google Scholar for literature search from Jan 2020 to Jul 2023.

4.2 Eligibility and screening strategy

With an aim to retain literature related to survival prediction, two different screenings are performed on the basis of the following criteria;

• Articles that use only image-based datasets for survival prediction.

• Articles that do not make use of ML, DL, or statistical methods for survival prediction.

• Articles with closed access.

Initially, guided by the title and abstract of the articles, more than 800 studies are discarded. Subsequently, at the final step, based on a comprehensive review of the full text a second screening is performed, resulting in the exclusion of an additional 20 studies. Ultimately, 90 papers are selected for the final comparison and discussion of survival prediction.

5 Results

5.1 RQ I, II, III: survival predictors distribution analysis across diseases and survival endpoints

The primary aim of this section is to summarize the distribution of survival predictors across various diseases and survival endpoints. Predictors distribution analysis under individual diseases offers insights into the most active trends of predictors associated with specific diseases. This consolidated distribution provides a centralized platform to access valuable information about their disease of interest. Similarly, examining the distribution of articles across survival endpoints is valuable for identifying current trends in forecasting multiple events. This approach not only enhances our understanding of the current state of predictive modeling but also facilitates researchers in efficiently accessing information specific to their desired endpoints. Through this exploration, we aim to contribute to a deeper understanding of the diverse landscape of survival prediction research and its applications across various diseases and endpoints.

Table 3 illustrates disease specific predictors distribution for both cancer and other diseases, respectively. In the last 3 years, 74 predictors have been designed for different cancer subtypes related survival prediction (Tan et al., 2020; Fan et al., 2023; Majji et al., 2023) while only 17 predictors have been designed for other diseases such as cardiovascular diseases, COVID-19, cardiomyopathy, esophagectomy and trauma (Kantidakis et al., 2020; Abdelhamid et al., 2022; Feng et al., 2022; Farahani et al., 2023; Qian et al., 2023; Rahman et al., 2023).

Table 3

Table 3. Distribution of survival predictors across individual diseases.

To date, approximately more than 100 different cancer subtypes have been identified (Grever et al., 1992). However, a deeper analysis of the last 3 years reveals that survival prediction models have been developed for only 40 distinct cancer subtypes, as outlined in Table 3. Among 36 different subtypes, most of the predictors have been designed for breast cancer, lung adenocarcinoma, ovarian cancer, and glioblastoma. On the other hand, seven different predictors have been designed for pancancer. Notably, there is a difference between other cancer types and pan-cancer because under this paradigm predictors simultaneously deal with multiple cancer subtypes. Pan-cancer based survival prediction entails predicting patient survival outcomes using data and models applicable to various cancer types (Fan et al., 2023). Instead of focusing on just one type of cancer, this approach draws on data from multiple cancers to identify shared patterns and markers that influence survival. By combining a diverse array of genetic, molecular, and clinical features that are common across different cancers, this method aims to improve the accuracy of survival predictions (Wu et al., 2023). For the development of pan-cancer based predictors, there exists public data having more than 30 distinct cancer subtypes (Liu et al., 2018). However, researchers are utilizing different subsets for the development of predictors (Fan et al., 2023). Figure 3 provides an overview of multiple survival prediction studies that encompass a range of cancer subtypes, either within a pan-cancer context or within the context of predicting survival for different subtypes. A total of 14 studies have taken into account multiple cancer subtypes whereas the majority of the studies have only covered only a single type of cancer subtype such as colorectal cancer (Willems et al., 2023), lymphoma (Li et al., 2023), colon adenocarcinoma (Lv et al., 2020), gastric cancer (Li et al., 2020), and so on.

Figure 3

Figure 3. Cancer subtypes coverage based on pan-cancer or individual subtype settings.

Figures 4, 5 illustrate predictors distribution across survival endpoints. A majority of studies 67 (76%) have OS as an endpoint of survival prediction (Chai et al., 2021a; Abdelhamid et al., 2022; Benkirane et al., 2023; Bhat and Hashmy, 2023), whereas eight studies have incorporated multiple survival endpoints in their analysis. Out of eight studies, three studies have incorporated DFS and BC (Lee and Wang, 2003; Baek and Lee, 2020; Pellegrini, 2023). Two studies have incorporated OS, DFS, and PFS (Tan et al., 2020; Tang et al., 2021) and two studies have OS, and PFS as the survival endpoints (Jiang et al., 2022; Chauhan et al., 2023), one focuses on OS and DFS (Pant et al., 2023). A single study has focused on DFS only (Manganaro et al., 2023), and two only on BC (Li et al., 2021; Vahabi et al., 2021). The rest of studies either did not explicitly specify their endpoints for survival prediction or predominantly concentrated on predicting patients' survival outcomes without a specific focus on distinct survival endpoints.

Figure 4

Figure 4. Survival endpoint distribution across diverse studies.

Figure 5

Figure 5. Distribution of explored survival prediction streams from existing literature. DFS, disease-free survival; PFS, progression-free survival; OS, overall survival; BC, biochemical recurrence.

5.2 RQ IV: survival prediction data availability in public and private sources and opportunities for development of predictors

Survival prediction models development relies on the quality and quantity of annotated data, which is generated through extensive wet lab experiments. Experimental findings are stored in different types of databases that open new doors for the development of survival prediction applications. However, there exist multiple databases and each database encompasses particular diseases and modality specific survival data. For instance, CGGA (Zhao Z. et al., 2021) focuses on brain tumors, and MESA (Bild et al., 2002) contains data related to atherosclerosis. To accelerate the development of more competent survival predictors, it is essential to summarize which database contains which type of disease and what data modalities. In the highlight of research question IV, Table 4 illustrates public databases details in terms of diseases and data modalities they offer.

Table 4

Table 4. The ample collection of survival data within diverse public databases.

A deeper analysis of existing survival predictors reveals that among the 90 studies 58 utilized publicly accessible data from three key databases: the Cancer Genome Atlas Program (TCGA) (Tomczak et al., 2015), NCI Genomic Data Commons (GDC) (Jensen et al., 2017), and the Gene Expression Omnibus (GEO) (Clough and Barrett, 2016; Chai et al., 2021a; Hu Q. et al., 2021; Poirion et al., 2021; Zhao L. et al., 2021; Han et al., 2022; Jiang et al., 2022; Redekar et al., 2022; Wu and Fang, 2022; Wu et al., 2022; Zhang R. et al., 2022). Apart from public databases, there also exist private databases that have been utilized in existing survival prediction studies (Vahabi et al., 2021; Feng et al., 2022; Miao et al., 2022; Richard et al., 2022; Chauhan et al., 2023; Lee et al., 2023; Moreno-Sanchez, 2023). However, these private databases often restrict data access and may require extensive research proposals for data retrieval. Among these databases commonly used databases are Heidelberg University Hospital (Jung et al., 2023), COMBO-01 (Zhou et al., 2023), Life cohort (Unterhuber et al., 2021), and UNOS (Kantidakis et al., 2020; Raju and Sathyalakshmi, 2023). The reliance on private databases for survival prediction creates significant hurdles for research in several ways (Raufaste-Cazavieille et al., 2022). Firstly, limited accessibility to such data impedes the reproducibility and verification of study findings by other researchers, hindering the validation and robustness of predictive models (Misra et al., 2019). Secondly, the lack of transparency and standardized access procedures for private datasets introduces challenges in benchmarking and comparing different survival prediction models (Raufaste-Cazavieille et al., 2022). Lastly, the exclusivity of private databases may contribute to a potential bias in research outcomes, as the diversity and representativeness of the data are often compromised which impacts the generalizability of survival predictions to broader patient cohorts (Boffa et al., 2021).

Public access to databases enables researchers to create survival benchmark datasets that fosters the development of survival prediction models (Liu et al., 2018; Rahimi et al., 2023). However, many researchers develop datasets without making them public which hinders transparency and the broader scientific community progress (Weston et al., 2019). The lack of shared data and presence of multiple datasets associated with a single disease pose a notable challenge in survival prediction. For instance, it hinders the establishment of standardized testing and benchmarking procedures for newly proposed survival prediction methods, leading to ambiguities in identifying the most advanced techniques (Wissel et al., 2022). Moreover, recognizing the need for standardization in benchmarking survival prediction models, Wissel et al. (2022) introduced benchmark survival datasets tailored for both individual cancer subtypes and pan-cancer settings. These datasets are accessible at https://survboard.vercel.app/, contributing to a more uniform and transparent benchmarking framework within the survival prediction landscape. Particularly, here we emphasize the use of these datasets for benchmarking in addition to newly created datasets to have unified benchmarking for cancer-specific survival prediction models.

5.3 RQ V, VI: survival prediction data modalities and utilization of their combinations for disease and survival endpoints specific predictors development

Following the objective of research question V, the primary focus of this section is to investigate and provide a comprehensive summary of the various data modalities utilized in the development of diverse survival predictors. To address research question V, it describes the distribution of data modalities across predictors associated with four distinct survival endpoints, and 44 different diseases. Furthermore, in response to research question VI, it furnishes information regarding the specific clinical features utilized by various survival prediction studies.

Out of 90 different studies, data modalities details of only 84 studies are available. Within this subset, 27 studies exclusively used clinical data, 39 studies utilized multiomics data, and 16 studies investigated the combined potential of both clinical and multiomics data modalities. Moreover, based on characteristics of molecular information omics data is generally categorized into nine different classes namely gene expression (mRNA), micro RNA (miRNA), methylation, copy number variation (CNV), whole exome sequencing (WES), long noncoding RNA (lncRNA), mutation, metabolic, and proteomics. The specifics of different predictors, in terms of variations in the combinations of clinical and various omics data modalities, are outlined in Table 5. Among 55 survival prediction studies based on multiomics, 49 studies utilized different combinations of four distinct omics types: mRNA, methylation, miRNA, and CNV (Baek and Lee, 2020; Jiang et al., 2020; Li et al., 2020; Tan et al., 2020; Tong D. et al., 2020; Tong L. et al., 2020; Yang Q. et al., 2020; Chai et al., 2021a; Hira et al., 2021; Hu Q. et al., 2021; Owens et al., 2021; Tong et al., 2021; Zhang X. et al., 2021; Zhang Z.-S. et al., 2021; Zhao L. et al., 2021; Bhat and Hashmy, 2023; Ellen et al., 2023; Hao et al., 2023). Only seven studies utilized additional modalities such as whole exome sequencing (WES) (Baek and Lee, 2020; Jiang et al., 2022), long coding RNA (lncRNA) (Jiang et al., 2022), proteomics (Tan et al., 2020; Malik et al., 2021; Unterhuber et al., 2021; Richard et al., 2022; Pellegrini, 2023), and mutation data (Tan et al., 2020; Malik et al., 2021; Unterhuber et al., 2021; Pellegrini, 2023).

Table 5

Table 5. Distribution of data modalities across diverse surival prediction studies.

The choice of omics type hinges on the specific disease under investigation, as indicated by the disease-wise distribution of omics types in Figure 6. Out of nine omics types, mRNA, CNV, miRNA, and methylation have been the most commonly utilized modalities for 33 cancer subtypes i.e., breast cancer (Tong L. et al., 2020; Malik et al., 2021; Zhou et al., 2021; Wu and Fang, 2022; Zhang J. Z. et al., 2022; Hao et al., 2023; Othman et al., 2023; Zhang et al., 2023), pan-cancer (Tan et al., 2020; Poirion et al., 2021; Zhang X. et al., 2021; Zheng et al., 2021; Redekar et al., 2022; Yin et al., 2022; Fan et al., 2023), colon cancer (Lv et al., 2020; Tong D. et al., 2020; Yang H. et al., 2020; Zhang J. Z. et al., 2022; Lee et al., 2023), lung adenocarcinoma (Jiang et al., 2020; Lee et al., 2020; Bhat and Hashmy, 2023), and ovarian cancer (Hira et al., 2021; Tong et al., 2021; Zhao L. et al., 2021; Pawar et al., 2022; Wu and Fang, 2022; Zhang S. et al., 2022). In addition, mutation data has been utilized for seven cancer subtypes namely, adult diffuse glioma (Yang Q. et al., 2020), breast cancer (Malik et al., 2021), cervical cancer (Hu Q. et al., 2021), non-small cell lung cancer (Manganaro et al., 2023), ovarian cancer (Zhang S. et al., 2022), and pancreatic cancer (Han et al., 2022). Among 10 data modalities, three modalities namely, proteomic, lncRNA and WES have been utilized the least having limited applicability to clear renal cell cancer (Jiang et al., 2022), pancreatic cancer (Baek and Lee, 2020), breast cancer (Malik et al., 2021), localized prostate cancer (Pellegrini, 2023), and pan-cancer (Zheng et al., 2021). In terms of other diseases i.e., COVID-19 and heart diseases, proteomics, methylation, mRNA, metabolic, and methylation have been the only omics types utilized for survival prediction (Unterhuber et al., 2021; Vahabi et al., 2021; Richard et al., 2022).

Figure 6

Figure 6. Distribution of omics data modalities across a diverse set of diseases. Bar heights represent the counts of each data modality with respect to disease specific published research papers. For instance, CNV has been used in six papers related to breast cancer, mRNA has been used in seven breast cancer papers and so on.

The variability in omics-type selection is not solely bound to diseases but notably varies across a wide spectrum of survival endpoints. Figure 7 shows the counts of different omics types that have been utilized for different survival endpoints prediction. In the context of OS prediction, mRNA, miRNA, methylation, and CNV have been primarily utilized in more than 31 studies, with 10 studies based on proteomics, mutation, and metabolic data. However, in terms of DFS and PFS the selection of omics types appears less distinct. These endpoints have been frequently studied in conjunction with OS, predominantly utilizing mRNA, miRNA, and methylation data. This combination suggests a commonality in the predictive factors across these survival endpoints, indicating potential interconnections or shared biological processes.

Figure 7

Figure 7. Distribution of different omics modalities with respect to survival endpoints.

Clinical data modality has been utilized in 42 different studies. However, in this modality number of features varied from study to study and it is still unclear which particular set of features is most important. To perform an in-depth analysis, which study utilized which subset of features across diverse cancer subtypes and heart diseases, a comprehensive collection of clinical features is presented in Table 6. In order to better understand and discern the trends in clinical features across diverse diseases, hereby they are placed in seven different categories i.e., demographic features (6), disease-specific clinical markers (71), treatment-related features (17), laboratory and biomarkers (48), comorbidity and lifestyle factors (18), and other factors (15).

Table 6

Table 6. Diverse collection of clinical features utilized in various survival prediction studies.

A closer look at the clinical features across diverse diseases reveals a consistent set of fundamental demographic features i.e., age and gender which are prevalent in nearly all studies (Hathaway Q. A. et al., 2021; Unterhuber et al., 2021; Feng et al., 2022; Redekar et al., 2022; Li et al., 2023; Wang X. et al., 2023). Beyond demographic features, disease-specific features also play critical role for disease-specific survival prediction. For instance, cancer-related studies invariably focus on tumor stage, histological type, and treatment specifics, underlining the critical role of disease-specific clinical markers in prognosis (Lee et al., 2023; Pellegrini, 2023).

Treatment-related features such as chemotherapy, radiotherapy, and immunotherapy, are particularly evident in cancer subtypes specific studies which reflect the profound influence of therapeutic interventions on survival outcomes (Othman et al., 2023; Wang X. et al., 2023). Moreover, the recurrent inclusion of lifestyle and comorbidity factors ranging from smoking history and BMI to hypertension and diabetes across multiple diseases underlines their pervasive impact on prognostic modeling (Hathaway Q. A. et al., 2021; Bhat and Hashmy, 2023). These lifestyle and comorbidity features show the complex relationship between individual health choices and their potential influence on survival outcomes.

5.4 RQ VII: feature engineering trends across data modalities and disease-specific survival predictors

This section addresses research question VII by investigating the application of feature engineering methods in survival prediction studies across a variety of diseases. This will help researchers to analyze and understand trends of feature engineering techniques in disease or endpoint specific survival prediction pipelines. Additionally, it delves into the trends in diverse feature engineering methods and their relevance to clinical and multiomics data modalities. This investigation aims to reveal trends and patterns in the dynamic interplay between feature engineering methods and the specific characteristics of different data modalities, and survival endpoints.

Table 7 illustrates 30 different feature engineering methods that have been utilized in diverse survival prediction studies. These methods are broadly categorized into five categories, namely supervised methods, incorporating L1 regularized Cox regression (Qian et al., 2023), RSF algorithm (Qian et al., 2023), Cox regression (Zhang S. et al., 2022), least absolute shrinkage and selection operator (lasso) regression (Abdelhamid et al., 2022), cascaded Wx (Yin et al., 2022), recursive feature elimination (Wang et al., 2022), Boruta (Jiang et al., 2022), Akaike information criterion (AIC) regression (Zeng et al., 2021), variance (Zhao L. et al., 2021), lasso analysis (Tang et al., 2021), multivariate regression (Tang et al., 2021), Chi-squared (Moreno-Sanchez, 2023), mutual information (Moreno-Sanchez, 2023), and ANOVA (Lv et al., 2020; Moreno-Sanchez, 2023). Additionally, Network based methods include network based stratification (NBS) (Shetty et al., 2023), weighted correlation network analysis (WGCNA) (Wang X. et al., 2023), canonical correlation analyses (CCA) (Wang J. et al., 2023), patient similarity networks (Wang et al., 2022), and neighborhood component analysis (NCA) (Malik et al., 2021). Dimensionality reduction methods include non-negative matrix factorization (NMF) (Tang et al., 2021), autoencoders (AEs) (Benkirane et al., 2023), variational autoencoders (VAEs) (Owens et al., 2021), principal component analysis (PCA) (Lv et al., 2020), and dominant effect of the cancer driver genes (DEOD) (Amgalan and Lee, 2015; Lee et al., 2023). Moreover, clustering methods comprise Kruskal-Wallis and Gaussian clustering (Poirion et al., 2021), hierarchical clustering (Chai et al., 2021a), and Guassian clustering (Poirion et al., 2021). In addition, to deal with clinical data, Palmal et al. (2023) showed the application of Tab-transformer for feature extraction.

Table 7

Table 7. Diverse feature engineering methods for survival prediction.

A comprehensive analysis of feature engineering methods across a range of disease-specific survival prediction studies unveils that supervised methods, such as Cox regression, L1 regularized Cox regression, and RSF algorithm, have been prevalent in diseases like ASCVD, trauma, and ovarian cancer (Abdelhamid et al., 2022; Zhang S. et al., 2022). On the other hand, network based methods including NBS and WGCNA, have been applied in diseases like KIRP, and hepatocellular carcinoma, which shows the significance of network structures in certain medical contexts (Wang X. et al., 2023). Univariate analyses, including ANOVA, chi-squared, and univariate Cox regression, have been prevalent in diseases such as pancreatic cancer and heart failure, underscoring the significance of statistical testing in identifying relevant features (Moreno-Sanchez, 2023; Zhou et al., 2023). Furthermore, dimensionality reduction methods such as PCA, and NMF have been consistently used across various diseases namely, ovarian cancer (Zhang S. et al., 2022), lower grade glioma (Wu et al., 2022), colon adenocarcinoma (Lv et al., 2020), bladder and breast cancers (Tang et al., 2021; Lin et al., 2022). In addition, the potential of AEs, and VAEs have also been explored in diseases like glioblastoma multiforme, breast cancer, pan-cancer, and Lung Adenocarcinoma for feature integration and dimensionality reduction (Benkirane et al., 2023; Bhat and Hashmy, 2023; Hao et al., 2023).

While feature engineering methods exhibit specificity tailored to distinct diseases, their efficacy is influenced by the inherent characteristics of the utilized data (Jiang et al., 2017). This raises the pertinent question of which particular feature engineering method proves most effective in the context of clinical and multiomics datasets. A thorough analysis of feature engineering methods and their applicability with respect to clinical and multiomics datasets reveals that methods like Cox regression, CCA, AIC, and ANOVA have been quite widely utilized in studies involving only clinical data (Zeng et al., 2021; Moreno-Sanchez, 2023; Qian et al., 2023; Wang J. et al., 2023). These methods have been applied to clinical data for multiple reasons for instance, such methods are interpretable which is important to gain meaningful insights for healthcare professionals (Jiang, 2022). Clinical data is always multifactorial, which means that multiple features of the data can lead to a specific event, and methods like ANOVA are quite efficient in analyzing such contributors (Azizi et al., 2022). Although, such models have shown promising performance with clinical data, yet one of the drawbacks of such models is their inability to handle non-linear data which is the case in terms of multiomics data (Cleves, 2008). Considering similar limitations, multiple methods such as cascaded wx (Yin et al., 2022), RFI (Wang et al., 2022), PSN (Jiang et al., 2022), NMF (Tang et al., 2021), Boruta (Jiang et al., 2022), PCA (Chai et al., 2021a) variance (Zhao L. et al., 2021), DEOD (Lee et al., 2023), have been utilized to handle multiomics to capture important interactions among the features and to integrate cross modalities properly. Particularly, here methods such as AEs and VAEs play a significant role and recent studies also show a growing interest in using such methods for dimensionality reduction and feature integration by such methods for multiomics and clinical datasets i.e., AEs (Baek and Lee, 2020; Jiang et al., 2020, 2022; Li et al., 2020; Lv et al., 2020; Wang et al., 2020; Yang H. et al., 2020; Owens et al., 2021; Wu and Fang, 2022), and VAEs (Tong L. et al., 2020; Hira et al., 2021; Zhang X. et al., 2021; Benkirane et al., 2023).

Although the selection of a feature engineering method is tied to the characteristics of the disease and the nature of the data (Dong and Liu, 2018), there is no significant evidence to suggest that it is substantially impacted by survival endpoints such as DFS, PFS, BC, and OS. This assumption arises due to the absence of a consistent pattern in feature engineering method selection across different survival endpoints. Studies, such as Lv et al. (2020), Tang et al. (2021), and Manganaro et al. (2023), demonstrate a varied use of feature engineering techniques irrespective of the specific survival endpoints (DFS, PFS, BC, or OS). This lack of uniformity implies that feature engineering method selection is driven more by the unique characteristics of the data and disease than by the nature of the survival endpoint itself.

On the basis of various trends and patterns it can be concluded that for heart diseases, univariate analyses and supervised feature engineering methods have been utilized. Conversely, in terms of cancer subtypes a mixture of dimensionality reduction methods is observed with a recent trend toward the AEs. In terms of survival datasets, the prime focus has been to use supervised methods for clinical data and multiple dimensionality reduction methods for multiomics data. Moreover, there are no conclusive remarks that feature engineering methods get affected by the survival endpoints, as the current literature also suggests a varied use of feature engineering methods regardless of the survival endpoints.

5.5 RQ VIII: survival prediction methods insights and distribution across disease types and survival endpoints

In pursuit of addressing research question VIII, this section presents an overview and insights about statistical, ML, and DL algorithms that have been utilized in existing survival prediction pipelines. It succinctly examines their emerging trends across diseases and survival endpoints. This exploration aims to empower researchers in identifying gaps within disease-specific and survival endpoint-focused studies, ultimately contributing to the enhancement of survival predictive pipelines.

Table 8 provides information about 44 diseases and the corresponding survival prediction algorithms utilized in these diseases. A deeper analysis of Table 8 shows that Cox-PH and lasso Cox-PH models have been extensively utilized for disease specific survival prediction i.e., ASCVD (Hathaway Q. A. et al., 2021; Qian et al., 2023), bladder cancer (Chai et al., 2021a; Tang et al., 2021), colorectal cancer (Tong D. et al., 2020; Yang H. et al., 2020; Zhang J. Z. et al., 2022; Lee et al., 2023), hepatocellular carcinoma (Owens et al., 2021; Zhang R. et al., 2022; Wang X. et al., 2023), ovarian cancer (Hira et al., 2021; Pawar et al., 2022; Wu and Fang, 2022; Zhang S. et al., 2022), lung adenocarcinoma (Bhat and Hashmy, 2023), heart failure (Moreno-Sanchez, 2023), HER2-negative metastatic breast cancer (Wang J. et al., 2023), pancreatic cancer (Baek and Lee, 2020; Zhou et al., 2023), trauma (Abdelhamid et al., 2022), nasopharyngeal carcinoma (Miao et al., 2022), triple-negative breast cancer (Zhang et al., 2023), lymphoma (Li et al., 2023), breast cancer (Chai et al., 2021a; Tang et al., 2021; Chauhan et al., 2023), ovarian cancer (Hira et al., 2021; Pawar et al., 2022; Wu and Fang, 2022; Zhang S. et al., 2022), and lower-grade glioma (Wu et al., 2022), cardiovascular disease (Unterhuber et al., 2021; Vahabi et al., 2021; Xu et al., 2021; Zeng et al., 2021; Feng et al., 2022), invasive ductal carcinoma (Lin et al., 2022), liver transplantation (Kantidakis et al., 2020), gastric cancer (Li et al., 2020), lung cancer (Jiang et al., 2020), esophageal squamous cell carcinoma (Yu et al., 2020), glioma (Yang Q. et al., 2020), and liver cancer (Wang et al., 2020). RSF has been employed in 13 studies for six diseases namely, ASCVD (Qian et al., 2023), bladder cancer (Chai et al., 2021a), gastrointestinal cancer (Jung et al., 2023), cervical cancer (Hu Q. et al., 2021), liver transplantation (Kantidakis et al., 2020), and heart failure (Moreno-Sanchez, 2023). DL model DeepSurv, has been utilized in five studies related to gastrointestinal cancer (Jung et al., 2023), ASCVD (Hathaway Q. A. et al., 2021), NSCLC (Zhang Z.-S. et al., 2021). On the other hand, in the analyzed survival predictive pipelines less frequently utilized methods are i.e., survival SVM (Yu et al., 2020; Abdelhamid et al., 2022; Manganaro et al., 2023), partial logistic regression (Lin et al., 2022; Lee et al., 2023), log hazard net (Lee et al., 2023; Majji et al., 2023), boosting (Wang et al., 2020; Feng et al., 2022), stepCox (Wang X. et al., 2023), elastic net (Manganaro et al., 2023), CNN-cox (Majji et al., 2023), DeepOmix (Majji et al., 2023), ordinal Cox-PH (Bichindaritz and Liu, 2022), DeepHit (Feng et al., 2022), and linear multitask logistic regression (MTLR) (Feng et al., 2022).

Table 8

Table 8. Distribution of survival predictors across diverse diseases.

Furthermore, Supplementary Table S3 provides details about predictors distribution with respect to survival endpoints. A detailed analysis reveals, out of 90 predictors, 47, 8, 1, and 6 models have been utilized for OS, DFS, PFS, and BC survival endpoints, respectively. Unlike disease-specific predictors, here a mixture of methods is utilized and no particular trend exists. To provide high-level overview of multiple methods that have been utilized in all four survival endpoints we have provided a graphical representation of methods in Figure 8.

Figure 8

Figure 8. Hierarchal illustration of survival prediction methods under three different categories.

It can be seen in Figure 8, diverse types of methods that have been utilized in survival predictive pipelines can be categorized into three different categories i.e., statistical, ML, and DL. Statistical methods are broadly classified into three different categories i.e., parametric, semi-parametric, and non-parametric models. Parametric methods make assumptions about the survival time distribution (Lee and Wang, 2003; Kubi et al., 2022). Parametric methods include exponential, Weibull, log-normal, Weibull, gamma models, and so on (Ishak et al., 2013; Kubi et al., 2022). Comparatively, semi-parametric methods make no assumptions about the shape of the baseline hazard function (non-parametric) (Kleinbaum and Klein, 1996). Rather, these methods assume a specific functional form for the effect of covariates (parametric) (Sinha and Dey, 1997). In comparison, non-parametric methods do not take into account assumptions about the underlying distribution of survival times and the shape of the hazard function. These methods include Kalpan-Meier, Nelson-Aalen, Breslow, Gehan-Eilcoxon, and life table methods (Stevenson and EpiCentre, 2009). Some statistical methods (i.e., COX-PH) have certain disadvantages with multiomics based survival prediction (Lee and Lim, 2019). For instance, COX-PH assumes linear relationships among variables and fails to capture complex and non-linear data patterns (Therneau et al., 2000). These methods perform poorly on high dimensional data where the number of features is larger than the number of samples. This specific gap is filled by the emergence of AI based models. Various ML models are utilized for survival analysis such as random survival forest (Ishwaran et al., 2008), and boosting-based methods (Binder and Schumacher, 2008). Shivaswamy et al. (2007), Van Belle et al. (2007), and Khan and Zubek (2008) proposed ranking and regression-based survival SVM for survival prediction while handling right censored data. Particularly, survival SVM is used in three ways for survival prediction i.e., ranking, regression, and combined. Ishwaran et al. (2008) proposed RSF where log-rank test is utilized for the splitting as compared to the Gini impurity of the classical random forest models.

DL methods are utilized in two ways to model survival prediction tasks i.e., continuous and discrete time (Kvamme et al., 2019). Models like CoxCC and time (Kvamme et al., 2019), piecewise constant hazard or PEANN (Fornili et al., 2014), and DeepSruv (Katzman et al., 2018) are utilized for continuous survival time prediction. Whereas, Nnet-survival (Gensheimer and Narasimhan, 2019), Nnet-survival probability mass function (PMF) (Kvamme and Borgan, 2019b), DeepHit and DeepHit Single (Lee et al., 2018), multi-task logistic regression (MTLR) (Yu et al., 2011; Fotso, 2018), and BCESurv (Kvamme and Borgan, 2019a) are utilized to predict survival in a discrete-time setting.

5.6 RQ IX: open source tools and libraries potential for development of survival prediction pipelines

Following the objective research question IX, this section summarizes details of open-source libraries and source codes of existing survival predictors. This comprehensive information will facilitate researchers to build upon existing work, fostering a collaborative environment and accelerating the development of robust and effective survival prediction models.

Table 9 presents an overview of open-source survival prediction models. Among the 90 distinct survival prediction studies, only 28 have provided publicly accessible source code. Among these studies, six studies have utilized R (Kantidakis et al., 2020; Li et al., 2021; Redekar et al., 2022; Zhang S. et al., 2022; Ellen et al., 2023; Willems et al., 2023) and 22 have opted for Python (Jiang et al., 2020; Tong L. et al., 2020; Chai et al., 2021a; Hathaway Q. A. et al., 2021; Hira et al., 2021; Malik et al., 2021; Poirion et al., 2021; Xu et al., 2021; Zhang X. et al., 2021; Zhao L. et al., 2021; Wang et al., 2022; Wu and Fang, 2022; Yin et al., 2022; Zhang J. Z. et al., 2022; Benkirane et al., 2023; Fan et al., 2023; Hao et al., 2023; Lang et al., 2023; Manganaro et al., 2023; Moreno-Sanchez, 2023; Palmal et al., 2023; Shetty et al., 2023). A comprehensive analysis of open source codes reveals that a majority of these tools have been developed from scratch without utilizing any specific survival prediction library (Benkirane et al., 2023; Hao et al., 2023; Manganaro et al., 2023; Shetty et al., 2023).

Table 9

Table 9. Summary of open-source survival prediction methods in existing studies.

Approximately 10 different survival prediction packages or libraries have been developed as shown in Table 10. Each library offers a diverse set of preimplemented statistical, ML, and DL survival prediction models. For instance, Pycox (Kvamme et al., 2019) primarily focuses on continuous and discrete DL survival prediction models such as CoxTime, CoxCC, MTLR, and so on. Lifelines (Davidson-Pilon, 2019), scikit-survival (Pölsterl, 2020), and pysurvival (Fotso et al., 2019 ) cover a wide range of statistical and ML survival prediction models like Cox-PH, RSF, survival support vector machine, and gradient boosting survival (Davidson-Pilon, 2019; Fotso et al., 2019; Pölsterl, 2020).

Table 10

Table 10. Survival analysis libraries, models, and evaluation metrics.

Notably, addressing the lack of interpretability or explainability in the previously discussed libraries, Spytek et al. (2023) introduced Survex. This library allows researchers to analyze the features responsible for a specific event by offering different methods for both local and global explanations of various survival prediction models.

The selection of a specific library is inherently subjective and depends on factors such as the preferred development platform, choice of survival prediction models, and the specific research question in hand. Therefore, recommendations are made based on the number of survival prediction models and evaluation measures each library offers. For Python, Lifelines (Davidson-Pilon, 2019) and Pycox (Kvamme et al., 2019) are recommended, with Lifelines (Davidson-Pilon, 2019) providing a diverse range of statistical and ML models, while Pycox (Kvamme et al., 2019) is specialized in DL models. Additionally, for R, mlr3proba (Sonabend et al., 2021) is recommended, as it offers a variety of statistical and ML models for survival prediction. Ultimately, selecting a library aligned with individual research needs not only streamlines the development process but also contributes to the overall reliability of survival prediction models.

5.7 RQ X: strategies for assessing survival predictors: unveiling common evaluation measures

The main objective of this section is to provide a concise overview of research question X, which focuses on the commonly employed evaluation measures for survival predictive pipelines.

Table 11 shows a compilation of 18 distinct evaluation measures that have been commonly used to evaluate survival prediction pipelines. The survival prediction pipelines can be categorized into two distinct classes namely survival outcome prediction (Lynch et al., 2017) and survival prediction (Tarkhan et al., 2021). Details related to these categories is provided in the background section. Out of 18 evaluation measures mentioned in Table 11, a set of 10 evaluation measures have been employed to assess the performance of survival outcome prediction models. In addition to the aforementioned measures, 8 other evaluation measures have been utilized to assess the performance of survival prediction models.

Table 11

Table 11. A summary of evaluation measures used in survival prediction and survival outcome prediction pipelines.

In survival prediction category based evaluation measures, the objective is to capture two distinct characteristics namely, calibration and discrimination (D'Agostino and Nam, 2003; Simino, 2009). Specifically, calibration refers to how well the predicted probabilities of survival align with the actual observed survival rates over time (D'Agostino and Nam, 2003). Under this paradigm most widely used evaluation measures are BS (Schumacher et al., 2003), IBS (Gerds and Schumacher, 2006), TD-ROC (Heagerty et al., 2000), and DCA (Vickers and Elkin, 2006). Discrimination paradigm based evaluation measures capture differentiation between individuals with different survival times. Under this paradigm most widely used measures are C-index (Hartman et al., 2023), AUC-ROC (Terrematte et al., 2022), and likelihood ratio (Murphy, 1995).

On the other hand objective of survival outcome prediction evaluation measures is to assess diverse characteristics of a model i.e., efficacy of the model, overall accurate predictions, biasness toward type I or type II errors (Hao et al., 2023; Lee et al., 2023). Specifically, accuracy and F1 score are used to measure overall accurate predictions, precision, and recall examine the model's biasness with respect to type I and type II errors (Zeng et al., 2021; Wang et al., 2022). Additionally, MCC provides a comprehensive assessment, taking into account overall accurate predictions, and errors (Othman et al., 2023). In addition, AUC-ROC assesses the predictive potential of a model by analyzing the true positive rate (TPR) and true negative rate (TNR) at different thresholds (Hao et al., 2023; Pellegrini, 2023; Qian et al., 2023).

5.8 RQ XI: publisher and journal-wise distribution of research papers

This section addresses research question XI by presenting the distribution of survival prediction literature across diverse journals and publishers. Overall, this analysis not only enables researchers to strategically position their work but also offers opportunities for interdisciplinary collaboration, promoting a more interconnected and dynamic research landscape within the domain of survival prediction.

In Figures 9, 10, the distribution of survival prediction literature is presented based on journals and publishers. The studies have been published in 25 different publishers, including but not limited to Springer, Elsevier, Oxford Press, and BioMed Central. Notably, around 30 out of 90 survival prediction studies have been disseminated through Springer, and BioMed Central. Furthermore, Elsevier has contributed to the field by publishing 10 relevant papers in recent years. Particularly, these studies have been published in more than 50 different conferences/journals, which shows the diversity of the survival prediction landscape.

Figure 9

Figure 9. Journal-wise distribution of articles.

Figure 10

Figure 10. Publisher-wise distribution of articles.

6 Discussion

The field of disease survival prediction has become a pivotal aspect of effective healthcare, especially within the domain of precision medicine. Recognizing the significant variability present among patients within specific diseases, there is an increasing demand and development for disease specific survival predictors. Our analysis reveals that researchers place a profound emphasis on predicting survival in cancer as compared to other diseases, and there are compelling reasons behind this focus. First, cancer exhibits significant variability from one patient to another as compared to other diseases, which highlights the imperative need for cancer survival prediction to explore and comprehend the heterogeneity of cancer. Second, cancer is a leading cause of death worldwide, and effective survival prediction can aid in early detection and intervention, potentially saving lives. Third, a huge amount of data sources are developed to make cancer-related data publicly available to accelerate and optimize cancer-related research.

Furthermore, to analyze the trajectory of the disease, researchers place great focus on studying different survival endpoints that suit the respective research setting i.e., treatment, progression, recurrence, and death. Among four different survival endpoints i.e., OS, DFS, BC, and PFS, OS is often emphasized more in survival prediction studies. Despite the prime focus on OS, the significance of other survival endpoints in understanding disease trajectories cannot be understated. These survival endpoints help to analyze different characteristics of diseases such as understanding treatment efficacy and durability, treatments that not only extend life but also effectively manage the course of the illness, and markers responsible for disease recurrence. The lack of research in other survival endpoints opens up new research avenues for the AI experts to develop novel methods that can help explore various characteristics related to disease.

Although both public and private databases have been utilized in survival prediction studies, yet the preference for public databases stems from their accessibility and the wealth of information they provide. For instance, TCGA (Tomczak et al., 2015) offers a vast array of genomic and clinical data across different cancer types. This invaluable resource aids researchers in developing accurate survival prediction models. Likewise, GDC (Jensen et al., 2017) and GEO (Clough and Barrett, 2016) offer comprehensive datasets that encompass a wide range of diseases, making them appealing choices for various research endeavors. Furthermore, a crucial observation regarding private data sources is that they are not universally accessible. This argument is supported by the limited accessibility of omics datasets related to cardiovascular diseases. Despite a singular study employing omics data for survival prediction in cardiovascular diseases, the challenge lies in the difficulty of retrieving the original data. Authors often refrain from sharing their datasets, and obtaining access to databases requires extensive proposals, adding a layer of complexity to the development of novel survival prediction pipelines for cardiovascular diseases. This obstacle may impede the advancement of innovative survival prediction pipelines for cardiovascular disease.

Overall, the use of omics and clinical data in survival prediction tools marks a significant stride toward precision medicine. The distribution of omics types in survival prediction studies reveals a preference for mRNA, methylation, microRNA, and CNV across various cancer subtypes. In addition, the limited number of multiomics based survival prediction studies in cardiovascular diseases hinders definitive conclusions on the importance of specific omics types. Disease-specific patterns highlight the importance of tailored clinical markers, prominently seen in cancer studies with a focus on tumor stage and histological type. Treatment-related features, notably chemotherapy and radiotherapy, underscore the impact of therapeutic interventions on survival predictions. Moreover, clinical features along with omics data with diverse molecular aspects are utilized together to improve the performance of survival prediction models. Diverse survival prediction research accentuates the pivotal role of leveraging patient information, such as medical history, demographics, disease-related features, and diagnostic records. This trend reflects an increasing recognition of the potential of clinical data in not only understanding disease progression but also in guiding personalized treatment strategies and enhancing patient care. A recent benchmark study on survival prediction models with multiomics and clinical data also shows the significant role of clinical data in survival prediction across multiple cancer subtypes (Herrmann et al., 2021).

In addition, our analysis reveals that increasing the total number of data modalities does not necessarily offer improved survival predictions, yet data modalities are quite specific to the disease and survival endpoints. Therefore, the selection of data modalities should be made very carefully as rather than improving the overall performance it can induce undesirable noise in the analysis.

One of the common problems in survival analysis is data censoring (Leung et al., 1997). Censoring arises when there is incomplete information about the time points and/or events of some subjects in a study. There are different types of censoring i.e., (I) Right Censoring is the most common type of data censoring, where an event does not occur for some subjects by the end of study or by the last time point at which data is collected. For example, a subject withdraws from the study or there is a lost follow up for a specific subject (II) Left Censoring is the least common type of censoring where the event may occur before the start of the study or during the data collection phase. (III) Interval Censoring arises when the event of interest occurs in a time interval but the exact time point is not known. In survival analysis, three assumptions are taken into account to infer censored data i.e., (I) Independent Censoring: assumes that the censoring times for multiple subjects are independent of each other. (II) Random censoring assumes that the time t at which individuals are censored must be random and the failure rate for subjects who are censored is assumed to be equal to the failure rate for subjects who remained in the risk set who are not censored. (III) Non-informative censoring occurs if the distribution of survival times (T) provides no information about the distribution of censorship times (C), and vice versa. Although, data censoring is quite important in terms of survival prediction, yet it has been discussed and dealt with properly in the existing studies. We recommend to incorporate comprehensive details of data censoring in future survival prediction studies. Particularly details on how each type of data censoring is handled should not be neglected.

Our analysis of the utilization of feature engineering methods raises two crucial points. First, even though a plethora of methods have been already tested for various survival prediction studies, autoencoder based methods tend to reduce the dimensionality of omics data modalities more efficiently. In addition, the rest of the methods work much better with clinical features. The success of feature engineering approaches is contingent upon the chosen technique with the inherent properties of the data. This highlights the importance of large-scale benchmark studies in guiding the selection of feature engineering strategies for the development of accurate predictive pipelines.

In end-to-end survival predictive pipelines, researchers have utilized methods from three different families namely statistical (Hazard models, Kaplan-Meier Estimator, Log-Rank Test, and Frailty Models) (Kleinbaum and Klein, 1996), ML (Random Forests, Support Vector Machines, Gradient Boosting Machines, and Nearest Neighbors) (Ishwaran et al., 2008; Ma et al., 2022), and DL (CoxNnet, DeepSurv) (Ching et al., 2018; Katzman et al., 2018). Statistical methods are unable to extract complex non-linear patterns that is why in current predictors focus of researchers is on ML or DL based methods (Katzman et al., 2018). In spite of the applications and usefulness of traditional ML methods, they face numerous limitations when applied to survival prediction. These limitations arise either from the inherent challenges of survival data or from the models themselves. Such limitations include censored observations (Khan and Zubek, 2008), overfitting and outliers (Biccler et al., 2020; Nariya et al., 2023), and complex relationships among variables. ML models also suffer from outliers in survival prediction datasets (Biccler et al., 2020). DL methods address many of these limitations through their advanced architectures and ability to learn complex patterns from large datasets. DL models such as DeepSurv, extend the Cox proportional hazards model by learning non-linear representations of the covariates and handling censored data effectively (Katzman et al., 2018). This model leverages the strengths of neural networks to capture complex relationships and interactions between variables, improving prediction accuracy (Katzman et al., 2018). In addition, there are some advantages of ML methods as well, i.e., they perform better even on small datasets while DL methods require large data (LeCun et al., 2015). Similarly, ML methods decisions are explainable and DL methods decisions are black box (Dwivedi et al., 2023). Although, a research comunity is focusing on unveiling black box decisions of predictors. However, in survival prediction, most of predictors do not have explainability component (Krzyziński et al., 2023). But researchers are trying to incorporate explainability methods with survival models (Krzyziński et al., 2023).

While developing different data modalities based on survival predictor, predictive pipelines require dimensionality reduction methods that avoid the curse of the dimensionality problem (Feldner-Busztin et al., 2023). Although several traditional methods (PCA, LDA, TSNE, UMAP etc.) have been developed to transform data into new space that have more comprehensive patterns and less number of features. However, these methods lacks in extracting and incorporating non-linear patterns of features (Gastinel, 2012; Kirpich et al., 2018; Degenhardt et al., 2019). On the other hand in deep learning based predictive pipelines, researchers are utilizing auto-encoders that are capable of generating more comprehensive feature space by extracting both linear and non-linear patterns of features (Tan et al., 2020). Following overall pros and cons of ML and DL based predictive pipelines, new predictors can be developed by utilizing ML based methods with smaller datasets. Moreover, in these predictors rather than utilizing traditional dimensionality reduction methods, autoencoders can be utilized. Moreover, when data is large, it is better to develop DL predictors but these predictors must be enriched with explainability methods.

With an aim to evaluate the performance of predictive pipelines, diverse types of evaluation measures have been developed. Each evaluation measure addresses a specific aspect of survival prediction models, precluding the possibility of any single metric being universally ideal for a comprehensive evaluation of survival prediction. For instance, C-index estimates the robustness and discriminatory power of the survival prediction model. In addition, BS and IBS measure the accuracy of a model on time distribution. Moreover, log-rank p-value evaluates the potential of the model by testing the differences in different survival groups. Although these measures are the most commonly utilized, there are diverse other evaluation measures for similar purposes i.e., restricted mean survival time (RMST), odds ratio (Pellegrini, 2023), Kappa for inter-rater reliability (Zheng et al., 2021), integrated absolute error (IAE), integrated square error (ISE), mean absolute error (MAE), integrated AUC (IAUC) time-dependent integrated discrimination improvement, and time-dependent net reclassification improvement (NRI). Furthermore, while these individual measures provide valuable insights, it is noteworthy to mention that their collective application offers a more comprehensive evaluation. Therefore, we recommend utilizing multiple evaluation measures to assess discrimination and calibration of survival prediction models.

7 Reccomendations

With an aim to expedite and enhance research in survival prediction. Hereby, on the basis of Table 12, we summarize some important recommendations for future survival prediction studies.

Table 12

Table 12. A summary of key research questions of our review and main findings.

We highly recommend leveraging open-source tools and libraries for developing survival prediction pipelines. Pycox (Kvamme et al., 2019), Lifelines (Davidson-Pilon, 2019), and scikit-survival (Pölsterl, 2020) are excellent choices, offering a rich array of pre-implemented statistical, ML, and DL models. In addition, selecting appropriate evaluation measures is paramount. We advise researchers to carefully choose measures aligned with their research question and survival prediction task. Utilizing multiple measures ensures a comprehensive assessment of model performance i.e., C-index, IBS, BS, and ROC (Schumacher et al., 2003; Gerds and Schumacher, 2006; Terrematte et al., 2022; Hartman et al., 2023).

Integration of clinical and omics data is key to improving prediction accuracy. Researchers should explore diverse data sources and consider disease-specific patterns and survival endpoints to enhance the predictive power of their models. Researchers should carefully use feature engineering methods tailored to their data characteristics. Autoencoder-based dimensionality reduction for omics data and traditional methods for clinical features can significantly enhance predictive pipelines. Particularly it is important to note that addressing data censoring transparently is essential for model reliability. We recommend providing comprehensive details on censoring types and handling methods to ensure the robustness of survival prediction models.

Both traditional ML and DL methods offer unique advantages. Researchers should explore the strengths of each approach, with a particular focus on DL methods like DeepSurv for capturing complex relationships. In addition, models like Transformers can also be used to deal with clinical data which shall be an interesting research perspective in future (Pant et al., 2023). Enriching survival prediction models with explainability methods is crucial for improving interpretability. By understanding and unveiling model decisions, researchers can enhance trust and adoption in clinical settings. By following such recommendations, researchers can contribute to the development of robust and effective survival prediction models, ultimately facilitating personalized treatment strategies and improving patient care across various disease.

Data availability statement

The original contributions presented in the study are included in the article/Supplementary material, further inquiries can be directed to the corresponding author.

Author contributions

AA: Conceptualization, Data curation, Formal analysis, Investigation, Methodology, Software, Validation, Visualization, Writing – original draft, Writing – review & editing. MA: Conceptualization, Data curation, Investigation, Methodology, Software, Supervision, Validation, Writing – original draft, Writing – review & editing. SA: Supervision, Writing – review & editing. SV: Supervision, Visualization, Writing – original draft, Writing – review & editing. AD: Supervision, Writing – review & editing.

Funding

The author(s) declare that financial support was received for the research, authorship, and/or publication of this article. The project EVENTFUL on which report is based was funded by Federal Ministry of Education and Research under grant number 01|W23005. The responsibility for the content of this publication lies with the authors.

Conflict of interest

The authors declare that the research was conducted in the absence of any commercial or financial relationships that could be construed as a potential conflict of interest.

Publisher's note

All claims expressed in this article are solely those of the authors and do not necessarily represent those of their affiliated organizations, or those of the publisher, the editors and the reviewers. Any product that may be evaluated in this article, or claim that may be made by its manufacturer, is not guaranteed or endorsed by the publisher.

Supplementary material

The Supplementary Material for this article can be found online at: https://www.frontiersin.org/articles/10.3389/frai.2024.1428501/full#supplementary-material

References

Abdelhamid, S., Scioscia, J., Li, S., Das, J., Rahman, S., Bonaroti, J. W., et al. (2022). Multi-omic admission-based biomarkers predict 30-day survival and persistent critical illness in trauma patients after injury. J. Am. Coll. Surg. 235:S95. doi: 10.1097/01.XCS.0000896540.67938.36

Crossref Full Text | Google Scholar

Ahmed, F. E. (2005). Artificial neural networks for diagnosis and survival prediction in colon cancer. Mol. Cancer 4, 1–12. doi: 10.1186/1476-4598-4-29

PubMed Abstract | Crossref Full Text | Google Scholar

Al-Lazikani, B., Banerji, U., and Workman, P. (2012). Combinatorial drug therapy for cancer in the post-genomic era. Nat. Biotechnol. 30, 679–692. doi: 10.1038/nbt.2284

PubMed Abstract | Crossref Full Text | Google Scholar

Altuhaifa, F. A., Win, K. T., and Su, G. (2023). Predicting lung cancer survival based on clinical data using machine learning: a review. Comp. Biol. Med. 165:107338. doi: 10.1016/j.compbiomed.2023.107338

PubMed Abstract | Crossref Full Text | Google Scholar

Amgalan, B., and Lee, H. (2015). Deod: uncovering dominant effects of cancer-driver genes based on a partial covariance selection method. Bioinformatics 31, 2452–2460. doi: 10.1093/bioinformatics/btv175

PubMed Abstract | Crossref Full Text | Google Scholar

Arjmand, B., Hamidpour, S. K., Tayanloo-Beik, A., Goodarzi, P., Aghayan, H. R., Adibi, H., et al. (2022). Machine learning: a new prospect in multi-omics data analysis of cancer. Front. Genet. 13:824451. doi: 10.3389/fgene.2022.824451

PubMed Abstract | Crossref Full Text | Google Scholar

Ashley, E. A. (2016). Towards precision medicine. Nat. Rev. Genet. 17, 507–522. doi: 10.1038/nrg.2016.86

PubMed Abstract | Crossref Full Text | Google Scholar

Azizi, F., Ghasemi, R., and Ardalan, M. (2022). Two common mistakes in applying anova test: guide for biological researchers. Preprint. doi: 10.20944/preprints202207.0082.v1

Crossref Full Text | Google Scholar

Baek, B., and Lee, H. (2020). Prediction of survival and recurrence in patients with pancreatic cancer by integrating multi-omics data. Sci. Rep. 10:18951. doi: 10.1038/s41598-020-76025-1

PubMed Abstract | Crossref Full Text | Google Scholar

Bakasa, W., and Viriri, S. (2021). Pancreatic cancer survival prediction: a survey of the state-of-the-art. Comput. Math. Methods Med. 2021:1188414. doi: 10.1155/2021/1188414

PubMed Abstract | Crossref Full Text | Google Scholar

Bashiri, A., Ghazisaeedi, M., Safdari, R., Shahmoradi, L., and Ehtesham, H. (2017). Improving the prediction of survival in cancer patients by using machine learning techniques: experience of gene expression data: a narrative review. Iran. J. Public Health 46:165.

PubMed Abstract | Google Scholar

Benkirane, H., Pradat, Y., Michiels, S., and Cournède, P.-H. (2023). Customics: a versatile deep-learning based strategy for multi-omics integration. PLoS Comput. Biol. 19:e1010921. doi: 10.1371/journal.pcbi.1010921

PubMed Abstract | Crossref Full Text | Google Scholar

Bhat, A. R., and Hashmy, R. (2023). Hierarchical autoencoder-based multi-omics subtyping and prognosis prediction framework for lung adenocarcinoma. Int. J. Inf. Technol. 15, 1–9. doi: 10.1007/s41870-023-01310-x

Crossref Full Text | Google Scholar

Biccler, J. L., Bøgsted, M., Van Aelst, S., and Verdonck, T. (2020). Outlier robust modeling of survival curves in the presence of potentially time-varying coefficients. Stat. Methods Med. Res. 29, 2683–2696. doi: 10.1177/0962280220910193

PubMed Abstract | Crossref Full Text | Google Scholar

Bichindaritz, I., and Liu, G. (2022). “Adaptive multi-omics survival analysis in cancer,” in Innovation in Medicine and Healthcare: Proceedings of 10th KES-InMed 2022 (Singapore: Springer), 51–62. Available online at: https://link.springer.com/book/10.1007/978-981-19-3440-7

Google Scholar

Bild, D. E., Bluemke, D. A., Burke, G. L., Detrano, R., Diez Roux, A. V., Folsom, A. R., et al. (2002). Multi-ethnic study of atherosclerosis: objectives and design. Am. J. Epidemiol. 156, 871–881. doi: 10.1093/aje/kwf113

PubMed Abstract | Crossref Full Text | Google Scholar

Billheimer, D., Gerner, E. W., McLaren, C. E., and LaFleur, B. (2014). Combined benefit of prediction and treatment: a criterion for evaluating clinical prediction models. Cancer Inf. 13:CIN-S13780. doi: 10.4137/CIN.S13780

PubMed Abstract | Crossref Full Text | Google Scholar

Binder, H., and Schumacher, M. (2008). Allowing for mandatory covariates in boosting estimation of sparse high-dimensional survival models. BMC Bioinform. 9, 1–10. doi: 10.1186/1471-2105-9-14

PubMed Abstract | Crossref Full Text | Google Scholar

Boffa, D. J., Churchwell, K. B., and Maduka, R. C. (2021). Diversity, equity, and representativeness: coming to terms with the henrietta lacks act. J. Natl. Comp. Cancer Netw. 19, 993–996. doi: 10.6004/jnccn.2021.7071

PubMed Abstract | Crossref Full Text | Google Scholar

Bolstad, B. M., Irizarry, R. A., Åstrand, M., and Speed, T. P. (2003). A comparison of normalization methods for high density oligonucleotide array data based on variance and bias. Bioinformatics 19, 185–193. doi: 10.1093/bioinformatics/19.2.185

PubMed Abstract | Crossref Full Text | Google Scholar

Boorjian, S. A., Thompson, R. H., Tollefson, M. K., Rangel, L. J., Bergstralh, E. J., Blute, M. L., et al. (2011). Long-term risk of clinical progression after biochemical recurrence following radical prostatectomy: the impact of time from surgery to recurrence. Eur. Urol. 59, 893–899. doi: 10.1016/j.eururo.2011.02.026

PubMed Abstract | Crossref Full Text | Google Scholar

Boshier, P. R., Swaray, A., Vadhwana, B., O'Sullivan, A., Low, D. E., Hanna, G. B., et al. (2022). Systematic review and validation of clinical models predicting survival after oesophagectomy for adenocarcinoma. Br. J. Surg. 109, 418–425. doi: 10.1093/bjs/znac044

PubMed Abstract | Crossref Full Text | Google Scholar

Bycroft, C., Freeman, C., Petkova, D., Band, G., Elliott, L. T., Sharp, K., et al. (2018). The UK biobank resource with deep phenotyping and genomic data. Nature 562, 203–209. doi: 10.1038/s41586-018-0579-z

PubMed Abstract | Crossref Full Text | Google Scholar

Carobbio, A., Guglielmelli, P., Rumi, E., Cavalloni, C., De Stefano, V., Betti, S., et al. (2020). A multistate model of survival prediction and event monitoring in prefibrotic myelofibrosis. Blood Cancer J. 10:100. doi: 10.1038/s41408-020-00368-1

PubMed Abstract | Crossref Full Text | Google Scholar

Chai, H., Zhang, Z., Wang, Y., and Yang, Y. (2021a). Predicting bladder cancer prognosis by integrating multi-omics data through a transfer learning-based cox proportional hazards network. CCF Transact. High Perform. Comp. 3, 311–319. doi: 10.1007/s42514-021-00074-9

Crossref Full Text | Google Scholar

Chai, H., Zhou, X., Zhang, Z., Rao, J., Zhao, H., and Yang, Y. (2021b). Integrating multi-omics data through deep learning for accurate cancer prognosis prediction. Comput. Biol. Med. 134:104481. doi: 10.1016/j.compbiomed.2021.104481

PubMed Abstract | Crossref Full Text | Google Scholar

Chauhan, P. S., Shiang, A., Alahi, I., Sundby, R. T., Feng, W., Gungoren, B., et al. (2023). Urine cell-free dna multi-omics to detect MRD and predict survival in bladder cancer patients. npj Precis. Oncol. 7:6. doi: 10.1038/s41698-022-00345-w

PubMed Abstract | Crossref Full Text | Google Scholar

Chen, Y.-C., Lee, U. J., Tsai, C.-A., and Chen, J. J. (2018). Development of predictive signatures for treatment selection in precision medicine with survival outcomes. Pharm. Stat. 17, 105–116. doi: 10.1002/pst.1842

PubMed Abstract | Crossref Full Text | Google Scholar

Ching, T., Zhu, X., and Garmire, L. X. (2018). Cox-nnet: an artificial neural network method for prognosis prediction of high-throughput omics data. PLoS Comput. Biol. 14:e1006076. doi: 10.1371/journal.pcbi.1006076

PubMed Abstract | Crossref Full Text | Google Scholar

Clements, M. (2019). Introduction to the rstpm2 package. Karolinska Institutet.

Google Scholar

Cleves, M. (2008). An Introduction to Survival Analysis Using Stata. College Station, TX: Stata Press.

Google Scholar

Clough, E., and Barrett, T. (2016). The gene expression omnibus database. Stat. Genom. 1418, 93–110. doi: 10.1007/978-1-4939-3578-9_5

PubMed Abstract | Crossref Full Text | Google Scholar

D'Agostino, R. B., and Nam, B.-H. (2003). Evaluation of the performance of survival analysis models: discrimination and calibration measures. Handb. Stat. 23, 1–25. doi: 10.1016/S0169-7161(03)23001-7

Crossref Full Text | Google Scholar

Davidson-Pilon, C. (2019). Lifelines: survival analysis in python. J. Open Source Softw. 4:1317. doi: 10.21105/joss.01317

Crossref Full Text | Google Scholar

Deepa, P., and Gunavathi, C. (2022). A systematic review on machine learning and deep learning techniques in cancer survival prediction. Progr. Biophys. Mol. Biol. 174, 62–71. doi: 10.1016/j.pbiomolbio.2022.07.004

PubMed Abstract | Crossref Full Text | Google Scholar

Degenhardt, F., Seifert, S., and Szymczak, S. (2019). Evaluation of variable selection methods for random forests and omics data sets. Brief. Bioinformat. 20, 492–503. doi: 10.1093/bib/bbx124

PubMed Abstract | Crossref Full Text | Google Scholar

Doja, M., Kaur, I., and Ahmad, T. (2020). Age-specific survival in prostate cancer using machine learning. Data Technol. Appl. 54, 215–234. doi: 10.1108/DTA-10-2019-0189

Crossref Full Text | Google Scholar

Dong, G., and Liu, H. (2018). Feature Engineering for Machine Learning and Data Analytics. CRC Press.

Google Scholar

Driscoll, J. J., and Rixe, O. (2009). Overall survival: still the gold standard: why overall survival remains the definitive end point in cancer clinical trials. Cancer J. 15, 401–405. doi: 10.1097/PPO.0b013e3181bdc2e0

PubMed Abstract | Crossref Full Text | Google Scholar

Du, J., Yan, X., Mi, S., Li, Y., Ji, H., Hou, K., et al. (2020). Identification of prognostic model and biomarkers for cancer stem cell characteristics in glioblastoma by network analysis of multi-omics data and stemness indices. Front. Cell Dev. Biol. 8:558961. doi: 10.3389/fcell.2020.558961

PubMed Abstract | Crossref Full Text | Google Scholar

Dwivedi, R., Dave, D., Naik, H., Singhal, S., Omer, R., Patel, P., et al. (2023). Explainable AI (XAI): core ideas, techniques, and solutions. ACM Comp. Surv. 55, 1–33. doi: 10.1145/3561048

Crossref Full Text | Google Scholar

Eckardt, J.-N., Röllig, C., Metzeler, K., Kramer, M., Stasik, S., Georgi, J.-A., et al. (2023). Prediction of complete remission and survival in acute myeloid leukemia using supervised machine learning. Haematologica 108:690. doi: 10.3324/haematol.2021.280027

PubMed Abstract | Crossref Full Text | Google Scholar

Ellen, J. G., Jacob, E., Nikolaou, N., and Markuzon, N. (2023). Autoencoder-based multimodal prediction of non-small cell lung cancer survival. Sci. Rep. 13:15761. doi: 10.1038/s41598-023-42365-x

PubMed Abstract | Crossref Full Text | Google Scholar

Fala, S. Y., and Osman, M. (2023). Machine learning-based model for survival prediction after immunotherapy in patients with solid tumor. Cancer Res. 83 (7_Suppl.), 4298–4298. doi: 10.1158/1538-7445.AM2023-4298

Crossref Full Text | Google Scholar

Fan, Z., Jiang, Z., Liang, H., and Han, C. (2023). Pancancer survival prediction using a deep learning architecture with multimodal representation and integration. Bioinformat. Adv. 3:vbad006. doi: 10.1093/bioadv/vbad006

PubMed Abstract | Crossref Full Text | Google Scholar

Farahani, N. Z., Enayati, M., Pumarejo, A., Aguirre, M. A., Scott, C., Siontis, K., et al. (2023). Arrhythmic sudden death survival prediction model for hypertrophic cardiomyopathy patients: an interpretable machine learning analysis. Front. Biomed. Devices 86731:V001T01A004. doi: 10.1115/DMD2023-2989

Crossref Full Text | Google Scholar

Farrokhi, M., Taheri, F., Khouzani, P. J., Rahmani, E., Tavakoli, R., Fard, A. M., et al. (2023). Role of precision medicine and personalized medicine in the treatment of diseases. Kindle 3, 1–164.

Google Scholar

Feldner-Busztin, D., Firbas Nisantzis, P., Edmunds, S. J., Boza, G., Racimo, F., Gopalakrishnan, S., et al. (2023). Dealing with dimensionality: the application of machine learning to multi-omics data. Bioinformatics 39:btad021. doi: 10.1093/bioinformatics/btad021

PubMed Abstract | Crossref Full Text | Google Scholar

Feng, Y., Leung, A. A., Lu, X., Liang, Z., Quan, H., and Walker, R. L. (2022). Personalized prediction of incident hospitalization for cardiovascular disease in patients with hypertension using machine learning. BMC Med. Res. Methodol. 22, 1–11. doi: 10.1186/s12874-022-01814-3

PubMed Abstract | Crossref Full Text | Google Scholar

Fiteni, F., Westeel, V., Pivot, X., Borg, C., Vernerey, D., and Bonnetain, F. (2014). Endpoints in cancer clinical trials. J. Visc. Surg. 151, 17–22. doi: 10.1016/j.jviscsurg.2013.10.001

PubMed Abstract | Crossref Full Text | Google Scholar

Fornili, M., Ambrogi, F., Boracchi, P., and Biganzoli, E. (2014). “Piecewise exponential artificial neural networks (peann) for modeling hazard function with right censored data,” in Computational Intelligence Methods for Bioinformatics and Biostatistics: 10th International Meeting, CIBB 2013, Nice, France, June 20-22, 2013, Revised Selected Papers 10 (Cham: Springer), 125–136.

Google Scholar

Fotso, S. (2018). Deep neural networks for survival analysis based on a multi-task framework. arXiv [preprint]. doi: 10.48550/arXiv.1801.05512

Crossref Full Text | Google Scholar

Fotso, S. (2019). PySurvival: Open Source Package for Survival Analysis Modeling.

Google Scholar

García-Laencina, P. J., Abreu, P. H., Abreu, M. H., and Afonoso, N. (2015). Missing data imputation on the 5-year survival prediction of breast cancer patients with unknown discrete values. Comput. Biol. Med. 59, 125–133. doi: 10.1016/j.compbiomed.2015.02.006

PubMed Abstract | Crossref Full Text | Google Scholar

Gastinel, L. N. (2012). Principal Component Analysis in the Era of « Omics» Data. Principle Component Analysis—Multidisciplinary Applications. Rijeka: InTech, 21–42.

Google Scholar

Gensheimer, M. F., and Narasimhan, B. (2019). A scalable discrete-time survival model for neural networks. PeerJ 7:e6257. doi: 10.7717/peerj.6257

PubMed Abstract | Crossref Full Text | Google Scholar

Gerds, T. A., and Schumacher, M. (2006). Consistent estimation of the expected brier score in general survival models with right-censored event times. Biom. J. 48, 1029–1040. doi: 10.1002/bimj.200610301

PubMed Abstract | Crossref Full Text | Google Scholar

Glare, P., Virik, K., Jones, M., Hudson, M., Eychmuller, S., Simes, J., et al. (2003). A systematic review of physicians' survival predictions in terminally ill cancer patients. BMJ 327:195. doi: 10.1136/bmj.327.7408.195

PubMed Abstract | Crossref Full Text | Google Scholar

Goldman, M., Craft, B., Hastie, M., Repečka, K., McDade, F., Kamath, A., et al. (2018). The ucsc xena platform for public and private cancer genomics data visualization and interpretation. biorxiv 326470. doi: 10.1101/326470

Crossref Full Text | Google Scholar

Grever, M. R., Schepartz, S. A., and Chabner, B. A. (1992). The national cancer institute: cancer drug discovery and development program. Semin. Oncol. 19, 622–638.

Google Scholar

Guan, F., Ni, T., Zhu, W., Williams, L. K., Cui, L.-B., Li, M., et al. (2022). Integrative omics of schizophrenia: from genetic determinants to clinical classification and risk prediction. Mol. Psychiatry 27, 113–126. doi: 10.1038/s41380-021-01201-2

PubMed Abstract | Crossref Full Text | Google Scholar

Gupta, V., Coburn, N., Kidane, B., Hess, K. R., Compton, C., Ringash, J., et al. (2018). Survival prediction tools for esophageal and gastroesophageal junction cancer: a systematic review. J. Thorac. Cardiovasc. Surg. 156, 847–856. doi: 10.1016/j.jtcvs.2018.03.146

PubMed Abstract | Crossref Full Text | Google Scholar

Gyawali, B., Eisenhauer, E., Tregear, M., and Booth, C. M. (2022). Progression-free survival: it is time for a new name. Lancet Oncol. 23, 328–330. doi: 10.1016/S1470-2045(22)00015-8

PubMed Abstract | Crossref Full Text | Google Scholar

Haendel, M., Vasilevsky, N., Unni, D., Bologa, C., Harris, N., Rehm, H., et al. (2020). How many rare diseases are there? Nat. Rev. Drug Discov. 19, 77–78. doi: 10.1038/d41573-019-00180-y

PubMed Abstract | Crossref Full Text | Google Scholar

Han, M., He, J., and Jiao, X. (2022). “Research on prognostic risk assessment algorithm based on graph neural networks and attention mechanisms,” in 2022 International Conference on Information Technology, Communication Ecosystem and Management (ITCEM) (New York, NY: IEEE), 101–106.

Google Scholar

Hao, Y., Jing, X.-Y., and Sun, Q. (2023). Cancer survival prediction by learning comprehensive deep feature representation for multiple types of genetic data. BMC bioinformatics 24, 267. doi: 10.21203/rs.3.rs-2560223/v1

Crossref Full Text | Google Scholar

Hartman, N., Kim, S., He, K., and Kalbfleisch, J. D. (2023). Pitfalls of the concordance index for survival outcomes. Stat. Med. 42, 2179–2190. doi: 10.1002/sim.9717

PubMed Abstract | Crossref Full Text | Google Scholar

Hathaway, Q., Yanamala, N., Budoff, M., Sengupta, P., and Zeby, I. (2021). Cardiovascular risk stratification through deep neural survival networks-the multi-ethnic study of atherosclerosis (mesa). J. Am. Coll. Cardiol. 77(18_Suppl_1), 561–561. doi: 10.1016/S0735-1097(21)01920-3

PubMed Abstract | Crossref Full Text | Google Scholar

Hathaway, Q. A., Yanamala, N., Budoff, M. J., Sengupta, P. P., and Zeb, I. (2021). Deep neural survival networks for cardiovascular risk prediction: The multi-ethnic study of atherosclerosis (mesa). Comput. Biol. Med. 139:104983. doi: 10.1016/j.compbiomed.2021.104983

PubMed Abstract | Crossref Full Text | Google Scholar

Heagerty, P. J., Lumley, T., and Pepe, M. S. (2000). Time-dependent roc curves for censored survival data and a diagnostic marker. Biometrics 56, 337–344. doi: 10.1111/j.0006-341X.2000.00337.x

PubMed Abstract | Crossref Full Text | Google Scholar

Herrmann, M., Probst, P., Hornung, R., Jurinovic, V., and Boulesteix, A.-L. (2021). Large-scale benchmark study of survival prediction methods using multi-omics data. Brief. Bioinformat. 22:bbaa167. doi: 10.1093/bib/bbaa167

PubMed Abstract | Crossref Full Text | Google Scholar

Hira, M. T., Razzaque, M., Angione, C., Scrivens, J., Sawan, S., and Sarker, M. (2021). Integrated multi-omics analysis of ovarian cancer using variational autoencoders. Sci. Rep. 11:6265. doi: 10.1038/s41598-021-85285-4

PubMed Abstract | Crossref Full Text | Google Scholar

Hu, Q., Wang, Y., Zhang, Y., Ge, Y., Yin, Y., and Zhu, H. (2021a). A new HPV score system predicts the survival of patients with cervical cancers. Front. Genet. 12:747090. doi: 10.3389/fgene.2021.747090

PubMed Abstract | Crossref Full Text | Google Scholar

Hu, S., Fridgeirsson, E., van Wingen, G., and Welling, M. (2021b). “Transformer-based deep survival analysis,” in Survival Prediction-Algorithms, Challenges and Applications (PMLR, AAAI Spring Symposium Series California), 132–148.

Google Scholar

Ishak, K. J., Kreif, N., Benedict, A., and Muszbek, N. (2013). Overview of parametric survival analysis for health-economic applications. Pharmacoeconomics 31, 663–675. doi: 10.1007/s40273-013-0064-3

PubMed Abstract | Crossref Full Text | Google Scholar

Ishwaran, H., Kogalur, U. B., Blackstone, E. H., and Lauer, M. S. (2008). Random survival forests. Ann. Appl. Stat. 2, 841–860. doi: 10.1214/08-AOAS169

Crossref Full Text | Google Scholar

Jackson, C. H. (2016). flexsurv: a platform for parametric survival modeling in R. J. Stat. Softw. 70:i08. doi: 10.18637/jss.v070.i08

PubMed Abstract | Crossref Full Text | Google Scholar

Jamison, D. T. (2018). Disease control priorities: improving health and reducing poverty. Lancet 391, e11—e14. doi: 10.1016/S0140-6736(15)60097-6

PubMed Abstract | Crossref Full Text | Google Scholar

Jensen, M. A., Ferretti, V., Grossman, R. L., and Staudt, L. M. (2017). The NCI genomic data commons as an engine for precision medicine. Blood 130, 453–459. doi: 10.1182/blood-2017-03-735654

PubMed Abstract | Crossref Full Text | Google Scholar

Jiang, A., Bao, Y., Wang, A., Gong, W., Gan, X., Wang, J., et al. (2022). Establishment of a prognostic prediction and drug selection model for patients with clear cell renal cell carcinoma by multiomics data analysis. Oxid. Med. Cell. Longev. 2022:3617775. doi: 10.1155/2022/3617775

PubMed Abstract | Crossref Full Text | Google Scholar

Jiang, F., Jiang, Y., Zhi, H., Dong, Y., Li, H., Ma, S., et al. (2017). Artificial intelligence in healthcare: past, present and future. Stroke Vasc. Neurol. 2:101. doi: 10.1136/svn-2017-000101

PubMed Abstract | Crossref Full Text | Google Scholar

Jiang, Y., Alford, K., Ketchum, F., Tong, L., and Wang, M. D. (2020). ‘TLSurv: integrating multi-omics data by multi-stage transfer learning for cancer survival prediction,” in Proceedings of the 11th ACM International Conference on Bioinformatics, Computational Biology and Health Informatics (ACM), 1–10.

Google Scholar

Jiang, Z. (2022). CoxNAMS: Interpretable Deep Learning Model for Survival Analysis (Master's thesis). ETH Zurich.

Google Scholar

Jung, J.-O., Crnovrsanin, N., Wirsik, N. M., Nienhüser, H., Peters, L., Popp, F., et al. (2023). Machine learning for optimized individual survival prediction in resectable upper gastrointestinal cancer. J. Cancer Res. Clin. Oncol. 149, 1691–1702. doi: 10.1007/s00432-022-04063-5

PubMed Abstract | Crossref Full Text | Google Scholar

Kamps, R., Brandão, R. D., van den Bosch, B. J., Paulussen, A. D., Xanthoulea, S., Blok, M. J., et al. (2017). Next-generation sequencing in oncology: genetic diagnosis, risk prediction and cancer classification. Int. J. Mol. Sci. 18:308. doi: 10.3390/ijms18020308

PubMed Abstract | Crossref Full Text | Google Scholar

Kantidakis, G., Hazewinkel, A.-D., and Fiocco, M. (2022). Neural networks for survival prediction in medicine using prognostic factors: a review and critical appraisal. Comput. Math. Methods Med. 2022:1176060. doi: 10.1155/2022/1176060

PubMed Abstract | Crossref Full Text | Google Scholar

Kantidakis, G., Putter, H., Lancia, C., de Boer, J., Braat, A. E., Fiocco, M., et al. (2020). Survival prediction models since liver transplantation-comparisons between Cox models and machine learning techniques. BMC Med. Res. Methodol. 20, 1–14. doi: 10.1186/s12874-020-01153-1

PubMed Abstract | Crossref Full Text | Google Scholar

Katzman, J. L., Shaham, U., Cloninger, A., Bates, J., Jiang, T., and Kluger, Y. (2018). DeepSurv: personalized treatment recommender system using a cox proportional hazards deep neural network. BMC Med. Res. Methodol. 18, 1–12. doi: 10.1186/s12874-018-0482-1

PubMed Abstract | Crossref Full Text | Google Scholar

Kaur, I., Doja, M., and Ahmad, T. (2022). Data mining and machine learning in cancer survival research: an overview and future recommendations. J. Biomed. Inform. 128:104026. doi: 10.1016/j.jbi.2022.104026

PubMed Abstract | Crossref Full Text | Google Scholar

Kazerooni, A. F., Saxena, S., Toorens, E., Tu, D., Bashyam, V., Akbari, H., et al. (2021). Multi-omic prediction of overall survival in patients with glioblastoma: additive and synergistic value of clinical measures, radiomics, and genomics. Nat. Sci. Rep. doi: 10.21203/rs.3.rs-908405/v1

PubMed Abstract | Crossref Full Text | Google Scholar

Khan, F. M., and Zubek, V. B. (2008). “Support vector regression for censored data (SVRc): a novel tool for survival analysis,” in 2008 Eighth IEEE International Conference on Data Mining (New Jersey, NJ: IEEE), 863–868.

Google Scholar

Kim, S. Y. (2023). GNN-surv: discrete-time survival prediction using graph neural networks. Bioengineering 10:1046. doi: 10.3390/bioengineering10091046

PubMed Abstract | Crossref Full Text | Google Scholar

Kirpich, A., Ainsworth, E. A., Wedow, J. M., Newman, J. R., Michailidis, G., and McIntyre, L. M. (2018). Variable selection in omics data: a practical evaluation of small sample sizes. PLoS ONE 13:e0197910. doi: 10.1371/journal.pone.0197910

PubMed Abstract | Crossref Full Text | Google Scholar

Kleinbaum, D. G., and Klein, M. (1996). Survival Analysis a Self-Learning Text. New York, NY: Springer.

PubMed Abstract | Google Scholar

Kosorok, M. R., and Laber, E. B. (2019). Precision medicine. Ann. Rev. Stat. Appl. 6, 263–286. doi: 10.1146/annurev-statistics-030718-105251

PubMed Abstract | Crossref Full Text | Google Scholar

Kourou, K., Exarchos, T. P., Exarchos, K. P., Karamouzis, M. V., and Fotiadis, D. I. (2015). Machine learning applications in cancer prognosis and prediction. Comput. Struct. Biotechnol. J. 13, 8–17. doi: 10.1016/j.csbj.2014.11.005

PubMed Abstract | Crossref Full Text | Google Scholar

Kresoja, K.-P., Unterhuber, M., Wachter, R., Thiele, H., and Lurz, P. (2023). A cardiologist's guide to machine learning in cardiovascular disease prognosis prediction. Basic Res. Cardiol. 118:10. doi: 10.1007/s00395-023-00982-7

PubMed Abstract | Crossref Full Text | Google Scholar

Krzyziński, M., Spytek, M., Baniecki, H., and Biecek, P. (2023). SurvSHAP (t): time-dependent explanations of machine learning survival models. Knowl. Based Syst. 262:110234. doi: 10.1016/j.knosys.2022.110234

PubMed Abstract | Crossref Full Text | Google Scholar

Kubi, M. G., Lasisi, K., and Rasheed, B. A. (2022). Parametric and semi-parametric survival models with application to diabetes data. Sci. J. Biomed. Eng. Biomed. Sci. 3, 001–010.

Google Scholar

Kvamme, H., and Borgan, Ø. (2019a). The brier score under administrative censoring: problems and solutions. arXiv [preprint]. doi: 10.48550/arXiv.1912.08581

Crossref Full Text | Google Scholar

Kvamme, H., and Borgan, Ø. (2019b). Continuous and discrete-time survival prediction with neural networks. arXiv [preprint]. doi: 10.48550/arXiv.1910.06724

Crossref Full Text | Google Scholar

Kvamme, H., and Borgan, Ø. (2021). Continuous and discrete-time survival prediction with neural networks. Lifetime Data Anal. 27, 710–736. doi: 10.1007/s10985-021-09532-6

PubMed Abstract | Crossref Full Text | Google Scholar

Kvamme, H., Borgan, Ø., and Scheel, I. (2019). Time-to-event prediction with neural networks and cox regression. arXiv [preprint]. doi: 10.48550/arXiv.1907.00825

Crossref Full Text | Google Scholar

Lang, T., Yang, M., Xia, Y., Liu, J., Li, Y., Yang, L., et al. (2023). Development of a molecular feature-based survival prediction model of ovarian cancer using the deep neural network. Genes Dis. 10:1190. doi: 10.1016/j.gendis.2022.10.011

PubMed Abstract | Crossref Full Text | Google Scholar

LeCun, Y., Bengio, Y., and Hinton, G. (2015). Deep learning. Nature 521, 436–444. doi: 10.1038/nature14539

PubMed Abstract | Crossref Full Text | Google Scholar

Lee, C., Zame, W., Yoon, J., and Van Der Schaar, M. (2018). Deephit: a deep learning approach to survival analysis with competing risks. Proc. AAAI Conf. Artif. Intell. 32:11842. doi: 10.1609/aaai.v32i1.11842

PubMed Abstract | Crossref Full Text | Google Scholar

Lee, C.-J., Baek, B., Cho, S. H., Jang, T.-Y., Jeon, S.-E., Lee, S., et al. (2023). Machine learning with in silico analysis markedly improves survival prediction modeling in colon cancer patients. Cancer Med. 12, 7603–7615. doi: 10.1002/cam4.5420

PubMed Abstract | Crossref Full Text | Google Scholar

Lee, E. T., and Wang, J. (2003). Statistical Methods for Survival Data Analysis, Volume 476. Hoboken, NJ: John Wiley & Sons.

Google Scholar

Lee, S., and Lim, H. (2019). Review of statistical methods for survival analysis using genomic data. Genom. Inf. 17:e41. doi: 10.5808/GI.2019.17.4.e41

PubMed Abstract | Crossref Full Text | Google Scholar

Lee, T.-Y., Huang, K.-Y., Chuang, C.-H., Lee, C.-Y., and Chang, T.-H. (2020). Incorporating deep learning and multi-omics autoencoding for analysis of lung adenocarcinoma prognostication. Comput. Biol. Chem. 87:107277. doi: 10.1016/j.compbiolchem.2020.107277

PubMed Abstract | Crossref Full Text | Google Scholar

Leung, K.-M., Elashoff, R. M., and Afifi, A. A. (1997). Censoring issues in survival analysis. Annu. Rev. Public Health 18, 83–104. doi: 10.1146/annurev.publhealth.18.1.83

PubMed Abstract | Crossref Full Text | Google Scholar

Li, R., Wang, S., Cui, Y., Qu, H., Chater, J. M., Zhang, L., et al. (2021). Extended application of genomic selection to screen multiomics data for prognostic signatures of prostate cancer. Brief. Bioinformat. 22:bbaa197. doi: 10.1093/bib/bbaa197

PubMed Abstract | Crossref Full Text | Google Scholar

Li, X., Chen, Y., Sun, A., Wang, Y., Liu, Y., and Lei, H. (2023). Development and validation of prediction model for overall survival in patients with lymphoma: a prospective cohort study in china. BMC Med. Inform. Decis. Mak. 23, 1–11. doi: 10.1186/s12911-023-02198-0

PubMed Abstract | Crossref Full Text | Google Scholar

Li, Y., Sun, R., Zhang, Y., Yuan, Y., and Miao, Y. (2020). A methylation-based mRNA signature predicts survival in patients with gastric cancer. Cancer Cell Int. 20, 1–10. doi: 10.1186/s12935-020-01374-w

PubMed Abstract | Crossref Full Text | Google Scholar

Liberzon, A., Subramanian, A., Pinchback, R., Thorvaldsdóttir, H., Tamayo, P., and Mesirov, J. P. (2011). Molecular signatures database (MSigDB) 3.0. Bioinformatics 27, 1739–1740. doi: 10.1093/bioinformatics/btr260

PubMed Abstract | Crossref Full Text | Google Scholar

Lin, Z., He, Y., Qiu, C., Yu, Q., Huang, H., Zhang, Y., et al. (2022). A multi-omics signature to predict the prognosis of invasive ductal carcinoma of the breast. Comput. Biol. Med. 151:106291. doi: 10.1016/j.compbiomed.2022.106291

PubMed Abstract | Crossref Full Text | Google Scholar

Liu, J., Lichtenberg, T., Hoadley, K. A., Poisson, L. M., Lazar, A. J., Cherniack, A. D., et al. (2018). An integrated TCGA pan-cancer clinical data resource to drive high-quality survival outcome analytics. Cell 173, 400–416. doi: 10.1016/j.cell.2018.02.052

PubMed Abstract | Crossref Full Text | Google Scholar

Lun, Y., Yuan, H., Ma, P., Chen, J., Lu, P., Wang, W., et al. (2024). A prediction model based on random survival forest analysis of the overall survival of elderly female papillary thyroid carcinoma patients: a seer-based study. Endocrine 1–9. doi: 10.1007/s12020-024-03797-1

PubMed Abstract | Crossref Full Text | Google Scholar

Lv, J., Wang, J., Shang, X., Liu, F., and Guo, S. (2020). Survival prediction in patients with colon adenocarcinoma via multiomics data integration using a deep learning algorithm. Biosci. Rep. 40:BSR20201482. doi: 10.1042/BSR20201482

PubMed Abstract | Crossref Full Text | Google Scholar

Lynch, C. M., Abdollahi, B., Fuqua, J. D., De Carlo, A. R., Bartholomai, J. A., Balgemann, R. N., et al. (2017). Prediction of lung cancer patient survival via supervised machine learning classification techniques. Int. J. Med. Inform. 108, 1–8. doi: 10.1016/j.ijmedinf.2017.09.013

PubMed Abstract | Crossref Full Text | Google Scholar

Ma, B., Yan, G., Chai, B., and Hou, X. (2022). XGBLC: an improved survival prediction model based on XGBoost. Bioinformatics 38, 410–418. doi: 10.1093/bioinformatics/btab675

PubMed Abstract | Crossref Full Text | Google Scholar

Majji, R., Rajeswari, R., Vidyadhari, C., and Cristin, R. (2023). Squirrel search deer hunting-based deep recurrent neural network for survival prediction using pan-cancer gene expression data. Comp. J. 66, 245–266. doi: 10.1093/comjnl/bxab158

Crossref Full Text | Google Scholar

Malik, V., Kalakoti, Y., and Sundar, D. (2021). Deep learning assisted multi-omics integration for survival and drug-response prediction in breast cancer. BMC Genom. 22, 1–11. doi: 10.1186/s12864-021-07524-2

PubMed Abstract | Crossref Full Text | Google Scholar

Manganaro, L., Sabbatini, G., Bianco, S., Bironzo, P., Borile, C., Colombi, D., et al. (2023). Non-small cell lung cancer survival estimation through multi-omic two-layer SVM: a multi-omics and multi-sources integrative model. Curr. Bioinform. 18, 658–669. doi: 10.2174/1574893618666230502102712

Crossref Full Text | Google Scholar

McKinney, W., Perktold, J., and Seabold, S. (2011). Time series analysis in python with statsmodels. Jarrodmillman Com. 96–102. doi: 10.25080/Majora-ebaa42b7-012

Crossref Full Text | Google Scholar

Miao, S., Lei, H., Li, X., Zhou, W., Wang, G., Sun, A., et al. (2022). Development and validation of a risk prediction model for overall survival in patients with nasopharyngeal carcinoma: a prospective cohort study in china. Cancer Cell Int. 22, 1–11. doi: 10.1186/s12935-022-02776-8

PubMed Abstract | Crossref Full Text | Google Scholar

Mirbabaie, M., Stieglitz, S., and Frick, N. R. (2021). Artificial intelligence in disease diagnostics: a critical review and classification on the current state of research guiding future direction. Health Technol. 11, 693–731. doi: 10.1007/s12553-021-00555-5

Crossref Full Text | Google Scholar

Misra, B. B., Langefeld, C., Olivier, M., and Cox, L. A. (2019). Integrated omics: tools, advances and future approaches. J. Mol. Endocrinol. 62, R21—R45. doi: 10.1530/JME-18-0055

PubMed Abstract | Crossref Full Text | Google Scholar

Mo, L., Su, Y., Yuan, J., Xiao, Z., Zhang, Z., Lan, X., et al. (2022). Comparisons of forecasting for survival outcome for head and neck squamous cell carcinoma by using machine learning models based on multi-omics. Curr. Genom. 23:94. doi: 10.2174/1389202923666220204153744

PubMed Abstract | Crossref Full Text | Google Scholar

Moher, D., Liberati, A., Tetzlaff, J., Altman, D. G., Group, P., et al. (2010). Preferred reporting items for systematic reviews and meta-analyses: the prisma statement. Int. J. Surg. 8, 336–341. doi: 10.1016/j.ijsu.2010.02.007

PubMed Abstract | Crossref Full Text | Google Scholar

Moreno-Sanchez, P. A. (2023). Improvement of a prediction model for heart failure survival through explainable artificial intelligence. Front. Cardiovasc. Med. 10:1219586. doi: 10.3389/fcvm.2023.1219586

PubMed Abstract | Crossref Full Text | Google Scholar

Murphy, S. (1995). Likelihood ratio-based confidence intervals in survival analysis. J. Am. Stat. Assoc. 90, 1399–1405. doi: 10.1080/01621459.1995.10476645

Crossref Full Text | Google Scholar

Murthy, D. P., Xie, M., and Jiang, R. (2004). Weibull Models. Hoboken, NJ: John Wiley & Sons.

Google Scholar

Nariya, M. K., Mills, C. E., Sorger, P. K., and Sokolov, A. (2023). Paired evaluation of machine-learning models characterizes effects of confounders and outliers. Patterns 4:100791. doi: 10.1016/j.patter.2023.100791

PubMed Abstract | Crossref Full Text | Google Scholar

National Research Council (US) (2010). Research at the Intersection of the Physical and Life Sciences. Washington, DC.

Google Scholar

Ni, A., and Qin, L.-X. (2021). Performance evaluation of transcriptomics data normalization for survival risk prediction. Brief. Bioinf. 22:bbab257. doi: 10.1093/bib/bbab257

PubMed Abstract | Crossref Full Text | Google Scholar

Othman, N. A., Abdel-Fattah, M. A., and Ali, A. T. (2023). A hybrid deep learning framework with decision-level fusion for breast cancer survival prediction. Big Data Cogn. Comp. 7:50. doi: 10.3390/bdcc7010050

Crossref Full Text | Google Scholar

Owens, A. R., McInerney, C. E., Prise, K. M., McArt, D. G., and Jurek-Loughrey, A. (2021). Novel deep learning-based solution for identification of prognostic subgroups in liver cancer (hepatocellular carcinoma). BMC Bioinform. 22, 1–22. doi: 10.1186/s12859-021-04454-4

PubMed Abstract | Crossref Full Text | Google Scholar

Palmal, S., Arya, N., Saha, S., and Tripathy, S. (2023). Breast cancer survival prognosis using the graph convolutional network with choquet fuzzy integral. Sci. Rep. 13:14757. doi: 10.1038/s41598-023-40341-z

PubMed Abstract | Crossref Full Text | Google Scholar

Pant, S., Kang, S.-R., Lee, M., Phuc, P.-S., Yang, H.-J., and Yang, D.-H. (2023). Survival prediction using transformer-based categorical feature representation in the treatment of diffuse large b-cell lymphoma. Healthcare 11:1171. doi: 10.3390/healthcare11081171

PubMed Abstract | Crossref Full Text | Google Scholar

Pawar, A., Chowdhury, O. R., Chauhan, R., Talole, S., and Bhattacharjee, A. (2022). Identification of key gene signatures for the overall survival of ovarian cancer. J. Ovar. Res. 15, 1–13. doi: 10.1186/s13048-022-00942-0

PubMed Abstract | Crossref Full Text | Google Scholar

Pellegrini, M. (2023). Accurate prognosis for localized prostate cancer through coherent voting networks with multi-omic and clinical data. Sci. Rep. 13:7875. doi: 10.1038/s41598-023-35023-9

PubMed Abstract | Crossref Full Text | Google Scholar

Pobar, I., Job, M., Holt, T., Hargrave, C., and Hickey, B. (2021). Prognostic tools for survival prediction in advanced cancer patients: a systematic review. J. Med. Imaging Radiat. Oncol. 65, 806–816. doi: 10.1111/1754-9485.13185

PubMed Abstract | Crossref Full Text | Google Scholar

Poirion, O. B., Jing, Z., Chaudhary, K., Huang, S., and Garmire, L. X. (2021). Deepprog: an ensemble of deep-learning and machine-learning models for prognosis prediction using multi-omics data. Genome Med. 13, 1–15. doi: 10.1186/s13073-021-00930-x

PubMed Abstract | Crossref Full Text | Google Scholar

Pölsterl, S. (2020). scikit-survival: a library for time-to-event analysis built on top of scikit-learn. J. Mach. Learn. Res. 21, 8747–8752.

Google Scholar

Qian, X., Keerman, M., Zhang, X., Guo, H., He, J., Maimaitijiang, R., et al. (2023). Study on the prediction model of atherosclerotic cardiovascular disease in the rural xinjiang population based on survival analysis. BMC Public Health 23, 1–11. doi: 10.1186/s12889-023-15630-x

PubMed Abstract | Crossref Full Text | Google Scholar

Rahimi, M., Akbari, A., Asadi, F., and Emami, H. (2023). Cervical cancer survival prediction by machine learning algorithms: a systematic. BMC Cancer 23:341. doi: 10.1186/s12885-023-10808-3

PubMed Abstract | Crossref Full Text | Google Scholar

Rahman, S. A., Walker, R. C., Maynard, N., Trudgill, N., Crosby, T., Cromwell, D. A., et al. (2023). The augis survival predictor: prediction of long-term and conditional survival after esophagectomy using random survival forests. Ann. Surg. 277, 267–274. doi: 10.1097/SLA.0000000000004794

PubMed Abstract | Crossref Full Text | Google Scholar

Raju, J., and Sathyalakshmi, S. (2023). “Long-term survival prediction of liver transplantation using deep learning techniques,” in 2023 2nd International Conference on Computational Systems and Communication (ICCSC) (New Jersey, NJ: IEEE), 1–6.

Google Scholar

Raufaste-Cazavieille, V., Santiago, R., and Droit, A. (2022). Multi-omics analysis: paving the path toward achieving precision medicine in cancer treatment and immuno-oncology. Front. Mol. Biosci. 9:962743. doi: 10.3389/fmolb.2022.962743

PubMed Abstract | Crossref Full Text | Google Scholar

Redekar, S. S., Varma, S. L., and Bhattacharjee, A. (2022). Identification of key genes associated with survival of glioblastoma multiforme using integrated analysis of tcga datasets. Comp. Methods Progr. Biomed. Update 2:100051. doi: 10.1016/j.cmpbup.2022.100051

PubMed Abstract | Crossref Full Text | Google Scholar

Richard, V. R., Gaither, C., Popp, R., Chaplygina, D., Brzhozovskiy, A., Kononikhin, A., et al. (2022). Early prediction of covid-19 patient survival by targeted plasma multi-omics and machine learning. Mol. Cell. Proteom. 21:100277. doi: 10.1016/j.mcpro.2022.100277

PubMed Abstract | Crossref Full Text | Google Scholar

Salerno, S., and Li, Y. (2023). High-dimensional survival analysis: methods and applications. Ann. Rev. Stat. Appl. 10, 25–49. doi: 10.1146/annurev-statistics-032921-022127

PubMed Abstract | Crossref Full Text | Google Scholar

Sargent, D. J., Wieand, H. S., Haller, D. G., Gray, R., Benedetti, J. K., Buyse, M., et al. (2005). Disease-free survival versus overall survival as a primary end point for adjuvant colon cancer studies: individual patient data from 20,898 patients on 18 randomized trials. J. Clin. Oncol. 23, 8664–8670. doi: 10.1200/JCO.2005.01.6071

PubMed Abstract | Crossref Full Text | Google Scholar

Sarma, A., Calfee, C. S., and Ware, L. B. (2020). Biomarkers and precision medicine: state of the art. Crit. Care Clin. 36, 155–165. doi: 10.1016/j.ccc.2019.08.012

PubMed Abstract | Crossref Full Text | Google Scholar

Schumacher, M., Graf, E., and Gerds, T. (2003). How to assess prognostic models for survival data: a case study in oncology. Methods Inf. Med. 42, 564–571. doi: 10.1055/s-0038-1634384

PubMed Abstract | Crossref Full Text | Google Scholar

Sellin, J. A. (2015). Does one size fit all? Patents, the right to health and access to medicines. Netherlands Int. Law Rev. 62, 445–473. doi: 10.1007/s40802-015-0047-5

Crossref Full Text | Google Scholar

Shen, J., Zhang, C. J., Jiang, B., Chen, J., Song, J., Liu, Z., et al. (2019). Artificial intelligence versus clinicians in disease diagnosis: systematic review. JMIR Med. Inf. 7:e10010. doi: 10.2196/10010

PubMed Abstract | Crossref Full Text | Google Scholar

Shetty, K. S., Jose, A., Bani, M., and Vinod, P. (2023). Network diffusion-based approach for survival prediction and identification of biomarkers using multi-omics data of papillary renal cell carcinoma. Mol. Genet. Genom. 298, 1–12. doi: 10.1007/s00438-023-02022-4

PubMed Abstract | Crossref Full Text | Google Scholar

Shivaswamy, P. K., Chu, W., and Jansche, M. (2007). “A support vector approach to censored targets,” in Seventh IEEE International Conference on Data Mining (ICDM 2007) (New Jersey, NJ: IEEE), 655–660.

Google Scholar

Simino, J. M. (2009). Discrimination and Calibration of Prognostic Survival Models. The Florida State University.

Google Scholar

Sinha, D., and Dey, D. K. (1997). Semiparametric bayesian analysis of survival data. J. Am. Stat. Assoc. 92, 1195–1212. doi: 10.1080/01621459.1997.10474077

Crossref Full Text | Google Scholar

Sonabend, R., Király, F. J., Bender, A., Bischl, B., and Lang, M. (2021). mlr3proba: an R package for machine learning in survival analysis. Bioinformatics 37, 2789–2791. doi: 10.1093/bioinformatics/btab039

PubMed Abstract | Crossref Full Text | Google Scholar

Spytek, M., Krzyziński, M., Langbein, S. H., Baniecki, H., Wright, M. N., and Biecek, P. (2023). survex: an R package for explaining machine learning survival models. arXiv [preprint]. arXiv:2308.16113. doi: 10.1093/bioinformatics/btad723

PubMed Abstract | Crossref Full Text | Google Scholar

Stanfill, A. G., and Cao, X. (2021). Enhancing research through the use of the genotype-tissue expression (gtex) database. Biol. Res. Nurs. 23, 533–540. doi: 10.1177/1099800421994186

PubMed Abstract | Crossref Full Text | Google Scholar

Stevenson, M., and EpiCentre, I. (2009). An Introduction to Survival Analysis. Palmerston North: EpiCentre, IVABS, Massey University.

Google Scholar

Tan, K., Huang, W., Hu, J., and Dong, S. (2020). A multi-omics supervised autoencoder for pan-cancer clinical outcome endpoints prediction. BMC Med. Inform. Decis. Mak. 20, 1–9. doi: 10.1186/s12911-020-1114-3

PubMed Abstract | Crossref Full Text | Google Scholar

Tang, C., Yu, M., Ma, J., and Zhu, Y. (2021). Metabolic classification of bladder cancer based on multi-omics integrated analysis to predict patient prognosis and treatment response. J. Transl. Med. 19, 1–15. doi: 10.1186/s12967-021-02865-8

PubMed Abstract | Crossref Full Text | Google Scholar

Tarango, R., Hadjiiski, L., Alva, A., Chan, H.-P., Cohan, R. H., Caoili, E. M., et al. (2023). Survival prediction for patients with metastatic urothelial cancer after immunotherapy using machine learning. Med. Imaging 12465, 779–784. doi: 10.1117/12.2655482

PubMed Abstract | Crossref Full Text | Google Scholar

Tarkhan, A., Simon, N., Bengtsson, T., Nguyen, K., and Dai, J. (2021). “Survival prediction using deep learning,” in Survival Prediction-Algorithms, Challenges and Applications (PMLR, AAAI Spring Symposium Series California), 207–214.

Google Scholar

Terrematte, P., Andrade, D. S., Justino, J., Stransky, B., de Araújo, D. S. A., and Dória Neto, A. D. (2022). A novel machine learning 13-gene signature: Improving risk analysis and survival prediction for clear cell renal cell carcinoma patients. Cancers 14:2111. doi: 10.3390/cancers14092111

PubMed Abstract | Crossref Full Text | Google Scholar

Tewarie, I. A., Senders, J. T., Kremer, S., Devi, S., Gormley, W. B., Arnaout, O., et al. (2021). Survival prediction of glioblastoma patients—are we there yet? A systematic review of prognostic modeling for glioblastoma and its clinical potential. Neurosurg. Rev. 44, 2047–2057. doi: 10.1007/s10143-020-01430-z

PubMed Abstract | Crossref Full Text | Google Scholar

Therneau, T. M., Grambsch, P. M., Therneau, T. M., and Grambsch, P. M. (2000). The Cox Model. New York, NY: Springer.

Google Scholar

Therneau, T. M., and Lumley, T. (2015). Package ‘survival'. R. Top. Doc. 128, 28–33.

Google Scholar

Tomczak, K., Czerwińska, P., and Wiznerowicz, M. (2015). Review the cancer genome atlas (TCGA): an immeasurable source of knowledge. Contemp. Oncol. 2015, 68–77. doi: 10.5114/wo.2014.47136

PubMed Abstract | Crossref Full Text | Google Scholar

Tong, D., Tian, Y., Zhou, T., Ye, Q., Li, J., Ding, K., et al. (2020). Improving prediction performance of colon cancer prognosis based on the integration of clinical and multi-omics data. BMC Med. Inform. Decis. Mak. 20, 1–15. doi: 10.1186/s12911-020-1043-1

PubMed Abstract | Crossref Full Text | Google Scholar

Tong, L., Mitchel, J., Chatlin, K., and Wang, M. D. (2020). Deep learning based feature-level integration of multi-omics data for breast cancer patients survival analysis. BMC Med. Inform. Decis. Mak. 20, 1–12. doi: 10.1186/s12911-020-01225-8

PubMed Abstract | Crossref Full Text | Google Scholar

Tong, L., Wu, H., and Wang, M. D. (2021). Integrating multi-omics data by learning modality invariant representations for improved prediction of overall survival of cancer. Methods 189, 74–85. doi: 10.1016/j.ymeth.2020.07.008

PubMed Abstract | Crossref Full Text | Google Scholar

Tsimberidou, A.-M., Hong, D. S., Wheler, J. J., Falchook, G. S., Janku, F., Naing, A., et al. (2019). Long-term overall survival and prognostic score predicting survival: the impact study in precision medicine. J. Hematol. Oncol. 12, 1–12. doi: 10.1186/s13045-019-0835-1

PubMed Abstract | Crossref Full Text | Google Scholar

Unterhuber, M., Kresoja, K.-P., Rommel, K.-P., Besler, C., Baragetti, A., Klöting, N., et al. (2021). Proteomics-enabled deep learning machine algorithms can enhance prediction of mortality. J. Am. Coll. Cardiol. 78, 1621–1631. doi: 10.1016/j.jacc.2021.08.018

PubMed Abstract | Crossref Full Text | Google Scholar

Vahabi, N., McDonough, C. W., Desai, A. A., Cavallari, L. H., Duarte, J. D., and Michailidis, G. (2021). Cox-smbpls: an algorithm for disease survival prediction and multi-omics module discovery incorporating cis-regulatory quantitative effects. Front. Genet. 12:701405. doi: 10.3389/fgene.2021.701405

PubMed Abstract | Crossref Full Text | Google Scholar

Van Belle, V., Pelckmans, K., Suykens, J. A., and Van Huffel, S. (2007). “Support vector machines for survival analysis,” in Proceedings of the Third International Conference on Computational Intelligence in Medicine and Healthcare (cimed2007), 1–8.

Google Scholar

Van Buuren, S., Boshuizen, H. C., and Knook, D. L. (1999). Multiple imputation of missing blood pressure covariates in survival analysis. Stat. Med. 18, 681–694. doi: 10.1002/(SICI)1097-0258(19990330)18:6<681::AID-SIM71>3.0.CO;2-R

Crossref Full Text | Google Scholar

Vickers, A. J., and Elkin, E. B. (2006). Decision curve analysis: a novel method for evaluating prediction models. Med. Decis. Making 26, 565–574. doi: 10.1177/0272989X06295361

PubMed Abstract | Crossref Full Text | Google Scholar

Voet, D., Lin, P., Lichtenstein, L. R. Z. II., Saksena, G., Noble, M., Cibulskis, K., et al. (2022). Firehose: An Analysis Infrastructure. Harvard: Firehose Broad GDAC, Broad Institute of MIT, 1.

Google Scholar

Wang, C., Lue, W., Kaalia, R., Kumar, P., and Rajapakse, J. C. (2022). Network-based integration of multi-omics data for clinical outcome prediction in neuroblastoma. Sci. Rep. 12:15425. doi: 10.1038/s41598-022-19019-5

PubMed Abstract | Crossref Full Text | Google Scholar

Wang, J., Liu, Y., Zhang, R., Liu, Z., Yi, Z., Guan, X., et al. (2023). Multi-omics fusion analysis models with machine learning predict survival of HER2-negative metastatic breast cancer: a multicenter prospective observational study. Chin. Med. J. 136, 863–865. doi: 10.1097/CM9.0000000000002625

PubMed Abstract | Crossref Full Text | Google Scholar

Wang, Q., Yang, C., Kuo, C. S., Hsu, P., Chang, J.-C., and Wu, C. (2023). 572P multivariable five-year survival prediction model for prognosing patients with egfr-mutated nsclc treated with EGFR-TKIs. Ann. Oncol. 34:S1694. doi: 10.1016/j.annonc.2023.10.650

Crossref Full Text | Google Scholar

Wang, X., Chen, J., Lin, L., Li, Y., Tao, Q., Lang, Z., et al. (2023). Machine learning integrations develop an antigen-presenting-cells and T-cells-infiltration derived lncRNA signature for improving clinical outcomes in hepatocellular carcinoma. BMC Cancer 23, 1–16. doi: 10.1186/s12885-023-10766-w

PubMed Abstract | Crossref Full Text | Google Scholar

Wang, Z., Yan, R., Liu, J., Liu, Y., Ren, F., Zheng, C., et al. (2020). “An integration framework for liver cancer subtype classification and survival prediction based on multi-omics data,” in Intelligent Computing Methodologies: 16th International Conference, ICIC 2020, Bari, Italy, October 2-5, 2020, Proceedings, Part III 16 (Springer), 247–257.

PubMed Abstract | Google Scholar

Wekesa, J. S., and Kimwele, M. (2023). A review of multi-omics data integration through deep learning approaches for disease diagnosis, prognosis, and treatment. Front. Genet. 14:1199087. doi: 10.3389/fgene.2023.1199087

PubMed Abstract | Crossref Full Text | Google Scholar

Westerlund, A. M., Hawe, J. S., Heinig, M., and Schunkert, H. (2021). Risk prediction of cardiovascular events by exploration of molecular data with explainable artificial intelligence. Int. J. Mol. Sci. 22:10291. doi: 10.3390/ijms221910291

PubMed Abstract | Crossref Full Text | Google Scholar

Weston, S. J., Ritchie, S. J., Rohrer, J. M., and Przybylski, A. K. (2019). Recommendations for increasing the transparency of analysis of preexisting data sets. Adv. Methods Pract. Psychol. Sci. 2, 214–227. doi: 10.1177/2515245919848684

PubMed Abstract | Crossref Full Text | Google Scholar

Wiegrebe, S., Kopper, P., Sonabend, R., and Bender, A. (2023). Deep learning for survival analysis: a review. arXiv [preprint] arXiv:2305.14961. doi: 10.1007/s10462-023-10681-3

Crossref Full Text | Google Scholar

Willems, A., Panchy, N., and Hong, T. (2023). Using single-cell RNA sequencing and microrna targeting data to improve colorectal cancer survival prediction. Cells 12:228. doi: 10.3390/cells12020228

PubMed Abstract | Crossref Full Text | Google Scholar

Wissel, D., Janakarajan, N., Grover, A., Toniato, E., Martínez, M. R., and Boeva, V. (2022). Survboard: standardised benchmarking for multi-omics cancer survival models. bioRxiv. doi: 10.1101/2022.11.18.517043

PubMed Abstract | Crossref Full Text | Google Scholar

World Health Organization (2020). The Top 10 Causes of Death. Available online at: https://www.who.int/news-room/fact-sheets/detail/the-top-10-causes-of-death (accessed December 9, 2020).

Google Scholar

Wu, W., Wang, Y., Xiang, J., Li, X., Wahafu, A., Yu, X., et al. (2022). A novel multi-omics analysis model for diagnosis and survival prediction of lower-grade glioma patients. Front. Oncol. 12:729002. doi: 10.3389/fonc.2022.729002

PubMed Abstract | Crossref Full Text | Google Scholar

Wu, X., and Fang, Q. (2022). Stacked autoencoder based multi-omics data integration for cancer survival prediction. arXiv [preprint] arXiv:2207.04878. doi: 10.48550/arXiv.2207.04878

Crossref Full Text | Google Scholar

Wu, Z., Uhl, B., Gires, O., and Reichel, C. A. (2023). A transcriptomic pan-cancer signature for survival prognostication and prediction of immunotherapy response based on endothelial senescence. J. Biomed. Sci. 30:21. doi: 10.1186/s12929-023-00915-5

PubMed Abstract | Crossref Full Text | Google Scholar

Xu, Z., Arnold, M., Stevens, D., Kaptoge, S., Pennells, L., Sweeting, M. J., et al. (2021). Prediction of cardiovascular disease risk accounting for future initiation of statin treatment. Am. J. Epidemiol. 190, 2000–2014. doi: 10.1093/aje/kwab031

PubMed Abstract | Crossref Full Text | Google Scholar

Yang, H., Jin, W., Liu, H., Wang, X., Wu, J., Gan, D., et al. (2020). A novel prognostic model based on multi-omics features predicts the prognosis of colon cancer patients. Mol. Genet. Genom. Med. 8:e1255. doi: 10.1002/mgg3.1255

PubMed Abstract | Crossref Full Text | Google Scholar

Yang, Q., Xiong, Y., Jiang, N., Zeng, F., Huang, C., and Li, X. (2020). Integrating genomic data with transcriptomic data for improved survival prediction for adult diffuse glioma. J. Cancer 11:3794. doi: 10.7150/jca.44032

PubMed Abstract | Crossref Full Text | Google Scholar

Yin, Q., Chen, W., Zhang, C., and Wei, Z. (2022). A convolutional neural network model for survival prediction based on prognosis-related cascaded WX feature selection. Lab. Investig. 102, 1064–1074. doi: 10.1038/s41374-022-00801-y

PubMed Abstract | Crossref Full Text | Google Scholar

Yu, C.-N., Greiner, R., Lin, H.-C., and Baracos, V. (2011). Learning patient-specific cancer survival distributions as a sequence of dependent regressors. Adv. Neural Inf. Process. Syst. 24, 1845–1853.

Google Scholar

Yu, J., Wu, X., Lv, M., Zhang, Y., Zhang, X., Li, J., et al. (2020). A model for predicting prognosis in patients with esophageal squamous cell carcinoma based on joint representation learning. Oncol. Lett. 20, 1–10. doi: 10.3892/ol.2020.12250

PubMed Abstract | Crossref Full Text | Google Scholar

Zarean Shahraki, S., Azizmohammad Looha, M., Mohammadi kazaj, P., Aria, M., Akbari, A., Emami, H., et al. (2023). Time-related survival prediction in molecular subtypes of breast cancer using time-to-event deep-learning-based models. Front. Oncol. 13:1147604. doi: 10.3389/fonc.2023.1147604

PubMed Abstract | Crossref Full Text | Google Scholar

Zeng, W., Wang, X., Xu, K., Zhang, Y., and Fu, H. (2021). “Prediction of cardiovascular disease survival based on artificial neural network,” in 2021 IEEE International Conference on Computer Science, Electronic Information Engineering and Intelligent Control Technology (CEI) (New Jersey, NJ: IEEE), 219–224.

Google Scholar

Zhang, J., Zhang, M., Tian, Q., and Yang, J. (2023). a novel model associated with tumor microenvironment on predicting prognosis and immunotherapy in triple negative breast cancer. Clin. Exp. Med. 23, 1–15. doi: 10.1007/s10238-023-01090-5

PubMed Abstract | Crossref Full Text | Google Scholar

Zhang, J. Z., Xu, W., and Hu, P. (2022). Tightly integrated multiomics-based deep tensor survival model for time-to-event prediction. Bioinformatics 38, 3259–3266. doi: 10.1093/bioinformatics/btac286

PubMed Abstract | Crossref Full Text | Google Scholar

Zhang, R., Wu, J., Zhao, Y., Xu, X., Liu, X., and Wu, J. (2022). Using integrated multi-omics data analysis to identify 5-gene signature for predicting survival of patients with hepatocellular carcinoma. [Preprint]. doi: 10.21203/rs.3.rs-710165/v2

Crossref Full Text | Google Scholar

Zhang, S., Zeng, X., Lin, S., Liang, M., and Huang, H. (2022). Identification of seven-gene marker to predict the survival of patients with lung adenocarcinoma using integrated multi-omics data analysis. J. Clin. Lab. Anal. 36:e24190. doi: 10.1002/jcla.24190

PubMed Abstract | Crossref Full Text | Google Scholar

Zhang, W., Yu, Y., Hertwig, F., Thierry-Mieg, J., Zhang, W., Thierry-Mieg, D., et al. (2015). Comparison of rna-seq and microarray-based models for clinical endpoint prediction. Genome Biol. 16, 1–12. doi: 10.1186/s13059-015-0694-1

PubMed Abstract | Crossref Full Text | Google Scholar

Zhang, X., Xing, Y., Sun, K., and Guo, Y. (2021). Omiembed: a unified multi-task deep learning framework for multi-omics data. Cancers 13,:3047. doi: 10.3390/cancers13123047

PubMed Abstract | Crossref Full Text | Google Scholar

Zhang, Z.-S., Xu, F., Jiang, H.-J., and Chen, Z.-H. (2021). “Prognostic prediction for non-small-cell lung cancer based on deep neural network and multimodal data,” in Intelligent Computing Theories and Application: 17th International Conference, ICIC 2021, Shenzhen, China, August 12-15, 2021, Proceedings, Part III 17 (Cham: Springer), 549–560.

Google Scholar

Zhao, L., Dong, Q., Luo, C., Wu, Y., Bu, D., Qi, X., et al. (2021). Deepomix: a scalable and interpretable multi-omics deep learning framework and application in cancer survival analysis. Comput. Struct. Biotechnol. J. 19, 2719–2725. doi: 10.1016/j.csbj.2021.04.067

PubMed Abstract | Crossref Full Text | Google Scholar

Zhao, Y., Wong, L., and Goh, W. W. B. (2020). How to do quantile normalization correctly for gene expression data analyses. Sci. Rep. 10:15534. doi: 10.1038/s41598-020-72664-6

PubMed Abstract | Crossref Full Text | Google Scholar

Zhao, Z., Zhang, K.-N., Wang, Q., Li, G., Zeng, F., Zhang, Y., et al. (2021). Chinese glioma genome atlas (CGGA): a comprehensive resource with functional genomic data from chinese glioma patients. Genom. Proteom. Bioinf. 19, 1–12. doi: 10.1016/j.gpb.2020.10.005

PubMed Abstract | Crossref Full Text | Google Scholar

Zheng, X., Amos, C. I., and Frost, H. R. (2021). Pan-cancer evaluation of gene expression and somatic alteration data for cancer prognosis prediction. BMC Cancer 21, 1–11. doi: 10.1186/s12885-021-08796-3

PubMed Abstract | Crossref Full Text | Google Scholar

Zhou, H.-F., Wang, J.-L., Yang, W., Zhou, C., Shen, Y., Wu, L.-L., et al. (2023). Survival prediction for patients with malignant biliary obstruction caused by pancreatic cancer undergoing biliary drainage: the combo-pas model. Surg. Endosc. 37, 1943–1955. doi: 10.1007/s00464-022-09698-6

PubMed Abstract | Crossref Full Text | Google Scholar

Zhou, L., Rueda, M., and Alkhateeb, A. (2021). “Identifying biomarkers of nottingham prognosis index in breast cancer survivability,” in Proceedings of the 12th ACM Conference on Bioinformatics, Computational Biology, and Health Informatics (New York, NY: ACM), 1–9.

Google Scholar

Zhu, M., Chen, L., Kong, X., Wang, X., Li, X., Fang, Y., et al. (2023). The systemic immune-inflammation index is an independent predictor of survival in breast cancer patients. Cancer Manag. Res. 775–820. doi: 10.2147/CMAR.S346406

PubMed Abstract | Crossref Full Text | Google Scholar