The emergence of artificial intelligence has brought new expectations to the field of medicine, particularly for disease diagnosis and prognostication. Classical models such as cox proportional hazard model and the log-rank test assume that patient outcome consists of a linear combination of covariates, and do not provide decision rules for prediction in the real-world. On the contrary, machine learning is a field of artificial intelligence that performs outcome prediction based on complex interactions between multiple variables. Machine learning makes little assumptions about the relationship between the dependent and independent variables. In machine learning, a model is trained with examples and not programmed with human-made rules. In the case of survival data, machine learning needs to take into account the time to event and censoring of the data.
Machine learning (ML) has been applied to predict survival in different clinical scenarios with encouraging results. The implementation of ML-based survival models is increasingly popular in order to provide patient-centered risk information that can assist both the clinician and the patient. A growing number of research lines are focused on the application of ML to genomic data and electronic health records in order to derive new predictors to anticipate important clinical scenarios. Additionally, new machine learning algorithms are becoming increasingly popular, such as reinforcement learning, and their application will be useful to optimize treatment strategies in the long term.
Hematological cancer research is a promising area for artificial intelligence applications, as the global burden of genomic research has provided vast amounts of publicly available data for artificial intelligence applications. These tools can integrate the complex clinical, imaging (histology, radiology…) and molecular landscape of tumors in order to provide better risk stratification, optimal treatments and risk of adverse events. Overall, the application of ML to hematological cancer will enable personalized approaches that will facilitate the development of novel therapeutic strategies for different groups of patients.
Basic, translational and clinical research manuscripts are welcome. Original research papers as well as reviews that add value to our previous knowledge can be submitted.
The following are specific themes to be addressed:
1. Big data and machine learning models for improved risk stratification in hematological cancer
2. Big data and machine learning models for single drug or drug combination prioritization in hematological cancer.
3. Big data and machine learning models to predict the risk of clinical complications in hematological cancer.
4. Big data and machine learning models to uncover new biological disease subgroups.
5. Application of novel artificial intelligence tools (e.g., reinforcement learning) to optimize treatment routes in the long term.
6. Computer vision tools for improved diagnosis and prognostication in hematological cancer (both in the field of radiology and pathology).
7. Big data and machine learning tools for application in clinical trials and real world data (RWD).
Manuscripts consisting solely of bioinformatics, computational analysis, or predictions of public databases which are not accompanied by validation (independent cohort or biological validation in vitro or in vivo) will not be accepted in any of the sections of Frontiers in Oncology.
The emergence of artificial intelligence has brought new expectations to the field of medicine, particularly for disease diagnosis and prognostication. Classical models such as cox proportional hazard model and the log-rank test assume that patient outcome consists of a linear combination of covariates, and do not provide decision rules for prediction in the real-world. On the contrary, machine learning is a field of artificial intelligence that performs outcome prediction based on complex interactions between multiple variables. Machine learning makes little assumptions about the relationship between the dependent and independent variables. In machine learning, a model is trained with examples and not programmed with human-made rules. In the case of survival data, machine learning needs to take into account the time to event and censoring of the data.
Machine learning (ML) has been applied to predict survival in different clinical scenarios with encouraging results. The implementation of ML-based survival models is increasingly popular in order to provide patient-centered risk information that can assist both the clinician and the patient. A growing number of research lines are focused on the application of ML to genomic data and electronic health records in order to derive new predictors to anticipate important clinical scenarios. Additionally, new machine learning algorithms are becoming increasingly popular, such as reinforcement learning, and their application will be useful to optimize treatment strategies in the long term.
Hematological cancer research is a promising area for artificial intelligence applications, as the global burden of genomic research has provided vast amounts of publicly available data for artificial intelligence applications. These tools can integrate the complex clinical, imaging (histology, radiology…) and molecular landscape of tumors in order to provide better risk stratification, optimal treatments and risk of adverse events. Overall, the application of ML to hematological cancer will enable personalized approaches that will facilitate the development of novel therapeutic strategies for different groups of patients.
Basic, translational and clinical research manuscripts are welcome. Original research papers as well as reviews that add value to our previous knowledge can be submitted.
The following are specific themes to be addressed:
1. Big data and machine learning models for improved risk stratification in hematological cancer
2. Big data and machine learning models for single drug or drug combination prioritization in hematological cancer.
3. Big data and machine learning models to predict the risk of clinical complications in hematological cancer.
4. Big data and machine learning models to uncover new biological disease subgroups.
5. Application of novel artificial intelligence tools (e.g., reinforcement learning) to optimize treatment routes in the long term.
6. Computer vision tools for improved diagnosis and prognostication in hematological cancer (both in the field of radiology and pathology).
7. Big data and machine learning tools for application in clinical trials and real world data (RWD).
Manuscripts consisting solely of bioinformatics, computational analysis, or predictions of public databases which are not accompanied by validation (independent cohort or biological validation in vitro or in vivo) will not be accepted in any of the sections of Frontiers in Oncology.