Skip to main content

REVIEW article

Front. Physiol.
Sec. Computational Physiology and Medicine
Volume 15 - 2024 | doi: 10.3389/fphys.2024.1473125
This article is part of the Research Topic Multiscale cancer modeling, in silico oncology, in silico psycho-oncology and digital (virtual) twins in the cancer domain View all articles

Towards Verifiable Cancer Digital Twins: Tissue level Modeling Protocol for Precision Medicine

Provisionally accepted
Ravi Radhakrishnan Ravi Radhakrishnan 1*Sharvari Kemkar Sharvari Kemkar 1Mengdi Tao Mengdi Tao 1Alokendra Ghosh Alokendra Ghosh 1Georgios S. Stamatakos Georgios S. Stamatakos 2Norbert Graf Norbert Graf 3Kunal Poorey Kunal Poorey 4Uma Balakrishnan Uma Balakrishnan 4Nathaniel Trask Nathaniel Trask 1
  • 1 University of Pennsylvania, Philadelphia, PA, United States
  • 2 National Technical University of Athens, Athens, Greece
  • 3 Saarland University, Saarbrücken, Saarland, Germany
  • 4 Sandia National Laboratories (DOE), Livermore, California, United States

The final, formatted version of the article will be published soon.

    Cancer's heterogeneity often undermines the efficacy of conventional treatments. Advances in multiomics and sequencing have provided insights, but the complexity of the data requires robust mathematical models for full interpretation. This review highlights recent advancements in computational methodologies for precision oncology, emphasizing the potential of cancer digital twins to enhance patient-specific decision-making. We propose a framework that integrates agent-based modeling with cellular systems biology models, utilizing patient-specific data to predict tissue-level responses. Additionally, we discuss machine learning approaches to build surrogates for these models, facilitating sensitivity analysis, verification, validation, and uncertainty quantification. These advancements are crucial for improving the accuracy and reliability of clinical predictions. Abstract 2 Introduction 2 Cellular systems biology models to encode cell behavior 5 Multi-agent models for simulating tissue-level spatiotemporal dynamics 7 Embedding cellular models for decision-making in a multi-agent modeling framework 8 Differential equation based and boolean approaches for cellular modeling 8 Machine learning approaches to speed up multi-agent simulations 8 Sensitivity analysis and feature importance in the multi-scale hybrid model 9 Surrogate models for sensitivity analysis and feature importance 10 Clinical exploration of feature importance predictions 11 Verification, Validation, and Uncertainty Quantification (VVUQ) of the multi-scale hybridmodeling framework 12 Discussion 14 Building verifiable cancer digital twins for precision medicine 14 Data-driven methods for multi-modal model interpretability and forecasting 17 Current Limitations and Future Perspectives 19 References 20

    Keywords: Multiphysics models, machine learing algorithms, verification validation uncertainty quatification, model interpretability and forecasting, Agent based models

    Received: 30 Jul 2024; Accepted: 07 Oct 2024.

    Copyright: © 2024 Radhakrishnan, Kemkar, Tao, Ghosh, Stamatakos, Graf, Poorey, Balakrishnan and Trask. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) or licensor are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.

    * Correspondence: Ravi Radhakrishnan, University of Pennsylvania, Philadelphia, 08540, PA, United States

    Disclaimer: 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.