A Comprehensive Review of Digital Twin Models for Stroke Prediction: Towards Software-Driven and Agent-Based Approaches

DOI

10.2991/978-94-6239-723-1_30How to use a DOI?

Keywords

Digital Twin; Stroke Prediction; Agent-Based Modeling; Machine Learning in Healthcare; Software-Driven Models; Personalized Medicine; Preventive Healthcare

Abstract

Stroke has remained among the top contributors to mortality and chronic disability over the past few years. The prediction of the likelihood of patients having strokes has remained a challenge despite the development of risk scores, statistical models, and machine learning algorithms, due to the limitations associated with the dynamic interactions between various genetic, physiological, behavior-related, and environmental factors. In addition, most healthcare-related digital twins employ a vast array of IoT sensors that not only increase healthcare costs but also lack the necessary scalability. This review considers a software-based digital twin solution that combines machine learning and agent-based modeling for the prediction of stroke risk within a dynamic, personalized approach. The solution is more effective since it does not depend on hardware-based monitoring systems, but instead on data gathered from various sources including clinical data, patient behavior, and environmental factors. Through the ABM component, interactions are simulated among the various risk factors, which are then processed by the machine learning component into dynamic risk scores that change based on the patient situation. Through a systematic review of various models used in predicting the risk of stroke, including risk scores and more advanced deep learning and hybrid models, the various advantages and disadvantages are highlighted. The proposed software-based digital twin solution is more scalable and inclusive, and can work within various healthcare systems without the need for expensive IoT infrastructure.

Copyright

© 2026 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Sheetal Shinde
AU  - Akanksha Pal
PY  - 2026
DA  - 2026/07/14
TI  - A Comprehensive Review of Digital Twin Models for Stroke Prediction: Towards Software-Driven and Agent-Based Approaches
BT  - Proceedings of the International Conference on Responsible, Risk-aware, and Regulated AI (RRRAI 2026)
PB  - Atlantis Press
SP  - 324
EP  - 341
SN  - 1951-6851
UR  - https://doi.org/10.2991/978-94-6239-723-1_30
DO  - 10.2991/978-94-6239-723-1_30
ID  - Shinde2026
ER  -