REVIEW article
Front. Digit. Health
Sec. Personalized Medicine
This article is part of the Research TopicIntelligent Digital Twins in MedicineView all articles
Digital Twins in Healthcare: A Comprehensive Review and Future Directions
Provisionally accepted
Hamid Khoshfekr Rudsari
Becky TsengHongxu ZhuLulu Song
Chunhui GuAbhishikta Roy
Ehsan IrajizadJoseph Butner
James LongKim-Anh Do*- The University of Texas MD Anderson Cancer Center, Houston, United States
Select one of your emails
You have multiple emails registered with Frontiers:
Notify me on publication
Please enter your email address:
If you already have an account, please login
You don't have a Frontiers account ? You can register here
Digital Twin (DT) technology has emerged as a transformative force in healthcare, offering unprecedented opportunities for personalized medicine, treatment optimization, and disease prevention. This comprehensive review examines the current state of DTs in healthcare, analyzing their implementation across different physiological levels - from cellular to whole-body systems. We systematically review the latest developments, methodologies, and applications while identifying challenges and opportunities. Our analysis encompasses technical frameworks for cardiovascular, neurological, respiratory, metabolic, hepatic, oncological, and cellular DTs, highlighting significant achievements such as population-scale cardiac modeling (3,461 patient cohort), reduced atrial fibrillation recurrence rates through patient-specific cardiac models, improved brain tumor radiotherapy planning, advanced liver regeneration modeling with real-time simulation capabilities, and enhanced glucose management in diabetes. We detail the methodological foundations supporting different DT implementations, including data acquisition strategies, physics-based modeling approaches, statistical learning algorithms, neural network-based control systems, and emerging artificial intelligence techniques. While discussing implementation challenges related to data quality, computational constraints, and validation requirements, we provide a forward-looking perspective on future opportunities for enhanced personalization, expanded application areas, and integration with emerging technologies. This review offers a multidimensional assessment of healthcare DTs and outlines future directions for their development and integration. This review demonstrates that while healthcare DTs have achieved remarkable clinical successes—from reducing cardiac arrhythmia recurrence rates by over 13% to enabling 97% accuracy in neurodegenerative disease prediction, and achieving sub-millisecond liver response predictions with high accuracy—their clinical translation requires addressing challenges such as data integration, computational scalability, digital equity, and validation frameworks.
Keywords: Digital Twin, personalized medicine, Healthcare modeling, Predictive healthcare, AI in medicine, Patient-specific models, virtual simulation, Computational Medicine
Received: 22 May 2025; Accepted: 04 Nov 2025.
Copyright: © 2025 Khoshfekr Rudsari, Tseng, Zhu, Song, Gu, Roy, Irajizad, Butner, Long and Do. 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: Kim-Anh Do, kimdo@mdanderson.org
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.