Journal of evaluation in clinical practice · 2026
Reinforcement Learning in Healthcare Analytics: Transforming Personalised Medicine and Clinical Decision-Making.
СтатьяОбзорНазвание и аннотация: Перевод пока не подготовлен
Обработка статьи · этапы, ошибки и управление
Загрузка состояния…
Ошибки и ограничения
История · было → стало
Состояние обновляется каждые 5 секунд, пока блок открыт. Процент показывается только там, где известен объём работы. Пауза останавливает продолжение этапа; текущий запрос к источнику может завершиться.
Mathankumar T, Vijayarani S
Аннотация
RATIONALE: Reinforcement Learning (RL) has emerged as a promising artificial intelligence paradigm for adaptive and sequential decision-making in healthcare, enabling personalised treatment optimisation and intelligent clinical resource management beyond the capabilities of conventional static models.
AIM: This review aims to examine recent advances in RL for healthcare analytics, focusing on its applications, emerging techniques, challenges, and future research directions.
METHODS: The review studies model-free, model-based, deep reinforcement learning, and multi-agent reinforcement learning techniques applied to personalised treatment planning, chronic disease management, clinical decision support, healthcare resource optimisation, and robotic-assisted healthcare. It also explores Federated Reinforcement Learning (FRL), Explainable Reinforcement Learning (XRL), and longitudinal outcome prediction. The reviewed studies utilise healthcare datasets, including the Osteoporosis Dataset, UCI Heart Disease Dataset, Pima Indians Diabetes Dataset, SEER Cancer Dataset, and MIMIC-IV Dataset.
RESULTS: The reviewed studies demonstrate that RL-based approaches support adaptive clinical decision-making, personalised treatment recommendations, improved operational efficiency, and patient outcome prediction. FRL offers opportunities for privacy-preserving collaborative learning, while XRL enhances the transparency and interpretability of clinical decisions. However, challenges remain concerning data quality, reward function design, model interpretability, computational scalability, ethical considerations, and regulatory compliance.
CONCLUSION: R.L has significant potential to advance intelligent healthcare analytics through personalised, adaptive, and efficient clinical solutions. Future research should prioritise privacy preservation, interpretability, scalability, ethical AI, and regulatory compliance to develop safe, reliable, and trustworthy RL-based healthcare systems.
AIM: This review aims to examine recent advances in RL for healthcare analytics, focusing on its applications, emerging techniques, challenges, and future research directions.
METHODS: The review studies model-free, model-based, deep reinforcement learning, and multi-agent reinforcement learning techniques applied to personalised treatment planning, chronic disease management, clinical decision support, healthcare resource optimisation, and robotic-assisted healthcare. It also explores Federated Reinforcement Learning (FRL), Explainable Reinforcement Learning (XRL), and longitudinal outcome prediction. The reviewed studies utilise healthcare datasets, including the Osteoporosis Dataset, UCI Heart Disease Dataset, Pima Indians Diabetes Dataset, SEER Cancer Dataset, and MIMIC-IV Dataset.
RESULTS: The reviewed studies demonstrate that RL-based approaches support adaptive clinical decision-making, personalised treatment recommendations, improved operational efficiency, and patient outcome prediction. FRL offers opportunities for privacy-preserving collaborative learning, while XRL enhances the transparency and interpretability of clinical decisions. However, challenges remain concerning data quality, reward function design, model interpretability, computational scalability, ethical considerations, and regulatory compliance.
CONCLUSION: R.L has significant potential to advance intelligent healthcare analytics through personalised, adaptive, and efficient clinical solutions. Future research should prioritise privacy preservation, interpretability, scalability, ethical AI, and regulatory compliance to develop safe, reliable, and trustworthy RL-based healthcare systems.