AI-driven multi-agent reinforcement learning framework for real-time monitoring of physiological signals in stress and depression contexts

Abstract Purpose Effective patient monitoring is crucial for timely healthcare interventions and improved outcomes, especially in managing conditions influenced by stress and depression, which can manifest through physiological changes. Traditional monitoring systems often struggle with the complexi...

Full description

Saved in:
Bibliographic Details
Main Authors: Thanveer Shaik, Xiaohui Tao, Lin Li, Haoran Xie, Hong-Ning Dai, Feng Zhao, Jianming Yong
Format: Article
Language:English
Published: SpringerOpen 2025-06-01
Series:Brain Informatics
Subjects:
Online Access:https://doi.org/10.1186/s40708-025-00262-1
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850221787883765760
author Thanveer Shaik
Xiaohui Tao
Lin Li
Haoran Xie
Hong-Ning Dai
Feng Zhao
Jianming Yong
author_facet Thanveer Shaik
Xiaohui Tao
Lin Li
Haoran Xie
Hong-Ning Dai
Feng Zhao
Jianming Yong
author_sort Thanveer Shaik
collection DOAJ
description Abstract Purpose Effective patient monitoring is crucial for timely healthcare interventions and improved outcomes, especially in managing conditions influenced by stress and depression, which can manifest through physiological changes. Traditional monitoring systems often struggle with the complexity and dynamic nature of such conditions, leading to delays in identifying critical scenarios. This study proposes a novel multi-agent deep reinforcement learning (DRL) framework to address these challenges by monitoring vital signs and providing real-time decision-making capabilities. Methods Our framework deploys multiple learning agents, each dedicated to monitoring specific physiological features such as heart rate, respiration, and temperature. These agents interact with a generic healthcare monitoring environment, learn patients’ behavior patterns, and estimate the level of emergency to alert Medical Emergency Teams (METs) accordingly. The study evaluates the proposed system using two real-world datasets-PPG-DaLiA and WESAD-designed to capture physiological and stress-related data. The performance is compared with baseline models, including Q-Learning, PPO, Actor-Critic, Double DQN, and DDPG, as well as existing monitoring frameworks like WISEML and CA-MAQL. Hyperparameter optimization is also performed to fine-tune learning rates and discount factors. Results Experimental results demonstrate that the proposed multi-agent DRL framework outperforms baseline models in accurately monitoring patients’ vital signs under stress and varying conditions. The optimized agents adapt effectively to dynamic environments, ensuring timely detection of critical health deviations. Comparative evaluations reveal superior performance in metrics related to decision-making accuracy and response efficiency, highlighting the robustness of the framework. Conclusions The proposed AI-driven monitoring system offers significant advancements over traditional methods by handling complex and uncertain environments, adapting to varying patient conditions influenced by stress and depression, and making autonomous, real-time decisions. While the framework demonstrates high accuracy and adaptability, challenges related to data scale and future vital sign prediction remain. Future research will focus on extending predictive capabilities to further enhance proactive healthcare interventions.
format Article
id doaj-art-1f21d37751e1407dbd57f553d202b433
institution OA Journals
issn 2198-4018
2198-4026
language English
publishDate 2025-06-01
publisher SpringerOpen
record_format Article
series Brain Informatics
spelling doaj-art-1f21d37751e1407dbd57f553d202b4332025-08-20T02:06:36ZengSpringerOpenBrain Informatics2198-40182198-40262025-06-0112111810.1186/s40708-025-00262-1AI-driven multi-agent reinforcement learning framework for real-time monitoring of physiological signals in stress and depression contextsThanveer Shaik0Xiaohui Tao1Lin Li2Haoran Xie3Hong-Ning Dai4Feng Zhao5Jianming Yong6School of Mathematics, Physics & Computing, University of Southern QueenslandSchool of Mathematics, Physics & Computing, University of Southern QueenslandSchool of Computer and Artificial Intelligence, Wuhan University of TechnologyDivision of Artificial Intelligence, School of Data Science, Lingnan UniversityDepartment of Computer Science, Hong Kong Baptist UniversityHuazhong University of Science and TechnologySchool of Business, University of Southern QueenslandAbstract Purpose Effective patient monitoring is crucial for timely healthcare interventions and improved outcomes, especially in managing conditions influenced by stress and depression, which can manifest through physiological changes. Traditional monitoring systems often struggle with the complexity and dynamic nature of such conditions, leading to delays in identifying critical scenarios. This study proposes a novel multi-agent deep reinforcement learning (DRL) framework to address these challenges by monitoring vital signs and providing real-time decision-making capabilities. Methods Our framework deploys multiple learning agents, each dedicated to monitoring specific physiological features such as heart rate, respiration, and temperature. These agents interact with a generic healthcare monitoring environment, learn patients’ behavior patterns, and estimate the level of emergency to alert Medical Emergency Teams (METs) accordingly. The study evaluates the proposed system using two real-world datasets-PPG-DaLiA and WESAD-designed to capture physiological and stress-related data. The performance is compared with baseline models, including Q-Learning, PPO, Actor-Critic, Double DQN, and DDPG, as well as existing monitoring frameworks like WISEML and CA-MAQL. Hyperparameter optimization is also performed to fine-tune learning rates and discount factors. Results Experimental results demonstrate that the proposed multi-agent DRL framework outperforms baseline models in accurately monitoring patients’ vital signs under stress and varying conditions. The optimized agents adapt effectively to dynamic environments, ensuring timely detection of critical health deviations. Comparative evaluations reveal superior performance in metrics related to decision-making accuracy and response efficiency, highlighting the robustness of the framework. Conclusions The proposed AI-driven monitoring system offers significant advancements over traditional methods by handling complex and uncertain environments, adapting to varying patient conditions influenced by stress and depression, and making autonomous, real-time decisions. While the framework demonstrates high accuracy and adaptability, challenges related to data scale and future vital sign prediction remain. Future research will focus on extending predictive capabilities to further enhance proactive healthcare interventions.https://doi.org/10.1186/s40708-025-00262-1Behavior patternsDecision makingPatient monitoringReinforcement learningVital signs
spellingShingle Thanveer Shaik
Xiaohui Tao
Lin Li
Haoran Xie
Hong-Ning Dai
Feng Zhao
Jianming Yong
AI-driven multi-agent reinforcement learning framework for real-time monitoring of physiological signals in stress and depression contexts
Brain Informatics
Behavior patterns
Decision making
Patient monitoring
Reinforcement learning
Vital signs
title AI-driven multi-agent reinforcement learning framework for real-time monitoring of physiological signals in stress and depression contexts
title_full AI-driven multi-agent reinforcement learning framework for real-time monitoring of physiological signals in stress and depression contexts
title_fullStr AI-driven multi-agent reinforcement learning framework for real-time monitoring of physiological signals in stress and depression contexts
title_full_unstemmed AI-driven multi-agent reinforcement learning framework for real-time monitoring of physiological signals in stress and depression contexts
title_short AI-driven multi-agent reinforcement learning framework for real-time monitoring of physiological signals in stress and depression contexts
title_sort ai driven multi agent reinforcement learning framework for real time monitoring of physiological signals in stress and depression contexts
topic Behavior patterns
Decision making
Patient monitoring
Reinforcement learning
Vital signs
url https://doi.org/10.1186/s40708-025-00262-1
work_keys_str_mv AT thanveershaik aidrivenmultiagentreinforcementlearningframeworkforrealtimemonitoringofphysiologicalsignalsinstressanddepressioncontexts
AT xiaohuitao aidrivenmultiagentreinforcementlearningframeworkforrealtimemonitoringofphysiologicalsignalsinstressanddepressioncontexts
AT linli aidrivenmultiagentreinforcementlearningframeworkforrealtimemonitoringofphysiologicalsignalsinstressanddepressioncontexts
AT haoranxie aidrivenmultiagentreinforcementlearningframeworkforrealtimemonitoringofphysiologicalsignalsinstressanddepressioncontexts
AT hongningdai aidrivenmultiagentreinforcementlearningframeworkforrealtimemonitoringofphysiologicalsignalsinstressanddepressioncontexts
AT fengzhao aidrivenmultiagentreinforcementlearningframeworkforrealtimemonitoringofphysiologicalsignalsinstressanddepressioncontexts
AT jianmingyong aidrivenmultiagentreinforcementlearningframeworkforrealtimemonitoringofphysiologicalsignalsinstressanddepressioncontexts