Related Experiment Video
Updated: Jun 9, 2026
Introduction of an Integrated Pathology Image Management, Artificial Intelligence, and Reporting System
Published on: July 11, 2025
Artificial intelligence in clinical physiology: System-wise applications in diagnostics, monitoring, and medical
Chetna Chhabra1, Rohit Saroha1, Muneeb Kosvi2
1Department of Physiology, Santosh Deemed to be University, Ghaziabad, Uttar Pradesh, India.
Background:
Artificial Intelligence (AI) is gradually revolutionizing clinical physiology by enhancing diagnostic capabilities, fostering real-time monitoring, and enabling personalized medical education. Its incorporation into various physiological domains and wearable health technologies has redefined approaches to both patient care and medical training.
Objective:
This review seeks to systematically assess the applications of AI within the cardiovascular, respiratory, neurophysiological, and endocrine systems, as well as in physiology education. The focus is on diagnostic innovations, educational tools, ethical considerations, and emerging solutions.
Methods:
A comprehensive literature review was conducted utilizing PubMed, Scopus, Web of Science, and IEEE Xplore databases, covering the period from 2015 to 2025, to identify peer-reviewed studies on the application of AI in physiological diagnostics, monitoring, and competency-based medical education (CBME). Due to the heterogeneity in data types and methodologies, thematic synthesis was employed instead of meta-analysis.
Results:
AI has demonstrated exceptional capabilities in the interpretation of electrocardiograms and pulmonary function tests, as well as in seizure prediction, sleep analysis, diabetes management, and the enhancement of CBME tools. To address challenges such as algorithmic bias, data privacy, and accessibility, key strategies have emerged, including Explainable AI, edge computing, and federated learning frameworks.
Conclusion:
AI possesses the potential to revolutionize clinical physiology by facilitating predictive, personalized, and participatory healthcare. Nonetheless, its effective implementation necessitates ethical governance, inclusive datasets, and regulatory oversight to ensure equitable, transparent, and effective deployment.
