AI-Driven Interpretation of Human Physiology in Health, Medicine, and Education

This Research Topic focuses on the integration of physiological signals with artificial intelligence to enable meaningful interpretation of human states in health, clinical, and empirical educational research contexts. We invite contributions that process biosignals (such as heart rate variability, EEG, EDA, EMG, proteomics, or multimodal sensor data) using machine learning, AI-based models, or novel algorithmic approaches. A particular emphasis lies on moving beyond retrospective analysis toward real-time and adaptive systems capable of continuous physiological interpretation. Contributions may address both methodological foundations and applied use cases, including clinical monitoring, stress and resilience assessment, learning analytics, and human-machine interaction. By bridging physiology, data science, medicine, and education, this Research Topic aims to shape the next generation of bioadaptive and intelligent systems.This Research Topic welcomes contributions on (but not limited to): - AI-based processing of physiological signals, including HRV, EEG, EDA, EMG, proteomics, eye-tracking, or multimodal biosensor data;- Towards Real-time and near-real-time analysis pipelines for physiological monitoring and state inference;- Machine learning and algorithmic approaches for detecting stress, cognitive load, affective states, or physiological resilience;- Methodological frameworks and interfaces linking biosignal acquisition to AI-driven interpretation systems;- Clinical applications, such as patient monitoring, early risk detection, or decision-support systems;- Educational and learning-related contexts, including medical education, health sciences education, and empirical educational research;- Physiological markers during learning and performance, including stress responses, attention, and adaptive learning environments;- Translational and interdisciplinary approaches connecting physiology, medicine, education, and human–computer interaction;- Retrospective analyses, validation studies, and proof-of-concept implementations, as well as forward-looking real-time models. Topic editors: Morris Gellisch, Robert Richer, Thorsten Schäfer Source: https://www.frontiersin.org/research-topics/77661/ai-driven-interpretation-of-human-physiology-in-health-medicine-and-education