Wearable physiological sensor fusion for pain episode detection: a review

Abstract

Pain episode detection and forecasting from physiological signals collected by wearable devices is becoming increasingly important. Self-reported pain ratings in daily life are recorded irregularly, leaving episode onset, duration, and dynamics incompletely documented. The reviewed literature shows that physiological changes are driven not only by pain but also by movement, emotional arousal, sleep, and environmental factors. Therefore, real-world reliability and false-episode reduction remain key obstacles. This focused review synthesizes clinical and naturalistic use cases, data acquisition strategies, and modeling approaches. These approaches range from feature engineering and classical machine learning to multimodal fusion with attention mechanisms and transformer architectures. Beyond summarizing established findings from the literature, the paper adds two literature-derived synthesis recommendations. The 2 + 1 rule treats at least two physiological signal families plus one context channel as a practical design heuristic for robust wearable pain detection. The KKS principle uses quality indicators and context information to control fusion weights dynamically. Across the reviewed studies, single-signal solutions are frequently vulnerable to signal-quality fluctuations. By contrast, hybrid strategies with explicit quality and context handling show stronger translational potential. However, these recommendations should be interpreted as conceptual guidance requiring further empirical validation, especially across participants, devices, protocols, and uncontrolled daily-life conditions.