Chronic Pain Protective Behavior Detection with Deep Learning
Autor: | Chongyang Wang, Nadia Bianchi-Berthouze, Amanda C. de C. Williams, Nicholas D. Lane, Akhil Mathur, Temitayo A. Olugbade |
---|---|
Rok vydání: | 2021 |
Předmět: |
FOS: Computer and information sciences
Computer Science - Machine Learning medicine.medical_specialty Computer Science - Artificial Intelligence medicine.medical_treatment Computer Science - Human-Computer Interaction Biomedical Engineering Medicine (miscellaneous) Wearable computer Health Informatics 02 engineering and technology Motion capture Human-Computer Interaction (cs.HC) Machine Learning (cs.LG) 03 medical and health sciences 0302 clinical medicine Physical medicine and rehabilitation Health Information Management 020204 information systems 0202 electrical engineering electronic engineering information engineering medicine Affective computing Rehabilitation business.industry Deep learning Chronic pain Body movement medicine.disease Computer Science Applications Artificial Intelligence (cs.AI) Artificial intelligence Psychology business F1 score 030217 neurology & neurosurgery Software Information Systems |
Zdroj: | ACM Transactions on Computing for Healthcare |
ISSN: | 2637-8051 2691-1957 |
Popis: | In chronic pain rehabilitation, physiotherapists adapt physical activity to patients' performance based on their expression of protective behavior, gradually exposing them to feared but harmless and essential everyday activities. As rehabilitation moves outside the clinic, technology should automatically detect such behavior to provide similar support. Previous works have shown the feasibility of automatic protective behavior detection (PBD) within a specific activity. In this paper, we investigate the use of deep learning for PBD across activity types, using wearable motion capture and surface electromyography data collected from healthy participants and people with chronic pain. We approach the problem by continuously detecting protective behavior within an activity rather than estimating its overall presence. The best performance reaches mean F1 score of 0.82 with leave-one-subject-out cross validation. When protective behavior is modelled per activity type, performance is mean F1 score of 0.77 for bend-down, 0.81 for one-leg-stand, 0.72 for sit-to-stand, 0.83 for stand-to-sit, and 0.67 for reach-forward. This performance reaches excellent level of agreement with the average experts' rating performance suggesting potential for personalized chronic pain management at home. We analyze various parameters characterizing our approach to understand how the results could generalize to other PBD datasets and different levels of ground truth granularity. 24 pages, 12 figures, 7 tables. Accepted by ACM Transactions on Computing for Healthcare |
Databáze: | OpenAIRE |
Externí odkaz: |