Evaluation of at-home physiotherapy: machine-learning prediction with smart watch inertial sensors

Bone & Joint Research

article

Philip Boyer¹  David Burns²  Cari Whyne¹ 

[1] Institute of Biomedical Engineering, University of Toronto;Harborview Medical Center

关键词: Physiotherapy;    Physical therapy;    Rehabilitation;    Inertial measurement units;    Machine learning;    physiotherapy;    shoulder;    rotator cuff injuries;    physiotherapists;    rotator cuff;    accelerometer;    Full-thickness rotator cuff tears;    variances;    standard deviation;    flexion;   

DOI  :  10.1302/2046-3758.123.BJR-2022-0126.R1

学科分类：骨科学

来源: British Editorial Society Of Bone And Joint Surgery

【 摘 要 】

AimsAn objective technological solution for tracking adherence to at-home shoulder physiotherapy is important for improving patient engagement and rehabilitation outcomes, but remains a significant challenge. The aim of this research was to evaluate performance of machine-learning (ML) methodologies for detecting and classifying inertial data collected during in-clinic and at-home shoulder physiotherapy exercise.MethodsA smartwatch was used to collect inertial data from 42 patients performing shoulder physiotherapy exercises for rotator cuff injuries in both in-clinic and at-home settings. A two-stage ML approach was used to detect out-of-distribution (OOD) data (to remove non-exercise data) and subsequently for classification of exercises. We evaluated the performance impact of grouping exercises by motion type, inclusion of non-exercise data for algorithm training, and a patient-specific approach to exercise classification. Algorithm performance was evaluated using both in-clinic and at-home data.ResultsThe patient-specific approach with engineered features achieved the highest in-clinic performance for differentiating physiotherapy exercise from non-exercise activity (area under the receiver operating characteristic (AUROC) = 0.924). Including non-exercise data in algorithm training further improved classifier performance (random forest, AUROC = 0.985). The highest accuracy achieved for classifying individual in-clinic exercises was 0.903, using a patient-specific method with deep neural network model extracted features. Grouping exercises by motion type improved exercise classification. For at-home data, OOD detection yielded similar performance with the non-exercise data in the algorithm training (fully convolutional network AUROC = 0.919).ConclusionIncluding non-exercise data in algorithm training improves detection of exercises. A patient-specific approach leveraging data from earlier patient-supervised sessions should be considered but is highly dependent on per-patient data quality.

【 授权许可】

CC BY-NC