IMU-based rotator cuff injury recognition with varying configurations and combinations.
Shoulder frontal range-of-motion test alone best identified rotator cuff injury using RCIRNet
IMU-based rotator cuff injury recognition with varying configurations and combinations.
Assessing functional movements is important for evaluating shoulder impairments, as these movements directly reflect patients' capacity to perform daily activities.
This study aimed to develop accurate and cost-effective rotator cuff injury recognition models by integrating machine learning (machine learning)/deep learning (deep learning) algorithms with upper limb kinematic data collected in functional movement, and to explore optimal motion task combinations and model configurations for clinical practice.
A total of 102 participants were prospectively enrolled, comprising 51 patients diagnosed with rotator cuff injury, 25 patients diagnosed with adhesive capsulitis and 26 healthy volunteers.
higher scores mean better identification of rotator cuff injury
Combining four tasks increased Recall to 1.0 with high level Accuracy, F1-score, and AUC.
However, adding more movements (5-8 tasks) did not improve model performance.
Among different model configurations, RCIRNet performed best, SVM demonstrated overall stability, and KNN excelled in Recall.
The shoulder frontal ROM test combined with RCIRNet provides an optimal approach for accurate and efficient clinical screening and rehabilitation monitoring.