There’s a notable shortage of publicly available datasets featuring rehabilitation exercises performed by patients with musculoskeletal conditions.
Within @SUNxr.he project, researchers from @Thingenious have managed to collect KneE-PAD (https://zenodo.org/records/12112951) consisting of 3 common knee rehabilitation exercises (squat, seated knee extension, gait) performed by 31 patients suffering from knee pathologies. At each participant a set of 8 EMG and IMU #Delsys sensors was placed at important lower limb muscle groups. For the creation of KneE-PAD, 267 patients were monitored over a 6-month period without any supervision from the physiotherapists. After curating and grouping the wrongly executed exercises, 2 common wrong variations for each exercise were identified in 31 participants.
The goal of KneE-PAD is to be used for training machine learning algorithms for automatic postural assessment using only wearable sensors, which could become a vital part of an #XR-based virtual coach to supervise the patients and provide useful feedback to them while executing their prescribed rehabilitation exercises remotely.