Deep-Learning Algorithms for Prescribing Insoles to Patients with Foot Pain

Foot pain is a common musculoskeletal disorder. Orthotic insoles are widely used in patients with foot pain. Inexperienced clinicians have difficulty prescribing orthotic appropriately by considering various factors associated the alteration of alignment. We attempted to develop deep-learning algorithms that can automatically prescribe and assess their accuracy. In total, 838 were included this study; 70% (n = 586) 30% 252) as training validation sets, respectively. The resting calcaneal stance position data related pelvic elevation, tilt, rotation input for developing insole prescription. target posture index modified root technique necessity heel lift, entire lateral wedge, medial calcaneocuboid arch supports. results, regarding technique, left foot, mean absolute error (MAE) square (RMSE) dataset developed model 1.408 3.365, For right MAE RMSE 1.601 3.549, accuracies supports 89.7%, 94.8%, 72.2%, 98.4%, 79.8%, micro-average area under receiver operating characteristic curves 0.949, 0.941, 0.826, 0.792, 0.827, conclusion, our models prescribed showed outstanding acceptable