Prediction of Foot Soft Tissue Stiffness Based on Plantar Pressure During Walking

Abstract

Abstract Purpose: To predict foot soft tissue stiffness based on plantar pressure characteristics during walking using a neural network model, and the association between plantar pressure features and foot soft tissue stiffness was examined utilizing mean impact value analysis. Methods: 30 male subjects were recruited. A foot pressure measurement system was used to collect average pressure data from different foot regions during 5 trials of walking for both feet. Foot soft tissue stiffness was recorded using a MyotonPRO biological soft tissue stiffness meter before each walking trial. Intraclass correlation coefficient was used to evaluate within-session reliability for each measurement. A backpropagation neural network, optimized by integrating particle swarm optimization and genetic algorithm, was constructed to predict foot soft tissue stiffness using plantar pressure data collected during walking. Mean impact value analysis was conducted in parallel to investigate the relative importance of different plantar pressure features. Results: All parameters except average pressure in the 4th metatarsal region demonstrated moderate to high within-session reliability. For the training set, the maximum relative error percentage between predicted and actual data was 7.82%, average relative error percentage was 1.98%, mean absolute error was 9.42 N/m, mean bias error was 0.77 N/m, and root mean square error was 11.89 N/m. For the test set, maximum relative error percentage was 7.35%, average relative error percentage was 2.55%. Mean absolute error, mean bias error and root mean square error were 12.28 N/m, -4.43 N/m, and 14.73 N/m, respectively. Regions with highest contribution rates to foot soft tissue stiffness prediction were the 3rd metatarsal (13.58%), 4th metatarsal (14.71%), midfoot (12.43%) and medial heel (12.58%) regions, which accounted for 53.3% of total contribution. Conclusions: The optimized algorithm developed in this study can effectively predict foot soft tissue stiffness from regional plantar pressures during walking. Pressures in the medial heel, midfoot, 3rd and 4th metatarsal regions during walking best reflect foot soft tissue stiffness. Future studies are suggested to develop subject-specific prediction models for different foot types and foot conditions based on biomechanical characteristics during actual movements.