Autoencoder Composite Scoring to Evaluate Prosthetic Performance in Individuals with Lower Limb Amputation

• Published in: Bioengineering (Basel) Vol. 9; no. 10; p. 572
• Main Authors: Tabashum, Thasina, Xiao, Ting, Jayaraman, Chandrasekaran, Mummidisetty, Chaithanya K., Jayaraman, Arun, Albert, Mark V.
• Format: Journal Article
• Language: English
• Published: Switzerland MDPI AG 01.10.2022; MDPI
• Subjects: Amputation; autoencoder; Bioengineering; Datasets; Deep learning; Diabetes; Gait; Knee; lower limb amputation; Machine learning; Mechanical knees; Microprocessors; Neural networks; Physiological aspects; principal component analysis; Principal components analysis; Prostheses; Prosthetics; Quality of life; Variables; Variance; United States; United States > US; principal component analysis; autoencoder; lower limb amputation

We created an overall assessment metric using a deep learning autoencoder to directly compare clinical outcomes in a comparison of lower limb amputees using two different prosthetic devices—a mechanical knee and a microprocessor-controlled knee. Eight clinical outcomes were distilled into a single m...