Evaluating the Effectiveness of Transtibial Prosthetic Socket Shape Design Using Artificial Intelligence: A Clinical...

Area of Science:

• Biomedical Engineering
• Artificial Intelligence in Healthcare
• Prosthetics and Orthotics

Background:

• Current prosthetic socket design relies on manual methods, which can be operator-dependent and lack standardization.
• Enhancing prosthetic socket shapes is crucial for patient comfort and prosthesis functionality.

Purpose of the Study:

• To investigate the feasibility of an artificial intelligence (AI) algorithm for creating standardized prosthetic socket shapes for transtibial prostheses.
• To develop a less operator-dependent approach to prosthetic socket design.

Main Methods:

• An AI algorithm was developed using retrospective data from 116 patients.
• The AI-predicted digitally measured and standardized designed (DMSD) sockets were compared to manually measured and designed (MMD) sockets.
• Socket comfort scores and fitting ratings were collected from participants and clinicians.

Main Results:

• AI-predicted prosthetic shapes had a mean deviation of 2.51 mm from actual designs.
• 8 out of 10 DMSD sockets and all 10 MMD sockets were satisfactory for home testing.
• Participants rated DMSD sockets slightly higher (7.1) than MMD sockets (6.6) for comfort.

Conclusions:

• The AI algorithm shows potential for improving prosthetic socket design, offering a more standardized approach.
• Further research is required to assess long-term effectiveness and refine the AI for diverse patient needs and improved comfort.