Game-Based Assessment of Peripheral Neuropathy Combining Sensor-Equipped Insoles, Video Games, and AI:...

Area of Science:

• Neurology
• Biomedical Engineering
• Digital Health

Background:

• Peripheral neuropathy (PNP) detection is critical for preventing complications like foot ulceration.
• Current clinical PNP assessments are often limited by resource constraints.
• Gamified health assessments with wearable sensors offer a potential solution for accessible, real-time feedback.

Purpose of the Study:

• To develop and evaluate a novel application for assessing peripheral neuropathy (PNP).
• The application utilizes video games controlled by pressure sensor-equipped insoles for PNP assessment.

Main Methods:

• A proof-of-concept study developed a game framework controlled by plantar pressure modulation via sensor insoles.
• Plantar pressure data was transmitted wirelessly to an Android tablet for real-time game control.
• 299 patients with diabetes mellitus and 30 with metabolic syndrome were tested; machine learning models were trained and evaluated.

Main Results:

• Clinically evident PNP was present in 75.1% of participants.
• Game features significantly correlated with nerve conduction study findings and PNP presence.
• Predictive models achieved 76.1% (left) and 81.7% (right) accuracy for PNP detection.

Conclusions:

• The game-based application shows significant promise for PNP screening and classification.
• Further evaluation in larger cohorts is recommended to optimize AI model efficacy.
• Integration of motivational elements and automated interpretation can support its use as a telemedical tool.