Objective:

To develop a wearable device for continuous gait monitoring and early detection of lower limb dysfunction, enhancing disease management.

Key Findings:

• The system identified foot arch abnormalities with 96% accuracy, crucial for early intervention.
• It classified 12 different gait patterns with 97.6% accuracy, including limping and shuffling gait.
• The device can effectively distinguish between normal and abnormal gait patterns, enhancing diagnostic capabilities.

Interpretation:

Wearable diagnostics may provide continuous, objective data on patient movement, potentially identifying early changes in gait that traditional methods miss, thus improving patient outcomes.

Limitations:

• Validation conducted in controlled and relatively small study settings, which may not reflect broader populations.
• Further research needed in larger and more diverse populations to confirm findings.

Conclusion:

The study demonstrates the potential of combining high-resolution sensing, self-powered operation, and AI analysis in wearable devices for improved gait diagnostics, with significant implications for real-world applications.