Abstract
Abstract Flatfoot is an orthopedic malformation where the inner foot arch flattens during motion, potentially leading to chronic musculoskeletal issues. Monitoring foot conditions is essential, as existing screening methods often need more objectivity and cost‐effectiveness. This research develops an insole‐based screening device using self‐powered triboelectric nanogenerators (TENGs) as tactile sensors and Arduino hardware setup. TENG converts mechanical energy into electrical energy, offering simple fabrication, cost‐effectiveness, longevity, and high‐output power benefits. The device records the electrical output generated by foot movements via Arduino and sends data via Bluetooth to the processing tool. Machine learning algorithms employing the Random Forest Classifier process the data to detect flatfoot conditions accurately after training sessions. For data collection, 100 participants are asked to march and walk for the same duration and distance, ensuring consistent output. Analysis reveals that the insoles' middle sensors produce higher electricity levels in individuals with flatfoot, showing a uniform pressure distribution across the foot and contact in the arch area. In contrast, individuals with normal feet exert more pressure on the toe and heel foot areas. The system achieves an overall accuracy of 82%, demonstrating the insole's potential as a commercial flatfoot detection device.