This research examines whether changes in walking patterns can predict frailty before serious health events occur. Using smart insoles, GPS tracking, and machine learning, mobility data from older adults is analyzed to identify early warning signs of decline. The goal is to enable proactive interventions and support healthier aging.

This research develops a fast, space-efficient method for assessing fall risk in older adults using wearable sensors and AI analysis of a seated foot-tapping task. Early findings show that slower, inconsistent tapping predicts higher fall risk. The approach could improve prevention strategies, reduce healthcare costs, and help older adults maintain independence.