Abstract
A one-size-fits-all approach to fall risk assessment in older adults has critical limitations. This study aimed to overcome this by identifying distinct gait phenotypes and their specific fall mechanisms using foot-mounted IMU waveform data from 146 older adults (mean age 82.6 ± 6.2 years). A data-driven clustering algorithm identified four phenotypes (Robust, High-cadence, Intermediate, and Cautious), each with different fall prevalence rates (27-68%). Interpretable machine learning (SHAP) revealed that fall trajectories were phenotype-dependent. While physiological declines such as gait speed were the primary cause of falls in the Cautious group, fear of falling (FES-I) was the primary cause in the physically healthy Robust group, suggesting a psychological pathway. Consequently, the optimal Timed Up and Go (TUG) test screening cutoff varied across phenotypes, ranging from 11.95 s to 14.00 s, demonstrating the limitations of a one-size-fits-all approach. These findings demonstrate that fall mechanisms are phenotype-dependent, underscoring the necessity of a personalized assessment strategy to improve fall prevention.