Toward Automated Fall Risk Assessment: Validation of an FMCW Radar-Based Timed Up and Go Test

Falls among the elderly present a significant healthcare and socioeconomic challenge. The timed up and go (TUG) test is a widely used tool for assessing mobility and fall risk. However, traditional methods are limited in terms of objectivity and scalability. This study introduces a radar-based approach to automating the TUG test using frequency-modulated continuous-wave (FMCW) radar. The main objective is to provide an automated, nonintrusive, and privacy-preserving system for fall risk assessment through precise segmentation of TUG test phases (standing up, walking, turning around, and sitting down) and extraction of key gait parameters, such as walking speed, distance traveled, and phase durations. Validated against a cohort of 100 participants, the system achieved a mean relative velocity error of 8.89% and a mean absolute time error of 0.159 s. These results demonstrate high accuracy and robustness, making it a promising tool for fall risk assessment in both clinical and home environments. The strong correlation agreement for studied metrics (asymmetry and cadence) is confirmed by the intraclass correlation coefficient (ICC) between Motion Capture (MoCap) and radar, with $\text {ICC}_{\text {asymmetry}} = 81.7\%$ and $\text {ICC}_{\text {cadence}} = 76.2\%$ . Additionally, the Bland–Altman analysis further supports this agreement, showing a strong concordance between the radar and MoCap measurements for both metrics.