Predicting gait and timed up and go time using foot-tapping test and accelerometer.

Objective.Gait and the timed up and go (TUG) time are the two tests that are widely used to assess functional mobility; however, their administration requires space and trained personnel, limiting feasibility for routine assessment. A brief, seated foot-tapping test may offer a practical alternative. This study examined whether accelerometer-derived features from unilateral foot-tapping can predict gait and TUG times across the adult lifespan.Approach.Seventy-eight adults aged 19-95 years (58 older adults: 80.25 ± 8.2 yrs; 20 young-to-midlife: 32.2 ± 14.1 yrs) performed 30-second unilateral foot-tapping trials with the dominant and nondominant foot. Time, frequency, and time-frequency domain features were extracted from triaxial accelerometer signals. Least absolute shrinkage and selection operator (LASSO) and Random Forest regression models were trained within a nested 5-fold cross-validation to predict gait and TUG.Main Results.Significant correlations (p< 0.05) were observed between foot-tapping features and both outcomes, with coefficients ranging from -0.5 to -0.35 for gait time and -0.6 to 0.55 for TUG time. Most of the corrected features were derived from time-frequency domain (∼65%) and time domain (∼35%), with the strongest associations observed for tapping rate, inter-tap variability, and variability in instantaneous tapping energy across trials. LASSO achieved lower average root mean square error (RMSE) than Random Forest for dominant-foot gait time (0.88 ± 0.23 s vs. 0.93 ± 0.21 s) and TUG time (2.76 ± 0.60 s vs. 2.88 ± 0.65 s), and for nondominant-foot gait time (0.89 ± 0.20 s vs 0.90 ± 0.20 s), and TUG time (2.93 ± 0.54 s vs. 2.96 ± 0.55 s). Prediction of both outcomes using the dominant foot with LASSO resulted in a lower RMSE than the nondominant foot.Significance.These findings suggest that accelerometer-based unilateral foot tapping may serve as a fast, space efficient, and low-burden complement to conventional mobility assessments. Further validation in larger clinical populations and comparison with additional regression methods are warranted.