Assessing balance is crucial in neurological rehabilitation, yet while wearable sensors enable real-world monitoring, identifying reliable digital biomarkers remains challenging. This study utilized a high-fidelity instrumented walkway to determine which gait parameters best predict balance impairment, providing robust targets for future wearable applications. We analyzed 49 steady-state gait metrics from 140 individuals with diverse neurological conditions. Using statistical analysis and machine learning, we evaluated these parameters against objective force plate sway scores and clinical fall-history labels. Group analysis identified 16 parameters significantly distinguishing fallers from non-fallers, and a neural network classified fallers with an area under the curve of 0.75. Across all analytical approaches, overall gait variability, e.g., Stride Width S.D. and the Gait Variability Index, emerged as a universal predictor of balance impairment and fall risk. Furthermore, while traditional linear models emphasized spatial postural control, machine learning classification uniquely identified inter-limb asymmetry as a premier driver of fall prediction. These findings indicate that instrumented gait analysis effectively identifies digital biomarkers for balance deficits. Isolating these specific metrics provides a clear blueprint for meaningful metrics required for continuous objective monitoring and future development of personalized, adaptive rehabilitation strategies.
Concurrent Validity and Between-System Agreement of a Commercial Wearable Inertial Sensor System for Gait and Postural Sway Assessment in Progressive Supranuclear Palsy
Wearable inertial measurement units (IMUs) offer an accessible alternative to optical motion capture (MoCap) gait analysis, but their performance in Progressive Supranuclear Palsy (PSP) requires validation. We assessed the concurrent validity of IMU-derived versus MoCap-derived gait metrics and static postural sway in 30 patients with PSP using Bland–Altman analysis, Intraclass Correlation Coefficients (ICC), and Spearman rank correlations. Finally, we assessed equivalence using the Two one-sided tests (TOST) procedure. Multivariable linear regression was used to determine whether clinical severity, as measured by the PSP Rating Scale (PSPRS), independently predicted absolute IMU measurement error while controlling for patient age and gait velocity. IMUs demonstrated excellent between-system agreement for parameters such as cadence (100.76 ± 11.42 vs. 100.52 ± 11.59) and cycle time (1.21 ± 0.15 vs. 1.22 ± 0.15; ICC > 0.98), despite a systematic underestimation of gait velocity (p < 0.05). Agreement significantly diminished for micro-phases (e.g., single/double support times) and spatial asymmetry. Interestingly, the TOST procedure revealed that only sagittal and transverse trunk kinematics were equivalent between systems, with all other measures failing to find equivalency. For static sway, the IMU demonstrated strong rank-order correspondence for tracking relative postural instability (ρ = 0.82, p < 0.05). Multivariable analysis revealed that higher PSPRS scores are independently associated with greater between-system discrepancies in support phases and pelvic and trunk kinematics (p < 0.05), irrespective of reduced gait speed. These findings highlight the need to develop disease-specific algorithms, rather than relying on normative commercial models, to establish reliable digital biomarkers for monitoring progressive motor decline.