Clinic-Oriented Feasibility of a Sensor-Fused Wearable for Upper-Limb Function
Thanyanee Srichaisak, Arissa Ieochai, Aueaphum Aueawattthanaphisut
TL;DR
This study demonstrates the technical feasibility of a sensor-fused wearable that combines sEMG, IMU, and force sensing to support upper-limb function. By on-device INT8 inference with a safety-bounded control policy, the system delivers low-latency assistance targeting the triceps brachii and EPB, while yielding clinician-relevant metrics such as Tremor Index, ROM, and Reps. In 12 healthy adults performing three ADL-like tasks, assistance reduced tremor prominence (TI) and increased movement throughput (ROM and Reps) with a median latency of 8.7 ms at 100 Hz and no adverse events, indicating practical viability for clinic-to-home use. The work lays the groundwork for IRB-approved patient trials, providing interpretable endpoints and a robust engineering-and-clinical reporting pipeline that supports future validation and deployment in rehabilitation workflows.
Abstract
Background: Upper-limb weakness and tremor (4--12 Hz) limit activities of daily living (ADL) and reduce adherence to home rehabilitation. Objective: To assess technical feasibility and clinician-relevant signals of a sensor-fused wearable targeting the triceps brachii and extensor pollicis brevis. Methods: A lightweight node integrates surface EMG (1 kHz), IMU (100--200 Hz), and flex/force sensors with on-device INT8 inference (Tiny 1D-CNN/Transformer) and a safety-bounded assist policy (angle/torque/jerk limits; stall/time-out). Healthy adults (n = 12) performed three ADL-like tasks. Primary outcomes: Tremor Index (TI), range of motion (ROM), repetitions (Reps min$^{-1}$). Secondary: EMG median-frequency slope (fatigue trend), closed-loop latency, session completion, and device-related adverse events. Analyses used subject-level paired medians with BCa 95\% CIs; exact Wilcoxon $p$-values are reported in the Results. Results: Assistance was associated with lower tremor prominence and improved task throughput: TI decreased by $-0.092$ (95\% CI [$-0.102$, $-0.079$]), ROM increased by $+12.65\%$ (95\% CI [$+8.43$, $+13.89$]), and Reps rose by $+2.99$ min$^{-1}$ (95\% CI [$+2.61$, $+3.35$]). Median on-device latency was 8.7 ms at a 100 Hz loop rate; all sessions were completed with no device-related adverse events. Conclusions: Multimodal sensing with low-latency, safety-bounded assistance produced improved movement quality (TI $\downarrow$) and throughput (ROM, Reps $\uparrow$) in a pilot technical-feasibility setting, supporting progression to IRB-approved patient studies. Trial registration: Not applicable (pilot non-clinical).