RESUMO
Objective: To determine the feasibility of a self-directed training protocol to promote actual arm use in everyday life. The secondary aim was to explore the initial efficacy on upper extremity (UE) outcome measures. Design: Feasibility study using multiple methods. Setting: Home and outpatient research lab. Participants: Fifteen adults (6 women, 9 men, mean age=53.08 years) with chronic stroke living in the community. There was wide range of UE functional levels, ranging from dependent stabilizer (limited function) to functional assist (high function). Intervention: Use My Arm-Remote protocol. Phase 1 consisted of clinician training on motivational interviewing (MI). Phase 2 consisted of MI sessions with participants to determine participant generated goals, training activities, and training schedules. Phase 3 consisted of UE task-oriented training (60 minutes/day, 5 days/week, for 4 weeks). Participants received daily surveys through an app to monitor arm training behavior and weekly virtual check-ins with clinicians to problem-solve challenges and adjust treatment plans. Outcome Measures: Primary outcome measures were feasibility domains after intervention, measured by quantitative study data and qualitative semi-structured interviews. Secondary outcomes included the Canadian Occupational Performance Measure (COPM), Motor Activity Log (MAL), Fugl-Meyer Assessment (FMA), and accelerometry-based duration of use metric measured at baseline, discharge, and 4-week follow-up. Results: The UMA-R was feasible in the following domains: recruitment rate, retention rate, intervention acceptance, intervention delivery, adherence frequency, and safety. Adherence to duration of daily practice did not meet our criteria. Improvements in UE outcomes were achieved at discharge and maintained at follow-up as measured by COPM-Performance subscale (F[1.42, 19.83]=17.72, P<.001) and COPM-Satisfaction subscale (F[2, 28]=14.73, P<.001), MAL (F[1.31, 18.30]=12.05, P<.01) and the FMA (F[2, 28]=16.62, P<.001). Conclusion: The UMA-R was feasible and safe to implement for individuals living in the community with chronic stroke. Adherence duration was identified as area of refinement. Participants demonstrated improvements in standardized UE outcomes to support initial efficacy of the UMA-R. Shared decision-making and behavior change frameworks can support the implementation of UE self-directed rehabilitation. Our results warrant the refinement and further testing of the UMA-R.
RESUMO
Automatic assessment of impairment and disease severity is a key challenge in data-driven medicine. We propose a framework to address this challenge, which leverages AI models trained exclusively on healthy individuals. The COnfidence-Based chaRacterization of Anomalies (COBRA) score exploits the decrease in confidence of these models when presented with impaired or diseased patients to quantify their deviation from the healthy population. We applied the COBRA score to address a key limitation of current clinical evaluation of upper-body impairment in stroke patients. The gold-standard Fugl-Meyer Assessment (FMA) requires in-person administration by a trained assessor for 30-45 minutes, which restricts monitoring frequency and precludes physicians from adapting rehabilitation protocols to the progress of each patient. The COBRA score, computed automatically in under one minute, is shown to be strongly correlated with the FMA on an independent test cohort for two different data modalities: wearable sensors (ρ = 0.814, 95% CI [0.700,0.888]) and video (ρ = 0.736, 95% C.I [0.584, 0.838]). To demonstrate the generalizability of the approach to other conditions, the COBRA score was also applied to quantify severity of knee osteoarthritis from magnetic-resonance imaging scans, again achieving significant correlation with an independent clinical assessment (ρ = 0.644, 95% C.I [0.585,0.696]).