Wearable Sensor to Monitor Quality of Upper Limb Task Practice for Stroke Survivors at Home

Area of Science:

• Neuroscience
• Rehabilitation Medicine
• Biomedical Engineering

Background:

• Stroke survivors often have persistent upper extremity impairment, limiting daily activities.
• Effective upper limb recovery necessitates high repetitions of task-specific practice.
• Current home-based rehabilitation lacks tools to monitor the quality of task practice, potentially leading to maladaptive neuroplasticity.

Purpose of the Study:

• To evaluate the feasibility of classifying movement quality during at-home upper limb task practice using a wearable inertial measurement unit (IMU).

Main Methods:

• Nineteen stroke survivors performed four functional upper limb tasks at home, wearing an IMU on their paretic wrist and recording themselves.
• Lab-based data served as a reference for classifying home movement quality using dynamic time warping.
• Therapist labeling distinguished between correct and incorrect movement quality.

Main Results:

• The IMU system achieved 92% accuracy and an F1 score of 0.95 in classifying home movement quality across all tasks.
• Analysis identified specific movement types contributing to misclassifications.
• The findings support the feasibility of remote monitoring for upper limb rehabilitation.

Conclusions:

• A wearable IMU system demonstrates feasibility for monitoring movement quality in stroke survivors' home-based rehabilitation.
• This technology can provide valuable feedback to improve task practice and enhance motor recovery.
• Further development could lead to a robust system for remote upper limb rehabilitation support post-stroke.