Development of a smart glove for affordable diagnosis of stroke-driven upper extremity paresis

Stroke is the third highest cause of disability-adjusted-life-years (DALYs) and is becoming an important cause of disability in low-and-middleincome countries (LMICs). It has been found that in developing countries, especially in rural areas, patients suffering from disabilities due to stroke do not receive appropriate on-time treatment due to infrastructural limitations and financial barriers. Conventional rehabilitation management systems fail to cater the demanding requirements thereby arousing the need for evolution of wearable m-Health devices for uninterrupted health monitoring of patients with upper extremity paresis. In the present research, we have developed an instrumented glove incorporated with wearable sensors (bend sensors, pressure sensors, and accelerometers) for continuous monitoring of activities of daily living (ADLs) by capturing and transmitting sensory information related to finger bend angle, tip pressure, and acceleration or orientation while doing specified grasps. The sensors were calibrated using standard instruments before installation. Two subjects, a healthy individual and an individual suffering from upper extremity disability after stroke impaired, were employed for experimental validation. The subjects were instructed to perform certain pre-defined tasks and the related finger bending angles, finger-tip pressures, and acceleration were recorded. The trend of the dataset obtained was graphically visualized and analyzed for statistical parameters like mean, variance, maxima, and minima, leading to a generation of appreciably distinguishable results that discriminated against a stroke patient from a healthy individual. Therefore, the present glove-based stroke diagnosis method can be adopted for an affordable and efficient stroke rehabilitation process while promoting m-health at the same time.