Variables influencing wearable sensor outcome estimates in individuals with stroke and incomplete spinal cord injury: a pilot investigation validating two research grade sensors

This study looked at how well wearable sensors measure physical activity in people with stroke and incomplete spinal cord injury (iSCI). It checked if the standard calculations used by these sensors work accurately for these individuals, comparing the sensor data to gold standard measures. The study also examined whether the location of the sensor on the body, the type of sensor, and the kind of activity being done affect how accurate the measurements are. The goal was to see if these factors influence the reliability of physical activity readings from wearable sensors in people with neurological conditions. The findings suggest that sensor location, type, and activity characteristics, along with the specific condition of the person, all play a role in how accurately wearable sensors measure physical activity. Using customized calculations that consider these factors could improve the accuracy of these measurements in people with stroke and iSCI.

• 1
  The sensor type, sensor location, activity characteristics and the population specific condition influences the validity of estimation of physical activity metrics using standard proprietary algorithms.
• 2
  Implementing population specific customized algorithms accounting for the influences of sensor location, type and activity characteristics for estimating physical activity metrics in individuals with stroke and iSCI could be beneficial.
• 3
  The physical activity metrics (EE, MET and step count) estimated by SPAs could be influenced significantly by these factors across the spectrum of activity levels studied.