Visualization-Driven Time-Series Extraction from Wearable Systems Can Facilitate Differentiation of Passive ADL Characteristics among Stroke and Healthy Older Adults.

Wearable technologies allow the measurement of unhindered activities of daily living (ADL) among patients who had a stroke in their natural settings. However, methods to extract meaningful information from large multi-day datasets are limited. This study investigated new visualization-driven time-series extraction methods for distinguishing activities from stroke and healthy adults. Fourteen stroke and fourteen healthy adults wore a wearable sensor at the L5/S1 position for three consecutive days and collected accelerometer data passively in the participant's naturalistic environment. Data from visualization facilitated selecting information-rich time series, which resulted in classification accuracy of 97.3% using recurrent neural networks (RNNs). Individuals with stroke showed a negative correlation between their body mass index (BMI) and higher-acceleration fraction produced during ADL. We also found individuals with stroke made lower activity amplitudes than healthy counterparts in all three activity bands (low, medium, and high). Our findings show that visualization-driven time series can accurately classify movements among stroke and healthy groups using a deep recurrent neural network. This novel visualization-based time-series extraction from naturalistic data provides a physical basis for analyzing passive ADL monitoring data from real-world environments. This time-series extraction method using unit sphere projections of acceleration can be used by a slew of analysis algorithms to remotely track progress among stroke survivors in their rehabilitation program and their ADL abilities.