Supplementary materials for statistical and machine learning analyses demonstrate test-retest reliability assessment is misled by focusing on total duration of mobility tasks in Parkinson's disease

Abstract

Mobility tasks like the Timed Up and Go test (TUG), cognitive TUG (cogTUG), and walking with turns provide insight into dynamic motor control, balance, and cognitive functions affected by Parkinson’s disease (PD). We evaluate the test-retest reliability of these tasks by assessing the performance of machine learning models based on quantitative sensor-derived measures, and statistical measures to examine total duration, subtask duration, and other quantitative measures across both trials. We show that the diagnostic accuracy of differentiating between PD and control participants decreases from the first to the second trial of our mobility tasks, suggesting that mobility testing can be simplified by not repeating tasks without losing relevant information. Although the total duration remains relatively consistent between trials, there is more variability in subtask duration and sensor-derived measures, evident in the differences in machine learning model performance and statistical metrics. Relying solely on total task duration and conventional statistical metrics to gauge the reliability of mobility tasks overlooks the nuanced variations in movement captured by other quantitative measures.