ABSTRACT

Objective: To introduce a technical framework for evaluating digital measures for their ability to track Parkinson’s disease (PD) progression and apply the framework to digital measures of physical activity.

Background: Wearable sensors enable remote, objective, and continuous monitoring of physical activity in people with Parkinson’s disease (PwPD) [1, 2]. However, there is little consensus on how to validate digital measures for monitoring disease progression. This is especially relevant in early stage PD, where traditional gold-standard clinical instruments (e.g., MDS-UPDRS) may not be sensitive enough to detect within-subject progression in the initial years following diagnosis.

Method: We included two years of passively collected data from the Personalized Parkinson Project via a wrist-worn sensor in 223 participants within ≤ 4 years of PD diagnosis at enrollment. Physical activity measures were derived from inertial motor unit (IMU) data [3, 4]. We trained ML models to generate composite measures using monthly aggregated single measures as input, with clinical assessment scores (MDS-UPDRS part 2 and 3) and patient reported outcomes (e.g., PDQ-39) as reference labels. Five ML models (linear regression with Lasso, ridge or elasticnet regularization, random forest regression, gradient boosted regression trees) were trained. We also compared different loss functions and evaluated model training approaches that do not require reference labels.

Results: The derived composite measures demonstrated statistically significant monotonic change over 2 years, with an absolute value of Cohen’s D ranging from 0.188 to 0.610 (random slope model with test for time effect, p < 0.05). As a comparison, the modified MDS-UPDRS Part 3 (excluding speech, facial expression and tremor items) has a Cohen’s D of 0.455. The test-retest reliability (ICC) of two consecutive months of the measures ranged from 0.705 to 0.911. The best measure had a Cohen’s D of 0.610, and ICC of 0.884.

Conclusion: This work provides a foundation to utilize ML techniques in building composite measures. The composite measures may provide a more comprehensive picture of one’s physical function and potentially be more sensitive to capture physical activity change along with the progression of PD.

Parkinson’s Disease
Neurology
Digital Biomarkers