Detecting Sensitive Mobility Features for Parkinson's Disease Stages Via Machine Learning.

BACKGROUND: It is not clear how specific gait measures reflect disease severity across the disease spectrum in Parkinson's disease (PD). OBJECTIVE: To identify the gait and mobility measures that are most sensitive and reflective of PD motor stages and determine the optimal sensor location in each disease stage. METHODS: Cross-sectional wearable-sensor records were collected in 332 patients with PD (Hoehn and Yahr scale I-III) and 100 age-matched healthy controls. Sensors were adhered to the participant's lower back, bilateral ankles, and wrists. Study participants walked in a ~15-meter corridor for 1 minute under two walking conditions: (1) preferred, usual walking speed and (2) walking while engaging in a cognitive task (dual-task). A subgroup (n = 303, 67% PD) also performed the Timed Up and Go test. Multiple machine-learning feature selection and classification algorithms were applied to discriminate between controls and PD and between the different PD severity stages. RESULTS: High discriminatory values were found between motor disease stages with mean sensitivity in the range 72%-83%, specificity 69%-80%, and area under the curve (AUC) 0.76-0.90. Measures from upper-limb sensors best discriminated controls from early PD, turning measures obtained from the trunk sensor were prominent in mid-stage PD, and stride timing and regularity were discriminative in more advanced stages. CONCLUSIONS: Applying machine-learning to multiple, wearable-derived features reveals that different measures of gait and mobility are associated with and discriminate distinct stages of PD. These disparate feature sets can augment the objective monitoring of disease progression and may be useful for cohort selection and power analyses in clinical trials of PD. © 2021 International Parkinson and Movement Disorder Society.

Two-Year Trajectory of Fall Risk in People With Parkinson Disease: A Latent Class Analysis.

OBJECTIVE: To examine fall risk trajectories occurring naturally in a sample of individuals with early to middle stage Parkinson disease (PD). DESIGN: Latent class analysis, specifically growth mixture modeling (GMM), of longitudinal fall risk trajectories. SETTING: Assessments were conducted at 1 of 4 universities. PARTICIPANTS: Community-dwelling participants with PD of a longitudinal cohort study who attended at least 2 of 5 assessments over a 2-year follow-up period (N=230). INTERVENTIONS: Not applicable. MAIN OUTCOME MEASURES: Fall risk trajectory (low, medium, or high risk) and stability of fall risk trajectory (stable or fluctuating). Fall risk was determined at 6 monthly intervals using a simple clinical tool based on fall history, freezing of gait, and gait speed. RESULTS: The GMM optimally grouped participants into 3 fall risk trajectories that closely mirrored baseline fall risk status (P=.001). The high fall risk trajectory was most common (42.6%) and included participants with longer and more severe disease and with higher postural instability and gait disability (PIGD) scores than the low and medium fall risk trajectories (P<.001). Fluctuating fall risk (posterior probability <0.8 of belonging to any trajectory) was found in only 22.6% of the sample, most commonly among individuals who were transitioning to PIGD predominance. CONCLUSIONS: Regardless of their baseline characteristics, most participants had clear and stable fall risk trajectories over 2 years. Further investigation is required to determine whether interventions to improve gait and balance may improve fall risk trajectories in people with PD.