Journal of Parkinson s Disease · 2020 · 92 citations · 43 references
Health ProfessionsPhysical MedicineFunctional Movement AssessmentMovement AnalysisMovement DisordersGait AnalysisGait AssessmentGait EvaluationMobility AssessmentMobility ImpairmentParkinson DiseaseBiomarkersContinuous MonitoringDigital BiomarkersInertial SensorsLogistic RegressionMobility Outcome MeasurementOutcome MeasuresParkinson Disease Biomarkers
Digital mobility biomarkers are increasingly used in Parkinson’s disease research, and turning and gait variability measures have emerged as the most reliable indicators for distinguishing patients from healthy controls. This study aimed to identify which continuous‑wear digital outcome measures of mobility best discriminate Parkinson’s disease patients from healthy controls over a week of monitoring. Twenty‑nine PD patients and twenty‑seven age‑matched healthy controls wore inertial sensors on both feet, the lumbar spine, and sometimes the wrists for a week, from which 43 mobility measures across five domains were extracted and evaluated using AUC calculations and logistic regression with a best‑subsets selection strategy. Six measures achieved AUCs above 0.80, with turn angle (AUC = 0.89) and swing‑time variability (AUC = 0.87) being the most discriminative, indicating that turning and variability metrics should be prioritized in future digital‑biomarker studies of Parkinson’s disease.
Identifying digital biomarkers of mobility is important for clinical trials in Parkinson's disease (PD).To determine which digital outcome measures of mobility discriminate mobility in people with PD from healthy control (HC) subjects over a week of continuous monitoring.We recruited 29 people with PD, and 27 age-matched HC subjects. Subjects were asked to wear three inertial sensors (Opal by APDM) attached to both feet and to the lumbar region, and a subset of subjects also wore two wrist sensors, for a week of continuous monitoring. We derived 43 digital outcome measures of mobility grouped into five domains. An Area Under Curve (AUC) was calculated for each digital outcome measures of mobility, and logistic regression employing a 'best subsets selection strategy' was used to find combinations of measures that discriminated mobility in PD from HC.Duration of recordings was 66±14 hours in the PD and 59±16 hours in the HC. Out of a total of 43 digital outcome measures of mobility, we found six digital outcome measures of mobility with AUC > 0.80. Turn angle (AUC = 0.89, 95% CI: 0.79-0.97) and swing time variability (AUC = 0.87, 95% CI: 0.75-0.96) were the most discriminative individual measures. Turning measures were most consistently selected via the best subsets strategy to discriminate people with PD from HC, followed by gait variability measures.Clinical studies and clinical practice with digital biomarkers of daily life mobility in PD should include turning and variability measures.
43
An introduction to ROC analysis
Tom Fawcett · Pattern Recognition Letters · 2005 · 21.3K citations
pROC: an open-source package for R and S+ to analyze and compare ROC curves
Xavier Robin, Natacha Turck, Alexandre Hainard et al. · BMC Bioinformatics · 2011 · 14K citations · Full text
Christopher G. Goetz, Barbara C. Tilley, Stephanie R. Shaftman et al. · Movement Disorders · 2008 · 7.5K citations · Full text