Simplification of Mobility Tests and Data Processing to Increase Applicability of Wearable Sensors as Diagnostic Tools for Parkinson’s Disease
Authors:
- Rana M. KhalilRKRana M. Khalil
- Lisa M. ShulmanLSLisa M. Shulman
- Ann L. Gruber-BaldiniAGAnn L. Gruber-Baldini
- Sunita ShakyaSSSunita Shakya
- Rebecca FendersonRFRebecca Fenderson
- Maxwell Van HovenMHMaxwell Van Hoven
- Jeffrey M. HausdorffJeffrey M. Hausdorff
- Rainer von CoellnRCRainer von Coelln
- Michael P. CummingsMCMichael P. Cummings
Open Access
Abstract
Quantitative mobility analysis using wearable sensors, while promising as a diagnostic tool for Parkinson’s disease (PD), is not commonly applied in clinical settings. Major obstacles include uncertainty regarding the best protocol for instrumented mobility testing and subsequent data processing, as well as the added workload and complexity of this multi-step process. To simplify sensor-based mobility testing in diagnosing PD, we analyzed data from 262 PD participants and 50 controls performing several motor tasks wearing a sensor on their lower back containing a triaxial accelerometer and a triaxial gyroscope. Using ensembles of heterogeneous machine learning models incorporating a range of classifiers trained on a set of sensor features, we show that our models effectively differentiate between participants with PD and controls, both for mixed-stage PD (92.6% accuracy) and a group selected for mild PD only (89.4% accuracy). Omitting algorithmic segmentation of complex mobility tasks decreased the diagnostic accuracy of our models, as did the inclusion of kinesiological features. Feature importance analysis revealed that Timed Up and Go (TUG) tasks to contribute the highest-yield predictive features, with only minor decreases in accuracy for models based on cognitive TUG as a single mobility task. Our machine learning approach facilitates major simplification of instrumented mobility testing without compromising predictive performance.Keywords
Funding Information
- University of Maryland MPower Seed Grant Award (R.v.C. and M.P.C.), the Rosalyn Newman Foundation (L.M.S.), and the University of Maryland Claude D. Pepper Older Americans Independence Center (P30-AG028747)
This publication has 186 references indexed in Scilit:
- Gait analysis with wearables predicts conversion to Parkinson diseaseAnnals of Neurology, 2019
- Prioritized research recommendations from the National Institute of Neurological Disorders and Stroke Parkinson'sDisease 2014 conferenceAnnals of Neurology, 2014
- Quantitative wearable sensors for objective assessment of Parkinson's diseaseMovement Disorders, 2013
- The Clinically Important Difference on the Unified Parkinson's Disease Rating ScaleArchives of Neurology, 2010
- The evolution of disability in Parkinson diseaseMovement Disorders, 2008
- Evidence of increased odds of essential tremor in Parkinson's diseaseMovement Disorders, 2008
- Perceived imbalance and risk of Parkinson's diseaseMovement Disorders, 2008
- Movement Disorder Society Task Force report on the Hoehn and Yahr staging scale: Status and recommendations The Movement Disorder Society Task Force on rating scales for Parkinson's diseaseMovement Disorders, 2004
- The Unified Parkinson's Disease Rating Scale (UPDRS): Status and recommendationsMovement Disorders, 2003
- Association between essential tremor and Parkinson's diseaseAnnals of Neurology, 1985