Supplementary material for Machine learning analysis of wearable sensor data from mobility testing distinguishes Parkinson's disease from other forms of parkinsonism

Khalil, Rana M.; Shulman, Lisa M.; Gruber-Baldini, Ann L.; Hausdorff, Jeffrey M.; von Coelln, Rainer; Cummings, Michael P.

Supplementary material for Machine learning analysis of wearable sensor data from mobility testing distinguishes Parkinson's disease from other forms of parkinsonism

dc.contributor.advisor	Cummings, Michael P.
dc.contributor.author	Khalil, Rana M.
dc.contributor.author	Shulman, Lisa M.
dc.contributor.author	Gruber-Baldini, Ann L.
dc.contributor.author	Hausdorff, Jeffrey M.
dc.contributor.author	von Coelln, Rainer
dc.contributor.author	Cummings, Michael P.
dc.date.accessioned	2024-03-13T21:11:58Z
dc.date.available	2024-03-13T21:11:58Z
dc.date.issued	2024-03-13
dc.description.abstract	Parkinson's Disease (PD) and other forms of parkinsonism share characteristic motor symptoms, including tremor, bradykinesia, and rigidity. This overlap in the clinical presentation creates a diagnostic challenge, underscoring the need for objective differentiation tools. In this study, we analyzed wearable sensor data collected during mobility testing from 260 PD participants and 18 participants with etiologically diverse forms of parkinsonism. Our findings illustrate that machine learning-based analysis of data from a single wearable sensor can effectively distinguish idiopathic PD from non-PD parkinsonism with a balanced accuracy of 83.5%, comparable to expert diagnosis. Moreover, we found that diagnostic performance can be improved through severity-based partitioning of participants, achieving a balanced accuracy of 95.9%, 91.2% and 100% for mild, moderate and severe cases, respectively. Beyond its diagnostic implications, our results suggest the possibility of streamlining the testing protocol by using the Timed Up and Go test as a single mobility task. Furthermore, we present a detailed analysis of several case studies of challenging scenarios commonly encountered in clinical practice, including diagnostic uncertainty at the initial visit, and changes in clinical diagnosis at a subsequent visit. Together, these findings demonstrate the potential of applying machine learning on sensor-based measures of mobility to distinguish between PD and other forms of parkinsonism.
dc.description.sponsorship	Funding for this study was provided by a University of Maryland MPower Seed Grant Award to R.v.C. and M.P.C. The Health Outcomes Measurement (HOME) study is supported by the Rosalyn Newman Foundation. Funding for the study on mobility analysis in parkinsonism (“Towards Next-Generation Phenotyping in Parkinson Disease: Quantitative Analysis of Gait and Balance Using a Portable Biosensor Device”) was supported by a pilot grant and a Junior Scholar Award from the University of Maryland Claude Pepper Older Americans Independence Center to R.v.C.
dc.identifier	https://doi.org/10.13016/evaq-ytcg
dc.identifier.uri	http://hdl.handle.net/1903/32369
dc.language.iso	en_US
dc.relation.isAvailableAt	College of Computer, Mathematical & Natural Sciences	en_us
dc.relation.isAvailableAt	Computer Science	en_us
dc.relation.isAvailableAt	Digital Repository at the University of Maryland	en_us
dc.relation.isAvailableAt	University of Maryland (College Park, MD)	en_us
dc.rights	CC0 1.0 Universal	en
dc.rights.uri	http://creativecommons.org/publicdomain/zero/1.0/
dc.title	Supplementary material for Machine learning analysis of wearable sensor data from mobility testing distinguishes Parkinson's disease from other forms of parkinsonism
dc.type	Dataset
local.equitableAccessSubmission	No