Dataset Information

Heterogeneous digital biomarker integration out-performs patient self-reports in predicting Parkinson's disease.

ABSTRACT: Parkinson's disease (PD) is one of the first diseases where digital biomarkers demonstrated excellent performance in differentiating disease from healthy individuals. However, no study has systematically compared and leveraged multiple types of digital biomarkers to predict PD. Particularly, machine learning works on the fine-motor skills of PD are limited. Here, we developed deep learning methods that achieved an AUC (Area Under the receiver operator characteristic Curve) of 0.933 in identifying PD patients on 6418 individuals using 75048 tapping accelerometer and position records. Performance of tapping is superior to gait/rest and voice-based models obtained from the same benchmark population. Assembling the three models achieved a higher AUC of 0.944. Notably, the models not only correlated strongly to, but also performed better than patient self-reported symptom scores in diagnosing PD. This study demonstrates the complementary predictive power of tapping, gait/rest and voice data and establishes integrative deep learning-based models for identifying PD.

SUBMITTER: Deng K

PROVIDER: S-EPMC8763910 | biostudies-literature | 2022 Jan

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Heterogeneous digital biomarker integration out-performs patient self-reports in predicting Parkinson's disease.

Deng Kaiwen K Li Yueming Y Zhang Hanrui H Wang Jian J Albin Roger L RL Guan Yuanfang Y

Communications biology 20220117 1

Parkinson's disease (PD) is one of the first diseases where digital biomarkers demonstrated excellent performance in differentiating disease from healthy individuals. However, no study has systematically compared and leveraged multiple types of digital biomarkers to predict PD. Particularly, machine learning works on the fine-motor skills of PD are limited. Here, we developed deep learning methods that achieved an AUC (Area Under the receiver operator characteristic Curve) of 0.933 in identifyin ...[more]

PMID: 35039601

Similar Datasets

Project description:ObjectivePrior research has identified that people with Parkinson's reporting lower levels of self-efficacy exhibit worsening motor and non-motor symptomology, reduced quality of life, and self-management. Our key objective was to conduct a scoping review examining the impact of digital health technologies on self-efficacy in people with Parkinson's.DesignA scoping review using Arksey and O'Malley's (2005) framework was undertaken.Data sourcesMEDLINE, Embase, PsychINFO, CINAHL, Web of Science, IEEE Xplore, and Google Scholar principally for grey literature were searched from 1 January 2008 to the 24th of July 2024.Eligibility criteria for selecting studiesPrimary studies which incorporated digital health technologies, measured self-efficacy and had a sample population of people with Parkinson's were searched.Data extraction and synthesisFollowing identification of potentially eligible records, two independent reviewers undertook title and abstract screening, followed by full-text screening. Data was extracted using our earlier published data extraction sheet which incorporated the Practical Reviews in Self-Management Support (PRISMS) taxonomy, and the template for intervention description and replication (TIDieR) checklist. Data was extracted from a Microsoft Excel spreadsheet and synthesised by describing themes, demographic data and numerical data.ResultsFrom 33 165 unique records following screening and independent review by two reviewers, 11 eligible records were found. Of these five elevated self-efficacy to a statistically significant level, five did not and one lowered self-efficacy. Of the studies which raised self-efficacy to a statistically significant level, all adopted a multimodal approach with a variety of devices. Thematically, these devices were focused on physical activity, falls/falls prevention, or both. The level of heterogeneity precluded comparisons between studies.ConclusionsThis scoping review identified significant knowledge and evidence gaps in the literature, and the limited number of eligible studies make these findings not generalisable. Future self-management research might benefit from also considering self-efficacy.

Dataset Information

Heterogeneous digital biomarker integration out-performs patient self-reports in predicting Parkinson's disease.

Publications

Heterogeneous digital biomarker integration out-performs patient self-reports in predicting Parkinson's disease.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets