Smartphone-derived multidomain features including voice, finger-tapping movement and gait aid early identification of Parkinson’s disease

Abstract Smart devices can easily capture changes in voice, movements, and gait in people with Parkinson’s disease (PD). We investigated whether smartphone-derived multimodal features combined with machine learning algorithms can aid in early PD identification. We recruited 496 participants, split i...

Full description

Saved in:
Bibliographic Details
Main Authors: Wee-Shin Lim, Sung-Pin Fan, Shu-I Chiu, Meng-Ciao Wu, Pu-He Wang, Kun-Pei Lin, Yung-Ming Chen, Pei-Ling Peng, Jyh-Shing Roger Jang, Chin-Hsien Lin
Format: Article
Language:English
Published: Nature Portfolio 2025-05-01
Series:npj Parkinson's Disease
Online Access:https://doi.org/10.1038/s41531-025-00953-w
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849311632539254784
author Wee-Shin Lim
Sung-Pin Fan
Shu-I Chiu
Meng-Ciao Wu
Pu-He Wang
Kun-Pei Lin
Yung-Ming Chen
Pei-Ling Peng
Jyh-Shing Roger Jang
Chin-Hsien Lin
author_facet Wee-Shin Lim
Sung-Pin Fan
Shu-I Chiu
Meng-Ciao Wu
Pu-He Wang
Kun-Pei Lin
Yung-Ming Chen
Pei-Ling Peng
Jyh-Shing Roger Jang
Chin-Hsien Lin
author_sort Wee-Shin Lim
collection DOAJ
description Abstract Smart devices can easily capture changes in voice, movements, and gait in people with Parkinson’s disease (PD). We investigated whether smartphone-derived multimodal features combined with machine learning algorithms can aid in early PD identification. We recruited 496 participants, split into a training cohort (127 PD patients during “on” phase and 198 age-matched controls) and a test dataset (86 patients during “off” phase and 85 age-matched controls). Multidomain features from smartphone recordings were analyzed using machine learning classifiers with integration of a hyperparameter grid. Single-modality models for voice, hand movements, and gait showed diagnostic values of 0.88, 0.74, and 0.81, respectively, with test dataset values of 0.80, 0.74, and 0.76. An integrated multimodal model using a support vector machine improved performance to 0.86 and achieved 0.82 for identifying early-stage PD during the “off” phase. A smartphone-based integrated multimodality model combining voice, hand movement, and gait shows promise for early PD identification.
format Article
id doaj-art-8be60ed1813e44dc8a27ed252eb10cc8
institution Kabale University
issn 2373-8057
language English
publishDate 2025-05-01
publisher Nature Portfolio
record_format Article
series npj Parkinson's Disease
spelling doaj-art-8be60ed1813e44dc8a27ed252eb10cc82025-08-20T03:53:21ZengNature Portfolionpj Parkinson's Disease2373-80572025-05-0111111410.1038/s41531-025-00953-wSmartphone-derived multidomain features including voice, finger-tapping movement and gait aid early identification of Parkinson’s diseaseWee-Shin Lim0Sung-Pin Fan1Shu-I Chiu2Meng-Ciao Wu3Pu-He Wang4Kun-Pei Lin5Yung-Ming Chen6Pei-Ling Peng7Jyh-Shing Roger Jang8Chin-Hsien Lin9Department of Computer Science and Information Engineering, National Taiwan UniversityDepartment of Neurology, National Taiwan University HospitalDepartment of Computer Science, National Chengchi UniversityDepartment of Electronic Engineering, National Taiwan UniversityDepartment of Computer Science and Information Engineering, National Taiwan UniversityDepartment of Geriatrics, National Taiwan University Hospital, College of Medicine, National Taiwan UniversityDepartment of Internal Medicine, National Taiwan University Hospital, College of Medicine, National Taiwan UniversityDepartment of Neurology, National Taiwan University HospitalDepartment of Computer Science and Information Engineering, National Taiwan UniversityDepartment of Neurology, National Taiwan University HospitalAbstract Smart devices can easily capture changes in voice, movements, and gait in people with Parkinson’s disease (PD). We investigated whether smartphone-derived multimodal features combined with machine learning algorithms can aid in early PD identification. We recruited 496 participants, split into a training cohort (127 PD patients during “on” phase and 198 age-matched controls) and a test dataset (86 patients during “off” phase and 85 age-matched controls). Multidomain features from smartphone recordings were analyzed using machine learning classifiers with integration of a hyperparameter grid. Single-modality models for voice, hand movements, and gait showed diagnostic values of 0.88, 0.74, and 0.81, respectively, with test dataset values of 0.80, 0.74, and 0.76. An integrated multimodal model using a support vector machine improved performance to 0.86 and achieved 0.82 for identifying early-stage PD during the “off” phase. A smartphone-based integrated multimodality model combining voice, hand movement, and gait shows promise for early PD identification.https://doi.org/10.1038/s41531-025-00953-w
spellingShingle Wee-Shin Lim
Sung-Pin Fan
Shu-I Chiu
Meng-Ciao Wu
Pu-He Wang
Kun-Pei Lin
Yung-Ming Chen
Pei-Ling Peng
Jyh-Shing Roger Jang
Chin-Hsien Lin
Smartphone-derived multidomain features including voice, finger-tapping movement and gait aid early identification of Parkinson’s disease
npj Parkinson's Disease
title Smartphone-derived multidomain features including voice, finger-tapping movement and gait aid early identification of Parkinson’s disease
title_full Smartphone-derived multidomain features including voice, finger-tapping movement and gait aid early identification of Parkinson’s disease
title_fullStr Smartphone-derived multidomain features including voice, finger-tapping movement and gait aid early identification of Parkinson’s disease
title_full_unstemmed Smartphone-derived multidomain features including voice, finger-tapping movement and gait aid early identification of Parkinson’s disease
title_short Smartphone-derived multidomain features including voice, finger-tapping movement and gait aid early identification of Parkinson’s disease
title_sort smartphone derived multidomain features including voice finger tapping movement and gait aid early identification of parkinson s disease
url https://doi.org/10.1038/s41531-025-00953-w
work_keys_str_mv AT weeshinlim smartphonederivedmultidomainfeaturesincludingvoicefingertappingmovementandgaitaidearlyidentificationofparkinsonsdisease
AT sungpinfan smartphonederivedmultidomainfeaturesincludingvoicefingertappingmovementandgaitaidearlyidentificationofparkinsonsdisease
AT shuichiu smartphonederivedmultidomainfeaturesincludingvoicefingertappingmovementandgaitaidearlyidentificationofparkinsonsdisease
AT mengciaowu smartphonederivedmultidomainfeaturesincludingvoicefingertappingmovementandgaitaidearlyidentificationofparkinsonsdisease
AT puhewang smartphonederivedmultidomainfeaturesincludingvoicefingertappingmovementandgaitaidearlyidentificationofparkinsonsdisease
AT kunpeilin smartphonederivedmultidomainfeaturesincludingvoicefingertappingmovementandgaitaidearlyidentificationofparkinsonsdisease
AT yungmingchen smartphonederivedmultidomainfeaturesincludingvoicefingertappingmovementandgaitaidearlyidentificationofparkinsonsdisease
AT peilingpeng smartphonederivedmultidomainfeaturesincludingvoicefingertappingmovementandgaitaidearlyidentificationofparkinsonsdisease
AT jyhshingrogerjang smartphonederivedmultidomainfeaturesincludingvoicefingertappingmovementandgaitaidearlyidentificationofparkinsonsdisease
AT chinhsienlin smartphonederivedmultidomainfeaturesincludingvoicefingertappingmovementandgaitaidearlyidentificationofparkinsonsdisease