Using AI to measure Parkinson’s disease severity at home
Abstract We present an artificial intelligence (AI) system to remotely assess the motor performance of individuals with Parkinson’s disease (PD). In our study, 250 global participants performed a standardized motor task involving finger-tapping in front of a webcam. To establish the severity of Park...
Main Authors: | , , , , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Nature Portfolio
2023-08-01
|
Series: | npj Digital Medicine |
Online Access: | https://doi.org/10.1038/s41746-023-00905-9 |
_version_ | 1797451365846351872 |
---|---|
author | Md Saiful Islam Wasifur Rahman Abdelrahman Abdelkader Sangwu Lee Phillip T. Yang Jennifer Lynn Purks Jamie Lynn Adams Ruth B. Schneider Earl Ray Dorsey Ehsan Hoque |
author_facet | Md Saiful Islam Wasifur Rahman Abdelrahman Abdelkader Sangwu Lee Phillip T. Yang Jennifer Lynn Purks Jamie Lynn Adams Ruth B. Schneider Earl Ray Dorsey Ehsan Hoque |
author_sort | Md Saiful Islam |
collection | DOAJ |
description | Abstract We present an artificial intelligence (AI) system to remotely assess the motor performance of individuals with Parkinson’s disease (PD). In our study, 250 global participants performed a standardized motor task involving finger-tapping in front of a webcam. To establish the severity of Parkinsonian symptoms based on the finger-tapping task, three expert neurologists independently rated the recorded videos on a scale of 0–4, following the Movement Disorder Society Unified Parkinson’s Disease Rating Scale (MDS-UPDRS). The inter-rater reliability was excellent, with an intra-class correlation coefficient (ICC) of 0.88. We developed computer algorithms to obtain objective measurements that align with the MDS-UPDRS guideline and are strongly correlated with the neurologists’ ratings. Our machine learning model trained on these measures outperformed two MDS-UPDRS certified raters, with a mean absolute error (MAE) of 0.58 points compared to the raters’ average MAE of 0.83 points. However, the model performed slightly worse than the expert neurologists (0.53 MAE). The methodology can be replicated for similar motor tasks, providing the possibility of evaluating individuals with PD and other movement disorders remotely, objectively, and in areas with limited access to neurological care. |
first_indexed | 2024-03-09T14:53:38Z |
format | Article |
id | doaj.art-d5d0e082b58f4067b5cc575615d7fea9 |
institution | Directory Open Access Journal |
issn | 2398-6352 |
language | English |
last_indexed | 2024-03-09T14:53:38Z |
publishDate | 2023-08-01 |
publisher | Nature Portfolio |
record_format | Article |
series | npj Digital Medicine |
spelling | doaj.art-d5d0e082b58f4067b5cc575615d7fea92023-11-26T14:19:43ZengNature Portfolionpj Digital Medicine2398-63522023-08-016111410.1038/s41746-023-00905-9Using AI to measure Parkinson’s disease severity at homeMd Saiful Islam0Wasifur Rahman1Abdelrahman Abdelkader2Sangwu Lee3Phillip T. Yang4Jennifer Lynn Purks5Jamie Lynn Adams6Ruth B. Schneider7Earl Ray Dorsey8Ehsan Hoque9Department of Computer Science, University of RochesterDepartment of Computer Science, University of RochesterDepartment of Computer Science, University of RochesterDepartment of Computer Science, University of RochesterDepartment of Neurology, University of Rochester Medical CenterDepartment of Neurology, University of Rochester Medical CenterDepartment of Neurology, University of Rochester Medical CenterDepartment of Neurology, University of Rochester Medical CenterDepartment of Neurology, University of Rochester Medical CenterDepartment of Computer Science, University of RochesterAbstract We present an artificial intelligence (AI) system to remotely assess the motor performance of individuals with Parkinson’s disease (PD). In our study, 250 global participants performed a standardized motor task involving finger-tapping in front of a webcam. To establish the severity of Parkinsonian symptoms based on the finger-tapping task, three expert neurologists independently rated the recorded videos on a scale of 0–4, following the Movement Disorder Society Unified Parkinson’s Disease Rating Scale (MDS-UPDRS). The inter-rater reliability was excellent, with an intra-class correlation coefficient (ICC) of 0.88. We developed computer algorithms to obtain objective measurements that align with the MDS-UPDRS guideline and are strongly correlated with the neurologists’ ratings. Our machine learning model trained on these measures outperformed two MDS-UPDRS certified raters, with a mean absolute error (MAE) of 0.58 points compared to the raters’ average MAE of 0.83 points. However, the model performed slightly worse than the expert neurologists (0.53 MAE). The methodology can be replicated for similar motor tasks, providing the possibility of evaluating individuals with PD and other movement disorders remotely, objectively, and in areas with limited access to neurological care.https://doi.org/10.1038/s41746-023-00905-9 |
spellingShingle | Md Saiful Islam Wasifur Rahman Abdelrahman Abdelkader Sangwu Lee Phillip T. Yang Jennifer Lynn Purks Jamie Lynn Adams Ruth B. Schneider Earl Ray Dorsey Ehsan Hoque Using AI to measure Parkinson’s disease severity at home npj Digital Medicine |
title | Using AI to measure Parkinson’s disease severity at home |
title_full | Using AI to measure Parkinson’s disease severity at home |
title_fullStr | Using AI to measure Parkinson’s disease severity at home |
title_full_unstemmed | Using AI to measure Parkinson’s disease severity at home |
title_short | Using AI to measure Parkinson’s disease severity at home |
title_sort | using ai to measure parkinson s disease severity at home |
url | https://doi.org/10.1038/s41746-023-00905-9 |
work_keys_str_mv | AT mdsaifulislam usingaitomeasureparkinsonsdiseaseseverityathome AT wasifurrahman usingaitomeasureparkinsonsdiseaseseverityathome AT abdelrahmanabdelkader usingaitomeasureparkinsonsdiseaseseverityathome AT sangwulee usingaitomeasureparkinsonsdiseaseseverityathome AT philliptyang usingaitomeasureparkinsonsdiseaseseverityathome AT jenniferlynnpurks usingaitomeasureparkinsonsdiseaseseverityathome AT jamielynnadams usingaitomeasureparkinsonsdiseaseseverityathome AT ruthbschneider usingaitomeasureparkinsonsdiseaseseverityathome AT earlraydorsey usingaitomeasureparkinsonsdiseaseseverityathome AT ehsanhoque usingaitomeasureparkinsonsdiseaseseverityathome |