{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,4]],"date-time":"2026-09-04T22:54:18Z","timestamp":1788562458866,"version":"build-2803163510"},"reference-count":36,"publisher":"Public Library of Science (PLoS)","issue":"8","license":[{"start":{"date-parts":[[2025,8,12]],"date-time":"2025-08-12T00:00:00Z","timestamp":1754956800000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Faculty of Medicine, Khon Kaen University","award":["RU65203"],"award-info":[{"award-number":["RU65203"]}]},{"name":"The Neurological Society of Thailand."}],"content-domain":{"domain":["www.plosone.org"],"crossmark-restriction":false},"short-container-title":["PLoS One"],"abstract":"<jats:sec id=\"sec001\">\n<jats:title>Background<\/jats:title>\n<jats:p>Identifying bradykinesia is crucial for diagnosing Parkinson\u2019s disease (PD). Traditionally, the finger-tapping test has been used, relying on subjective assessments by physicians. Computer vision offers a non-contact and cost-effective alternative for assessing Parkinson\u2019s disease.<\/jats:p>\n<\/jats:sec>\n<jats:sec id=\"sec002\">\n<jats:title>Objective<\/jats:title>\n<jats:p>This study aimed to detect Parkinson\u2019s disease by identifying bradykinesia using computer vision in the finger-tapping test and applying machine learning techniques for both hands.<\/jats:p>\n<\/jats:sec>\n<jats:sec id=\"sec003\">\n<jats:title>Methods<\/jats:title>\n<jats:p>We recruited 100 patients with PD and healthy controls. Four neurologists assessed bradykinesia, and 10-second smartphone-recorded finger-tapping movements were analyzed using Google MediaPipe Hands software. Six machine learning models were trained using a nested cross-validation framework.<\/jats:p>\n<\/jats:sec>\n<jats:sec id=\"sec004\">\n<jats:title>Results<\/jats:title>\n<jats:p>The differences in tapping scores between the left and right hands were significantly greater in the PD group (2.8 (5.0) vs 0.4 (0.7), p\u2009=\u20090.001) than in the healthy controls. Moreover, the tapping amplitude variation and all amplitude decremental parameters in the PD group differed significantly from those of the standard controls. The PD group had significantly lower tapping scores than the normal subjects (right: 17.9 (7.8)\/ left: 17.9 (5.6) vs. right: 24.6 (7.3)\/ left: 24.6 (7.2), p\u2009&lt;\u20090.001). The support vector machine outperformed the other models. The most influential features were the tapping difference, followed by the tapping score (right hand) and tapping amplitude mean (right hand).<\/jats:p>\n<\/jats:sec>\n<jats:sec id=\"sec005\">\n<jats:title>Conclusions<\/jats:title>\n<jats:p>A computer vision method can accurately detect bradykinesia using the tapping feature from the finger-tapping method, which involves the simultaneous tapping of both hands.<\/jats:p>\n<\/jats:sec>","DOI":"10.1371\/journal.pone.0330373","type":"journal-article","created":{"date-parts":[[2025,8,12]],"date-time":"2025-08-12T17:34:53Z","timestamp":1755020093000},"page":"e0330373","update-policy":"https:\/\/doi.org\/10.1371\/journal.pone.corrections_policy","source":"Crossref","is-referenced-by-count":2,"title":["Screening for Parkinson\u2019s disease using \u201ccomputer vision\u201d"],"prefix":"10.1371","volume":"20","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8706-9665","authenticated-orcid":true,"given":"Narongrit","family":"Kasemsap","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Purinat","family":"Tikkapanyo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Panupong","family":"Wanjantuk","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0751-8967","authenticated-orcid":true,"given":"Nisa","family":"Vorasoot","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kannikar","family":"Kongbunkiat","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7125-9886","authenticated-orcid":true,"given":"Anupol","family":"Panitchote","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"340","published-online":{"date-parts":[[2025,8,12]]},"reference":[{"issue":"9996","key":"pone.0330373.ref001","doi-asserted-by":"crossref","first-page":"896","DOI":"10.1016\/S0140-6736(14)61393-3","article-title":"Parkinson\u2019s disease","volume":"386","author":"LV Kalia","year":"2015","journal-title":"Lancet"},{"issue":"12","key":"pone.0330373.ref002","doi-asserted-by":"crossref","first-page":"1591","DOI":"10.1002\/mds.26424","article-title":"MDS clinical diagnostic criteria for Parkinson\u2019s disease","volume":"30","author":"RB Postuma","year":"2015","journal-title":"Mov Disord"},{"issue":"15","key":"pone.0330373.ref003","doi-asserted-by":"crossref","first-page":"2129","DOI":"10.1002\/mds.22340","article-title":"Movement Disorder Society-sponsored revision of the Unified Parkinson\u2019s Disease Rating Scale (MDS-UPDRS): scale presentation and clinimetric testing results","volume":"23","author":"CG Goetz","year":"2008","journal-title":"Mov Disord"},{"issue":"4","key":"pone.0330373.ref004","doi-asserted-by":"crossref","first-page":"641","DOI":"10.1002\/1531-8257(200007)15:4<641::AID-MDS1007>3.0.CO;2-2","article-title":"The bradykinesia akinesia incoordination test (BRAIN TEST), an objective and user-friendly means to evaluate patients with Parkinsonism","volume":"15","author":"CN Homann","year":"2000","journal-title":"Mov Disord"},{"key":"pone.0330373.ref005","first-page":"760196","article-title":"Objective quantification of neuromotor symptoms in Parkinson\u2019s disease: implementation of a portable, computerized measurement tool","volume":"2010","author":"S Papapetropoulos","year":"2010","journal-title":"Parkinsons Dis"},{"issue":"1","key":"pone.0330373.ref006","doi-asserted-by":"crossref","first-page":"36","DOI":"10.1002\/1531-8257(200001)15:1<36::AID-MDS1008>3.0.CO;2-M","article-title":"Quantitative digitography (QDG): a sensitive measure of digital motor control in idiopathic Parkinson\u2019s disease","volume":"15","author":"HM Bronte-Stewart","year":"2000","journal-title":"Mov Disord"},{"issue":"10","key":"pone.0330373.ref007","doi-asserted-by":"crossref","first-page":"1286","DOI":"10.1002\/mds.20556","article-title":"Quantitative measurements of alternating finger tapping in Parkinson\u2019s disease correlate with UPDRS motor disability and reveal the improvement in fine motor control from medication and deep brain stimulation","volume":"20","author":"AL Taylor Tavares","year":"2005","journal-title":"Mov Disord"},{"key":"pone.0330373.ref008","doi-asserted-by":"crossref","first-page":"34468","DOI":"10.1038\/srep34468","article-title":"Computer keyboard interaction as an indicator of early Parkinson\u2019s disease","volume":"6","author":"L Giancardo","year":"2016","journal-title":"Sci Rep"},{"issue":"7","key":"pone.0330373.ref009","article-title":"A validation study of a smartphone-based finger tapping application for quantitative assessment of Bradykinesia in Parkinson\u2019s disease","volume":"11","author":"CY Lee","year":"2016","journal-title":"PLoS ONE"},{"issue":"3","key":"pone.0330373.ref010","doi-asserted-by":"crossref","first-page":"365","DOI":"10.1007\/s11517-010-0697-8","article-title":"Quantification of bradykinesia during clinical finger taps using a gyrosensor in patients with Parkinson\u2019s disease","volume":"49","author":"J-W Kim","year":"2011","journal-title":"Med Biol Eng Comput"},{"issue":"1","key":"pone.0330373.ref011","doi-asserted-by":"crossref","first-page":"27","DOI":"10.1016\/j.artmed.2013.11.004","article-title":"A computer vision framework for finger-tapping evaluation in Parkinson\u2019s disease","volume":"60","author":"T Khan","year":"2014","journal-title":"Artif Intell Med"},{"key":"pone.0330373.ref012","doi-asserted-by":"crossref","first-page":"101966","DOI":"10.1016\/j.artmed.2020.101966","article-title":"Supervised classification of bradykinesia in Parkinson\u2019s disease from smartphone videos","volume":"110","author":"S Williams","year":"2020","journal-title":"Artif Intell Med"},{"issue":"7","key":"pone.0330373.ref013","doi-asserted-by":"crossref","first-page":"2152","DOI":"10.1038\/s41596-019-0176-0","article-title":"Using DeepLabCut for 3D markerless pose estimation across species and behaviors","volume":"14","author":"T Nath","year":"2019","journal-title":"Nat Protoc"},{"key":"pone.0330373.ref014","doi-asserted-by":"crossref","first-page":"117003","DOI":"10.1016\/j.jns.2020.117003","article-title":"The discerning eye of computer vision: can it measure Parkinson\u2019s finger tap bradykinesia?","volume":"416","author":"S Williams","year":"2020","journal-title":"J Neurol Sci"},{"key":"pone.0330373.ref015","unstructured":"Lugaresi C, Tang J, Nash H, McClanahan C, Uboweja E, Hays M. MediaPipe: framework for building perception pipelines. 2019. https:\/\/arxiv.org\/abs\/1906.08172"},{"key":"pone.0330373.ref016","unstructured":"google-ai-edge. MediaPipe Hands. [Accessed 2025 February 14]. https:\/\/github.com\/google-ai-edge\/mediapipe\/blob\/master\/docs\/solutions\/hands.md"},{"issue":"1","key":"pone.0330373.ref017","doi-asserted-by":"crossref","first-page":"30","DOI":"10.1007\/s13755-021-00159-3","article-title":"Hand tremor detection in videos with cluttered background using neural network based approaches","volume":"9","author":"X Wang","year":"2021","journal-title":"Health Inf Sci Syst"},{"issue":"20","key":"pone.0330373.ref018","doi-asserted-by":"crossref","first-page":"7992","DOI":"10.3390\/s22207992","article-title":"Video-Based hand movement analysis of Parkinson patients before and after medication using high-frame-rate videos and MediaPipe","volume":"22","author":"G G\u00fcney","year":"2022","journal-title":"Sensors"},{"key":"pone.0330373.ref019","doi-asserted-by":"crossref","first-page":"106508","DOI":"10.1016\/j.bspc.2024.106508","article-title":"Hand tracking for clinical applications: Validation of the Google MediaPipe Hand (GMH) and the depth-enhanced GMH-D frameworks","volume":"96","author":"G Amprimo","year":"2024","journal-title":"Biomed Signal Process Control"},{"key":"pone.0330373.ref020","unstructured":"Zhang F, Bazarevsky V, Vakunov A, Tkachenka A, Sung G, Chang C. MediaPipe Hands: On-device Real-time Hand Tracking. 2020. http:\/\/arxiv.org\/abs\/2006.10214"},{"issue":"3","key":"pone.0330373.ref021","doi-asserted-by":"crossref","first-page":"261","DOI":"10.1038\/s41592-019-0686-2","article-title":"SciPy 1.0: fundamental algorithms for scientific computing in Python","volume":"17","author":"P Virtanen","year":"2020","journal-title":"Nat Methods"},{"issue":"85","key":"pone.0330373.ref022","first-page":"2825","article-title":"Scikit-learn: machine learning in Python","volume":"12","author":"F Pedregosa","year":"2011","journal-title":"J Machine Learn Res"},{"issue":"11","key":"pone.0330373.ref023","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pone.0224365","article-title":"Machine learning algorithm validation with a limited sample size","volume":"14","author":"A Vabalas","year":"2019","journal-title":"PLoS One"},{"issue":"1","key":"pone.0330373.ref024","doi-asserted-by":"crossref","first-page":"61","DOI":"10.1177\/001316447003000105","article-title":"Estimating the reliability, systematic error and random error of interval data","volume":"30","author":"K Krippendorff","year":"1970","journal-title":"Educ Psychol Measure"},{"key":"pone.0330373.ref025","doi-asserted-by":"crossref","first-page":"93","DOI":"10.1186\/s12874-016-0200-9","article-title":"Measuring inter-rater reliability for nominal data - which coefficients and confidence intervals are appropriate?","volume":"16","author":"A Zapf","year":"2016","journal-title":"BMC Med Res Methodol"},{"issue":"1","key":"pone.0330373.ref026","doi-asserted-by":"crossref","first-page":"29","DOI":"10.1148\/radiology.143.1.7063747","article-title":"The meaning and use of the area under a receiver operating characteristic (ROC) curve","volume":"143","author":"JA Hanley","year":"1982","journal-title":"Radiology"},{"key":"pone.0330373.ref027","article-title":"A unified approach to interpreting model predictions","volume":"30","author":"SM Lundberg","year":"2017","journal-title":"Adv Neural Inform Process Syst"},{"issue":"6","key":"pone.0330373.ref028","doi-asserted-by":"crossref","first-page":"953","DOI":"10.1007\/s11517-016-1467-z","article-title":"Quantifying Parkinson\u2019s disease finger-tapping severity by extracting and synthesizing finger motion properties","volume":"54","author":"Y Sano","year":"2016","journal-title":"Med Biol Eng Comput"},{"key":"pone.0330373.ref029","doi-asserted-by":"crossref","first-page":"45","DOI":"10.1016\/j.sleep.2020.07.019","article-title":"Instrumental analysis of finger tapping reveals a novel early biomarker of parkinsonism in idiopathic rapid eye movement sleep behaviour disorder","volume":"75","author":"R Krupi\u010dka","year":"2020","journal-title":"Sleep Med"},{"issue":"4","key":"pone.0330373.ref030","doi-asserted-by":"crossref","first-page":"1141","DOI":"10.1093\/brain\/aws038","article-title":"Hypokinesia without decrement distinguishes progressive supranuclear palsy from Parkinson\u2019s disease","volume":"135","author":"H Ling","year":"2012","journal-title":"Brain"},{"key":"pone.0330373.ref031","doi-asserted-by":"crossref","first-page":"66961","DOI":"10.1109\/ACCESS.2022.3183232","article-title":"Automatic detection pipeline for accessing the motor severity of Parkinson\u2019s disease in finger tapping and postural stability","volume":"10","author":"N Yang","year":"2022","journal-title":"IEEE Access"},{"key":"pone.0330373.ref032","doi-asserted-by":"crossref","unstructured":"Amprimo G, Rechichi I, Ferraris C, Olmo G. Objective assessment of the finger tapping task in Parkinson\u2019s disease and control subjects using Azure Kinect and machine learning. In: 2023 IEEE 36th International Symposium on Computer-Based Medical Systems (CBMS). 2023.","DOI":"10.1109\/CBMS58004.2023.00293"},{"key":"pone.0330373.ref033","doi-asserted-by":"crossref","unstructured":"Cao Z, Simon T, Wei SE, Sheikh Y. Realtime multi-person 2d pose estimation using part affinity fields. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2017.","DOI":"10.1109\/CVPR.2017.143"},{"key":"pone.0330373.ref034","doi-asserted-by":"crossref","unstructured":"Wang C, Bochkovskiy A, Liao HY. YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors. 2022. http:\/\/arxiv.org\/abs\/2207.02696","DOI":"10.1109\/CVPR52729.2023.00721"},{"key":"pone.0330373.ref035","article-title":"Alphapose: Whole-body regional multi-person pose estimation and tracking in real-time","author":"HS Fang","year":"2022","journal-title":"IEEE Transact Pattern Analysis Machine Intell"},{"issue":"1","key":"pone.0330373.ref036","doi-asserted-by":"crossref","first-page":"10","DOI":"10.1038\/s41531-023-00454-8","article-title":"Computer vision quantification of whole-body Parkinsonian bradykinesia using a large multi-site population","volume":"9","author":"G Morinan","year":"2023","journal-title":"NPJ Parkinsons Dis"}],"container-title":["PLOS One"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0330373","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,12]],"date-time":"2025-08-12T17:35:00Z","timestamp":1755020100000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0330373"}},"subtitle":[],"editor":[{"given":"John A.","family":"Thompson","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2025,8,12]]},"references-count":36,"journal-issue":{"issue":"8","published-online":{"date-parts":[[2025,8,12]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pone.0330373","relation":{},"ISSN":["1932-6203"],"issn-type":[{"value":"1932-6203","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,8,12]]}}}