{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,16]],"date-time":"2026-05-16T05:36:59Z","timestamp":1778909819789,"version":"3.51.4"},"reference-count":21,"publisher":"Oxford University Press (OUP)","issue":"6","license":[{"start":{"date-parts":[[2024,3,18]],"date-time":"2024-03-18T00:00:00Z","timestamp":1710720000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/academic.oup.com\/pages\/standard-publication-reuse-rights"}],"funder":[{"name":"nQ-Medical Inc."},{"DOI":"10.13039\/100000002","name":"NIH","doi-asserted-by":"publisher","award":["R01NS121154"],"award-info":[{"award-number":["R01NS121154"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000002","name":"NIH","doi-asserted-by":"publisher","award":["R21EB029575"],"award-info":[{"award-number":["R21EB029575"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000002","name":"NIH","doi-asserted-by":"publisher","award":["U01AG070112"],"award-info":[{"award-number":["U01AG070112"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,5,20]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:sec>\n                  <jats:title>Objective<\/jats:title>\n                  <jats:p>Passive monitoring of touchscreen interactions generates keystroke dynamic signals that can be used to detect and track neurological conditions such as Parkinson\u2019s disease (PD) and psychomotor impairment with minimal burden on the user. However, this typically requires datasets with clinically confirmed labels collected in standardized environments, which is challenging, especially for a large subject pool. This study validates the efficacy of a self-supervised learning method in reducing the reliance on labels and evaluates its generalizability.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Materials and Methods<\/jats:title>\n                  <jats:p>We propose a new type of self-supervised loss combining Barlow Twins loss, which attempts to create similar feature representations with reduced feature redundancy for samples coming from the same subject, and a Dissimilarity loss, which promotes uncorrelated features for samples generated by different subjects. An encoder is first pre-trained using this loss on unlabeled data from an uncontrolled setting, then fine-tuned with clinically validated data. Our experiments test the model generalizability with controls and subjects with PD on 2 independent datasets.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Results<\/jats:title>\n                  <jats:p>Our approach showed better generalization compared to previous methods, including a feature engineering strategy, a deep learning model pre-trained on Parkinsonian signs, and a traditional supervised model.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Discussion<\/jats:title>\n                  <jats:p>The absence of standardized data acquisition protocols and the limited availability of annotated datasets compromise the generalizability of supervised models. In these contexts, self-supervised models offer the advantage of learning more robust patterns from the data, bypassing the need for ground truth labels.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Conclusion<\/jats:title>\n                  <jats:p>This approach has the potential to accelerate the clinical validation of touchscreen typing software for neurodegenerative diseases.<\/jats:p>\n               <\/jats:sec>","DOI":"10.1093\/jamia\/ocae050","type":"journal-article","created":{"date-parts":[[2024,3,18]],"date-time":"2024-03-18T19:37:08Z","timestamp":1710790628000},"page":"1239-1246","source":"Crossref","is-referenced-by-count":2,"title":["Generalizing Parkinson\u2019s disease detection using keystroke dynamics: a self-supervised approach"],"prefix":"10.1093","volume":"31","author":[{"given":"Shikha","family":"Tripathi","sequence":"first","affiliation":[{"name":"D. Bradley McWilliams School of Biomedical Informatics, University of Texas Health Science Center at Houston , Houston, TX 77030, United States"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Alejandro","family":"Acien","sequence":"additional","affiliation":[{"name":"nQ Medical , MA 02142, United States"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ashley A","family":"Holmes","sequence":"additional","affiliation":[{"name":"nQ Medical , MA 02142, United States"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Teresa","family":"Arroyo-Gallego","sequence":"additional","affiliation":[{"name":"nQ Medical , MA 02142, United States"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4862-2277","authenticated-orcid":false,"given":"Luca","family":"Giancardo","sequence":"additional","affiliation":[{"name":"D. Bradley McWilliams School of Biomedical Informatics, University of Texas Health Science Center at Houston , Houston, TX 77030, United States"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"286","published-online":{"date-parts":[[2024,3,18]]},"reference":[{"issue":"5","key":"2024052019464257400_ocae050-B1","doi-asserted-by":"crossref","first-page":"385","DOI":"10.1016\/S1474-4422(21)00030-2","article-title":"Challenges in the diagnosis of Parkinson\u2019s disease","volume":"20","author":"Tolosa","year":"2021","journal-title":"Lancet Neurol"},{"issue":"1","key":"2024052019464257400_ocae050-B2","doi-asserted-by":"crossref","first-page":"9","DOI":"10.1001\/jamaneurol.2017.3299","article-title":"The Parkinson pandemic\u2014a call to action","volume":"75","author":"Dorsey","year":"2018","journal-title":"JAMA Neurol"},{"issue":"1","key":"2024052019464257400_ocae050-B3","doi-asserted-by":"crossref","first-page":"9678","DOI":"10.1038\/srep09678","article-title":"Psychomotor impairment detection via finger interactions with a computer keyboard during natural typing","volume":"5","author":"Giancardo","year":"2015","journal-title":"Sci Rep"},{"issue":"3","key":"2024052019464257400_ocae050-B4","doi-asserted-by":"crossref","first-page":"e89","DOI":"10.2196\/jmir.9462","article-title":"Detecting motor impairment in early Parkinson\u2019s disease via natural typing interaction with keyboards: validation of the neuroQWERTY approach in an uncontrolled at-home setting","volume":"20","author":"Arroyo-Gallego","year":"2018","journal-title":"J Med Internet Res"},{"issue":"9","key":"2024052019464257400_ocae050-B5","doi-asserted-by":"crossref","first-page":"1994","DOI":"10.1109\/TBME.2017.2664802","article-title":"Detection of motor impairment in Parkinson\u2019s disease via mobile touchscreen typing","volume":"64","author":"Arroyo-Gallego","year":"2017","journal-title":"IEEE Trans Biomed Eng"},{"issue":"1","key":"2024052019464257400_ocae050-B6","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":"Giancardo","year":"2016","journal-title":"Sci Rep"},{"issue":"4","key":"2024052019464257400_ocae050-B7","doi-asserted-by":"crossref","first-page":"fcac194","DOI":"10.1093\/braincomms\/fcac194","article-title":"A novel framework to estimate cognitive impairment via finger interaction with digital devices","volume":"4","author":"Holmes","year":"2022","journal-title":"Brain Commun"},{"issue":"1","key":"2024052019464257400_ocae050-B8","doi-asserted-by":"crossref","first-page":"182","DOI":"10.1109\/TBME.2022.3187309","article-title":"Keystroke-dynamics for Parkinson\u2019s disease signs detection in an at-home uncontrolled population: a new benchmark and method","volume":"70","author":"Tripathi","year":"2023","journal-title":"IEEE Trans Biomed Eng"},{"issue":"1","key":"2024052019464257400_ocae050-B9","doi-asserted-by":"crossref","first-page":"21370","DOI":"10.1038\/s41598-020-78418-8","article-title":"Unobtrusive detection of Parkinson\u2019s disease from multi-modal and in-the-wild sensor data using deep learning techniques","volume":"10","author":"Papadopoulos","year":"2020","journal-title":"Sci Rep"},{"issue":"1","key":"2024052019464257400_ocae050-B10","doi-asserted-by":"crossref","first-page":"12623","DOI":"10.1038\/s41598-020-69369-1","article-title":"Screening of Parkinsonian subtle fine-motor impairment from touchscreen typing via deep learning","volume":"10","author":"Iakovakis","year":"2020","journal-title":"Sci Rep"},{"key":"2024052019464257400_ocae050-B11","doi-asserted-by":"crossref","first-page":"119522","DOI":"10.1016\/j.eswa.2023.119522","article-title":"Imbalanced ensemble learning in determining Parkinson\u2019s disease using keystroke dynamics","volume":"217","author":"Roy","year":"2023","journal-title":"Expert Syst Appl"},{"key":"2024052019464257400_ocae050-B12","first-page":"578","author":"Dhir","year":"2020"},{"issue":"1","key":"2024052019464257400_ocae050-B13","doi-asserted-by":"crossref","first-page":"7690","DOI":"10.1038\/s41598-022-11865-7","article-title":"Diagnostic accuracy of keystroke dynamics as digital biomarkers for fine motor decline in neuropsychiatric disorders: a systematic review and meta-analysis","volume":"12","author":"Alfalahi","year":"2022","journal-title":"Sci Rep"},{"issue":"10","key":"2024052019464257400_ocae050-B14","doi-asserted-by":"crossref","first-page":"1488","DOI":"10.1002\/mds.27772","article-title":"Remote monitoring of treatment response in Parkinson\u2019s disease: the habit of typing on a computer","volume":"34","author":"Matarazzo","year":"2019","journal-title":"Mov Disord"},{"key":"2024052019464257400_ocae050-B15","first-page":"3535","article-title":"Early Parkinson\u2019s disease detection via touchscreen typing analysis using convolutional neural networks","volume":"2019","author":"Iakovakis","year":"2019","journal-title":"Annu Int Conf IEEE Eng Med Biol Soc"},{"key":"2024052019464257400_ocae050-B16","author":"Klingelhoefer","year":"2017"},{"key":"2024052019464257400_ocae050-B17","first-page":"3960","author":"Jiang","year":"2021"},{"issue":"1","key":"2024052019464257400_ocae050-B18","doi-asserted-by":"crossref","first-page":"160011","DOI":"10.1038\/sdata.2016.11","article-title":"The mPower study, Parkinson disease mobile data collected using ResearchKit","volume":"3","author":"Bot","year":"2016","journal-title":"Sci Data"},{"issue":"suppl 2","key":"2024052019464257400_ocae050-B19","article-title":"Medical evaluation as gold standard to control iPrognosis application derived data for early Parkinson\u2019s disease detection [abstract]","volume":"34","author":"Klingelhoefer","year":"2019","journal-title":"Mov Disord"},{"issue":"12","key":"2024052019464257400_ocae050-B20","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":"Postuma","year":"2015","journal-title":"Mov Disord"},{"key":"2024052019464257400_ocae050-B21","first-page":"12310","author":"Zbontar","year":"2021"}],"container-title":["Journal of the American Medical Informatics Association"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/jamia\/article-pdf\/31\/6\/1239\/57769004\/ocae050.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/jamia\/article-pdf\/31\/6\/1239\/57769004\/ocae050.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,5,20]],"date-time":"2024-05-20T19:47:42Z","timestamp":1716234462000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/jamia\/article\/31\/6\/1239\/7630959"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,3,18]]},"references-count":21,"journal-issue":{"issue":"6","published-online":{"date-parts":[[2024,3,18]]},"published-print":{"date-parts":[[2024,5,20]]}},"URL":"https:\/\/doi.org\/10.1093\/jamia\/ocae050","relation":{},"ISSN":["1067-5027","1527-974X"],"issn-type":[{"value":"1067-5027","type":"print"},{"value":"1527-974X","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2024,6,1]]},"published":{"date-parts":[[2024,3,18]]}}}