{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T07:27:01Z","timestamp":1775028421758,"version":"3.50.1"},"reference-count":36,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2025,8,27]],"date-time":"2025-08-27T00:00:00Z","timestamp":1756252800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2025,8,27]],"date-time":"2025-08-27T00:00:00Z","timestamp":1756252800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/100000002","name":"National Institutes of Health","doi-asserted-by":"crossref","award":["1OT2OD032581-01"],"award-info":[{"award-number":["1OT2OD032581-01"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/100000002","name":"National Institutes of Health","doi-asserted-by":"crossref","award":["1OT2OD032581-01"],"award-info":[{"award-number":["1OT2OD032581-01"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/100000002","name":"National Institutes of Health","doi-asserted-by":"crossref","award":["1OT2OD032581-01"],"award-info":[{"award-number":["1OT2OD032581-01"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/100000002","name":"National Institutes of Health","doi-asserted-by":"crossref","award":["1OT2OD032581-01"],"award-info":[{"award-number":["1OT2OD032581-01"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["npj Digit. Med."],"abstract":"<jats:title>Abstract<\/jats:title>\n          <jats:p>We investigate issues pertaining to algorithmic fairness and digital health equity within the context of using machine learning to predict Parkinson\u2019s Disease (PD) with data recorded from structured assessments of finger and hand movements. We evaluate the impact of demographic bias and bias related to device type and handedness. We collected data from 251 participants (99 with PD or suspected PD, 152 without PD or any suspicion of PD). Using a random forest model, we observe 92% accuracy, 94% AUROC, 86% sensitivity, 92% specificity, and 84% F1-score. When examining only F1-score differences across groups, no significant bias appears. However, a closer look reveals bias regarding positive prediction and error rates. While we find that sex and ethnicity have no statistically significant impact on PD predictions, biases exist regarding device type and dominant hand, as evidenced by disparate impact and equalized odds. Our findings suggest that remote digital health diagnostics may exhibit underrecognized biases related to handedness and device characteristics, the latter of which can act as a proxy for socioeconomic factors.<\/jats:p>","DOI":"10.1038\/s41746-025-01934-2","type":"journal-article","created":{"date-parts":[[2025,8,27]],"date-time":"2025-08-27T03:34:38Z","timestamp":1756265678000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Quantifying device type and handedness biases in a remote Parkinson\u2019s disease AI-powered assessment"],"prefix":"10.1038","volume":"8","author":[{"given":"Zerin Nasrin","family":"Tumpa","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Md Rahat Shahriar","family":"Zawad","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lydia","family":"Sollis","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shubham","family":"Parab","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Irene Y.","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Peter","family":"Washington","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,8,27]]},"reference":[{"key":"1934_CR1","doi-asserted-by":"publisher","first-page":"S3","DOI":"10.3233\/JPD-181474","volume":"8","author":"ER Dorsey","year":"2018","unstructured":"Dorsey, E. R., Sherer, T., Okun, M. S. & Bloem, B. R. The emerging evidence of the Parkinson pandemic. J. Parkinsons Dis. 8, S3\u2013S8 (2018).","journal-title":"J. Parkinsons Dis."},{"key":"1934_CR2","doi-asserted-by":"publisher","first-page":"384","DOI":"10.1212\/01.wnl.0000247740.47667.03","volume":"68","author":"ER Dorsey","year":"2007","unstructured":"Dorsey, E. R. et al. Projected number of people with Parkinson disease in the most populous nations, 2005 through 2030. Neurology 68, 384\u2013386 (2007).","journal-title":"Neurology"},{"key":"1934_CR3","doi-asserted-by":"crossref","unstructured":"Almalaq, A., Dai, X., Zhang, J., Hanrahan, S. & Nedrud, J. Causality graph learning on cortical information flow in Parkinson\u2019s disease patients during behaviour tests. In Proc. 49th Asilomar Conference on Signals Systems, and Computers 925\u2013929 (IEEE, 2015).","DOI":"10.1109\/ACSSC.2015.7421273"},{"key":"1934_CR4","doi-asserted-by":"crossref","unstructured":"Benba, A., Jilbab, A., Hammouch, A. & Sandabad, S. Voiceprints analysis using MFCC and SVM for detecting patients with Parkinson\u2019s disease. In Proc. IEEE International Conference on Electronics and Information Technology (ICEIT) 300\u2013304 (IEEE, 2015).","DOI":"10.1109\/EITech.2015.7163000"},{"key":"1934_CR5","doi-asserted-by":"publisher","first-page":"255","DOI":"10.1016\/j.asoc.2018.10.022","volume":"74","author":"CO Sakar","year":"2019","unstructured":"Sakar, C. O. et al. A comparative analysis of speech signal processing algorithms for Parkinson\u2019s disease classification and the use of the tunable-factor wavelet transform. Appl. Soft Comput. 74, 255\u2013263 (2019).","journal-title":"Appl. Soft Comput."},{"key":"1934_CR6","doi-asserted-by":"crossref","unstructured":"Alqahtani, E. J., Alshamrani, F. H., Syed, H. F. & Olatunji, S. O. Classification of Parkinson\u2019s disease using NNge classification algorithm. In Proc. 21st Saudi Computer Society National Computer Conference (NCC) 1\u20137 (IEEE, 2018).","DOI":"10.1109\/NCG.2018.8592989"},{"key":"1934_CR7","first-page":"79","volume":"136","author":"CR Pereira","year":"2016","unstructured":"Pereira, C. R. et al. A new computer vision-based approach to aid the diagnosis of Parkinson\u2019s disease. Comput. Biol. Med. 136, 79\u201388 (2016).","journal-title":"Comput. Biol. Med."},{"key":"1934_CR8","doi-asserted-by":"publisher","first-page":"366","DOI":"10.1016\/j.future.2018.02.009","volume":"83","author":"E Abdulhay","year":"2018","unstructured":"Abdulhay, E. et al. Gait and tremor investigation using machine learning techniques for the diagnosis of Parkinson\u2019s disease. Future Gener. Comput. Syst. 83, 366\u2013373 (2018).","journal-title":"Future Gener. Comput. Syst."},{"key":"1934_CR9","doi-asserted-by":"publisher","first-page":"376","DOI":"10.1016\/j.ifacol.2021.10.285","volume":"54","author":"V Asanza","year":"2021","unstructured":"Asanza, V. et al. Classification of subjects with Parkinson\u2019s disease using finger tapping dataset. IFAC-PapersOnLine 54, 376\u2013381 (2021).","journal-title":"IFAC-PapersOnLine"},{"key":"1934_CR10","doi-asserted-by":"publisher","first-page":"e0188226","DOI":"10.1371\/journal.pone.0188226","volume":"12","author":"WR Adams","year":"2017","unstructured":"Adams, W. R. High-accuracy detection of early Parkinson\u2019s disease using multiple characteristics of finger movement while typing. PLoS One 12, e0188226 (2017).","journal-title":"PLoS One"},{"key":"1934_CR11","doi-asserted-by":"publisher","first-page":"e49898","DOI":"10.2196\/49898","volume":"7","author":"S Parab","year":"2023","unstructured":"Parab, S., Boster, J. & Washington, P. Parkinson's disease recognition using a gamified website: machine learning development and usability study. JMIR Form. Res. 7, e49898 (2023).","journal-title":"JMIR Form. Res."},{"key":"1934_CR12","doi-asserted-by":"publisher","first-page":"59","DOI":"10.1002\/mdc3.12239","volume":"3","author":"P Kassavetis","year":"2016","unstructured":"Kassavetis, P. et al. Developing a tool for remote digital assessment of Parkinson\u2019s disease. Mov. Disord. Clin. Pract. 3, 59\u201364 (2016).","journal-title":"Mov. Disord. Clin. Pract."},{"key":"1934_CR13","doi-asserted-by":"publisher","first-page":"34","DOI":"10.3389\/fneur.2015.00034","volume":"6","author":"S Papapetropoulos","year":"2015","unstructured":"Papapetropoulos, S., Mitsi, G. & Espay, A. J. Digital health revolution: is it time for affordable remote monitoring for Parkinson\u2019s disease?. Front. Neurol. 6, 34 (2015).","journal-title":"Front. Neurol."},{"key":"1934_CR14","doi-asserted-by":"publisher","first-page":"e16414","DOI":"10.2196\/16414","volume":"8","author":"D Gatsios","year":"2020","unstructured":"Gatsios, D. et al. Feasibility and utility of mHealth for the remote monitoring of Parkinson\u2019s disease: ancillary study of the PD_manager randomized controlled trial. JMIR Mhealth Uhealth 8, e16414 (2020).","journal-title":"JMIR Mhealth Uhealth"},{"key":"1934_CR15","doi-asserted-by":"publisher","unstructured":"Negi, A. S. et al. Remote real-time digital monitoring fills a critical gap in the management of Parkinson\u2019s disease. medRxiv. https:\/\/doi.org\/10.1101\/2024.12.12.24318893 (2024).","DOI":"10.1101\/2024.12.12.24318893"},{"key":"1934_CR16","doi-asserted-by":"publisher","first-page":"137","DOI":"10.1038\/s41531-024-00751-w","volume":"10","author":"SL Hoffman","year":"2024","unstructured":"Hoffman, S. L. et al. Comprehensive real-time remote monitoring for Parkinson\u2019s disease using quantitative DigitoGraphy. npj Parkinsons Dis. 10, 137 (2024).","journal-title":"npj Parkinsons Dis."},{"key":"1934_CR17","doi-asserted-by":"publisher","unstructured":"Zawad, M. R. S., Tumpa, Z. N., Sollis, L., Parab, S. & Washington, P. Deep learning prediction of Parkinson\u2019s disease using remotely collected structured mouse trace data. medRxiv https:\/\/doi.org\/10.1101\/2024.10.27.24316195 (2024).","DOI":"10.1101\/2024.10.27.24316195"},{"key":"1934_CR18","first-page":"47","volume":"8","author":"DB Neharika","year":"2020","unstructured":"Neharika, D. B. & Anusuya, S. Machine learning algorithms for detection of Parkinson\u2019s disease using motor symptoms: speech and tremor. Int. J. Recent Technol. Eng. 8, 47\u201350 (2020).","journal-title":"Int. J. Recent Technol. Eng."},{"key":"1934_CR19","doi-asserted-by":"publisher","first-page":"828","DOI":"10.1109\/JBHI.2013.2245674","volume":"17","author":"BE Sakar","year":"2013","unstructured":"Sakar, B. E. et al. Collection and analysis of a Parkinson speech dataset with multiple types of sound recordings. IEEE J. Biomed. Health Inform. 17, 828\u2013834 (2013).","journal-title":"IEEE J. Biomed. Health Inform."},{"key":"1934_CR20","doi-asserted-by":"publisher","unstructured":"Al-Wahishi, A., Belal, N. & Ghanem, N. Diagnosis of Parkinson\u2019s disease by deep learning techniques using handwriting dataset. In Proc. International Symposium on Signal Processing and Intelligent Recognition Systems (SIRS). https:\/\/doi.org\/10.1007\/978-981-16-0425-6_10 (Springer, 2020).","DOI":"10.1007\/978-981-16-0425-6_10"},{"key":"1934_CR21","unstructured":"Isenkul, M., Sakar, B. & Kursun, O. Improved spiral test using digitized graphics tablet for monitoring Parkinson\u2019s disease. In Proc. 2nd International Conference on e-Health Telemedicine (ICEHTM) 5 (ACM, 2014)."},{"key":"1934_CR22","doi-asserted-by":"publisher","first-page":"1488","DOI":"10.1002\/mds.27772","volume":"34","author":"M Matarazzo","year":"2019","unstructured":"Matarazzo, M. et al. Remote monitoring of treatment response in Parkinson\u2019s disease: the habit of typing on a computer. Mov. Disord. 34, 1488\u20131495 https:\/\/doi.org\/10.1002\/mds.27772 (2019).","journal-title":"Mov. Disord."},{"key":"1934_CR23","doi-asserted-by":"publisher","first-page":"e89","DOI":"10.2196\/jmir.9462","volume":"20","author":"T Arroyo-Gallego","year":"2018","unstructured":"Arroyo-Gallego, T. et al. 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. J. Med. Internet Res. 20, e89 https:\/\/doi.org\/10.2196\/jmir.9462 (2018).","journal-title":"J. Med. Internet Res."},{"key":"1934_CR24","doi-asserted-by":"publisher","first-page":"2746","DOI":"10.3390\/biomedicines10112746","volume":"10","author":"LS Bernardo","year":"2022","unstructured":"Bernardo, L. S. et al. Modified SqueezeNet architecture for Parkinson\u2019s disease detection based on keypress data. Biomedicines 10, 2746 (2022).","journal-title":"Biomedicines"},{"key":"1934_CR25","doi-asserted-by":"publisher","first-page":"35","DOI":"10.1038\/s41531-022-00288-w","volume":"8","author":"MB Makarious","year":"2022","unstructured":"Makarious, M. B. et al. Multi-modality machine learning predicting Parkinson\u2019s disease. npj Parkinsons Dis. 8, 35 (2022).","journal-title":"npj Parkinsons Dis."},{"key":"1934_CR26","doi-asserted-by":"publisher","first-page":"166","DOI":"10.3390\/diagnostics12010166","volume":"12","author":"S Paul","year":"2022","unstructured":"Paul, S. et al. Bias investigation in artificial intelligence systems for early detection of Parkinson\u2019s disease: a narrative review. Diagnostics 12, 166 (2022).","journal-title":"Diagnostics"},{"key":"1934_CR27","doi-asserted-by":"publisher","first-page":"218","DOI":"10.1038\/s41746-024-01217-2","volume":"7","author":"Y Sun","year":"2024","unstructured":"Sun, Y. et al. Digital biomarkers for precision diagnosis and monitoring in Parkinson\u2019s disease. npj Digit. Med. 7, 218 (2024).","journal-title":"npj Digit. Med."},{"key":"1934_CR28","doi-asserted-by":"publisher","first-page":"184","DOI":"10.1038\/s41746-024-01175-9","volume":"7","author":"C Su","year":"2024","unstructured":"Su, C. et al. Identification of Parkinson\u2019s disease PACE subtypes and repurposing treatments through integrative analyses of multimodal data. npj Digit. Med. 7, 184 (2024).","journal-title":"npj Digit. Med."},{"key":"1934_CR29","doi-asserted-by":"publisher","first-page":"170","DOI":"10.1038\/s41531-022-00410-y","volume":"8","author":"AW Willis","year":"2022","unstructured":"Willis, A. W. et al. Incidence of Parkinson disease in North America. npj Parkinsons Dis. 8, 170 (2022).","journal-title":"npj Parkinsons Dis."},{"key":"1934_CR30","doi-asserted-by":"publisher","first-page":"1859","DOI":"10.1002\/mds.23740","volume":"26","author":"DustinA Heldman","year":"2011","unstructured":"Heldman, D. ustinA. et al. The modified Bradykinesia rating scale for Parkinson\u2019s disease: reliability and comparison with kinematic measures. Mov. Disord. 26, 1859\u20131863 (2011).","journal-title":"Mov. Disord."},{"key":"1934_CR31","doi-asserted-by":"publisher","first-page":"65","DOI":"10.3233\/JPD-160878","volume":"7","author":"Hasan","year":"2017","unstructured":"Hasan et al. Technologies assessing limb Bradykinesia in Parkinson\u2019s disease. J. Parkinson\u2019s. Dis. 7, 65\u20137y (2017).","journal-title":"J. Parkinson\u2019s. Dis."},{"key":"1934_CR32","doi-asserted-by":"publisher","first-page":"54","DOI":"10.3389\/fneur.2013.00054","volume":"4","author":"Gian Pal","year":"2013","unstructured":"Pal, G. ian & Goetz, C. hristopherG. Assessing Bradykinesia in Parkinsonian disorders. Front. Neurol. 4, 54 (2013).","journal-title":"Front. Neurol."},{"key":"1934_CR33","doi-asserted-by":"publisher","first-page":"349","DOI":"10.1002\/mds.24893","volume":"27","author":"Irene Litvan","year":"2012","unstructured":"Litvan, I. rene et al. Diagnostic criteria for mild cognitive impairment in Parkinson\u2019s disease: movement disorder society task force guidelines. Mov. Disord. 27, 349\u2013356 (2012).","journal-title":"Mov. Disord."},{"key":"1934_CR34","doi-asserted-by":"crossref","unstructured":"Briscoe, J. & Gebremedhin, A. Facets of disparate impact: evaluating legally consistent bias in machine learning. In Proc. 33rd ACM International Conference on Information and Knowledge Management (ACM Digital Library, 2024).","DOI":"10.1145\/3627673.3679925"},{"key":"1934_CR35","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3616865","volume":"56","author":"S Caton","year":"2024","unstructured":"Caton, S. & Haas, C. Fairness in machine learning: a survey. ACM Comput. Surv. 56, 1\u201338 (2024).","journal-title":"ACM Comput. Surv."},{"key":"1934_CR36","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3457607","volume":"54","author":"N Mehrabi","year":"2021","unstructured":"Mehrabi, N. et al. A survey on bias and fairness in machine learning. ACM Comput. Surv. 54, 1\u201335 (2021).","journal-title":"ACM Comput. Surv."}],"container-title":["npj Digital Medicine"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41746-025-01934-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41746-025-01934-2","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41746-025-01934-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,10]],"date-time":"2025-09-10T03:51:29Z","timestamp":1757476289000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41746-025-01934-2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8,27]]},"references-count":36,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2025,12]]}},"alternative-id":["1934"],"URL":"https:\/\/doi.org\/10.1038\/s41746-025-01934-2","relation":{},"ISSN":["2398-6352"],"issn-type":[{"value":"2398-6352","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,8,27]]},"assertion":[{"value":"14 February 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"5 August 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"27 August 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"The authors declare no competing interests.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"550"}}