{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,6]],"date-time":"2026-04-06T15:51:01Z","timestamp":1775490661399,"version":"3.50.1"},"reference-count":35,"publisher":"Association for Computing Machinery (ACM)","issue":"2","funder":[{"name":"ICT Innovation Funds","award":["FY 2023\u201324, Round 1"],"award-info":[{"award-number":["FY 2023\u201324, Round 1"]}]},{"name":"ICT Division, Government of the People\u2019s Republic of Bangladesh, the National Institute of Neurological Disorders and Stroke of the National Institutes of Health","award":["P50NS108676"],"award-info":[{"award-number":["P50NS108676"]}]},{"DOI":"10.13039\/100000936","name":"Gordon and Betty Moore Foundation","doi-asserted-by":"crossref","id":[{"id":"10.13039\/100000936","id-type":"DOI","asserted-by":"crossref"}]},{"name":"Google Faculty Research Award"},{"DOI":"10.13039\/501100009500","name":"BUET","doi-asserted-by":"crossref","id":[{"id":"10.13039\/501100009500","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Comput. Healthcare"],"published-print":{"date-parts":[[2026,4,30]]},"abstract":"<jats:p>Timely diagnosis of movement disorders like Parkinson\u2019s Disease (PD) improves quality of life. However, access to clinical diagnosis is limited in low-income countries. Here, we present PULSAR, a novel method for classifying individuals with or without PD from webcam-recorded videos of the finger-tapping task used in the Movement Disorder Society\u2014Unified Parkinson\u2019s Disease Rating Scale (MDS-UPDRS). PULSAR was trained and evaluated on data from 382 participants, including 183 self-reported PD patients. We used an adaptive graph convolutional neural network to dynamically learn task-specific spatio-temporal edges and enhanced it with a multi-stream convolution model to capture critical features like finger joint locations, tapping velocity, and acceleration of tapping. As video labels are self-reported, some non-PD labels may be undiagnosed cases. To address this, we used Positive Unlabeled (PU) Learning, which outperformed traditional supervised learning. PULSAR achieved 80.95% accuracy on the validation set and 71.29% mean accuracy (2.49% standard deviation) on an independent test set. We hope PULSAR can aid in accessible PD screening and that these techniques may extend to assessing disorders like ataxia and Huntington\u2019s disease.<\/jats:p>","DOI":"10.1145\/3799417","type":"journal-article","created":{"date-parts":[[2026,2,26]],"date-time":"2026-02-26T14:02:48Z","timestamp":1772114568000},"page":"1-17","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["PULSAR: Graph-Based Positive Unlabeled Learning with Multi-Stream Adaptive Convolutions for Parkinson\u2019s Disease Recognition"],"prefix":"10.1145","volume":"7","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-8686-7335","authenticated-orcid":false,"given":"Md Zarif Ul","family":"Alam","sequence":"first","affiliation":[{"name":"Bangladesh University of Engineering and Technology, Bangladesh and University of Massachusetts Amherst, Amherst, Massachusetts, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-1227-4024","authenticated-orcid":false,"given":"Asif","family":"Azad","sequence":"additional","affiliation":[{"name":"Bangladesh University of Engineering and Technology, Dhaka, Bangladesh"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3725-3493","authenticated-orcid":false,"given":"Md Saiful","family":"Islam","sequence":"additional","affiliation":[{"name":"University of Rochester, Rochester, New York, USA and Bangladesh University of Engineering and Technology, Dhaka, Bangladesh"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4781-4733","authenticated-orcid":false,"given":"Ehsan","family":"Hoque","sequence":"additional","affiliation":[{"name":"University of Rochester, Rochester, New York, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9887-4456","authenticated-orcid":false,"given":"M Saifur","family":"Rahman","sequence":"additional","affiliation":[{"name":"Bangladesh University of Engineering and Technology, Dhaka, Bangladesh"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2026,4,6]]},"reference":[{"key":"e_1_3_2_2_2","doi-asserted-by":"publisher","DOI":"10.1038\/s41531-025-00956-7"},{"key":"e_1_3_2_3_2","doi-asserted-by":"publisher","DOI":"10.1109\/FG47880.2020.00008"},{"key":"e_1_3_2_4_2","doi-asserted-by":"publisher","DOI":"10.1145\/3459669"},{"key":"e_1_3_2_5_2","first-page":"640","volume-title":"Proceedings of the 2023 IEEE 36th International Symposium on Computer-Based Medical Systems (CBMS)","author":"Amprimo Gianluca","year":"2023","unstructured":"Gianluca Amprimo, Irene Rechichi, Claudia Ferraris, and Gabriella Olmo. 2023. Objective assessment of the finger tapping task in Parkinson\u2019s disease and control subjects using Azure Kinect and machine learning. In Proceedings of the 2023 IEEE 36th International Symposium on Computer-Based Medical Systems (CBMS). IEEE, 640\u2013645."},{"issue":"24","key":"e_1_3_2_6_2","doi-asserted-by":"crossref","first-page":"2150","DOI":"10.1212\/WNL.0b013e3182020123","article-title":"Tapping linked to function and structure in premanifest and symptomatic Huntington disease","volume":"75","author":"Bechtel Natalie","year":"2010","unstructured":"Natalie Bechtel, R. I. Scahill, Herminia Diana Rosas, Tanka Acharya, Simon J. A. van den Bogaard, Celine Jauffret, Miranda J. Say, Aaron Sturrock, Hans Johnson, Christina E. Onorato, et\u00a0al. 2010. Tapping linked to function and structure in premanifest and symptomatic Huntington disease. Neurology 75, 24 (2010), 2150\u20132160.","journal-title":"Neurology"},{"key":"e_1_3_2_7_2","first-page":"1","article-title":"Statistical comparisons of classifiers over multiple data sets","volume":"7","author":"Dem\u0161ar Janez","year":"2006","unstructured":"Janez Dem\u0161ar. 2006. Statistical comparisons of classifiers over multiple data sets. The Journal of Machine Learning Research 7 (2006), 1\u201330.","journal-title":"The Journal of Machine Learning Research"},{"key":"e_1_3_2_8_2","article-title":"Analysis of learning from positive and unlabeled data","volume":"27","author":"Du Plessis Marthinus C.","year":"2014","unstructured":"Marthinus C. Du Plessis, Gang Niu, and Masashi Sugiyama. 2014. Analysis of learning from positive and unlabeled data. In Proceedings of the Advances in Neural Information Processing Systems, Vol. 27.","journal-title":"Proceedings of the Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_9_2","doi-asserted-by":"publisher","DOI":"10.1145\/1401890.1401920"},{"issue":"3","key":"e_1_3_2_10_2","doi-asserted-by":"crossref","first-page":"181","DOI":"10.1136\/jnnp.55.3.181","article-title":"Accuracy of clinical diagnosis of idiopathic Parkinson\u2019s disease: A clinico-pathological study of 100 cases","volume":"55","author":"Hughes A. J.","year":"1992","unstructured":"A. J. Hughes, S. E. Daniel, L. Kilford, and A. J. Lees. 1992. Accuracy of clinical diagnosis of idiopathic Parkinson\u2019s disease: A clinico-pathological study of 100 cases. Journal of Neurology, Neurosurgery, and Psychiatry 55, 3 (1992), 181\u2013184.","journal-title":"Journal of Neurology, Neurosurgery, and Psychiatry"},{"key":"e_1_3_2_11_2","first-page":"rs\u20133","article-title":"Remote AI screening for Parkinson\u2019s disease: A multimodal, cross-setting validation study","author":"Islam Md Saiful","year":"2025","unstructured":"Md Saiful Islam, Tariq Adnan, Abdelrahman Abdelkader, Zipei Liu, Evelyn Ma, Sooyong Park, Asif Azad, Pai Liu, Meghan Pawlik, Emily Hartman, et\u00a0al. 2025. Remote AI screening for Parkinson\u2019s disease: A multimodal, cross-setting validation study. Research Square (2025), rs\u20133.","journal-title":"Research Square"},{"key":"e_1_3_2_12_2","doi-asserted-by":"crossref","first-page":"28125","DOI":"10.1609\/aaai.v39i27.35031","article-title":"Accessible, at-home detection of Parkinson\u2019s disease via multi-task video analysis","volume":"39","author":"Islam Md Saiful","year":"2025","unstructured":"Md Saiful Islam, Tariq Adnan, Jan Freyberg, Sangwu Lee, Abdelrahman Abdelkader, Meghan Pawlik, Cathe Schwartz, Karen Jaffe, Ruth B. Schneider, Ray Dorsey, et\u00a0al. 2025. Accessible, at-home detection of Parkinson\u2019s disease via multi-task video analysis. In Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 39, 28125\u201328133.","journal-title":"Proceedings of the AAAI Conference on Artificial Intelligence"},{"issue":"1","key":"e_1_3_2_13_2","doi-asserted-by":"crossref","first-page":"156","DOI":"10.1038\/s41746-023-00905-9","article-title":"Using AI to measure Parkinson\u2019s disease severity at home","volume":"6","author":"Islam Md Saiful","year":"2023","unstructured":"Md Saiful Islam, Wasifur Rahman, Abdelrahman Abdelkader, Sangwu Lee, Phillip T. Yang, Jennifer L. Purks, Jamie L. Adams, Ruth B. Schneider, E. Dorsey, and Ehsan Hoque. 2023. Using AI to measure Parkinson\u2019s disease severity at home. NPJ Digital Medicine 6, 1 (2023), 156.","journal-title":"NPJ Digital Medicine"},{"key":"e_1_3_2_14_2","unstructured":"Nitish Shirish Keskar Dheevatsa Mudigere Jorge Nocedal Mikhail Smelyanskiy and Ping Tak Peter Tang. 2016. On large-batch training for deep learning: Generalization gap and sharp minima. arXiv:1609.04836. Retrieved from https:\/\/arxiv.org\/abs\/1609.04836"},{"key":"e_1_3_2_15_2","doi-asserted-by":"crossref","unstructured":"S. V. Khadilkar. 2013. Neurology in India. Annals of Indian Academy of Neurology 16 4 (2013) 465\u2013466.","DOI":"10.4103\/0972-2327.120415"},{"key":"e_1_3_2_16_2","doi-asserted-by":"crossref","first-page":"120119","DOI":"10.1016\/j.jns.2021.120119","article-title":"Why does Africa have the lowest number of neurologists and how to cover the gap","volume":"434","author":"Kissani Najib","year":"2022","unstructured":"Najib Kissani, Laila Liqali, Khaoula Hakimi, Jacob Mugumbate, Gams Massi Daniel, Eetedal Ahmed A. Ibrahim, Enat Yewnetu, Mofou Belo, Jo Wilmshurst, Pascal Mbelesso, et\u00a0al. 2022. Why does Africa have the lowest number of neurologists and how to cover the gap? Journal of the Neurological Sciences 434 (2022), 120119.","journal-title":"Journal of the Neurological Sciences"},{"key":"e_1_3_2_17_2","doi-asserted-by":"publisher","DOI":"10.1145\/3328925"},{"key":"e_1_3_2_18_2","first-page":"1","article-title":"Spatial temporal graph convolutional networks for skeleton-based dynamic hand gesture recognition","volume":"1","author":"Li Yong","year":"2019","unstructured":"Yong Li, Zihang He, Xiang Ye, Zuguo He, and Kangrong Han. 2019. Spatial temporal graph convolutional networks for skeleton-based dynamic hand gesture recognition. EURASIP Journal on Image and Video Processing 1 (2019), 1\u20137.","journal-title":"EURASIP Journal on Image and Video Processing"},{"issue":"1","key":"e_1_3_2_19_2","doi-asserted-by":"crossref","first-page":"47","DOI":"10.1044\/jshd.4301.47","article-title":"Frequency and cooccurrence of vocal tract dysfunctions in the speech of a large sample of Parkinson patients","volume":"43","author":"Logemann J. A.","year":"1978","unstructured":"J. A. Logemann, H. B. Fisher, B. Boshes, and E. R. Blonsky. 1978. Frequency and cooccurrence of vocal tract dysfunctions in the speech of a large sample of Parkinson patients. The Journal of Speech and Hearing Disorders 43, 1 (1978), 47\u201357.","journal-title":"The Journal of Speech and Hearing Disorders"},{"issue":"4","key":"e_1_3_2_20_2","doi-asserted-by":"crossref","first-page":"826","DOI":"10.1007\/s00415-019-09202-6","article-title":"Individual Parkinsonian motor signs and striatal dopamine transporter deficiency: A study with [I-123] FP-CIT SPECT","volume":"266","author":"M\u00e4kinen Elina","year":"2019","unstructured":"Elina M\u00e4kinen, Juho Joutsa, Elina Jaakkola, Tommi Noponen, Jarkko Johansson, Miia Pitkonen, Reeta Levo, Tuomas Mertsalmi, Filip Scheperjans, and Valtteri Kaasinen. 2019. Individual Parkinsonian motor signs and striatal dopamine transporter deficiency: A study with [I-123] FP-CIT SPECT. Journal of Neurology 266, 4 (2019), 826\u2013834.","journal-title":"Journal of Neurology"},{"issue":"1","key":"e_1_3_2_21_2","doi-asserted-by":"crossref","first-page":"231","DOI":"10.1212\/WNL.46.1.231","article-title":"[sup 123 I] beta-CIT\/SPECT imaging demonstrates bilateral loss of dopamine transporters in hemi-Parkinson\u2019s disease","volume":"46","author":"Marek K. L.","year":"1996","unstructured":"K. L. Marek, J. P. Seibyl, S. S. Zoghbi, Y. Zea-Ponce, R. M. Baldwin, B. Fussell, D. S. Charney, C. Van Dyck, P. B. Hoffer, and R. B. Innis. 1996. [sup 123 I] beta-CIT\/SPECT imaging demonstrates bilateral loss of dopamine transporters in hemi-Parkinson\u2019s disease. Neurology 46, 1 (1996), 231\u2013237.","journal-title":"Neurology"},{"key":"e_1_3_2_22_2","volume-title":"Proceedings of the 22nd International Joint Conference on Artificial Intelligence","author":"Nhut Nguyen Minh","year":"2011","unstructured":"Minh Nhut Nguyen, Xiao Li Li, and See-Kiong Ng. 2011. Positive unlabeled learning for time series classification. In Proceedings of the 22nd International Joint Conference on Artificial Intelligence. Citeseer."},{"issue":"1","key":"e_1_3_2_23_2","doi-asserted-by":"crossref","first-page":"22","DOI":"10.1136\/jnnp.57.1.22","article-title":"Measuring ataxia: Quantification based on the standard neurological examination","volume":"57","author":"Notermans N. C.","year":"1994","unstructured":"N. C. Notermans, G. W. Van Dijk, Y. Van der Graaf, J. Van Gijn, and J. H. Wokke. 1994. Measuring ataxia: Quantification based on the standard neurological examination. Journal of Neurology, Neurosurgery, and Psychiatry 57, 1 (1994), 22\u201326.","journal-title":"Journal of Neurology, Neurosurgery, and Psychiatry"},{"key":"e_1_3_2_24_2","doi-asserted-by":"crossref","first-page":"795258","DOI":"10.3389\/fneur.2021.795258","article-title":"Automatic classification and severity estimation of ataxia from finger tapping videos","volume":"12","author":"Nunes Adonay S.","year":"2022","unstructured":"Adonay S. Nunes, Nataliia Kozhemiako, Christopher D. Stephen, Jeremy D. Schmahmann, Sheraz Khan, and Anoopum S. Gupta. 2022. Automatic classification and severity estimation of ataxia from finger tapping videos. Frontiers in Neurology 12 (2022), 795258.","journal-title":"Frontiers in Neurology"},{"key":"e_1_3_2_25_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-01307-2_54"},{"key":"e_1_3_2_26_2","doi-asserted-by":"publisher","DOI":"10.2196\/26305"},{"key":"e_1_3_2_27_2","doi-asserted-by":"crossref","first-page":"109603","DOI":"10.1016\/j.mehy.2020.109603","article-title":"Early diagnosis of Parkinson\u2019s disease using machine learning algorithms","volume":"138","author":"Karapinar Senturk Zehra","year":"2020","unstructured":"Zehra Karapinar Senturk. 2020. Early diagnosis of Parkinson\u2019s disease using machine learning algorithms. Medical Hypotheses 138 (2020), 109603.","journal-title":"Medical Hypotheses"},{"key":"e_1_3_2_28_2","doi-asserted-by":"publisher","DOI":"10.1007\/s13534-020-00156-7"},{"key":"e_1_3_2_29_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01230"},{"key":"e_1_3_2_30_2","doi-asserted-by":"crossref","first-page":"101813","DOI":"10.1016\/j.media.2020.101813","article-title":"Deep neural network models for computational histopathology: A survey","volume":"67","author":"Srinidhi Chetan L.","year":"2021","unstructured":"Chetan L. Srinidhi, Ozan Ciga, and Anne L. Martel. 2021. Deep neural network models for computational histopathology: A survey. Medical Image Analysis 67 (2021), 101813.","journal-title":"Medical Image Analysis"},{"key":"e_1_3_2_31_2","unstructured":"Wikipedia Contributors. 2022. Parkinson\u2019s Disease\u2014Wikipedia the Free Encyclopedia. Retrieved August 12 2023 from https:\/\/en.wikipedia.org\/w\/index.php?title=Parkinson\u2019s\\_disease&oldid=1085266278"},{"issue":"1","key":"e_1_3_2_32_2","doi-asserted-by":"crossref","first-page":"170","DOI":"10.1038\/s41531-022-00410-y","article-title":"Incidence of Parkinson disease in North America","volume":"8","author":"Willis A. W.","year":"2022","unstructured":"A. W. Willis, E. Roberts, J. C. Beck, B. Fiske, W. Ross, R. Savica, S. K. Van Den Eeden, C. M. Tanner, C. Marras, and Parkinson\u2019s Foundation P4 Group. 2022. Incidence of Parkinson disease in North America. NPJ Parkinson\u2019s Disease 8, 1 (2022), 170.","journal-title":"NPJ Parkinson\u2019s Disease"},{"key":"e_1_3_2_33_2","doi-asserted-by":"publisher","DOI":"10.1212\/WNL.0b013e31822c9123"},{"key":"e_1_3_2_34_2","doi-asserted-by":"publisher","DOI":"10.1038\/s41531-020-0117-1"},{"key":"e_1_3_2_35_2","doi-asserted-by":"publisher","DOI":"10.1001\/jamaneurol.2018.0809"},{"key":"e_1_3_2_36_2","unstructured":"Fan Zhang Valentin Bazarevsky Andrey Vakunov Andrei Tkachenka George Sung Chuo-Ling Chang and Matthias Grundmann. 2020. MediaPipe Hands: On-device real-time hand tracking. arXiv:2006.10214. Retrieved from https:\/\/arxiv.org\/abs\/2006.10214"}],"container-title":["ACM Transactions on Computing for Healthcare"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3799417","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,6]],"date-time":"2026-04-06T14:27:28Z","timestamp":1775485648000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3799417"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,6]]},"references-count":35,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2026,4,30]]}},"alternative-id":["10.1145\/3799417"],"URL":"https:\/\/doi.org\/10.1145\/3799417","relation":{},"ISSN":["2691-1957","2637-8051"],"issn-type":[{"value":"2691-1957","type":"print"},{"value":"2637-8051","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,4,6]]},"assertion":[{"value":"2024-10-27","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-02-11","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-04-06","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}