{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:43:26Z","timestamp":1785545006170,"version":"3.56.0"},"reference-count":59,"publisher":"JMIR Publications Inc.","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["JMIR Form Res"],"abstract":"Abstract<\/jats:title>\n \n Background<\/jats:title>\n Parkinson disease (PD) is a pervasive neurodegenerative disorder globally, largely characterized by motor symptoms. Most existing artificial intelligence models for PD detection are trained on participants in well-resourced settings with confirmed clinical diagnoses. However, specialist-confirmed labels are often infeasible in low-resource settings.<\/jats:p>\n <\/jats:sec>\n \n Objective<\/jats:title>\n We developed a web platform for structured mouse data collection through pattern tracing tests. We sought to assess the feasibility of leveraging data from a community-recruited sample of participants with suspected but undiagnosed PD to train artificial intelligence models that achieve respectable performance in predicting diagnosed PD. We tested whether using weaker diagnostic labels that may be more feasible to collect in community or global health settings, where access to professional neurologists is sparse or nonexistent, can lead to models that learn predictive signals that are diagnostically useful.<\/jats:p>\n <\/jats:sec>\n \n Methods<\/jats:title>\n 261 participants (73 self-reported PD, 155 non-PD, and 33 suspected PD) were recruited from community organizations in Hawaii and completed 3 pattern tracing tasks on our custom web assessment: straight line, sine wave, and spiral wave. During each task, cursor positions, screen dimensions, and an in-target boolean flag were recorded. From these data, we engineered features and generated mouse trace images. We built 3 categories of classifiers: (1) a feed-forward neural network using engineered features, (2) fine-tuned computer vision deep learning models, and (3) multimodal models concatenating a feed-forward neural network with computer vision models. Performance was evaluated using 1 primary experiment and 2 secondary analyses. The primary experiment involved training on suspected PD versus non-PD and testing on self-reported PD versus non-PD. A secondary analysis evaluated the reverse direction by training on participants with self-reported PD and without PD and then testing on participants with suspected PD versus participants without PD. Additionally, a cross-validation analysis was conducted using participants with self-reported PD versus those without PD with 5-fold cross-validation to establish baseline performance under well-defined diagnostic labels.<\/jats:p>\n <\/jats:sec>\n \n Results<\/jats:title>\n \n The best-performing models included a multimodal Vision Transformer in the primary experiment (\n F<\/jats:italic>\n 1<\/jats:sub>\n : mean 0.7619, SD 0.0535), a multimodal ResNet-50 in the secondary analysis (\n F<\/jats:italic>\n 1<\/jats:sub>\n : mean 0.9353, SD 0.0334), and an image-based DenseNet-201 in the cross-validation analysis (\n F<\/jats:italic>\n 1<\/jats:sub>\n : mean 0.9027, SD 0.0332). Training on patients with suspected PD yielded meaningful performance in predicting self-reported PD, supporting the feasibility of using lower-specificity labels for model development.\n <\/jats:p>\n <\/jats:sec>\n \n Conclusions<\/jats:title>\n This pilot feasibility study suggests that remotely collected mouse-tracing data can support PD screening models under data labeling conditions of low diagnostic specificity: models trained on suspected PD from a community sample may learn signals that can transfer to predicting actual PD. Future work may consider pretraining using weaker labels and then fine-tuning on stronger clinical labels.<\/jats:p>\n <\/jats:sec>","DOI":"10.2196\/81368","type":"journal-article","created":{"date-parts":[[2026,6,26]],"date-time":"2026-06-26T21:21:53Z","timestamp":1782508913000},"page":"e81368-e81368","source":"Crossref","is-referenced-by-count":0,"title":["Remote Assessment of Parkinson Disease Using Deep Learning on Structured Mouse-Trace Data From Suspected Cases: Machine-Learning Pilot Feasibility Study"],"prefix":"10.2196","volume":"10","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9047-7272","authenticated-orcid":false,"given":"Md Rahat","family":"Shahriar Zawad","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-6157-3371","authenticated-orcid":false,"given":"Zerin Nasrin","family":"Tumpa","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-7983-2906","authenticated-orcid":false,"given":"Lydia","family":"Sollis","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-8410-4465","authenticated-orcid":false,"given":"Shubham","family":"Parab","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3276-4411","authenticated-orcid":false,"given":"Peter","family":"Washington","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1010","published-online":{"date-parts":[[2026,6,26]]},"reference":[{"issue":"S1","key":"R1","doi-asserted-by":"publisher","first-page":"S76","DOI":"10.1002\/mds.22783","article-title":"Evaluation of the Braak staging scheme for Parkinson\u2019s disease: introduction to a panel presentation","volume":"25 Suppl 1","author":"Burke","journal-title":"Mov Disord"},{"issue":"21 Suppl 4","key":"R2","doi-asserted-by":"publisher","first-page":"S1","DOI":"10.1212\/WNL.0b013e3181a1d44c","article-title":"The scientific and clinical basis for the treatment of Parkinson disease (2009)","volume":"72","author":"Olanow","journal-title":"Neurology"},{"key":"R3","unstructured":"What is Parkinson\u2019s? Parkinson\u2019s foundation. 2024. URL: https:\/\/www.parkinson.org\/understanding-parkinsons\/what-is-parkinsons [Accessed 17-07-2024]"},{"key":"R4","unstructured":"Statistics. Parkinson\u2019s Foundation. URL: https:\/\/www.parkinson.org\/understanding-parkinsons\/statistics [Accessed 17-07-2024]"},{"issue":"4","key":"R5","doi-asserted-by":"publisher","first-page":"209","DOI":"10.1053\/apnr.2000.9231","article-title":"An examination of psychometric properties of the Mini-Mental State Examination and the standardized Mini-Mental State Examination: implications for clinical practice","volume":"13","author":"Pangman","journal-title":"Appl Nurs Res"},{"issue":"1","key":"R6","doi-asserted-by":"publisher","first-page":"12","DOI":"10.1186\/s13677-022-00388-1","article-title":"Predicting the total Unified Parkinson\u2019s Disease Rating Scale (UPDRS) based on ML techniques and cloud-based update","volume":"12","author":"Hamzehei","journal-title":"J Cloud Comp"},{"issue":"7","key":"R7","doi-asserted-by":"publisher","first-page":"652","DOI":"10.1080\/02699206.2019.1687757","article-title":"The Mini-Mental State Examination (MMSE) from a language perspective: an analysis of test interaction","volume":"34","author":"Myrberg","journal-title":"Clin Linguist Phon"},{"key":"R8","doi-asserted-by":"publisher","DOI":"10.1109\/EMBC44109.2020.9175343","article-title":"Predicting early stage drug induced parkinsonism using unsupervised and supervised machine learning","volume":"2020","author":"Nair","journal-title":"Annu Int Conf IEEE Eng Med Biol Soc"},{"key":"R9","unstructured":"How Parkinson\u2019s disease is diagnosed. American Parkinson Disease Association. URL: https:\/\/www.apdaparkinson.org\/what-is-parkinsons\/diagnosing\/ [Accessed 23-05-2026]"},{"key":"R10","unstructured":"Diagnosing Parkinson\u2019s. Parkinson\u2019s Europe. URL: https:\/\/www.parkinsonseurope.org\/about-parkinsons\/diagnosis\/how-is-parkinsons-diagnosed\/ [Accessed 21-09-2024]"},{"issue":"2","key":"R11","doi-asserted-by":"publisher","first-page":"229","DOI":"10.1016\/j.ncl.2024.12.005","article-title":"Biomarkers in Parkinson\u2019s disease","volume":"43","author":"Brooker","journal-title":"Neurol Clin"},{"key":"R12","doi-asserted-by":"publisher","DOI":"10.3389\/fnins.2017.00555","article-title":"How wearable sensors can support Parkinson's disease diagnosis and treatment: a systematic review","volume":"11","author":"Rovini","journal-title":"Front Neurosci"},{"issue":"3","key":"R13","doi-asserted-by":"publisher","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","journal-title":"J Med Internet Res"},{"issue":"13","key":"R14","doi-asserted-by":"publisher","first-page":"1653","DOI":"10.1080\/10255842.2023.2245516","article-title":"Detection of Parkinson\u2019s disease with keystroke data","volume":"26","author":"Demir","journal-title":"Comput Methods Biomech Biomed Eng"},{"issue":"4","key":"R15","doi-asserted-by":"publisher","first-page":"884","DOI":"10.1109\/TBME.2009.2036000","article-title":"Accurate telemonitoring of Parkinson\u2019s disease progression by noninvasive speech tests","volume":"57","author":"Tsanas","journal-title":"IEEE Trans Biomed Eng"},{"issue":"3","key":"R16","doi-asserted-by":"publisher","first-page":"357","DOI":"10.1002\/ana.25548","article-title":"Gait analysis with wearables predicts conversion to Parkinson disease","volume":"86","author":"Del Din","journal-title":"Ann Neurol"},{"issue":"2","key":"R17","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0056956","article-title":"Unbiased and mobile gait analysis detects motor impairment in Parkinson\u2019s disease","volume":"8","author":"Klucken","journal-title":"PLoS ONE"},{"issue":"9","key":"R18","doi-asserted-by":"publisher","first-page":"17235","DOI":"10.3390\/s140917235","article-title":"Wearability assessment of a wearable system for Parkinson\u2019s disease remote monitoring based on a body area network of sensors","volume":"14","author":"Cancela","journal-title":"Sensors (Basel)"},{"issue":"6","key":"R19","doi-asserted-by":"publisher","first-page":"864","DOI":"10.1109\/TITB.2009.2033471","article-title":"Monitoring motor fluctuations in patients with Parkinson\u2019s disease using wearable sensors","volume":"13","author":"Patel","journal-title":"IEEE Trans Inf Technol Biomed"},{"issue":"1","key":"R20","doi-asserted-by":"publisher","DOI":"10.1038\/srep34468","article-title":"Computer keyboard interaction as an indicator of early Parkinson\u2019s disease","volume":"6","author":"Giancardo","journal-title":"Sci Rep"},{"issue":"1","key":"R21","doi-asserted-by":"publisher","first-page":"145","DOI":"10.1016\/j.neuropsychologia.2008.08.001","article-title":"The effect of Parkinson\u2019s disease on interference control during action selection","volume":"47","author":"Wylie","journal-title":"Neuropsychologia"},{"key":"R22","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2022.3156659","article-title":"Smartphone-based digital biomarkers for Parkinson's disease in a remotely-administered setting","volume":"10","author":"Goni","journal-title":"IEEE Access"},{"issue":"2","key":"R23","doi-asserted-by":"publisher","first-page":"201","DOI":"10.3390\/signals2020016","article-title":"A study on the essential and Parkinson's arm tremor classification","volume":"2","author":"Skaramagkas","journal-title":"Signals"},{"issue":"12","key":"R24","doi-asserted-by":"publisher","first-page":"1563","DOI":"10.1002\/mds.25161","article-title":"A study of subtle motor signs in early Parkinson\u2019s disease","volume":"27","author":"Schneider","journal-title":"Mov Disord"},{"issue":"5","key":"R25","doi-asserted-by":"publisher","first-page":"1402","DOI":"10.1109\/TBME.2018.2873252","article-title":"Multi-source ensemble learning for the remote prediction of Parkinson\u2019s disease in the presence of source-wise missing data","volume":"66","author":"Prince","journal-title":"IEEE Trans Biomed Eng"},{"key":"R26","doi-asserted-by":"publisher","DOI":"10.2196\/65629","article-title":"Model-based feature extraction and classification for Parkinson disease screening using gait analysis: development and validation study","volume":"8","author":"Lim","journal-title":"JMIR Aging"},{"key":"R27","doi-asserted-by":"publisher","DOI":"10.2196\/46105","article-title":"Applied machine learning techniques to diagnose voice-affecting conditions and disorders: systematic literature review","volume":"25","author":"Idrisoglu","journal-title":"J Med Internet Res"},{"issue":"4","key":"R28","doi-asserted-by":"publisher","first-page":"1618","DOI":"10.1109\/JBHI.2018.2866873","article-title":"Multimodal assessment of Parkinson's disease: a deep learning approach","volume":"23","author":"Vasquez-Correa","journal-title":"IEEE J Biomed Health Inform"},{"issue":"2","key":"R29","doi-asserted-by":"publisher","first-page":"253","DOI":"10.1016\/j.neures.2004.03.004","article-title":"Quantitative magnetic detection of finger movements in patients with Parkinson\u2019s disease","volume":"49","author":"Kandori","journal-title":"Neurosci Res"},{"key":"R30","doi-asserted-by":"publisher","DOI":"10.1016\/j.sna.2019.05.006","article-title":"Flexible paper touchpad for Parkinson's hand tremor detection","volume":"294","author":"Bhattacharjee","journal-title":"Sens Actuators A Phys"},{"issue":"8","key":"R31","doi-asserted-by":"publisher","first-page":"1287","DOI":"10.1002\/mds.27376","article-title":"Evaluation of smartphone-based testing to generate exploratory outcome measures in a phase 1 Parkinson\u2019s disease clinical trial","volume":"33","author":"Lipsmeier","journal-title":"Mov Disord"},{"key":"R32","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2018.2851382","article-title":"Deep multi-layer perceptron classifier for behavior analysis to estimate Parkinson's disease severity using smartphones","volume":"6","author":"Wan","journal-title":"IEEE Access"},{"key":"R33","doi-asserted-by":"publisher","DOI":"10.1038\/s41531-016-0003-z","article-title":"Using a smartphone-based self-management platform to support medication adherence and clinical consultation in Parkinson\u2019s disease","volume":"3","author":"Lakshminarayana","journal-title":"NPJ Parkinsons Dis"},{"issue":"22","key":"R34","doi-asserted-by":"publisher","DOI":"10.3390\/s23229149","article-title":"Clinically informed automated assessment of finger tapping videos in Parkinson's disease","volume":"23","author":"Yu","journal-title":"Sensors (Basel)"},{"key":"R35","doi-asserted-by":"crossref","unstructured":"Pappas MC Boughanem DJ Baudendistel ST et al. Video-based clinical gait analysis in Parkinson\u2019s disease: a novel approach using frontal plane videos and machine learning. Presented at: 2024 46th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC); Jul 15-19, 2024; Orlando, FL, USA. [doi: 10.1109\/EMBC53108.2024.10781504]","DOI":"10.1109\/EMBC53108.2024.10781504"},{"issue":"7","key":"R36","doi-asserted-by":"publisher","DOI":"10.2196\/18697","article-title":"Diagnosing Parkinson disease through facial expression recognition: video analysis","volume":"22","author":"Jin","journal-title":"J Med Internet Res"},{"key":"R37","doi-asserted-by":"publisher","DOI":"10.2196\/71560","article-title":"Digital biomarkers for Parkinson disease: bibliometric analysis and a scoping review of deep learning for freezing of gait","volume":"27","author":"Qi","journal-title":"J Med Internet Res"},{"issue":"1","key":"R38","doi-asserted-by":"publisher","DOI":"10.1038\/s41531-024-00742-x","article-title":"Interpretable video-based tracking and quantification of parkinsonism clinical motor states","volume":"10","author":"Deng","journal-title":"NPJ Parkinsons Dis"},{"key":"R39","doi-asserted-by":"crossref","unstructured":"Li W Zhu W Dorsey ER Luo J . Predicting parkinson\u2019s disease with multimodal irregularly collected longitudinal smartphone data. Presented at: 2020 IEEE International Conference on Data Mining (ICDM); Nov 17-20, 2020; Sorrento, Italy. [doi: 10.1109\/ICDM50108.2020.00133]","DOI":"10.1109\/ICDM50108.2020.00133"},{"key":"R40","unstructured":"Parkinson\u2019s Study. URL: https:\/\/parkinsonsurvey.github.io\/ [Accessed 17-07-2025]"},{"issue":"4","key":"R41","doi-asserted-by":"publisher","first-page":"653","DOI":"10.1002\/mds.23499","article-title":"The patients\u2019 perception of prodromal symptoms before the initial diagnosis of Parkinson\u2019s disease","volume":"26","author":"Gaenslen","journal-title":"Mov Disord"},{"issue":"3","key":"R42","doi-asserted-by":"publisher","first-page":"362","DOI":"10.1001\/archneur.63.3.noc50312","article-title":"Subjective complaints precede Parkinson disease: the Rotterdam study","volume":"63","author":"de Lau","journal-title":"Arch Neurol"},{"issue":"4","key":"R43","doi-asserted-by":"publisher","first-page":"872","DOI":"10.1111\/1467-9566.13622","article-title":"Constructing the detecting stage: social processes and the diagnostic journey of early onset Parkinson\u2019s disease","volume":"45","author":"Valasaki","journal-title":"Sociol Health Illn"},{"issue":"4","key":"R44","doi-asserted-by":"publisher","first-page":"1537","DOI":"10.3233\/JPD-212735","article-title":"Barriers to accessing healthcare services for people with Parkinson's disease: a scoping review","volume":"11","author":"Zaman","journal-title":"J Parkinsons Dis"},{"key":"R45","doi-asserted-by":"publisher","DOI":"10.1016\/j.socscimed.2021.114148","article-title":"\u201cOld people problems\u201d, uncertainty and legitimacy: challenges with diagnosing Parkinson\u2019s disease in Kenya","volume":"282","author":"Fothergill-Misbah","journal-title":"Soc Sci Med"},{"key":"R46","doi-asserted-by":"publisher","DOI":"10.1145\/3292500.3330701","article-title":"Optuna: a next-generation hyperparameter optimization framework","author":"Akiba","journal-title":"KDD \u201919: Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining"},{"key":"R47","unstructured":"Lundberg SM Lee SI . A unified approach to interpreting model predictions. Presented at: 31st International Conference on Neural Information Processing Systems; Dec 4-9, 2017; Long Beach, California, USA. [doi: 10.5555\/3295222.3295230]"},{"issue":"8","key":"R48","doi-asserted-by":"publisher","first-page":"907","DOI":"10.3390\/electronics8080907","article-title":"Parkinson\u2019s disease detection from drawing movements using convolutional neural networks","volume":"8","author":"Gil-Mart\u00edn","journal-title":"Electronics (Basel)"},{"key":"R49","doi-asserted-by":"crossref","unstructured":"Pereira CR Weber SAT Hook C Rosa GH Papa JP . Deep learning-aided Parkinson\u2019s disease diagnosis from handwritten dynamics. Presented at: 2016 29th SIBGRAPI Conference on Graphics, Patterns and Images (SIBGRAPI); Oct 4-7, 2016; Sao Paulo, Brazil. [doi: 10.1109\/SIBGRAPI.2016.054]","DOI":"10.1109\/SIBGRAPI.2016.054"},{"key":"R50","doi-asserted-by":"crossref","unstructured":"Goel N Khanna A Gupta D Gupta N . Detection of Parkinson\u2019s disease using machine learning techniques for voice and handwriting features. Presented at: International Conference on Innovative Computing and Communications; Mar 21-22, 2019; Ostrava, Czech Republic. [doi: 10.1007\/978-981-15-1286-5_56]","DOI":"10.1007\/978-981-15-1286-5_56"},{"issue":"9","key":"R51","doi-asserted-by":"publisher","first-page":"23727","DOI":"10.3390\/s150923727","article-title":"Automatic spiral analysis for objective assessment of motor symptoms in Parkinson's disease","volume":"15","author":"Memedi","journal-title":"Sensors (Basel)"},{"key":"R52","doi-asserted-by":"publisher","DOI":"10.1016\/j.cmpb.2024.108066","article-title":"LSTM-CNN: an efficient diagnostic network for Parkinson\u2019s disease utilizing dynamic handwriting analysis","volume":"247","author":"Wang","journal-title":"Comput Methods Programs Biomed"},{"issue":"2","key":"R53","doi-asserted-by":"publisher","first-page":"354","DOI":"10.1002\/mds.27915","article-title":"Computer mouse use captures ataxia and parkinsonism, enabling accurate measurement and detection","volume":"35","author":"Gajos","journal-title":"Mov Disord"},{"key":"R54","doi-asserted-by":"publisher","DOI":"10.2196\/49898","article-title":"Parkinson disease recognition using a gamified website: machine learning development and usability study","volume":"7","author":"Parab","journal-title":"JMIR Form Res"},{"issue":"1","key":"R55","doi-asserted-by":"publisher","DOI":"10.1038\/s41746-021-00414-7","article-title":"Crowdsourcing digital health measures to predict Parkinson\u2019s disease severity: the Parkinson\u2019s disease digital biomarker DREAM Challenge","volume":"4","author":"Sieberts","journal-title":"NPJ Digit Med"},{"issue":"9","key":"R56","doi-asserted-by":"publisher","first-page":"e555","DOI":"10.1016\/S2589-7500(21)00101-1","article-title":"Discovery of Parkinson\u2019s disease states and disease progression modelling: a longitudinal data study using machine learning","volume":"3","author":"Severson","journal-title":"Lancet Digit Health"},{"issue":"1","key":"R57","doi-asserted-by":"publisher","DOI":"10.1038\/s41746-022-00643-4","article-title":"Identifying and characterising sources of variability in digital outcome measures in Parkinson\u2019s disease","volume":"5","author":"Roussos","journal-title":"NPJ Digit Med"},{"issue":"10","key":"R58","doi-asserted-by":"publisher","first-page":"1578","DOI":"10.1016\/j.apmr.2004.01.025","article-title":"Attending to the task: interference effects of functional tasks on walking in Parkinson\u2019s disease and the roles of cognition, depression, fatigue, and balance","volume":"85","author":"Rochester","journal-title":"Arch Phys Med Rehabil"},{"issue":"1","key":"R59","doi-asserted-by":"publisher","DOI":"10.1038\/s41746-025-01934-2","article-title":"Quantifying device type and handedness biases in a remote Parkinson\u2019s disease AI-powered assessment","volume":"8","author":"Tumpa","journal-title":"NPJ Digit Med"}],"container-title":["JMIR Formative Research"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/formative.jmir.org\/2026\/1\/e81368","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,31]],"date-time":"2026-07-31T22:26:30Z","timestamp":1785536790000},"score":1,"resource":{"primary":{"URL":"https:\/\/formative.jmir.org\/2026\/1\/e81368"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,26]]},"references-count":59,"URL":"https:\/\/doi.org\/10.2196\/81368","relation":{},"ISSN":["2561-326X"],"issn-type":[{"value":"2561-326X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,6,26]]},"article-number":"v10iS1e81368"}}