{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,10]],"date-time":"2026-10-10T09:49:25Z","timestamp":1791625765755,"version":"4.3.4"},"reference-count":52,"publisher":"Wiley","issue":"5","license":[{"start":{"date-parts":[[2026,4,28]],"date-time":"2026-04-28T00:00:00Z","timestamp":1777334400000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"},{"start":{"date-parts":[[2026,4,28]],"date-time":"2026-04-28T00:00:00Z","timestamp":1777334400000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/doi.wiley.com\/10.1002\/tdm_license_1.1"}],"content-domain":{"domain":["onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["Brain and Behavior"],"published-print":{"date-parts":[[2026,5]]},"abstract":"<jats:title>ABSTRACT<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Introduction<\/jats:title>\n                    <jats:p>Subtle PD motor abnormalities can be underappreciated in examination but are overtly present in handwriting. Spiral, meander, and wave drawings are noninvasive, low\u2010cost methods for capturing PD motor signatures and are easily collected on a tablet. Deep learning is a natural framework to decode such features, but most handwriting\u2010based PD classifiers have not been thoroughly optimized or tested for generalization, leaving their clinical utility unverified.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>PD\u2010MGMA\u2010DSCNN is a multiscale gated multi\u2010head attention depthwise separable convolutional network operating on a unified RGB image of spiral, meander, and wave tasks. A PD\u2010specific Bayesian\u2013genetic optimization scheme (PD\u2010BayGA) was used to tune a suite of key architectural and training hyperparameters. Model decisions were interpreted using SHAP\u2010based superpixel attribution maps to link discriminative regions to previously described Parkinsonian handwriting abnormalities.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>On the PaHaW dataset, PD\u2010MGMA\u2010DSCNN achieved 98.23% accuracy on the held\u2010out internal test set, outperforming CNN, RNN, 3D CNN, and ensemble baselines reported in the literature. Using the finalized configuration developed on PaHaW, external evaluation on the independent HandPD dataset yielded 99.42% accuracy, together with high ROC\u2013AUC and precision\u2013recall performance under clinically motivated rule\u2010out and rule\u2010in thresholds. These findings support the potential use of a three\u2010zone risk stratification scheme within a standardized image\u2010based drawing framework.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusions<\/jats:title>\n                    <jats:p>PD\u2010MGMA\u2010DSCNN provides state\u2010of\u2010the\u2010art performance in handwriting\u2010based PD detection while remaining a compact, systematically optimized model with clinically interpretable explanations. The framework may support tablet\u2010based PD screening or triage in movement\u2010disorder clinics and longitudinal monitoring, and serves as a practical starting point for incorporating digital handwriting biomarkers into clinical PD care.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1002\/brb3.71457","type":"journal-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T04:55:15Z","timestamp":1777438515000},"update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Clinically Deployable Handwriting Biomarkers of Parkinson's Disease via Multiscale Attention and Bayesian\u2013Genetic Optimization"],"prefix":"10.1002","volume":"16","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6763-6626","authenticated-orcid":false,"given":"Khosro","family":"Rezaee","sequence":"first","affiliation":[{"name":"Department of Biomedical Engineering Meybod University  Meybod Iran"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ali Khalili","family":"Fakhrabadi","sequence":"additional","affiliation":[{"name":"Department of Electrical Engineering, Kerman Branch Islamic Azad University  Kerman Iran"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"311","published-online":{"date-parts":[[2026,4,28]]},"reference":[{"key":"e_1_2_13_2_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jvcir.2020.102823"},{"key":"e_1_2_13_3_1","doi-asserted-by":"publisher","DOI":"10.3390\/diagnostics15222892"},{"key":"e_1_2_13_4_1","doi-asserted-by":"publisher","DOI":"10.3934\/math.2024334"},{"key":"e_1_2_13_5_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11042\u2010021\u201011846\u20107"},{"key":"e_1_2_13_6_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11042\u2010022\u201013759\u20102"},{"key":"e_1_2_13_7_1","doi-asserted-by":"publisher","DOI":"10.3390\/diagnostics15010004"},{"key":"e_1_2_13_8_1","doi-asserted-by":"publisher","DOI":"10.3390\/electronics13193962"},{"key":"e_1_2_13_9_1","doi-asserted-by":"publisher","DOI":"10.3390\/s23020634"},{"key":"e_1_2_13_10_1","doi-asserted-by":"publisher","DOI":"10.1038\/s44286\u2010025\u201000219\u20105"},{"key":"e_1_2_13_11_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2019.08.018"},{"key":"e_1_2_13_12_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2020.114405"},{"key":"e_1_2_13_13_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cmpb.2014.08.009"},{"key":"e_1_2_13_14_1","doi-asserted-by":"publisher","DOI":"10.3389\/fnagi.2025.1672971"},{"key":"e_1_2_13_15_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.retram.2025.103541"},{"key":"e_1_2_13_16_1","doi-asserted-by":"publisher","DOI":"10.3389\/fmed.2024.1453743"},{"key":"e_1_2_13_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2020.3048892"},{"key":"e_1_2_13_18_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11042\u2010024\u201018584\u20103"},{"key":"e_1_2_13_19_1","doi-asserted-by":"publisher","DOI":"10.3390\/info15040220"},{"key":"e_1_2_13_20_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.heliyon.2024.e25469"},{"key":"e_1_2_13_21_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.medengphy.2025.104333"},{"key":"e_1_2_13_22_1","doi-asserted-by":"publisher","DOI":"10.3389\/fneur.2025.1678463"},{"key":"e_1_2_13_23_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.future.2020.11.020"},{"key":"e_1_2_13_24_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41598\u2010025\u201029383\u20107"},{"key":"e_1_2_13_25_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jbi.2022.104085"},{"key":"e_1_2_13_26_1","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0318021"},{"key":"e_1_2_13_27_1","doi-asserted-by":"publisher","DOI":"10.3390\/biomedicines13071764"},{"key":"e_1_2_13_28_1","doi-asserted-by":"publisher","DOI":"10.1007\/s42979\u2010026\u201004893\u2010x"},{"key":"e_1_2_13_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/JTEHM.2024.3355432"},{"key":"e_1_2_13_30_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.artmed.2018.03.001"},{"key":"e_1_2_13_31_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cmpb.2016.08.006"},{"key":"e_1_2_13_32_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-50478-0_19"},{"key":"e_1_2_13_33_1","doi-asserted-by":"crossref","unstructured":"Pereira C. R. S. A. T.Weber C.Hook G. H.Rosa andJ. P.Papa.2016. \u201cDeep Learning\u2010Aided Parkinson's Disease Diagnosis From Handwritten Dynamics.\u201d Paper presented at2016 29th SIBGRAPI Conference on Graphics Patterns and Images (SIBGRAPI) S\u00e3o Paulo Brazil October 4\u20137 340\u2013346.https:\/\/doi.org\/10.1109\/SIBGRAPI.2016.054.","DOI":"10.1109\/SIBGRAPI.2016.054"},{"key":"e_1_2_13_34_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41598\u2010025\u201012636\u2010w"},{"key":"e_1_2_13_35_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.bspc.2023.105628"},{"key":"e_1_2_13_36_1","doi-asserted-by":"publisher","DOI":"10.1007\/s44163\u2010025\u201000241\u20109"},{"key":"e_1_2_13_37_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.dajour.2024.100470"},{"key":"e_1_2_13_38_1","doi-asserted-by":"publisher","DOI":"10.3389\/fdgth.2026.1771281"},{"key":"e_1_2_13_39_1","doi-asserted-by":"publisher","DOI":"10.3390\/diagnostics15212795"},{"key":"e_1_2_13_40_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2019.103477"},{"key":"e_1_2_13_41_1","doi-asserted-by":"publisher","DOI":"10.1002\/brb3.70770"},{"key":"e_1_2_13_42_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11042\u2010024\u201019314\u20105"},{"key":"e_1_2_13_43_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41598\u2010025\u201004807\u20106"},{"key":"e_1_2_13_44_1","doi-asserted-by":"publisher","DOI":"10.1177\/03601293251352642"},{"key":"e_1_2_13_45_1","doi-asserted-by":"publisher","DOI":"10.2196\/50117"},{"key":"e_1_2_13_46_1","doi-asserted-by":"publisher","DOI":"10.1007\/s12652\u2010022\u201004361\u20103"},{"key":"e_1_2_13_47_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41582\u2010026\u201001185\u2010z"},{"key":"e_1_2_13_48_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.parkreldis.2022.10.020"},{"key":"e_1_2_13_49_1","doi-asserted-by":"publisher","DOI":"10.1049\/ipr2.12820"},{"key":"e_1_2_13_50_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.bspc.2023.105436"},{"key":"e_1_2_13_51_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11042\u2010023\u201014647\u2010z"},{"key":"e_1_2_13_52_1","doi-asserted-by":"publisher","DOI":"10.1155\/2023\/9921809"},{"key":"e_1_2_13_53_1","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0331577"}],"container-title":["Brain and Behavior"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/brb3.71457","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/full-xml\/10.1002\/brb3.71457","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/brb3.71457","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,10,10]],"date-time":"2026-10-10T09:05:17Z","timestamp":1791623117000},"score":1,"resource":{"primary":{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/10.1002\/brb3.71457"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,28]]},"references-count":52,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2026,5]]}},"alternative-id":["10.1002\/brb3.71457"],"URL":"https:\/\/doi.org\/10.1002\/brb3.71457","archive":["Portico"],"relation":{},"ISSN":["2162-3279","2162-3279"],"issn-type":[{"value":"2162-3279","type":"print"},{"value":"2162-3279","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,4,28]]},"assertion":[{"value":"2025-12-23","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-04-16","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-04-28","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"e71457"}}