{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,19]],"date-time":"2026-10-19T07:41:48Z","timestamp":1792395708349,"version":"4.4.0"},"reference-count":11,"publisher":"Wiley","issue":"10","license":[{"start":{"date-parts":[[2026,10,8]],"date-time":"2026-10-08T00:00:00Z","timestamp":1791417600000},"content-version":"vor","delay-in-days":7,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"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":["Health Science Reports"],"published-print":{"date-parts":[[2026,10]]},"abstract":"<jats:title>ABSTRACT<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Background and Aims<\/jats:title>\n                    <jats:p>Artificial intelligence methods may support research on autism spectrum disorder (ASD)\u2010related screening, but they cannot replace comprehensive clinical assessment. We evaluated two image\u2010training scenarios public Kaggle data alone and a manually prepared combined training set containing Kaggle images plus local images and separately examined a structured DSM\u20105 checklist model. A child\u2010level reanalysis was used to evaluate public\u2010to\u2010local transfer and local adaptation while ensuring that images from the same child were not assigned to different partitions.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>This methodological study used 268 retrospectively abstracted DSM\u20105 records (134 ASD and 134 non\u2010ASD) and 162 local facial images from 92 children (43 ASD and 49 non\u2010ASD). The image experiment evaluated EfficientNet\u2010B2 and ResNet50 under two training scenarios: Kaggle\u2010only training with 2536 images (1268 per class) and a manually prepared combined training set with 2580 images (1290 per class), formed by adding 22 local images per class to the Kaggle training folders. Local images were linked to anonymous child identifiers before partitioning.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>The checklist model achieved 92.5% accuracy (248\/268; 95% CI, 89.6%\u201395.5%) and ROC\u2010AUC 0.984 (95% CI, 0.971\u20130.993) in internal out\u2010of\u2010fold evaluation. In the child\u2010level reanalysis, the Kaggle\u2010only scenario produced zero\u2010shot\/adapted accuracies of 42.1%\/68.4% for EfficientNet\u2010B2% and 68.4%\/89.5% for ResNet50 in 19 locked test children. With the 2580\u2010image combined training set, zero\u2010shot\/adapted accuracies were 71.4%\/78.6% for EfficientNet\u2010B2% and 57.1%\/85.7% for ResNet50 in 14 locked test children. These image results are preliminary and based on small local test cohorts.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>The checklist analysis showed high internal agreement with an existing psychiatrist\u2010assigned label, whereas image performance varied by architecture, training scenario, population transfer, and local adaptation. The results do not establish clinical validity or autonomous diagnosis. Future prospective, multicenter, participant\u2010level evaluation with independent reference standards is required before any clinical use.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1002\/hsr2.73360","type":"journal-article","created":{"date-parts":[[2026,10,9]],"date-time":"2026-10-09T06:17:41Z","timestamp":1791526661000},"update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Artificial Intelligence\u2010Based Approaches for Autism Screening Using Facial Images and DSM\u20105 Checklist Data: A Methodological Study"],"prefix":"10.1002","volume":"9","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5950-6717","authenticated-orcid":false,"given":"Fatemeh","family":"Mohammadi","sequence":"first","affiliation":[{"name":"Department of Health Information Technology, School of Management and Medical Informatics Tabriz University of Medical Sciences Tabriz Iran"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3980-5100","authenticated-orcid":false,"given":"Peyman","family":"Rezaei\u2010Hachesu","sequence":"additional","affiliation":[{"name":"Department of Health Information Technology, School of Management and Medical Informatics Tabriz University of Medical Sciences Tabriz Iran"},{"name":"Emergency and Trauma Care Research Center Tabriz University of Medical Sciences Tabriz Iran"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2511-3357","authenticated-orcid":false,"given":"Afsoon","family":"Asadzadeh","sequence":"additional","affiliation":[{"name":"Department of Health Information Technology, School of Management and Medical Informatics Tabriz University of Medical Sciences Tabriz Iran"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3640-5344","authenticated-orcid":false,"given":"Hassan","family":"Shahrokhi","sequence":"additional","affiliation":[{"name":"Autism and Related Neurodevelopmental Disorders Research Team Tabriz University of Medical Sciences Tabriz Iran"},{"name":"Department of Psychiatry Tabriz University of Medical Sciences Tabriz Iran"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"311","published-online":{"date-parts":[[2026,10,8]]},"reference":[{"key":"e_1_2_15_2_1","doi-asserted-by":"publisher","DOI":"10.21037\/tp.2019.09.09"},{"key":"e_1_2_15_3_1","doi-asserted-by":"publisher","DOI":"10.36255\/exonpublications.autismspectrumdisorders.2021.diagnosis"},{"key":"e_1_2_15_4_1","doi-asserted-by":"publisher","DOI":"10.3390\/diagnostics13182948"},{"issue":"2","key":"e_1_2_15_5_1","first-page":"75","article-title":"Bias in Artificial Intelligence for Medical Imaging: Fundamentals, Detection, Avoidance, Mitigation, Challenges, Ethics, and Prospects","volume":"31","author":"Ko\u00e7ak B.","year":"2025","journal-title":"Diagnostic and interventional Radiology (Ankara, Turkey)"},{"key":"e_1_2_15_6_1","doi-asserted-by":"publisher","DOI":"10.1177\/13623613241305723"},{"key":"e_1_2_15_7_1","doi-asserted-by":"publisher","DOI":"10.1136\/bmj-2023-078378"},{"key":"e_1_2_15_8_1","doi-asserted-by":"publisher","DOI":"10.1002\/hsr2.71476"},{"key":"e_1_2_15_9_1","unstructured":"J. C.JohnsonAutism [dataset]. Kaggle; 2023 https:\/\/www.kaggle.com\/datasets\/jobincjohnson\/autism?select=AutismDataset."},{"key":"e_1_2_15_10_1","volume-title":"Comparison of Human Experts and AI in Predicting Autism From Facial Behavior","author":"Sariyanidi E.","year":"2023"},{"key":"e_1_2_15_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICMLAS67792.2026.11483971"},{"key":"e_1_2_15_12_1","doi-asserted-by":"publisher","DOI":"10.3390\/diagnostics15131601"}],"container-title":["Health Science Reports"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/hsr2.73360","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/full-xml\/10.1002\/hsr2.73360","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/hsr2.73360","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,10,19]],"date-time":"2026-10-19T07:01:01Z","timestamp":1792393261000},"score":1,"resource":{"primary":{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/10.1002\/hsr2.73360"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,10]]},"references-count":11,"journal-issue":{"issue":"10","published-print":{"date-parts":[[2026,10]]}},"alternative-id":["10.1002\/hsr2.73360"],"URL":"https:\/\/doi.org\/10.1002\/hsr2.73360","archive":["Portico"],"relation":{},"ISSN":["2398-8835","2398-8835"],"issn-type":[{"value":"2398-8835","type":"print"},{"value":"2398-8835","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,10]]},"assertion":[{"value":"2026-04-28","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-09-30","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-10-08","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"e73360"}}