{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,31]],"date-time":"2026-10-31T21:47:01Z","timestamp":1793483221195,"version":"4.5.0"},"reference-count":38,"publisher":"American Medical Association (AMA)","issue":"5","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["JAMA Netw Open"],"abstract":"\n Importance<\/jats:title>\n Joint attention, composed of complex behaviors, is an early-emerging social function that is deficient in children with autism spectrum disorder (ASD). Currently, no methods are available for objectively quantifying joint attention.<\/jats:p>\n <\/jats:sec>\n \n Objective<\/jats:title>\n To train deep learning (DL) models to distinguish ASD from typical development (TD) and to differentiate ASD symptom severities using video data of joint attention behaviors.<\/jats:p>\n <\/jats:sec>\n \n Design, Setting, and Participants<\/jats:title>\n In this diagnostic study, joint attention tasks were administered to children with and without ASD, and video data were collected from multiple institutions from August 5, 2021, to July 18, 2022. Of 110 children, 95 (86.4%) completed study measures. Enrollment criteria were 24 to 72 months of age and ability to sit with no history of visual or auditory deficits.<\/jats:p>\n <\/jats:sec>\n \n Exposures<\/jats:title>\n Children were screened using the Childhood Autism Rating Scale. Forty-five children were diagnosed with ASD. Three types of joint attention were assessed using a specific protocol.<\/jats:p>\n <\/jats:sec>\n \n Main Outcomes and Measures<\/jats:title>\n Correctly distinguishing ASD from TD and different levels of ASD symptom severity using the DL model area under the receiver operating characteristic curve (AUROC), accuracy, precision, and recall.<\/jats:p>\n <\/jats:sec>\n \n Results<\/jats:title>\n The analytical population consisted of 45 children with ASD (mean [SD] age, 48.0 [13.4] months; 24 [53.3%] boys) vs 50 with TD (mean [SD] age, 47.9 [12.5] months; 27 [54.0%] boys). The DL ASD vs TD models showed good predictive performance for initiation of joint attention (IJA) (AUROC, 99.6% [95% CI, 99.4%-99.7%]; accuracy, 97.6% [95% CI, 97.1%-98.1%]; precision, 95.5% [95% CI, 94.4%-96.5%]; and recall, 99.2% [95% CI, 98.7%-99.6%]), low-level response to joint attention (RJA) (AUROC, 99.8% [95% CI, 99.6%-99.9%]; accuracy, 98.8% [95% CI, 98.4%-99.2%]; precision, 98.9% [95% CI, 98.3%-99.4%]; and recall, 99.1% [95% CI, 98.6%-99.5%]), and high-level RJA (AUROC, 99.5% [95% CI, 99.2%-99.8%]; accuracy, 98.4% [95% CI, 97.9%-98.9%]; precision, 98.8% [95% CI, 98.2%-99.4%]; and recall, 98.6% [95% CI, 97.9%-99.2%]). The DL-based ASD symptom severity models showed reasonable predictive performance for IJA (AUROC, 90.3% [95% CI, 88.8%-91.8%]; accuracy, 84.8% [95% CI, 82.3%-87.2%]; precision, 76.2% [95% CI, 72.9%-79.6%]; and recall, 84.8% [95% CI, 82.3%-87.2%]), low-level RJA (AUROC, 84.4% [95% CI, 82.0%-86.7%]; accuracy, 78.4% [95% CI, 75.0%-81.7%]; precision, 74.7% [95% CI, 70.4%-78.8%]; and recall, 78.4% [95% CI, 75.0%-81.7%]), and high-level RJA (AUROC, 84.2% [95% CI, 81.8%-86.6%]; accuracy, 81.0% [95% CI, 77.3%-84.4%]; precision, 68.6% [95% CI, 63.8%-73.6%]; and recall, 81.0% [95% CI, 77.3%-84.4%]).<\/jats:p>\n <\/jats:sec>\n \n Conclusions and Relevance<\/jats:title>\n In this diagnostic study, DL models for identifying ASD and differentiating levels of ASD symptom severity were developed and the premises for DL-based predictions were visualized. The findings suggest that this method may allow digital measurement of joint attention; however, follow-up studies are necessary for further validation.<\/jats:p>\n <\/jats:sec>","DOI":"10.1001\/jamanetworkopen.2023.15174","type":"journal-article","created":{"date-parts":[[2023,5,25]],"date-time":"2023-05-25T11:33:38Z","timestamp":1685014418000},"page":"e2315174","source":"Crossref","is-referenced-by-count":30,"title":["Development and Validation of a Joint Attention\u2013Based Deep Learning System for Detection and Symptom Severity Assessment of Autism Spectrum Disorder"],"prefix":"10.1001","volume":"6","author":[{"given":"Chanyoung","family":"Ko","sequence":"first","affiliation":[{"name":"Department of Biomedical Systems Informatics, Yonsei University College of Medicine, Seoul, South Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jae-Hyun","family":"Lim","sequence":"additional","affiliation":[{"name":"LumanLab Inc, Seoul, South Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"JaeSeong","family":"Hong","sequence":"additional","affiliation":[{"name":"Department of Biomedical Systems Informatics, Yonsei University College of Medicine, Seoul, South Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Soon-Beom","family":"Hong","sequence":"additional","affiliation":[{"name":"Division of Child and Adolescent Psychiatry, Department of Psychiatry, Seoul National University College of Medicine, Seoul, South Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yu Rang","family":"Park","sequence":"additional","affiliation":[{"name":"Department of Biomedical Systems Informatics, Yonsei University College of Medicine, Seoul, South Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"10","published-online":{"date-parts":[[2023,5,25]]},"reference":[{"issue":"3","key":"zoi230467r2","doi-asserted-by":"publisher","first-page":"938","DOI":"10.1111\/cdev.2007.78.issue-3","article-title":"Individual differences and the development of joint attention in infancy.","volume":"78","author":"Mundy","year":"2007","journal-title":"Child Dev"},{"issue":"3","key":"zoi230467r3","doi-asserted-by":"publisher","first-page":"195","DOI":"10.1016\/j.biopsych.2012.11.022","article-title":"Decreased spontaneous attention to social scenes in 6-month-old infants later diagnosed with autism spectrum disorders.","volume":"74","author":"Chawarska","year":"2013","journal-title":"Biol Psychiatry"},{"key":"zoi230467r4","doi-asserted-by":"publisher","first-page":"S55","DOI":"10.21037\/tp","article-title":"Autism spectrum disorder: definition, epidemiology, causes, and clinical evaluation.","volume":"9","author":"Hodges","year":"2020","journal-title":"Transl Pediatr"},{"issue":"4","key":"zoi230467r5","doi-asserted-by":"publisher","first-page":"556","DOI":"10.3390\/children9040556","article-title":"Joint attention and its relationship with autism risk markers at 18 months of age.","volume":"9","author":"Montagut-Asunci\u00f3n","year":"2022","journal-title":"Children (Basel)"},{"issue":"8","key":"zoi230467r6","doi-asserted-by":"publisher","first-page":"631","DOI":"10.1016\/j.biopsych.2019.05.006","article-title":"Joint attention in infancy and the emergence of autism.","volume":"86","author":"Nystr\u00f6m","year":"2019","journal-title":"Biol Psychiatry"},{"issue":"1","key":"zoi230467r8","doi-asserted-by":"publisher","first-page":"5014","DOI":"10.1038\/s41598-020-61213-w","article-title":"Multi-modular AI approach to streamline autism diagnosis in young children.","volume":"10","author":"Abbas","year":"2020","journal-title":"Sci Rep"},{"issue":"11","key":"zoi230467r10","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pmed.1002705","article-title":"Mobile detection of autism through machine learning on home video: a development and prospective validation study.","volume":"15","author":"Tariq","year":"2018","journal-title":"PLoS Med"},{"issue":"1","key":"zoi230467r11","doi-asserted-by":"publisher","first-page":"15069","DOI":"10.1038\/s41598-021-94378-z","article-title":"Using 2D video-based pose estimation for automated prediction of autism spectrum disorders in young children.","volume":"11","author":"Kojovic","year":"2021","journal-title":"Sci Rep"},{"issue":"7","key":"zoi230467r13","doi-asserted-by":"publisher","first-page":"787","DOI":"10.1007\/s10803-009-0926-x","article-title":"Using the childhood autism rating scale to diagnose autism spectrum disorders.","volume":"40","author":"Chlebowski","year":"2010","journal-title":"J Autism Dev Disord"},{"issue":"4","key":"zoi230467r14","doi-asserted-by":"publisher","first-page":"172","DOI":"10.5765\/jkacap.180015","article-title":"Comparison of the Autism Diagnostic Observation Schedule and Childhood Autism Rating Scale in the diagnosis of autism spectrum disorder: a preliminary study.","volume":"29","author":"Park","year":"2018","journal-title":"J Korean Acad Child Adolesc Psychiatry"},{"key":"zoi230467r15","doi-asserted-by":"publisher","first-page":"84","DOI":"10.1016\/j.rasd.2016.09.005","article-title":"ADOS-2 Toddler and Module 1 standardized severity scores as used by community practitioners.","volume":"32","author":"Hedley","year":"2016","journal-title":"Res Autism Spectr Disord"},{"issue":"10","key":"zoi230467r16","doi-asserted-by":"publisher","first-page":"2400","DOI":"10.1007\/s10803-012-1719-1","article-title":"Standardizing ADOS domain scores: separating severity of social affect and restricted and repetitive behaviors.","volume":"44","author":"Hus","year":"2014","journal-title":"J Autism Dev Disord"},{"issue":"9","key":"zoi230467r17","doi-asserted-by":"publisher","first-page":"2704","DOI":"10.1007\/s10803-015-2432-7","article-title":"The Autism Diagnostic Observation Schedule, Toddler Module: standardized severity scores.","volume":"45","author":"Esler","year":"2015","journal-title":"J Autism Dev Disord"},{"issue":"1","key":"zoi230467r19","doi-asserted-by":"publisher","first-page":"65","DOI":"10.5723\/KJCS.2015.36.1.65","article-title":"A study of concurrent validities of K-WPPSI-IV.","volume":"36","author":"Park","year":"2015","journal-title":"Korean J Child Studies"},{"issue":"6","key":"zoi230467r21","doi-asserted-by":"publisher","first-page":"899","DOI":"10.1007\/s10802-007-9142-3","article-title":"Joint attention and attachment in toddlers with autism.","volume":"35","author":"Naber","year":"2007","journal-title":"J Abnorm Child Psychol"},{"issue":"4","key":"zoi230467r22","doi-asserted-by":"publisher","first-page":"1304","DOI":"10.1016\/j.rasd.2012.04.003","article-title":"Assessment of joint attention in school-age children and adolescents.","volume":"6","author":"Bean","year":"2012","journal-title":"Res Autism Spectr Disord"},{"issue":"8","key":"zoi230467r24","doi-asserted-by":"publisher","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","article-title":"Long short-term memory.","volume":"9","author":"Hochreiter","year":"1997","journal-title":"Neural Comput"},{"issue":"31","key":"zoi230467r29","doi-asserted-by":"publisher","first-page":"1026","DOI":"10.21105\/joss","article-title":"Pingouin: statistics in Python.","volume":"3","author":"Vallat","year":"2018","journal-title":"J Open Source Softw"},{"issue":"60","key":"zoi230467r31","doi-asserted-by":"publisher","first-page":"3021","DOI":"10.21105\/joss","article-title":"Seaborn: statistical data visualization.","volume":"6","author":"Waskom","year":"2021","journal-title":"J Open Source Softw"},{"issue":"1","key":"zoi230467r33","doi-asserted-by":"publisher","first-page":"23","DOI":"10.1038\/s41746-022-00571-3","article-title":"Artificial intelligence to detect malignant eyelid tumors from photographic images.","volume":"5","author":"Li","year":"2022","journal-title":"NPJ Digit Med"},{"issue":"1","key":"zoi230467r34","doi-asserted-by":"publisher","first-page":"29","DOI":"10.1148\/radiology.143.1.7063747","article-title":"The meaning and use of the area under a receiver operating characteristic (ROC) curve.","volume":"143","author":"Hanley","year":"1982","journal-title":"Radiology"},{"issue":"8","key":"zoi230467r35","doi-asserted-by":"publisher","first-page":"827","DOI":"10.1001\/jamapediatrics.2021.0530","article-title":"Computational methods to measure patterns of gaze in toddlers with autism spectrum disorder.","volume":"175","author":"Chang","year":"2021","journal-title":"JAMA Pediatr"},{"issue":"12","key":"zoi230467r36","doi-asserted-by":"publisher","first-page":"2603","DOI":"10.1002\/aur.v14.12","article-title":"Joint attention and intelligence in children with autism spectrum disorder without severe intellectual disability.","volume":"14","author":"Sano","year":"2021","journal-title":"Autism Res"},{"issue":"3","key":"zoi230467r37","doi-asserted-by":"publisher","first-page":"275","DOI":"10.1177\/1362361307089521","article-title":"A comparison of contexts for assessing joint attention in toddlers on the autism spectrum.","volume":"12","author":"Roos","year":"2008","journal-title":"Autism"},{"issue":"1","key":"zoi230467r38","doi-asserted-by":"publisher","first-page":"333","DOI":"10.1038\/s41398-020-01015-w","article-title":"Computer vision in autism spectrum disorder research: a systematic review of published studies from 2009 to 2019.","volume":"10","author":"de Belen","year":"2020","journal-title":"Transl Psychiatry"},{"key":"zoi230467r1","volume-title":"Autism and Joint Attention","author":"Mundy","year":"2016"},{"key":"zoi230467r12","author":"Ko","year":"2022"},{"key":"zoi230467r20","volume-title":"Applied Behavior Analysis","author":"Cooper","year":"2007","edition":"2nd ed"},{"key":"zoi230467r30","author":"Seabold"},{"key":"zoi230467r7","unstructured":"Mundy? P, Delgado? C, Block? J, . Draft: a manual for the Early Social Communication Scales (ESCS). January 2003. Accessed August 1, 2021. https:\/\/education.ucdavis.edu\/sites\/main\/files\/file-attachments\/escs_manual_2003_2013.pdf"},{"key":"zoi230467r9","doi-asserted-by":"crossref","unstructured":"Zunino? A, Morerio? P, Cavallo? A, . Video gesture analysis for autism spectrum disorder detection. Paper presented at: 24th International Conference on Pattern Recognition. September 2018. Accessed October 6, 2021. https:\/\/www.researchgate.net\/publication\/327751352_Video_Gesture_Analysis_for_Autism_Spectrum_Disorder_Detection","DOI":"10.1109\/ICPR.2018.8545095"},{"key":"zoi230467r18","unstructured":"Aylward? GP, Zhu? J. The Bayley Scales: clarification for clinicians and researchers. 2019. Accessed July 26, 2022. https:\/\/www.pearsonassessments.com\/content\/dam\/school\/global\/clinical\/us\/assets\/bayley-4\/bayley-4-technical-report.pdf"},{"key":"zoi230467r23","unstructured":"Simonyan? K, Zisserman? A. Very deep convolutional networks for large-scale image recognition. International Conference on Learning Representations. 2015. Accessed August 2, 2022. https:\/\/www.robots.ox.ac.uk\/~vgg\/publications\/2015\/Simonyan15\/"},{"key":"zoi230467r25","unstructured":"Vaswani? A, Shazeer? N, Parmar? N, . Attention is all you need.? arXiv. Preprint posted online December 6, 2017. doi:10.48550\/arXiv.1706.03762."},{"key":"zoi230467r26","doi-asserted-by":"crossref","unstructured":"Selvaraju? RR, Cogswell? M, Das? A, Vedantam? R, Parikh? D, Batra? D. Grad-CAM: visual explanations from deep networks via gradient-based localization.? arXiv. Preprint posted online December 3, 2019. doi:10.48550\/arXiv.1610.02391?","DOI":"10.1007\/s11263-019-01228-7"},{"key":"zoi230467r27","unstructured":"M\u00fcllner? D. Modern hierarchical, agglomerative clustering algorithms.? arXiv. Preprint posted online September 12, 2011. doi:10.48550\/arXiv.1109.2378"},{"key":"zoi230467r28","unstructured":"Jones? E, Oliphant? T, Peterson? P. SciPy: open source scientific tools for Python. January 2001. Accessed December 1, 2022. https:\/\/scipy.org\/"},{"key":"zoi230467r32","unstructured":"Caswell? T, Droettboom? M, Hunter? J. Matplotlib, version 3.3.1. February 9, 2020. Accessed December 1, 2022. https:\/\/pypi.org\/project\/matplotlib\/3.3.1\/?"}],"container-title":["JAMA Network Open"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/jamanetwork.com\/journals\/jamanetworkopen\/articlepdf\/2805303\/ko_2023_oi_230467_1688139369.92821.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,7,7]],"date-time":"2023-07-07T11:00:34Z","timestamp":1688727634000},"score":1,"resource":{"primary":{"URL":"https:\/\/jamanetwork.com\/journals\/jamanetworkopen\/fullarticle\/2805303"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,5,25]]},"references-count":38,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2023,5,1]]}},"URL":"https:\/\/doi.org\/10.1001\/jamanetworkopen.2023.15174","relation":{},"ISSN":["2574-3805"],"issn-type":[{"value":"2574-3805","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,5,25]]}}}