{"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":1793483221790,"version":"4.5.0"},"reference-count":44,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2025,4,7]],"date-time":"2025-04-07T00:00:00Z","timestamp":1743984000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2025,4,7]],"date-time":"2025-04-07T00:00:00Z","timestamp":1743984000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"name":"This project is supported by an anonymous donation to develop the CHEO Precision Child and Youth Mental Health Initiative."}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Sci Rep"],"abstract":"<jats:title>Abstract<\/jats:title>\n          <jats:p>Early diagnosis and access to resources, support and therapy are critical for improving long-term outcomes for children with autism spectrum disorder (ASD). ASD is typically detected using a case-finding approach based on symptoms and family history, resulting in many delayed or missed diagnoses. While population-based screening would be ideal for early identification, available screening tools have limited accuracy. This study aims to determine whether machine learning models applied to health administrative and birth registry data can identify young children (aged 18 months to 5 years) who are at increased likelihood of developing ASD. We assembled the study cohort using individually linked maternal-newborn data from the Better Outcomes Registry and Network (BORN) Ontario database. The cohort included all live births in Ontario, Canada between April 1st, 2006, and March 31st, 2018, linked to datasets from Newborn Screening Ontario (NSO), Prenatal Screening Ontario (PSO), and Canadian Institute for Health Information (CIHI) (Discharge Abstract Database (DAD) and National Ambulatory Care Reporting System (NACRS)). The NSO and PSO datasets provided screening biomarker values and outcomes, while DAD and NACRS contained diagnosis codes and intervention codes for mothers and offspring. Extreme Gradient Boosting models and large-scale ensembled Transformer deep learning models were developed to predict ASD diagnosis between 18 and 60 months of age. Leveraging explainable artificial intelligence methods, we determined the impactful factors that contribute to increased likelihood of ASD at both an individual- and population-level. The final study cohort included 707,274 mother-offspring pairs, with 10,956 identified cases of ASD. The best-performing ensemble of Transformer models achieved an area under the receiver operating characteristic curve of 69.6% for predicting ASD diagnosis, a sensitivity of 70.9%, a specificity of 56.9%. We determine that our model can be used to identify an enriched pool of children with the greatest likelihood of developing ASD, demonstrating the feasibility of this approach.This study highlights the feasibility of employing machine learning models and routinely collected health data to systematically identify young children at high likelihood of developing ASD. Ensemble transformer models applied to health administrative and birth registry data offer a promising avenue for universal ASD screening. Such early detection enables targeted and formal assessment for timely diagnosis and early access to resources, support, or therapy.<\/jats:p>","DOI":"10.1038\/s41598-025-90216-8","type":"journal-article","created":{"date-parts":[[2025,4,7]],"date-time":"2025-04-07T01:08:16Z","timestamp":1743988096000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":16,"title":["Transformer-based deep learning ensemble framework predicts autism spectrum disorder using health administrative and birth registry data"],"prefix":"10.1038","volume":"15","author":[{"given":"Kevin","family":"Dick","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Emily","family":"Kaczmarek","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Robin","family":"Ducharme","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Alexa C.","family":"Bowie","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Alysha L.J.","family":"Dingwall-Harvey","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Heather","family":"Howley","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Steven","family":"Hawken","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mark C.","family":"Walker","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Christine M.","family":"Armour","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,4,7]]},"reference":[{"key":"90216_CR1","doi-asserted-by":"publisher","first-page":"508","DOI":"10.1016\/S0140-6736(18)31129-2","volume":"392","author":"C Lord","year":"2018","unstructured":"Lord, C., Elsabbagh, M., Baird, G. & Veenstra-Vanderweele, J. Autism spectrum disorder. Lancet 392, 508\u2013520 (2018).","journal-title":"Lancet"},{"key":"90216_CR2","doi-asserted-by":"publisher","first-page":"539","DOI":"10.1016\/j.rasd.2010.06.020","volume":"5","author":"M Mehtar","year":"2011","unstructured":"Mehtar, M. & Mukaddes, N. M. Posttraumatic stress disorder in individuals with diagnosis of autistic spectrum disorders. Res. Autism Spectr. Disord. 5, 539\u2013546 (2011).","journal-title":"Res. Autism Spectr. Disord"},{"key":"90216_CR3","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s11689-016-9160-y","volume":"8","author":"JL Taylor","year":"2016","unstructured":"Taylor, J. L. & Gotham, K. O. Cumulative life events, traumatic experiences, and psychiatric symptomatology in transition-aged youth with autism spectrum disorder. J. Neurodev Disord. 8, 1\u201311 (2016).","journal-title":"J. Neurodev Disord"},{"key":"90216_CR4","doi-asserted-by":"publisher","first-page":"1","DOI":"10.15585\/mmwr.ss7011a1","volume":"70","author":"MJ Maenner","year":"2021","unstructured":"Maenner, M. J. et al. Prevalence and characteristics of Autism Spectrum Disorder among children aged 8 years \u2014 Autism and Developmental Disabilities Monitoring Network, 11 sites, United States, 2018. MMWR Surveillance Summaries. 70, 1 (2021).","journal-title":"MMWR Surveillance Summaries"},{"key":"90216_CR5","unstructured":"Handleman, J. S. & Harris, S. L. Preschool Education Programs for Children with AutismCiteseer,. (2001)."},{"key":"90216_CR6","volume-title":"& others. Educating Children with Autism","author":"NR Council","year":"2001","unstructured":"Council, N. R. & Others. Educating Children with Autism (National Academies, 2001)."},{"key":"90216_CR7","doi-asserted-by":"publisher","first-page":"e17","DOI":"10.1542\/peds.2009-0958","volume":"125","author":"G Dawson","year":"2010","unstructured":"Dawson, G. et al. Controlled trial of an intervention for toddlers with autism: the early start Denver Model. Pediatrics 125, e17\u2013e23 (2010). Randomized.","journal-title":"Pediatrics"},{"key":"90216_CR8","doi-asserted-by":"publisher","first-page":"S41","DOI":"10.1542\/peds.2014-3667D","volume":"136","author":"L Zwaigenbaum","year":"2015","unstructured":"Zwaigenbaum, L. et al. Early screening of Autism Spectrum Disorder: recommendations for practice and research. Pediatrics 136, S41\u2013S59 (2015).","journal-title":"Pediatrics"},{"key":"90216_CR9","doi-asserted-by":"publisher","first-page":"23","DOI":"10.1007\/s10803-008-0596-0","volume":"39","author":"B Reichow","year":"2009","unstructured":"Reichow, B. & Wolery, M. Comprehensive synthesis of early intensive behavioral interventions for young children with autism based on the UCLA young autism project model. J. Autism Dev. Disord. 39, 23\u201341 (2009).","journal-title":"J. Autism Dev. Disord"},{"key":"90216_CR10","doi-asserted-by":"publisher","first-page":"593","DOI":"10.1097\/DBP.0000000000000483","volume":"38","author":"M Penner","year":"2017","unstructured":"Penner, M. et al. Community General pediatricians\u2019 perspectives on providing autism diagnoses in Ontario, Canada: a qualitative study. J. Dev. Behav. Pediatr. 38, 593 (2017).","journal-title":"J. Dev. Behav. Pediatr."},{"key":"90216_CR11","doi-asserted-by":"publisher","first-page":"e20","DOI":"10.1093\/pch\/20.5.e20","volume":"20","author":"AWS Ip","year":"2015","unstructured":"Ip, A. W. S., Zwaigenbaum, L., Nicholas, D. & Sharon, R. Factors influencing autism spectrum disorder screening by community paediatricians. Paediatr. Child. Health. 20, e20\u2013e24 (2015).","journal-title":"Paediatr. Child. Health"},{"key":"90216_CR12","doi-asserted-by":"crossref","unstructured":"Rahman, R. et al. Identification of newborns at risk for autism using electronic medical records and machine learning. Eur. Psychiatry 63, e22 (2020).","DOI":"10.1192\/j.eurpsy.2020.17"},{"key":"90216_CR13","doi-asserted-by":"publisher","first-page":"e100544","DOI":"10.1136\/bmjhci-2022-100544","volume":"29","author":"YH Chen","year":"2022","unstructured":"Chen, Y. H., Chen, Q., Kong, L. & Liu, G. Early detection of autism spectrum disorder in young children with machine learning using medical claims data. BMJ Health Care Inf. 29, e100544 (2022).","journal-title":"BMJ Health Care Inf."},{"key":"90216_CR14","doi-asserted-by":"crossref","unstructured":"Hazlett, H. C. et al. Early brain development in infants at high risk for autism spectrum disorder. Nature 542, 348\u2013351 (2017).","DOI":"10.1038\/nature21369"},{"key":"90216_CR15","doi-asserted-by":"crossref","unstructured":"Chaitra, N., Vijaya, P. A. & Deshpande, G. Diagnostic prediction of autism spectrum disorder using complex network measures in a machine learning framework. Biomed. Signal. Process. Control 62, 102099 (2020).","DOI":"10.1016\/j.bspc.2020.102099"},{"key":"90216_CR16","doi-asserted-by":"crossref","unstructured":"Ahammed, M. S. et al. DarkASDNet: Classification of ASD on functional MRI using deep neural network. Front. Neuroinform 15, 635657 (2021).","DOI":"10.3389\/fninf.2021.635657"},{"key":"90216_CR17","doi-asserted-by":"crossref","unstructured":"Maenner, M. J., Yeargin-Allsopp, M., Van Braun, K. N. & Christensen, D. L. & Schieve, L. A. Development of a machine learning algorithm for the surveillance of autism spectrum disorder. PLoS One 11, e0168224 (2016).","DOI":"10.1371\/journal.pone.0168224"},{"key":"90216_CR18","doi-asserted-by":"crossref","unstructured":"Akter, T. et al. Machine learning-based models for early stage detection of Autism Spectrum disorders. IEEE Access. 7, 166509\u2013166527 (2019).","DOI":"10.1109\/ACCESS.2019.2952609"},{"key":"90216_CR19","doi-asserted-by":"crossref","unstructured":"Omar, K. S., Mondal, P., Khan, N. S., Rizvi, M. R. K. & Islam, M. N. A machine learning approach to predict autism spectrum disorder. in 2019 International conference on electrical, computer and communication engineering (ECCE) 1\u20136 (2019).","DOI":"10.1109\/ECACE.2019.8679454"},{"key":"90216_CR20","doi-asserted-by":"crossref","unstructured":"Usta, M. B. et al. Use of machine learning methods in prediction of short-term outcome in autism spectrum disorders. Psychiatry Clin. Psychopharmacol. 29, 320\u2013325 (2019).","DOI":"10.1080\/24750573.2018.1545334"},{"key":"90216_CR21","doi-asserted-by":"publisher","unstructured":"Vishal, V. et al. A Comparative Analysis of Prediction of Autism Spectrum Disorder (ASD) using Machine Learning. in 2022 6th International Conference on Trends in Electronics and Informatics, ICOEI 2022 - Proceedings (2022). https:\/\/doi.org\/10.1109\/ICOEI53556.2022.9777240","DOI":"10.1109\/ICOEI53556.2022.9777240"},{"key":"90216_CR22","doi-asserted-by":"publisher","first-page":"883","DOI":"10.3390\/brainsci13060883","volume":"13","author":"M Briguglio","year":"2023","unstructured":"Briguglio, M. et al. A Machine Learning Approach to the diagnosis of Autism Spectrum Disorder and Multi-systemic Developmental Disorder based on Retrospective Data and ADOS-2 score. Brain Sci. 13, 883 (2023).","journal-title":"Brain Sci."},{"key":"90216_CR23","doi-asserted-by":"crossref","unstructured":"Oh, D. H., Kim, I., Bin, Kim, S. H. & Ahn, D. H. Predicting autism spectrum disorder using blood-based gene expression signatures and machine learning. Clin. Psychopharmacol. Neurosci. 15, 47 (2017).","DOI":"10.9758\/cpn.2017.15.1.47"},{"key":"90216_CR24","doi-asserted-by":"publisher","first-page":"2082","DOI":"10.3390\/ijms24032082","volume":"24","author":"I Voinsky","year":"2023","unstructured":"Voinsky, I., Fridland, O. Y., Aran, A., Frye, R. E. & Gurwitz, D. Machine learning-based blood RNA signature for diagnosis of Autism Spectrum Disorder. Int. J. Mol. Sci. 24, 2082 (2023).","journal-title":"Int. J. Mol. Sci."},{"key":"90216_CR25","unstructured":"Vaswani, A. et al. Attention is all you need. in Advances in Neural Information Processing Systems vols 2017-December (2017)."},{"key":"90216_CR26","doi-asserted-by":"publisher","first-page":"7857","DOI":"10.1038\/s41467-023-43715-z","volume":"14","author":"Z Yang","year":"2023","unstructured":"Yang, Z., Mitra, A., Liu, W., Berlowitz, D. & Yu, H. TransformEHR: transformer-based encoder-decoder generative model to enhance prediction of disease outcomes using electronic health records. Nat. Commun. 14, 7857 (2023).","journal-title":"Nat. Commun."},{"key":"90216_CR27","doi-asserted-by":"crossref","unstructured":"Amann, J., Blasimme, A., Vayena, E., Frey, D. & Madai V. I. Explainability for artificial intelligence in healthcare: a multidisciplinary perspective. BMC Med. Inf. Decis. Mak. 20, 1\u20139 (2020).","DOI":"10.1186\/s12911-020-01332-6"},{"key":"90216_CR28","doi-asserted-by":"publisher","unstructured":"Chaddad, A., Peng, J., Xu, J. & Bouridane, A. Survey of Explainable AI Techniques in Healthcare. Sensors vol. 23 Preprint at (2023). https:\/\/doi.org\/10.3390\/s23020634","DOI":"10.3390\/s23020634"},{"key":"90216_CR29","unstructured":"Personal Health Information Protection Act. S.O. 2004, c. 3, Sched. A | ontario.ca. (2004). Available at: https:\/\/www.ontario.ca\/laws\/statute\/04p03#BK44. (Accessed: 10th December 2024)."},{"key":"90216_CR30","doi-asserted-by":"publisher","first-page":"1416","DOI":"10.1093\/ije\/dyab033","volume":"50","author":"MSQ Murphy","year":"2021","unstructured":"Murphy, M. S. Q. et al. Data Resource Profile: Better Outcomes Registry & Network (BORN) Ontario. Int. J. Epidemiol. 50, 1416\u20131425 (2021).","journal-title":"Int. J. Epidemiol."},{"key":"90216_CR31","doi-asserted-by":"crossref","unstructured":"Chen, T., Guestrin, C. & XGBoost A scalable tree boosting system. in Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining vols 13-17-August-2016 (2016).","DOI":"10.1145\/2939672.2939785"},{"key":"90216_CR32","doi-asserted-by":"publisher","first-page":"1037","DOI":"10.1002\/aur.2491","volume":"14","author":"JD Brooks","year":"2021","unstructured":"Brooks, J. D. et al. Assessing the validity of administrative health data for the identification of children and youth with autism spectrum disorder in Ontario. Autism Res. 14, 1037\u20131045 (2021).","journal-title":"Autism Res."},{"key":"90216_CR33","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1038\/s41598-019-56847-4","volume":"10","author":"Y Li","year":"2020","unstructured":"Li, Y. et al. BEHRT: transformer for electronic health records. Sci. Rep. 10, 1\u201312 (2020).","journal-title":"Sci. Rep."},{"key":"90216_CR34","unstructured":"Chen, T. et al. Xgboost: extreme gradient boosting. R package version 0.4-2 1, 1\u20134 (2015)."},{"key":"90216_CR35","doi-asserted-by":"crossref","unstructured":"Dick, K., Chopra, A., Biggar, K. K. & Green, J. R. Multi-schema computational prediction of the comprehensive SARS-CoV-2 vs. human interactome. PeerJ 9, e11117 (2021).","DOI":"10.7717\/peerj.11117"},{"key":"90216_CR36","unstructured":"Lundberg, S. M., Allen, P. G. & Lee, S. I. A Unified Approach to interpreting model predictions. Adv. Neural Inf. Process. Syst. 30, 4765\u20134774 (2017)."},{"key":"90216_CR37","doi-asserted-by":"publisher","unstructured":"Hemu, A. A. et al. Identification of Significant Risk Factors and Impact for ASD Prediction among Children Using Machine Learning Approach. in 2022 2nd International Conference on Advances in Electrical, Computing, Communication and Sustainable Technologies, ICAECT 2022 (2022). https:\/\/doi.org\/10.1109\/ICAECT54875.2022.9808043","DOI":"10.1109\/ICAECT54875.2022.9808043"},{"key":"90216_CR38","doi-asserted-by":"publisher","first-page":"1120","DOI":"10.1002\/aur.1960","volume":"11","author":"L Bishop-Fitzpatrick","year":"2018","unstructured":"Bishop-Fitzpatrick, L. et al. Using machine learning to identify patterns of lifetime health problems in decedents with autism spectrum disorder. Autism Res. 11, 1120\u20131128 (2018).","journal-title":"Autism Res."},{"key":"90216_CR39","doi-asserted-by":"publisher","first-page":"941","DOI":"10.1002\/aur.2912","volume":"16","author":"KS Betts","year":"2023","unstructured":"Betts, K. S., Chai, K., Kisely, S. & Alati, R. Development and validation of a machine learning-based tool to predict autism among children. Autism Res. 16, 941\u2013952 (2023).","journal-title":"Autism Res."},{"key":"90216_CR40","unstructured":"Vaswani, A. et al. Attention is all you need. Adv. Neural Inf. Process. Syst. 30, 5998\u20136008 (2017)."},{"key":"90216_CR41","doi-asserted-by":"crossref","unstructured":"Friedman, J. H. Greedy function approximation: a gradient boosting machine. Ann. Stat. 29, 1189\u20131232 (2001).","DOI":"10.1214\/aos\/1013203451"},{"key":"90216_CR42","doi-asserted-by":"publisher","first-page":"337","DOI":"10.1214\/aos\/1016218223","volume":"28","author":"J Friedman","year":"2000","unstructured":"Friedman, J., Hastie, T. & Tibshirani, R. Additive logistic regression: a statistical view of boosting (with discussion and a rejoinder by the authors). Annals Stat. 28, 337\u2013407 (2000).","journal-title":"Annals Stat."},{"key":"90216_CR43","doi-asserted-by":"crossref","unstructured":"Dick, K. & Green, J. R. Reciprocal perspective for Improved Protein-Protein Interaction Prediction. Sci. Rep. 8, 11694 (2018).","DOI":"10.1038\/s41598-018-30044-1"},{"key":"90216_CR44","doi-asserted-by":"crossref","unstructured":"Dick, K. et al. Reciprocal perspective as a super learner improves drug-target interaction prediction (MUSDTI). Scientific Reports 12, 1\u201319 (2022). (2022).","DOI":"10.1038\/s41598-022-16493-9"}],"updated-by":[{"DOI":"10.1038\/s41598-025-19777-y","type":"correction","label":"Correction","source":"publisher","updated":{"date-parts":[[2025,9,29]],"date-time":"2025-09-29T00:00:00Z","timestamp":1759104000000}}],"container-title":["Scientific Reports"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41598-025-90216-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-025-90216-8","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-025-90216-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,29]],"date-time":"2025-09-29T22:02:36Z","timestamp":1759183356000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41598-025-90216-8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,7]]},"references-count":44,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2025,12]]}},"alternative-id":["90216"],"URL":"https:\/\/doi.org\/10.1038\/s41598-025-90216-8","relation":{},"ISSN":["2045-2322"],"issn-type":[{"value":"2045-2322","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,4,7]]},"assertion":[{"value":"24 July 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"11 February 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"7 April 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"29 September 2025","order":4,"name":"change_date","label":"Change Date","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"Correction","order":5,"name":"change_type","label":"Change Type","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"A Correction to this paper has been published:","order":6,"name":"change_details","label":"Change Details","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"https:\/\/doi.org\/10.1038\/s41598-025-19777-y","URL":"https:\/\/doi.org\/10.1038\/s41598-025-19777-y","order":7,"name":"change_details","label":"Change Details","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no competing interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"11816"}}