{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,10]],"date-time":"2026-07-10T14:44:23Z","timestamp":1783694663140,"version":"3.55.0"},"reference-count":13,"publisher":"Oxford University Press (OUP)","issue":"8","license":[{"start":{"date-parts":[[2018,5,7]],"date-time":"2018-05-07T00:00:00Z","timestamp":1525651200000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/academic.oup.com\/journals\/pages\/about_us\/legal\/notices"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2018,8,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:sec>\n                  <jats:title>Background<\/jats:title>\n                  <jats:p>Existing screening tools for early detection of autism are expensive, cumbersome, time- intensive, and sometimes fall short in predictive value. In this work, we sought to apply Machine Learning (ML) to gold standard clinical data obtained across thousands of children at-risk for autism spectrum disorder to create a low-cost, quick, and easy to apply autism screening tool.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Methods<\/jats:title>\n                  <jats:p>Two algorithms are trained to identify autism, one based on short, structured parent-reported questionnaires and the other on tagging key behaviors from short, semi-structured home videos of children. A combination algorithm is then used to combine the results into a single assessment of higher accuracy. To overcome the scarcity, sparsity, and imbalance of training data, we apply novel feature selection, feature engineering, and feature encoding techniques. We allow for inconclusive determination where appropriate in order to boost screening accuracy when conclusive. The performance is then validated in a controlled clinical study.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Results<\/jats:title>\n                  <jats:p>A multi-center clinical study of n\u2009=\u2009162 children is performed to ascertain the performance of these algorithms and their combination. We demonstrate a significant accuracy improvement over standard screening tools in measurements of AUC, sensitivity, and specificity.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Conclusion<\/jats:title>\n                  <jats:p>These findings suggest that a mobile, machine learning process is a reliable method for detection of autism outside of clinical settings. A variety of confounding factors in the clinical analysis are discussed along with the solutions engineered into the algorithms. Final results are statistically limited and will benefit from future clinical studies to extend the sample size.<\/jats:p>\n               <\/jats:sec>","DOI":"10.1093\/jamia\/ocy039","type":"journal-article","created":{"date-parts":[[2018,4,3]],"date-time":"2018-04-03T11:22:22Z","timestamp":1522754542000},"page":"1000-1007","source":"Crossref","is-referenced-by-count":169,"title":["Machine learning approach for early detection of autism by combining questionnaire and home video screening"],"prefix":"10.1093","volume":"25","author":[{"given":"Halim","family":"Abbas","sequence":"first","affiliation":[{"name":"Cognoa Inc., Palo Alto, CA, USA www.linkedin.com\/in\/halimabbas"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8290-4780","authenticated-orcid":false,"given":"Ford","family":"Garberson","sequence":"additional","affiliation":[{"name":"Cognoa Inc., Palo Alto, CA, USA www.linkedin.com\/in\/halimabbas"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Eric","family":"Glover","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dennis P","family":"Wall","sequence":"additional","affiliation":[{"name":"Cognoa Inc., Palo Alto, CA, USA www.linkedin.com\/in\/halimabbas"},{"name":"Department of Pediatrics, Stanford University, Stanford, CA, USA"},{"name":"Department of Biomedical Data Science, Stanford University, Stanford, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"286","published-online":{"date-parts":[[2018,5,7]]},"reference":[{"issue":"7","key":"2020110612233687900_ocy039-B1","doi-asserted-by":"crossref","first-page":"e11551","DOI":"10.1371\/journal.pone.0011551","article-title":"Socioeconomic inequality in the prevalence of autism spectrum disorder: evidence from a U.S. cross-sectional study","volume":"5","author":"Durkin","year":"2010","journal-title":"PLoS One"},{"issue":"3","key":"2020110612233687900_ocy039-B2","doi-asserted-by":"crossref","first-page":"1","DOI":"10.15585\/mmwr.ss6503a1","article-title":"Prevalence and characteristics of autism spectrum disorder among children aged 8 years\u2014autism and developmental disabilities monitoring network, 11 sites, United States, 2012","volume":"65","author":"Christensen","year":"2016","journal-title":"MMWR Surveill Summ"},{"issue":"5","key":"2020110612233687900_ocy039-B3","doi-asserted-by":"crossref","first-page":"1383","DOI":"10.1542\/peds.2008-1606","article-title":"Clinical assessment and management of toddlers with suspected autism spectrum disorder: insights from studies of high-risk infants","volume":"123","author":"Zwaigenbaum","year":"2009","journal-title":"Pediatrics"},{"issue":"1745","key":"2020110612233687900_ocy039-B4","first-page":"27","article-title":"Diagnosing autism spectrum disorders in primary care","volume":"255","author":"BernierMao","year":"2011","journal-title":"Practitioner"},{"key":"2020110612233687900_ocy039-B5","author":"Achenbach","year":"2001"},{"issue":"5","key":"2020110612233687900_ocy039-B6","doi-asserted-by":"crossref","first-page":"659","DOI":"10.1007\/BF02172145","article-title":"Autism diagnostic interview-revised: a revised version of a diagnostic interview for caregivers of individuals with possible pervasive developmental disorders","volume":"24","author":"Lord","year":"1994","journal-title":"J Autism Dev Disord"},{"issue":"2","key":"2020110612233687900_ocy039-B7","doi-asserted-by":"crossref","first-page":"185","DOI":"10.1007\/BF02211841","article-title":"Autism diagnostic observation schedule: a standardized observation of communicative and social behavior","volume":"19","author":"Lord","year":"1989","journal-title":"J Autism Dev Disord"},{"issue":"3","key":"2020110612233687900_ocy039-B8","doi-asserted-by":"crossref","first-page":"306","DOI":"10.1001\/archgenpsychiatry.2011.148","article-title":"A multisite study of the clinical diagnosis of different autism spectrum disorders","volume":"69","author":"Lord","year":"2012","journal-title":"Arch Gen Psychiatry"},{"issue":"8","key":"2020110612233687900_ocy039-B9","doi-asserted-by":"crossref","first-page":"e43855","DOI":"10.1371\/journal.pone.0043855","article-title":"Use of artificial intelligence to shorten the behavioral diagnosis of autism","volume":"7","author":"Wall","year":"2012","journal-title":"PLoS One"},{"issue":"8","key":"2020110612233687900_ocy039-B10","doi-asserted-by":"crossref","first-page":"e424","DOI":"10.1038\/tp.2014.65","article-title":"Testing the accuracy of an observation-based classifier for rapid detection of autism risk","volume":"4","author":"Duda","year":"2014","journal-title":"Transl Psychiatry"},{"issue":"6","key":"2020110612233687900_ocy039-B11","doi-asserted-by":"crossref","first-page":"1953","DOI":"10.1007\/s10803-016-2718-4","article-title":"Clinical evaluation of a novel and mobile autism risk assessment","volume":"46","author":"DudaDaniels","year":"2016","journal-title":"J Autism Dev Disord"},{"issue":"4","key":"2020110612233687900_ocy039-B12","doi-asserted-by":"crossref","first-page":"e93533","DOI":"10.1371\/journal.pone.0093533","article-title":"The potential of accelerating early detection of autism through content analysis of youtube videos","volume":"9","author":"Fusaro","year":"2014","journal-title":"PLoS One"},{"key":"2020110612233687900_ocy039-B13"}],"container-title":["Journal of the American Medical Informatics Association"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/academic.oup.com\/jamia\/article-pdf\/25\/8\/1000\/34150467\/ocy039.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"http:\/\/academic.oup.com\/jamia\/article-pdf\/25\/8\/1000\/34150467\/ocy039.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,11,6]],"date-time":"2020-11-06T17:28:57Z","timestamp":1604683737000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/jamia\/article\/25\/8\/1000\/4993666"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,5,7]]},"references-count":13,"journal-issue":{"issue":"8","published-online":{"date-parts":[[2018,5,7]]},"published-print":{"date-parts":[[2018,8,1]]}},"URL":"https:\/\/doi.org\/10.1093\/jamia\/ocy039","relation":{},"ISSN":["1067-5027","1527-974X"],"issn-type":[{"value":"1067-5027","type":"print"},{"value":"1527-974X","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2018,8]]},"published":{"date-parts":[[2018,5,7]]}}}