{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,9]],"date-time":"2026-06-09T07:50:29Z","timestamp":1780991429668,"version":"3.54.1"},"reference-count":29,"publisher":"Wiley","issue":"3","license":[{"start":{"date-parts":[[2025,3,4]],"date-time":"2025-03-04T00:00:00Z","timestamp":1741046400000},"content-version":"vor","delay-in-days":3,"URL":"http:\/\/onlinelibrary.wiley.com\/termsAndConditions#vor"}],"funder":[{"DOI":"10.13039\/100006108","name":"National Center for Advancing Translational Sciences","doi-asserted-by":"publisher","award":["UL1TR002378"],"award-info":[{"award-number":["UL1TR002378"]}],"id":[{"id":"10.13039\/100006108","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["Birth Defects Research"],"published-print":{"date-parts":[[2025,3]]},"abstract":"<jats:title>ABSTRACT<\/jats:title><jats:sec><jats:title>Background<\/jats:title><jats:p>International Classification of Disease (ICD) codes can accurately identify patients with certain congenital heart defects (CHDs). In ICD\u2010defined CHD data sets, the code for secundum atrial septal defect (ASD) is the most common, but it has a low positive predictive value for CHD, potentially resulting in the drawing of erroneous conclusions from such data sets. Methods with reduced false positive rates for CHD among individuals captured with the ASD ICD code are needed for public health surveillance.<\/jats:p><\/jats:sec><jats:sec><jats:title>Methods<\/jats:title><jats:p>We propose a two\u2010level classification system, which includes a CHD and an ASD classification model, to categorize cases with an ASD ICD code into three groups: ASD, other CHD, or no CHD (including patent foramen ovale). In the proposed approach, a machine learning model that leverages structured data is combined with a text classification system. We compare performances for three text classification strategies: support vector machines (SVMs) using text\u2010based features, a robustly optimized Transformer\u2010based model (RoBERTa), and a scalable tree boosting system using non\u2010text\u2010based features (XGBoost).<\/jats:p><\/jats:sec><jats:sec><jats:title>Results<\/jats:title><jats:p>Using SVM for both CHD and ASD resulted in the best performance for the ASD and no CHD group, achieving <jats:italic>F<\/jats:italic><jats:sub>1<\/jats:sub> scores of 0.53 (\u00b10.05) and 0.78 (\u00b10.02), respectively. XGBoost for CHD and SVM for ASD classification performed best for the other CHD group (<jats:italic>F<\/jats:italic><jats:sub>1<\/jats:sub> score: 0.39 [\u00b10.03]).<\/jats:p><\/jats:sec><jats:sec><jats:title>Conclusions<\/jats:title><jats:p>This study demonstrates that it is feasible to use patients' clinical notes and machine learning to perform more fine\u2010grained classification compared to ICD codes, particularly with higher PPV for CHD. The proposed approach can improve CHD surveillance.<\/jats:p><\/jats:sec>","DOI":"10.1002\/bdr2.2451","type":"journal-article","created":{"date-parts":[[2025,3,10]],"date-time":"2025-03-10T06:22:49Z","timestamp":1741587769000},"update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Machine Learning and Natural Language Processing to Improve Classification of Atrial Septal Defects in Electronic Health Records"],"prefix":"10.1002","volume":"117","author":[{"given":"Yuting","family":"Guo","sequence":"first","affiliation":[{"name":"Department of Biomedical Informatics, School of Medicine Emory University  Atlanta Georgia USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0228-6116","authenticated-orcid":false,"given":"Haoming","family":"Shi","sequence":"additional","affiliation":[{"name":"Department of Biomedical Engineering Georgia Institute Technology  Atlanta Georgia USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wendy M.","family":"Book","sequence":"additional","affiliation":[{"name":"Department of Cardiology, School of Medicine Emory University  Atlanta Georgia USA"},{"name":"Department of Epidemiology, Rollins School of Public Health Emory University  Atlanta Georgia USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lindsey Carrie","family":"Ivey","sequence":"additional","affiliation":[{"name":"Department of Epidemiology, Rollins School of Public Health Emory University  Atlanta Georgia USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"suffix":"III","given":"Fred H.","family":"Rodriguez","sequence":"additional","affiliation":[{"name":"Department of Cardiology, School of Medicine Emory University  Atlanta Georgia USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Reza","family":"Sameni","sequence":"additional","affiliation":[{"name":"Department of Biomedical Informatics, School of Medicine Emory University  Atlanta Georgia USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Cheryl","family":"Raskind\u2010Hood","sequence":"additional","affiliation":[{"name":"Department of Epidemiology, Rollins School of Public Health Emory University  Atlanta Georgia USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chad","family":"Robichaux","sequence":"additional","affiliation":[{"name":"Department of Biomedical Informatics, School of Medicine Emory University  Atlanta Georgia USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3063-1781","authenticated-orcid":false,"given":"Karrie F.","family":"Downing","sequence":"additional","affiliation":[{"name":"National Center on Birth Defects and Developmental Disabilities Centers for Disease Control and Prevention  Atlanta Georgia USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Abeed","family":"Sarker","sequence":"additional","affiliation":[{"name":"Department of Biomedical Informatics, School of Medicine Emory University  Atlanta Georgia USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"311","published-online":{"date-parts":[[2025,3,4]]},"reference":[{"key":"e_1_2_12_2_1","doi-asserted-by":"publisher","DOI":"10.1161\/JAHA.119.013450"},{"key":"e_1_2_12_3_1","doi-asserted-by":"publisher","DOI":"10.1161\/JAHA.118.008775"},{"key":"e_1_2_12_4_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10278-022-00712-w"},{"key":"e_1_2_12_5_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00246-014-1068-2"},{"key":"e_1_2_12_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/1961189.1961199"},{"key":"e_1_2_12_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/2939672.2939785"},{"key":"e_1_2_12_8_1","doi-asserted-by":"publisher","DOI":"10.1017\/S104795112300152X"},{"key":"e_1_2_12_9_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijcard.2022.04.019"},{"key":"e_1_2_12_10_1","doi-asserted-by":"publisher","DOI":"10.1214\/aos\/1176344552"},{"key":"e_1_2_12_11_1","doi-asserted-by":"publisher","DOI":"10.1002\/bdr2.1400"},{"key":"e_1_2_12_12_1","doi-asserted-by":"publisher","DOI":"10.1161\/JAHA.123.030046"},{"key":"e_1_2_12_13_1","first-page":"86","volume-title":"Proceedings of the Australasian Language Technology Workshop","author":"Guo Y.","year":"2020"},{"key":"e_1_2_12_14_1","doi-asserted-by":"publisher","DOI":"10.3390\/healthcare10081478"},{"key":"e_1_2_12_15_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jacc.2020.05.025"},{"key":"e_1_2_12_16_1","doi-asserted-by":"publisher","DOI":"10.1161\/JAHA.123.030821"},{"key":"e_1_2_12_17_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijcard.2023.131616"},{"key":"e_1_2_12_18_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2022.118997"},{"key":"e_1_2_12_19_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jbi.2015.08.002"},{"key":"e_1_2_12_20_1","doi-asserted-by":"publisher","DOI":"10.1161\/JAHA.117.007378"},{"key":"e_1_2_12_21_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1907.11692"},{"key":"e_1_2_12_22_1","doi-asserted-by":"publisher","DOI":"10.1161\/JAHA.122.026172"},{"key":"e_1_2_12_23_1","doi-asserted-by":"publisher","DOI":"10.3390\/diagnostics13132297"},{"key":"e_1_2_12_24_1","doi-asserted-by":"publisher","DOI":"10.1038\/srep26094"},{"key":"e_1_2_12_25_1","doi-asserted-by":"publisher","DOI":"10.1056\/NEJMra1814259"},{"key":"e_1_2_12_26_1","doi-asserted-by":"publisher","DOI":"10.1111\/chd.12563"},{"key":"e_1_2_12_27_1","doi-asserted-by":"publisher","DOI":"10.1161\/JAHA.121.024911"},{"key":"e_1_2_12_28_1","doi-asserted-by":"publisher","DOI":"10.1002\/bdr2.2245"},{"key":"e_1_2_12_29_1","doi-asserted-by":"publisher","DOI":"10.1136\/jamia.2009.001024"},{"key":"e_1_2_12_30_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1098"}],"container-title":["Birth Defects Research"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/bdr2.2451","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,4,21]],"date-time":"2025-04-21T10:47:38Z","timestamp":1745232458000},"score":1,"resource":{"primary":{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/10.1002\/bdr2.2451"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,3]]},"references-count":29,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2025,3]]}},"alternative-id":["10.1002\/bdr2.2451"],"URL":"https:\/\/doi.org\/10.1002\/bdr2.2451","archive":["Portico"],"relation":{},"ISSN":["2472-1727","2472-1727"],"issn-type":[{"value":"2472-1727","type":"print"},{"value":"2472-1727","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,3]]},"assertion":[{"value":"2024-06-06","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-02-02","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-03-04","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"e2451"}}