{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,11]],"date-time":"2026-11-11T21:57:57Z","timestamp":1794434277411,"version":"4.9.1"},"reference-count":85,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2022,9,28]],"date-time":"2022-09-28T00:00:00Z","timestamp":1664323200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2022,9,28]],"date-time":"2022-09-28T00:00:00Z","timestamp":1664323200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/100000968","name":"American Heart Association","doi-asserted-by":"publisher","award":["20PRE35080073"],"award-info":[{"award-number":["20PRE35080073"]}],"id":[{"id":"10.13039\/100000968","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000002","name":"National Institutes of Health","doi-asserted-by":"publisher","award":["T32GM007347"],"award-info":[{"award-number":["T32GM007347"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000002","name":"National Institutes of Health","doi-asserted-by":"publisher","award":["K01LM012381"],"award-info":[{"award-number":["K01LM012381"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000002","name":"National Institutes of Health","doi-asserted-by":"publisher","award":["K01LM012381"],"award-info":[{"award-number":["K01LM012381"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000002","name":"National Institutes of Health","doi-asserted-by":"publisher","award":["R35GM127087"],"award-info":[{"award-number":["R35GM127087"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000912","name":"March of Dimes Foundation","doi-asserted-by":"publisher","award":["Prematurity Research Center - Ohio Collaborative"],"award-info":[{"award-number":["Prematurity Research Center - Ohio Collaborative"]}],"id":[{"id":"10.13039\/100000912","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000861","name":"Burroughs Wellcome Fund","doi-asserted-by":"publisher","award":["Preterm Birth Initiative"],"award-info":[{"award-number":["Preterm Birth Initiative"]}],"id":[{"id":"10.13039\/100000861","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["BMC Med"],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>Identifying pregnancies at risk for preterm birth, one of the leading causes of worldwide infant mortality, has the potential to improve prenatal care. However, we lack broadly applicable methods to accurately predict preterm birth risk. The dense longitudinal information present in electronic health records (EHRs) is enabling scalable and cost-efficient risk modeling of many diseases, but EHR resources have been largely untapped in the study of pregnancy.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>Here, we apply machine learning to diverse data from EHRs with 35,282 deliveries to predict singleton preterm birth.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>We find that machine learning models based on billing codes alone can predict preterm birth risk at various gestational ages (e.g., ROC-AUC = 0.75, PR-AUC = 0.40 at 28 weeks of gestation) and outperform comparable models trained using known risk factors (e.g., ROC-AUC = 0.65, PR-AUC = 0.25 at 28 weeks). Examining the patterns learned by the model reveals it stratifies deliveries into interpretable groups, including high-risk preterm birth subtypes enriched for distinct comorbidities. Our machine learning approach also predicts preterm birth subtypes (spontaneous vs. indicated), mode of delivery, and recurrent preterm birth. Finally, we demonstrate the portability of our approach by showing that the prediction models maintain their accuracy on a large, independent cohort (5978 deliveries) from a different healthcare system.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusions<\/jats:title>\n                    <jats:p>By leveraging rich phenotypic and genetic features derived from EHRs, we suggest that machine learning algorithms have great potential to improve medical care during pregnancy. However, further work is needed before these models can be applied in clinical settings.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1186\/s12916-022-02522-x","type":"journal-article","created":{"date-parts":[[2022,9,27]],"date-time":"2022-09-27T20:02:36Z","timestamp":1664308956000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":42,"title":["Dense phenotyping from electronic health records enables machine learning-based prediction of preterm birth"],"prefix":"10.1186","volume":"20","author":[{"given":"Abin","family":"Abraham","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Brian","family":"Le","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Idit","family":"Kosti","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Peter","family":"Straub","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Digna R.","family":"Velez-Edwards","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lea K.","family":"Davis","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"J. M.","family":"Newton","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Louis J.","family":"Muglia","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Antonis","family":"Rokas","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Cosmin A.","family":"Bejan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Marina","family":"Sirota","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"John A.","family":"Capra","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2022,9,28]]},"reference":[{"key":"2522_CR1","doi-asserted-by":"publisher","first-page":"75","DOI":"10.1016\/S0140-6736(08)60074-4","volume":"371","author":"RL Goldenberg","year":"2008","unstructured":"Goldenberg RL, Culhane JF, Iams JD, Romero R. Epidemiology and causes of preterm birth. Lancet Lond Engl. 2008;371:75\u201384.","journal-title":"Lancet Lond Engl"},{"key":"2522_CR2","doi-asserted-by":"publisher","first-page":"2162","DOI":"10.1016\/S0140-6736(12)60820-4","volume":"379","author":"H Blencowe","year":"2012","unstructured":"Blencowe H, Cousens S, Oestergaard MZ, Chou D, Moller A-B, Narwal R, et al. National, regional, and worldwide estimates of preterm birth rates in the year 2010 with time trends since 1990 for selected countries: a systematic analysis and implications. Lancet Lond Engl. 2012;379:2162\u201372.","journal-title":"Lancet Lond Engl"},{"key":"2522_CR3","doi-asserted-by":"publisher","first-page":"220","DOI":"10.1001\/jamapediatrics.2014.3040","volume":"169","author":"FC Barros","year":"2015","unstructured":"Barros FC, Papageorghiou AT, Victora CG, Noble JA, Pang R, Iams J, et al. The distribution of clinical phenotypes of preterm birth syndrome. JAMA Pediatr. 2015;169:220\u201310.","journal-title":"JAMA Pediatr"},{"key":"2522_CR4","doi-asserted-by":"publisher","first-page":"1566","DOI":"10.1542\/peds.2006-0860","volume":"118","author":"WM Callaghan","year":"2006","unstructured":"Callaghan WM, MacDorman MF, Rasmussen SA, Qin C, Lackritz EM. The contribution of preterm birth to infant mortality rates in the United States. Pediatrics. 2006;118:1566\u201373.","journal-title":"Pediatrics."},{"key":"2522_CR5","doi-asserted-by":"publisher","first-page":"3027","DOI":"10.1016\/S0140-6736(16)31593-8","volume":"388","author":"L Liu","year":"2016","unstructured":"Liu L, Oza S, Hogan D, Chu Y, Perin J, Zhu J, et al. Global, regional, and national causes of under-5 mortality in 2000\u201315: an updated systematic analysis with implications for the Sustainable Development Goals. Lancet. 2016;388:3027\u201335.","journal-title":"Lancet."},{"key":"2522_CR6","doi-asserted-by":"publisher","first-page":"760","DOI":"10.1126\/science.1251816","volume":"345","author":"R Romero","year":"2014","unstructured":"Romero R, Dey SK, Fisher SJ. Preterm labor: one syndrome, many causes. Science. 2014;345:760\u20135.","journal-title":"Science."},{"key":"2522_CR7","doi-asserted-by":"publisher","first-page":"567","DOI":"10.1056\/NEJM199602293340904","volume":"334","author":"J Iams","year":"1996","unstructured":"Iams J, Goldenberg R, Meis P, Mercer B, Moawad A, Das A, et al. The length of the cervix and the risk of spontaneous premature delivery. New Engl J Med. 1996;334:567\u201373.","journal-title":"New Engl J Med"},{"key":"2522_CR8","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0191002","volume":"13","author":"F Fuchs","year":"2018","unstructured":"Fuchs F, Monet B, Ducruet T, Chaillet N, Audibert F. Effect of maternal age on the risk of preterm birth: a large cohort study. PLoS One. 2018;13:e0191002.","journal-title":"PLoS One"},{"key":"2522_CR9","doi-asserted-by":"publisher","first-page":"1216","DOI":"10.1016\/S0002-9378(99)70111-0","volume":"181","author":"BM Mercer","year":"1999","unstructured":"Mercer BM, Goldenberg RL, Moawad AH, Meis PJ, Iams JD, Das AF, et al. The preterm prediction study: effect of gestational age and cause of preterm birth on subsequent obstetric outcome. Am J Obstet Gynecol. 1999;181:1216\u201321.","journal-title":"Am J Obstet Gynecol"},{"key":"2522_CR10","doi-asserted-by":"publisher","first-page":"142","DOI":"10.1053\/j.semperi.2007.04.001","volume":"31","author":"S Mazaki-Tovi","year":"2007","unstructured":"Mazaki-Tovi S, Romero R, Kusanovic JP, Erez O, Pineles BL, Gotsch F, et al. Recurrent preterm birth. Semin Perinatol. 2007;31:142\u201358.","journal-title":"Semin Perinatol"},{"key":"2522_CR11","doi-asserted-by":"publisher","first-page":"289","DOI":"10.1080\/14767050802010206","volume":"21","author":"CV Ananth","year":"2008","unstructured":"Ananth CV, Kirby RS, Vintzileos AM. Recurrence of preterm birth in twin pregnancies in the presence of a prior singleton preterm birth. J Maternal Fetal Neonatal Med. 2008;21:289\u201395.","journal-title":"J Maternal Fetal Neonatal Med"},{"key":"2522_CR12","doi-asserted-by":"publisher","first-page":"529","DOI":"10.1056\/NEJMra0904308","volume":"362","author":"LJ Muglia","year":"2010","unstructured":"Muglia LJ, Katz M. The enigma of spontaneous preterm birth. N Engl J Med. 2010;362:529\u201335.","journal-title":"N Engl J Med"},{"key":"2522_CR13","doi-asserted-by":"publisher","first-page":"75","DOI":"10.1186\/1471-2393-11-67","volume":"11","author":"N Auger","year":"2011","unstructured":"Auger N, Le TUN, Park AL, Luo Z-C. Association between maternal comorbidity and preterm birth by severity and clinical subtype: retrospective cohort study. BMC Pregnancy Childbirth. 2011;11:75.","journal-title":"BMC Pregnancy Childbirth"},{"key":"2522_CR14","doi-asserted-by":"publisher","first-page":"703","DOI":"10.1055\/s-0031-1280592","volume":"28","author":"M Carter","year":"2011","unstructured":"Carter M, Fowler S, Holden A, Xenakis E, Dudley D. The late preterm birth rate and its association with comorbidities in a population-based study. Am J Perinatol. 2011;28:703\u20138.","journal-title":"Am J Perinatol"},{"key":"2522_CR15","first-page":"726","volume":"0","author":"L Francesca","year":"2019","unstructured":"Francesca L, Laura M, Giuseppe R, Francesco DA, Ersilia B, Leonardo P, et al. Biomarkers for predicting spontaneous preterm birth: an umbrella systematic review. J Matern Fetal Neonatal Med. 2019;0:726\u201334.","journal-title":"J Matern Fetal Neonatal Med"},{"key":"2522_CR16","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0171801","volume":"12","author":"Y Dabi","year":"2017","unstructured":"Dabi Y, Nedellec S, Bonneau C, Trouchard B, Rouzier R, Benachi A. Clinical validation of a model predicting the risk of preterm delivery. PLoS One. 2017;12:e0171801.","journal-title":"PLoS One"},{"key":"2522_CR17","doi-asserted-by":"publisher","first-page":"1133","DOI":"10.1126\/science.aar3819","volume":"360","author":"TTM Ngo","year":"2018","unstructured":"Ngo TTM, Moufarrej MN, Rasmussen M-LH, Camunas-Soler J, Pan W, Okamoto J, et al. Noninvasive blood tests for fetal development predict gestational age and preterm delivery. Science. 2018;360:1133\u20136.","journal-title":"Science."},{"key":"2522_CR18","doi-asserted-by":"publisher","DOI":"10.1016\/j.xcrm.2021.100323","volume":"2","author":"AL Tarca","year":"2021","unstructured":"Tarca AL, Pataki B\u00c1, Romero R, Sirota M, Guan Y, Kutum R, et al. Crowdsourcing assessment of maternal blood multi-omics for predicting gestational age and preterm birth. Cell Rep Med. 2021;2:100323.","journal-title":"Cell Rep Med"},{"key":"2522_CR19","doi-asserted-by":"publisher","first-page":"eabd9898","DOI":"10.1126\/scitranslmed.abd9898","volume":"13","author":"IA Stelzer","year":"2021","unstructured":"Stelzer IA, Ghaemi MS, Han X, Ando K, H\u00e9dou JJ, Feyaerts D, et al. Integrated trajectories of the maternal metabolome, proteome, and immunome predict labor onset. Sci Transl Med. 2021;13:eabd9898.","journal-title":"Sci Transl Med"},{"key":"2522_CR20","doi-asserted-by":"publisher","first-page":"150","DOI":"10.1016\/j.ejogrb.2012.07.007","volume":"164","author":"JM Schaaf","year":"2012","unstructured":"Schaaf JM, Ravelli ACJ, Mol BWJ, Abu-Hanna A. Development of a prognostic model for predicting spontaneous singleton preterm birth. Eur J Obstet Gynecol Reprod Biol. 2012;164:150\u20135.","journal-title":"Eur J Obstet Gynecol Reprod Biol"},{"key":"2522_CR21","doi-asserted-by":"publisher","first-page":"11","DOI":"10.1111\/ppe.12087","volume":"28","author":"NH Morken","year":"2014","unstructured":"Morken NH, K\u00e4llen K, Jacobsson B. Predicting risk of spontaneous preterm delivery in women with a singleton pregnancy. Paediatr Perinat Epidemiol. 2014;28:11\u201322.","journal-title":"Paediatr Perinat Epidemiol"},{"key":"2522_CR22","doi-asserted-by":"publisher","first-page":"783","DOI":"10.1016\/j.annepidem.2018.08.008","volume":"28","author":"A Weber","year":"2018","unstructured":"Weber A, Darmstadt GL, Gruber S, Foeller ME, Carmichael SL, Stevenson DK, et al. Application of machine-learning to predict early spontaneous preterm birth among nulliparous non-Hispanic black and white women. Ann Epidemiol. 2018;28:783\u2013789.e1.","journal-title":"Ann Epidemiol"},{"key":"2522_CR23","doi-asserted-by":"publisher","first-page":"235","DOI":"10.1016\/j.ejogrb.2018.11.004","volume":"231","author":"RJ Baer","year":"2018","unstructured":"Baer RJ, McLemore MR, Adler N, Oltman SP, Chambers BD, Kuppermann M, et al. Pre-pregnancy or first-trimester risk scoring to identify women at high risk of preterm birth. Eur J Obstet Gynecol. 2018;231:235\u201340.","journal-title":"Eur J Obstet Gynecol"},{"key":"2522_CR24","doi-asserted-by":"publisher","first-page":"2438","DOI":"10.1007\/s10995-015-1763-5","volume":"19","author":"CM Tucker","year":"2015","unstructured":"Tucker CM, Berrien K, Menard MK, Herring AH, Daniels J, Rowley DL, et al. Predicting preterm birth among women screened by North Carolina\u2019s pregnancy medical home program. Matern Child Health J. 2015;19:2438\u201352.","journal-title":"Matern Child Health J"},{"key":"2522_CR25","doi-asserted-by":"publisher","first-page":"27","DOI":"10.1016\/j.siny.2018.09.006","volume":"24","author":"N Suff","year":"2018","unstructured":"Suff N, Story L, Shennan A. The prediction of preterm delivery: what is new? Semin Fetal Neonat M. 2018;24:27\u201332.","journal-title":"Semin Fetal Neonat M"},{"key":"2522_CR26","doi-asserted-by":"publisher","first-page":"58","DOI":"10.1016\/j.cell.2019.02.039","volume":"177","author":"NS Abul-Husn","year":"2019","unstructured":"Abul-Husn NS, Kenny EE. Personalized medicine and the power of electronic health records. Cell. 2019;177:58\u201369.","journal-title":"Cell."},{"key":"2522_CR27","doi-asserted-by":"publisher","first-page":"eaay1059","DOI":"10.1126\/scitranslmed.aay1059","volume":"12","author":"AG Paquette","year":"2020","unstructured":"Paquette AG, Hood L, Price ND, Sadovsky Y. Deep phenotyping during pregnancy for predictive and preventive medicine. Sci Transl Med. 2020;12:eaay1059.","journal-title":"Sci Transl Med"},{"key":"2522_CR28","doi-asserted-by":"publisher","first-page":"71","DOI":"10.1038\/s41591-019-0724-8","volume":"26","author":"NS Artzi","year":"2020","unstructured":"Artzi NS, Shilo S, Hadar E, Rossman H, Barbash-Hazan S, Ben-Haroush A, et al. Prediction of gestational diabetes based on nationwide electronic health records. Nat Med. 2020;26:71\u20136.","journal-title":"Nat Med"},{"key":"2522_CR29","doi-asserted-by":"publisher","first-page":"57","DOI":"10.1038\/s41591-018-0239-8","volume":"25","author":"S Ravizza","year":"2019","unstructured":"Ravizza S, Huschto T, Adamov A, B\u00f6hm L, B\u00fcsser A, Fl\u00f6ther FF, et al. Predicting the early risk of chronic kidney disease in patients with diabetes using real-world data. Nat Med. 2019;25:57\u20139.","journal-title":"Nat Med"},{"key":"2522_CR30","first-page":"1","volume":"31","author":"R Li","year":"2020","unstructured":"Li R, Chen Y, Ritchie MD, Moore JH. Electronic health records and polygenic risk scores for predicting disease risk. Nat Publ Group. 2020;31:1\u201310.","journal-title":"Nat Publ Group"},{"key":"2522_CR31","doi-asserted-by":"publisher","first-page":"1156","DOI":"10.1056\/NEJMoa1612665","volume":"377","author":"G Zhang","year":"2017","unstructured":"Zhang G, Feenstra B, Bacelis J, Liu X, Muglia LM, Juodakis J, et al. Genetic associations with gestational duration and spontaneous preterm birth. New Engl J Med. 2017;377:1156\u201367.","journal-title":"New Engl J Med"},{"key":"2522_CR32","doi-asserted-by":"publisher","first-page":"116","DOI":"10.1038\/s41586-019-1390-1","volume":"572","author":"N Toma\u0161ev","year":"2019","unstructured":"Toma\u0161ev N, Glorot X, Rae JW, Zielinski M, Askham H, Saraiva A, et al. A clinically applicable approach to continuous prediction of future acute kidney injury. Nature. 2019;572:116\u20139.","journal-title":"Nature."},{"key":"2522_CR33","doi-asserted-by":"publisher","first-page":"1419","DOI":"10.1093\/jamia\/ocy068","volume":"25","author":"C Xiao","year":"2018","unstructured":"Xiao C, Choi E, Sun J. Opportunities and challenges in developing deep learning models using electronic health records data: a systematic review. J Am Med Inform Assn. 2018;25:1419\u201328.","journal-title":"J Am Med Inform Assn"},{"key":"2522_CR34","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1038\/s41598-018-37186-2","volume":"9","author":"J Zhao","year":"2019","unstructured":"Zhao J, Feng Q, Wu P, Lupu RA, Wilke RA, Wells QS, et al. Learning from longitudinal data in electronic health record and genetic data to improve cardiovascular event prediction. Sci Rep. 2019;9:1\u201310.","journal-title":"Sci Rep"},{"key":"2522_CR35","doi-asserted-by":"publisher","first-page":"198","DOI":"10.1093\/jamia\/ocw042","volume":"24","author":"BA Goldstein","year":"2017","unstructured":"Goldstein BA, Navar AM, Pencina MJ, Ioannidis JPA. Opportunities and challenges in developing risk prediction models with electronic health records data: a systematic review. J Am Med Inform Assoc. 2017;24:198\u2013208.","journal-title":"J Am Med Inform Assoc"},{"key":"2522_CR36","doi-asserted-by":"publisher","first-page":"17049","DOI":"10.1038\/s41598-019-53448-z","volume":"9","author":"MT Aung","year":"2019","unstructured":"Aung MT, Yu Y, Ferguson KK, Cantonwine DE, Zeng L, McElrath TF, et al. Prediction and associations of preterm birth and its subtypes with eicosanoid enzymatic pathways and inflammatory markers. Sci Rep. 2019;9:17049.","journal-title":"Sci Rep"},{"key":"2522_CR37","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0198919","volume":"14","author":"KJ Rittenhouse","year":"2019","unstructured":"Rittenhouse KJ, Vwalika B, Keil A, Winston J, Stoner M, Price JT, et al. Improving preterm newborn identification in low-resource settings with machine learning. PLoS One. 2019;14:e0198919.","journal-title":"PLoS One"},{"key":"2522_CR38","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0077154","volume":"8","author":"P Fergus","year":"2013","unstructured":"Fergus P, Cheung P, Hussain A, Al-Jumeily D, Dobbins C, Iram S. Prediction of preterm deliveries from EHG signals using machine learning. PLoS One. 2013;8:e77154.","journal-title":"PLoS One"},{"key":"2522_CR39","doi-asserted-by":"crossref","unstructured":"Chen T, Guestrin C. Xgboost: A scalable tree boosting system. In: Proceedings of the 22nd ACM SIGKDD International conference on knowledge discovery and data mining.\u00a02016. p. 785\u201394.","DOI":"10.1145\/2939672.2939785"},{"key":"2522_CR40","doi-asserted-by":"publisher","DOI":"10.1007\/978-0-387-84858-7","volume-title":"The elements of statistical learning, data mining, inference, and prediction","author":"T Hastie","year":"2009","unstructured":"Hastie T, Tibshirani R, Friedman J. The elements of statistical learning, data mining, inference, and prediction; 2009. https:\/\/doi.org\/10.1007\/978-0-387-84858-7."},{"key":"2522_CR41","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pmed.1002701","volume":"15","author":"KM Corey","year":"2018","unstructured":"Corey KM, Kashyap S, Lorenzi E, Lagoo-Deenadayalan SA, Heller K, Whalen K, et al. Development and validation of machine learning models to identify high-risk surgical patients using automatically curated electronic health record data (Pythia): a retrospective, single-site study. PLoS Med. 2018;15:e1002701.","journal-title":"PLoS Med"},{"key":"2522_CR42","doi-asserted-by":"publisher","first-page":"578","DOI":"10.1016\/j.jchf.2020.01.012","volume":"8","author":"L Jing","year":"2020","unstructured":"Jing L, Cerna AEU, Good CW, Sauers NM, Schneider G, Hartzel DN, et al. A machine learning approach to management of heart failure populations. Jacc Hear Fail. 2020;8:578\u201387.","journal-title":"Jacc Hear Fail"},{"key":"2522_CR43","doi-asserted-by":"publisher","first-page":"357","DOI":"10.1002\/uog.20422","volume":"55","author":"J Carter","year":"2020","unstructured":"Carter J, Seed PT, Watson HA, David AL, Sandall J, Shennan AH, et al. Development and validation of predictive models for QUiPP App v.2: tool for predicting preterm birth in women with symptoms of threatened preterm labor. Ultrasound Obstet Gynecol. 2020;55:357\u201367.","journal-title":"Ultrasound Obstet Gynecol"},{"key":"2522_CR44","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1016\/j.bpobgyn.2018.04.003","volume":"52","author":"JP Vogel","year":"2018","unstructured":"Vogel JP, Chawanpaiboon S, Moller A-B, Watananirun K, Bonet M, Lumbiganon P. The global epidemiology of preterm birth. Best Pract Res Cl Ob. 2018;52:3\u201312.","journal-title":"Best Pract Res Cl Ob"},{"key":"2522_CR45","doi-asserted-by":"publisher","first-page":"136","DOI":"10.1097\/00006254-200203000-00002","volume":"57","author":"GCS Smith","year":"2002","unstructured":"Smith GCS, Pell JP. Teenage pregnancy and risk of adverse perinatal outcomes associated with first and second births: population based retrospective cohort study. Obstet Gynecol Surv. 2002;57:136\u20137.","journal-title":"Obstet Gynecol Surv"},{"key":"2522_CR46","doi-asserted-by":"publisher","first-page":"104","DOI":"10.1097\/AOG.0000000000000062","volume":"123","author":"U Waldenstr\u00f6m","year":"2014","unstructured":"Waldenstr\u00f6m U, Aasheim V, Nilsen ABV, Rasmussen S, Pettersson HJ, Schytt E, et al. Adverse pregnancy outcomes related to advanced maternal age compared with smoking and being overweight. Obstet Gynecol. 2014;123:104\u201312.","journal-title":"Obstet Gynecol"},{"key":"2522_CR47","doi-asserted-by":"publisher","first-page":"479","DOI":"10.1016\/j.midw.2012.04.001","volume":"29","author":"M Carolan","year":"2013","unstructured":"Carolan M. Maternal age \u226545 years and maternal and perinatal outcomes: a review of the evidence. Midwifery. 2013;29:479\u201389.","journal-title":"Midwifery."},{"key":"2522_CR48","doi-asserted-by":"publisher","first-page":"347","DOI":"10.1093\/qjmed\/94.7.347","volume":"94","author":"JG Ray","year":"2001","unstructured":"Ray JG, Vermeulen MJ, Shapiro JL, Kenshole AB. Maternal and neonatal outcomes in pregestational and gestational diabetes mellitus, and the influence of maternal obesity and weight gain: the DEPOSIT study. Qjm Int J Med. 2001;94:347\u201356.","journal-title":"Qjm Int J Med"},{"key":"2522_CR49","doi-asserted-by":"publisher","first-page":"324","DOI":"10.1016\/j.ejogrb.2013.06.020","volume":"170","author":"V Whiteman","year":"2013","unstructured":"Whiteman V, Salinas A, Weldeselasse HE, August EM, Mbah AK, Aliyu MH, et al. Impact of sickle cell disease and thalassemias in infants on birth outcomes. Eur J Obstet Gyn R B. 2013;170:324\u20138.","journal-title":"Eur J Obstet Gyn R B"},{"key":"2522_CR50","doi-asserted-by":"publisher","first-page":"213","DOI":"10.1038\/hr.2016.126","volume":"40","author":"M Umesawa","year":"2017","unstructured":"Umesawa M, Kobashi G. Epidemiology of hypertensive disorders in pregnancy: prevalence, risk factors, predictors and prognosis. Hypertens Res. 2017;40:213\u201320.","journal-title":"Hypertens Res"},{"key":"2522_CR51","doi-asserted-by":"publisher","first-page":"80","DOI":"10.1016\/j.siny.2016.01.005","volume":"21","author":"B Koullali","year":"2016","unstructured":"Koullali B, Oudijk MA, Nijman TAJ, Mol BWJ, Pajkrt E. Risk assessment and management to prevent preterm birth. Semin Fetal Neonatal Med. 2016;21:80\u20138.","journal-title":"Semin Fetal Neonatal Med"},{"key":"2522_CR52","first-page":"4765","volume-title":"Advances in Neural Information Processing Systems 30","author":"SM Lundberg","year":"2017","unstructured":"Lundberg SM, Lee S-I. A unified approach to interpreting model predictions. In: Guyon I, Luxburg UV, Bengio S, Wallach H, Fergus R, Vishwanathan S, et al., editors. Advances in Neural Information Processing Systems 30: Curran Associates, Inc.; 2017. p. 4765\u201374."},{"key":"2522_CR53","doi-asserted-by":"publisher","first-page":"56","DOI":"10.1038\/s42256-019-0138-9","volume":"2","author":"SM Lundberg","year":"2020","unstructured":"Lundberg SM, Erion G, Chen H, DeGrave A, Prutkin JM, Nair B, et al. From local explanations to global understanding with explainable AI for trees. Nat Mach Intell. 2020;2:56\u201367.","journal-title":"Nat Mach Intell"},{"key":"2522_CR54","doi-asserted-by":"crossref","unstructured":"Davis J, Goadrich M. The relationship between Precision-Recall and ROC curves. In: Proceedings of the 23rd International Conference on Machine learning.\u00a02006. p. 233\u201324 .","DOI":"10.1145\/1143844.1143874"},{"key":"2522_CR55","doi-asserted-by":"publisher","first-page":"749","DOI":"10.1038\/s41551-018-0304-0","volume":"2","author":"SM Lundberg","year":"2018","unstructured":"Lundberg SM, Nair B, Vavilala MS, Horibe M, Eisses MJ, Adams T, et al. Explainable machine-learning predictions for the prevention of hypoxaemia during surgery. Nat Biomed Eng. 2018;2:749\u201360.","journal-title":"Nat Biomed Eng"},{"key":"2522_CR56","doi-asserted-by":"publisher","first-page":"5","DOI":"10.1097\/AOG.0000000000000564","volume":"125","author":"AA Creanga","year":"2015","unstructured":"Creanga AA, Berg CJ, Syverson C, Seed K, Bruce FC, Callaghan WM. Pregnancy-related mortality in the United States, 2006\u20132010. Obstet Gynecol. 2015;125:5\u201312.","journal-title":"Obstet Gynecol"},{"key":"2522_CR57","doi-asserted-by":"publisher","first-page":"332","DOI":"10.1053\/j.semperi.2017.07.007","volume":"41","author":"A Hirshberg","year":"2017","unstructured":"Hirshberg A, Srinivas SK. Epidemiology of maternal morbidity and mortality. Semin Perinatol. 2017;41:332\u20137.","journal-title":"Semin Perinatol"},{"key":"2522_CR58","doi-asserted-by":"publisher","first-page":"11981","DOI":"10.1038\/s41598-020-68771-z","volume":"10","author":"L Kopitar","year":"2020","unstructured":"Kopitar L, Kocbek P, Cilar L, Sheikh A, Stiglic G. Early detection of type 2 diabetes mellitus using machine learning-based prediction models. Sci Rep-Uk. 2020;10:11981.","journal-title":"Sci Rep-Uk"},{"key":"2522_CR59","doi-asserted-by":"publisher","first-page":"283","DOI":"10.1038\/s42256-020-0180-7","volume":"2","author":"L Yan","year":"2020","unstructured":"Yan L, Zhang H-T, Goncalves J, Xiao Y, Wang M, Guo Y, et al. An interpretable mortality prediction model for COVID-19 patients. Nat Mach Intell. 2020;2:283\u20138.","journal-title":"Nat Mach Intell"},{"key":"2522_CR60","doi-asserted-by":"publisher","first-page":"270","DOI":"10.1186\/s12859-018-2264-5","volume":"19","author":"R Couronn\u00e9","year":"2018","unstructured":"Couronn\u00e9 R, Probst P, Boulesteix A-L. Random forest versus logistic regression: a large-scale benchmark experiment. Bmc Bioinformatics. 2018;19:270.","journal-title":"Bmc Bioinformatics"},{"key":"2522_CR61","doi-asserted-by":"publisher","DOI":"10.1016\/j.jbi.2019.103334","volume":"100","author":"C Gao","year":"2019","unstructured":"Gao C, Osmundson S, Edwards DRV, Jackson GP, Malin BA, Chen Y. Deep learning predicts extreme preterm birth from electronic health records. J Biomed Inform. 2019;100:103334.","journal-title":"J Biomed Inform"},{"key":"2522_CR62","doi-asserted-by":"publisher","first-page":"1213","DOI":"10.1016\/j.jgyn.2016.09.013","volume":"45","author":"H Torchin","year":"2016","unstructured":"Torchin H, Ancel P-Y. Epidemiology and risk factors of preterm birth. J De Gynecol Obstetrique Et Biologie De La Reprod. 2016;45:1213\u201330.","journal-title":"J De Gynecol Obstetrique Et Biologie De La Reprod"},{"key":"2522_CR63","doi-asserted-by":"publisher","first-page":"44","DOI":"10.1038\/s41591-018-0300-7","volume":"25","author":"EJ Topol","year":"2019","unstructured":"Topol EJ. High-performance medicine: the convergence of human and artificial intelligence. Nat Med. 2019;25:44\u201356.","journal-title":"Nat Med"},{"key":"2522_CR64","doi-asserted-by":"publisher","first-page":"30","DOI":"10.1038\/s41591-018-0307-0","volume":"25","author":"J He","year":"2019","unstructured":"He J, Baxter SL, Xu J, Xu J, Zhou X, Zhang K. The practical implementation of artificial intelligence technologies in medicine. Nat Med. 2019;25:30\u20136.","journal-title":"Nat Med"},{"key":"2522_CR65","doi-asserted-by":"publisher","first-page":"236","DOI":"10.1055\/s-0035-1571146","volume":"33","author":"MS Esplin","year":"2016","unstructured":"Esplin MS. The importance of clinical phenotype in understanding and preventing spontaneous preterm birth. Am J Perinatol. 2016;33:236\u201344.","journal-title":"Am J Perinatol"},{"key":"2522_CR66","doi-asserted-by":"publisher","first-page":"487.e1","DOI":"10.1016\/j.ajog.2015.02.010","volume":"212","author":"TA Manuck","year":"2015","unstructured":"Manuck TA, Esplin MS, Biggio J, Bukowski R, Parry S, Zhang H, et al. The phenotype of spontaneous preterm birth: application of a clinical phenotyping tool. Am J Obstet Gynecol. 2015;212:487.e1\u2013487.e11.","journal-title":"Am J Obstet Gynecol"},{"key":"2522_CR67","first-page":"22","volume":"5","author":"M Phelan","year":"2017","unstructured":"Phelan M, Bhavsar NA, Goldstein BA. Illustrating informed presence bias in electronic health records data: how patient interactions with a health system can impact inference. Egems Wash Dc. 2017;5:22.","journal-title":"Egems Wash Dc"},{"key":"2522_CR68","doi-asserted-by":"publisher","unstructured":"Outcomes I of M (US) C on UPB and AH, Behrman RE, Butler AS. Preterm birth: causes, consequences, and prevention. 2007. https:\/\/doi.org\/10.17226\/11622.","DOI":"10.17226\/11622"},{"key":"2522_CR69","doi-asserted-by":"publisher","unstructured":"Kukhareva PV, Caverly TJ, Li H, Katki HA, Cheung LC, Reese TJ, et al. Inaccuracies in electronic health records smoking data and a potential approach to address resulting underestimation in determining lung cancer screening eligibility. J Am Med Inform Assoc. 2022. https:\/\/doi.org\/10.1093\/jamia\/ocac020.","DOI":"10.1093\/jamia\/ocac020"},{"key":"2522_CR70","doi-asserted-by":"publisher","first-page":"56","DOI":"10.1186\/s12911-020-1068-5","volume":"20","author":"S Garies","year":"2020","unstructured":"Garies S, Cummings M, Quan H, McBrien K, Drummond N, Manca D, et al. Methods to improve the quality of smoking records in a primary care EMR database: exploring multiple imputation and pattern-matching algorithms. Bmc Med Inform Decis. 2020;20:56.","journal-title":"Bmc Med Inform Decis"},{"key":"2522_CR71","doi-asserted-by":"publisher","first-page":"30","DOI":"10.1016\/S1470-0328(03)00021-1","volume":"110","author":"J-M Moutquin","year":"2003","unstructured":"Moutquin J-M. Classification and heterogeneity of preterm birth. BJOG. 2003;110:30\u20133.","journal-title":"BJOG"},{"key":"2522_CR72","doi-asserted-by":"publisher","DOI":"10.1136\/bmjopen-2016-015402","volume":"7","author":"C Phillips","year":"2017","unstructured":"Phillips C, Velji Z, Hanly C, Metcalfe A. Risk of recurrent spontaneous preterm birth: a systematic review and meta-analysis. BMJ Open. 2017;7:e015402.","journal-title":"BMJ Open"},{"key":"2522_CR73","doi-asserted-by":"publisher","first-page":"1351","DOI":"10.1001\/jama.2019.10306","volume":"322","author":"NH Shah","year":"2019","unstructured":"Shah NH, Milstein A, Bagley SC. Making machine learning models clinically useful. JAMA. 2019;322:1351\u20132.","journal-title":"JAMA."},{"key":"2522_CR74","doi-asserted-by":"publisher","first-page":"1544","DOI":"10.1001\/jamainternmed.2018.3763","volume":"178","author":"MA Gianfrancesco","year":"2018","unstructured":"Gianfrancesco MA, Tamang S, Yazdany J, Schmajuk G. Potential biases in machine learning algorithms using electronic health record data. JAMA Intern Med. 2018;178:1544.","journal-title":"JAMA Intern Med"},{"key":"2522_CR75","doi-asserted-by":"publisher","DOI":"10.1016\/j.jbi.2020.103433","volume":"105","author":"C Weng","year":"2020","unstructured":"Weng C, Shah N, Hripcsak G. Deep phenotyping: embracing complexity and temporality\u2014towards scalability, portability, and interoperability. J Biomed Inform. 2020;105:103433.","journal-title":"J Biomed Inform"},{"key":"2522_CR76","first-page":"115","volume-title":"International conference on machine learning","author":"J Bergstra","year":"2013","unstructured":"Bergstra J, Yamins D, Cox D. Making a science of model search: hyperparameter optimization in hundreds of dimensions for vision architectures. In:  International conference on machine learning; 2013. p. 115\u201323."},{"key":"2522_CR77","first-page":"2825","volume":"12","author":"F Pedregosa","year":"2011","unstructured":"Pedregosa F, Varoquaux G, Gramfort A, Michel V, Thirion B, Grisel O, et al. Scikit-learn: machine learning in Python. J Mach Learn Res. 2011;12:2825\u201330.","journal-title":"J Mach Learn Res"},{"key":"2522_CR78","doi-asserted-by":"publisher","first-page":"331","DOI":"10.1093\/jamia\/ocx132","volume":"25","author":"E Soysal","year":"2017","unstructured":"Soysal E, Wang J, Jiang M, Wu Y, Pakhomov S, Liu H, et al. CLAMP \u2013 a toolkit for efficiently building customized clinical natural language processing pipelines. J Am Med Inform Assn. 2017;25:331\u20136.","journal-title":"J Am Med Inform Assn"},{"key":"2522_CR79","doi-asserted-by":"crossref","unstructured":"Marees AT, de Kluiver H, Stringer S, Vorspan F, Curis E, Marie\u2010Claire C, et al. A tutorial on conducting genome\u2010wide association studies: Quality control and statistical analysis.\u00a0Int J Methods Psychiatr Res. 2018;27(2):e1608.","DOI":"10.1002\/mpr.1608"},{"key":"2522_CR80","doi-asserted-by":"publisher","first-page":"7","DOI":"10.1186\/s13742-015-0047-8","volume":"4","author":"CC Chang","year":"2015","unstructured":"Chang CC, Chow CC, Tellier LC, Vattikuti S, Purcell SM, Lee JJ. Second-generation PLINK: rising to the challenge of larger and richer datasets. GigaScience. 2015;4:7.","journal-title":"GigaScience."},{"key":"2522_CR81","doi-asserted-by":"publisher","first-page":"1466","DOI":"10.1093\/bioinformatics\/btu848","volume":"31","author":"J Euesden","year":"2015","unstructured":"Euesden J, Lewis CM, O\u2019Reilly PF. PRSice: polygenic risk score software. Bioinformatics. 2015;31:1466\u20138.","journal-title":"Bioinformatics."},{"key":"2522_CR82","doi-asserted-by":"crossref","unstructured":"Choi SW, O\u2019Reilly PF. PRSice-2: polygenic risk score software for biobank-scale data. Gigascience. 2019:giz082.","DOI":"10.1093\/gigascience\/giz082"},{"key":"2522_CR83","doi-asserted-by":"crossref","unstructured":"McInnes L, Healy J, Melville J. UMAP: Uniform manifold approximation and projection for dimension reduction. arXiv preprint. 2018;arXiv:1802.03426.","DOI":"10.21105\/joss.00861"},{"key":"2522_CR84","doi-asserted-by":"crossref","unstructured":"McInnes L, Healy J, Astels S. hdbscan: Hierarchical density based clustering. J Open Source Softw. 2017;2(11):205.","DOI":"10.21105\/joss.00205"},{"key":"2522_CR85","doi-asserted-by":"publisher","first-page":"261","DOI":"10.1038\/s41592-019-0686-2","volume":"17","author":"P Virtanen","year":"2020","unstructured":"Virtanen P, Gommers R, Oliphant TE, Haberland M, Reddy T, Cournapeau D, et al. SciPy 1.0: fundamental algorithms for scientific computing in Python. Nat Methods. 2020;17:261\u201372.","journal-title":"Nat Methods"}],"container-title":["BMC Medicine"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s12916-022-02522-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1186\/s12916-022-02522-x\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s12916-022-02522-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,11,18]],"date-time":"2022-11-18T04:57:00Z","timestamp":1668747420000},"score":1,"resource":{"primary":{"URL":"https:\/\/bmcmedicine.biomedcentral.com\/articles\/10.1186\/s12916-022-02522-x"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,9,28]]},"references-count":85,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2022,12]]}},"alternative-id":["2522"],"URL":"https:\/\/doi.org\/10.1186\/s12916-022-02522-x","relation":{"has-preprint":[{"id-type":"doi","id":"10.1101\/2020.07.15.20154864","asserted-by":"object"}]},"ISSN":["1741-7015"],"issn-type":[{"value":"1741-7015","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,9,28]]},"assertion":[{"value":"10 February 2022","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"10 August 2022","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"28 September 2022","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"This study exclusively utilized the information extracted from the medical records in the Vanderbilt University Medical Center (VUMC) \u201cSynthetic Derivative\u201d database (SD). The SD is a de-identified copy of the main hospital medical record databases created for research purposes. The de-identification of SD records was achieved primarily through the application of a commercial electronic program, which was applied and assessed for acceptable effectiveness in scrubbing identifiers. For instance, if the name \u201cJohn Smith\u201d appeared in the original medical record, its corresponding record in the SD does not contain \u201cJohn Smith.\u201d Instead, it is permanently replaced with a tag [NAMEAAA, BBB] to maintain the semantic integrity of the text. Similarly, dates, such as \u201cJanuary 1, 2004,\u201d have been replaced with a randomly generated date, such as \u201cFebruary 3, 2003.\u201dThe SD database (which contains over 3 million electronic records, with no defined exclusions) was accessed through database queries. Searches are logged and audited annually. As no HIPAA identifiers are available in the SD database, and this work does not plan to re-identify these records using the identified VUMC database, this study meets the criteria for non-human subjects research. Nonetheless, to ensure confidentiality and appropriate use of the SD, all relevant key personnel for this study entered a data use agreement, which prohibits any use of the data not described in this application, including the re-identification of the SD records.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics approval and consent to participate"}},{"value":"Not applicable.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent for publication"}},{"value":"LJM is a consultant for Mirvie, Inc. All other authors declare that they have no competing interests.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"333"}}