{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"institution":[{"name":"medRxiv"}],"indexed":{"date-parts":[[2026,3,12]],"date-time":"2026-03-12T23:47:30Z","timestamp":1773359250045,"version":"3.50.1"},"posted":{"date-parts":[[2025,7,10]]},"group-title":"Obstetrics and Gynecology","reference-count":60,"publisher":"openRxiv","license":[{"start":{"date-parts":[[2025,7,10]],"date-time":"2025-07-10T00:00:00Z","timestamp":1752105600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.medrxiv.org\/about\/FAQ#license"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"accepted":{"date-parts":[[2025,7,10]]},"abstract":"<jats:title>Summary<\/jats:title>\n                <jats:sec>\n                  <jats:title>Background<\/jats:title>\n                  <jats:p>Preterm birth, defined as birth occurring before 37 weeks of gestation, poses a significant and enduring public health challenge, with substantial emotional and financial burdens on families and society. To identify preterm births early in pregnancy, we investigated the predictive ability of machine learning models in a nulliparous (first-time pregnancy) study cohort. Preterm births are categorized into two major types: indicated preterm birth, which occurs due to medical conditions such as preeclampsia or other maternal\/fetal complications requiring early delivery, and spontaneous preterm birth, which involves the natural onset of preterm labor. Our research aims to develop predictive tools that could enable earlier intervention and improved outcomes for these vulnerable pregnancies.<\/jats:p>\n                <\/jats:sec>\n                <jats:sec>\n                  <jats:title>Methods<\/jats:title>\n                  <jats:p>Our study analyzed the Nulliparous Pregnancy Outcomes Study: Monitoring Mothers-to-be cohort (nu-MoM2b), comprising data from eight clinical sites throughout the United States from October 2010 to May 2014, including treatment, psychological, physiological, medical history, demographic, ultrasound, activity, toxicology, family history, pre-pregnancy diet, and genetic race. We distinguished between spontaneous and indicated preterm births to develop targeted predictive models for each subtype. We also used a novel approach to predict preterm birth called learning with privileged information, information available during training but often inaccessible during evaluation. Specifically, the set of privileged information that we utilized for PTB prediction includes the occurrence of adverse pregnancy outcomes (APOs), after-delivery physiology information, and maternal outcomes. We developed an enhanced model, XGBoost+, which incorporates this privileged information to improve predictive performance compared to traditional machine learning approaches.<\/jats:p>\n                <\/jats:sec>\n                <jats:sec>\n                  <jats:title>Results<\/jats:title>\n                  <jats:p>We selected XGBoost as our base model due to its robust performance with tabular data and its ensemble approach that effectively mitigates overfitting while capturing complex relationships between clinical variables, making it particularly well-suited for the heterogeneous risk factors associated with preterm birth prediction. XGboost-based models achieved higher AUC against all other models, including decision tree, random forest, logistic regression, and SVM for all visits. Our XGboost+ model, utilizing privileged information, achieved an AUC of 0.72. Analyzing the subcategories of preterm birth, XGboost+ achieved similar performance with XGboost for spontaneous preterm birth (0.68 AUC versus 0.67 AUC), but improvements were more significant for indicated preterm birth (0.78 versus 0.74). These results demonstrate the benefits of how information that is not typically utilized in traditional machine learning models can help build better models.<\/jats:p>\n                <\/jats:sec>\n                <jats:sec>\n                  <jats:title>Conclusion<\/jats:title>\n                  <jats:p>Our extensive analysis of this comprehensive set of risk factors revealed preterm birth as a multifaceted issue, with different risk factors associated with two subcategories of preterm birth - spontaneous and indicated. No-tably, we achieved significant success in predicting indicated preterm birth, demonstrating strong predictive performance (AUC 0.78) using our XGBoost+ model. This finding represents an important advancement, as indicated preterm birth is influenced mainly by conditions related to hypertension and preeclampsia, which our model effectively captured. While spontaneous preterm birth remains challenging to predict with clinical data alone, especially in early pregnancy, our research successfully differentiates between these subtypes and provides a valuable predictive tool for indicated preterm birth. The complexity of spontaneous preterm birth suggests that future research should focus on gathering more proximal biological data, including vaginal microbiota or raw cervical images, to complement our successful approach for indicated preterm birth prediction.<\/jats:p>\n                <\/jats:sec>","DOI":"10.1101\/2025.07.09.25329712","type":"posted-content","created":{"date-parts":[[2025,7,10]],"date-time":"2025-07-10T21:41:01Z","timestamp":1752183661000},"source":"Crossref","is-referenced-by-count":2,"title":["Differential Predictability of Preterm Birth Types: Strong Signals for Indicated Cases versus Limited Success in Spontaneous Preterm Birth"],"prefix":"10.64898","author":[{"given":"Yun Chao","family":"Lin","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Andrea","family":"Clark-Sevilla","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mahdi A.","family":"Loodaricheh","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Itsik","family":"Pe\u2019er","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Anita","family":"Raja","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ronald","family":"Wapner","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ansaf","family":"Salleb-Aouissi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"54368","reference":[{"key":"2025071202450692000_2025.07.09.25329712v1.1","unstructured":"WHO, UNFPA, UNICEF, PMNCH. Born too soon: The Global action report on Preterm Birth; 2012. Available from: https:\/\/iris.who.int\/bitstream\/handle\/10665\/44864\/9789241503433_eng.pdf?sequence=1."},{"key":"2025071202450692000_2025.07.09.25329712v1.2","unstructured":"Zerhouni EA . Prematuriy Research at the NIH. 2008. Department of Health and Human Services. Available from: https:\/\/www.nichd.nih.gov\/sites\/default\/files\/publications\/pubs\/documents\/nih_prematurity_research_2008.pdf."},{"key":"2025071202450692000_2025.07.09.25329712v1.3","unstructured":"Behrman RE , Butler AS , of Medicine (US) Committee on Understanding Premature Birth and Assuring Healthy Outcomes I. Preterm birth: causes, consequences, and prevention. Washington, DC: National Academies Press; 2007. Available from: http:\/\/books.google.com\/books?id=9c_7kxBsKzIC."},{"key":"2025071202450692000_2025.07.09.25329712v1.4","unstructured":"WHO, UNFPA, UNICEF, PMNCH. Born too soon: Decade of action on preterm birth; 2023. Available from: https:\/\/www.who.int\/publications\/i\/item\/9789240073890."},{"issue":"1","key":"2025071202450692000_2025.07.09.25329712v1.5","doi-asserted-by":"crossref","first-page":"ooae024","DOI":"10.1093\/jamiaopen\/ooae024","article-title":"Diving into CDC pregnancy data in the United States: longitudinal study and interactive application","volume":"7","year":"2024","journal-title":"JAMIA open"},{"key":"2025071202450692000_2025.07.09.25329712v1.6","doi-asserted-by":"publisher","DOI":"10.1016\/S0140-6736(08)60074-4"},{"key":"2025071202450692000_2025.07.09.25329712v1.7","doi-asserted-by":"publisher","DOI":"10.1097\/AOG.0b013e31818b1ff6"},{"issue":"1","key":"2025071202450692000_2025.07.09.25329712v1.8","doi-asserted-by":"crossref","first-page":"58","DOI":"10.1016\/j.siny.2011.08.001","article-title":"Prevention of preterm birth","volume":"17","year":"2012","journal-title":"Seminars in Fetal and Neonatal Medicine"},{"key":"2025071202450692000_2025.07.09.25329712v1.9","doi-asserted-by":"publisher","DOI":"10.1016\/S0002-9378(99)70111-0"},{"issue":"1","key":"2025071202450692000_2025.07.09.25329712v1.10","first-page":"F11","article-title":"Socioeconomic inequalities in very preterm birth rates","volume":"92","year":"2006","journal-title":"Arch Dis Child Fetal Neonatal"},{"key":"2025071202450692000_2025.07.09.25329712v1.11","doi-asserted-by":"publisher","DOI":"10.1111\/j.1365-3016.2006.00711.x"},{"key":"2025071202450692000_2025.07.09.25329712v1.12","doi-asserted-by":"publisher","DOI":"10.1016\/j.ajog.2004.09.021"},{"key":"2025071202450692000_2025.07.09.25329712v1.13","doi-asserted-by":"publisher","DOI":"10.1001\/archgenpsychiatry.2010.111"},{"key":"2025071202450692000_2025.07.09.25329712v1.14","doi-asserted-by":"publisher","DOI":"10.1016\/S0002-9378(96)70042-X"},{"issue":"1","key":"2025071202450692000_2025.07.09.25329712v1.15","first-page":"34","article-title":"Prenatal life events stress: implications for preterm birth and infant birthweight","volume":"203","year":"2010","journal-title":"American Journal of Obstetrics and Gynecology"},{"key":"2025071202450692000_2025.07.09.25329712v1.16","doi-asserted-by":"publisher","DOI":"10.1056\/NEJM200005183422007"},{"key":"2025071202450692000_2025.07.09.25329712v1.17","doi-asserted-by":"publisher","DOI":"10.1097\/GRF.0b013e31811ebef6"},{"key":"2025071202450692000_2025.07.09.25329712v1.18","doi-asserted-by":"publisher","DOI":"10.1111\/j.1471-0528.2006.01120.x"},{"key":"2025071202450692000_2025.07.09.25329712v1.19","doi-asserted-by":"publisher","DOI":"10.1016\/j.clp.2010.02.003"},{"key":"2025071202450692000_2025.07.09.25329712v1.20","doi-asserted-by":"publisher","DOI":"10.1001\/jama.295.15.1809"},{"issue":"3","key":"2025071202450692000_2025.07.09.25329712v1.21","doi-asserted-by":"crossref","first-page":"220","DOI":"10.1016\/S1701-2163(16)32112-0","article-title":"Pregnancy outcomes after assisted reproductive technology","volume":"28","year":"2006","journal-title":"Journal of obstetrics and gynaecology Canada"},{"key":"2025071202450692000_2025.07.09.25329712v1.22","doi-asserted-by":"publisher","DOI":"10.1023\/A:1016614217411"},{"key":"2025071202450692000_2025.07.09.25329712v1.23","doi-asserted-by":"publisher","DOI":"10.1097\/01.ede.0000142137.39619.60"},{"key":"2025071202450692000_2025.07.09.25329712v1.24","doi-asserted-by":"publisher","DOI":"10.1289\/ehp.01109557"},{"key":"2025071202450692000_2025.07.09.25329712v1.25","doi-asserted-by":"publisher","DOI":"10.1093\/ije\/27.2.248"},{"key":"2025071202450692000_2025.07.09.25329712v1.26","doi-asserted-by":"publisher","DOI":"10.1016\/S0029-7844(97)00215-9"},{"key":"2025071202450692000_2025.07.09.25329712v1.27","doi-asserted-by":"publisher","DOI":"10.1056\/NEJMoa1612665"},{"key":"2025071202450692000_2025.07.09.25329712v1.28","doi-asserted-by":"crossref","unstructured":"Tang ID , Mallia D , Yan Q , Pe\u2019er I , Raja A , Salleb-Aouissi A , et al. A Scoping Review of Preterm Birth Risk Factors. Am J Perinatol. 2023 Sep;41(S 01):e2804-17.","DOI":"10.1055\/s-0043-1775564"},{"issue":"2","key":"2025071202450692000_2025.07.09.25329712v1.29","doi-asserted-by":"crossref","first-page":"233","DOI":"10.2105\/AJPH.88.2.233","article-title":"The preterm prediction study: the value of new vs standard risk factors in predicting early and all spontaneous preterm births","volume":"88","year":"1998","journal-title":"NICHD MFMU Network. Am J Public Health"},{"key":"2025071202450692000_2025.07.09.25329712v1.30","doi-asserted-by":"publisher","DOI":"10.1002\/uog.202"},{"key":"2025071202450692000_2025.07.09.25329712v1.31","doi-asserted-by":"publisher","DOI":"10.1002\/uog.5323"},{"key":"2025071202450692000_2025.07.09.25329712v1.32","first-page":"793","article-title":"Le coefficient de risque d\u2019accouchement premature","volume":"77","year":"1969","journal-title":"Presse medicale"},{"issue":"6","key":"2025071202450692000_2025.07.09.25329712v1.33","first-page":"692","article-title":"System for predicting spontaneous preterm birth","volume":"55","year":"1980","journal-title":"Obstet Gynecol"},{"key":"2025071202450692000_2025.07.09.25329712v1.34","doi-asserted-by":"crossref","unstructured":"Edenfield S , Thomas S , Thompson W , Marcotte J. Validity of the Creasy risk appraisal instrument for prediction of preterm labor. Nursing research. 1995;44(2). Available from: http:\/\/europepmc.org\/abstract\/MED\/7892143.","DOI":"10.1097\/00006199-199503000-00003"},{"key":"2025071202450692000_2025.07.09.25329712v1.35","doi-asserted-by":"publisher","DOI":"10.1016\/S0002-9378(96)70225-9"},{"key":"2025071202450692000_2025.07.09.25329712v1.36","doi-asserted-by":"crossref","unstructured":"Davey M , Watson L , Rayner JA , Rowlands S. Risk scoring systems for predicting preterm birth with the aim of reducing associated adverse outcomes. Cochrane Database Syst Rev. 2011;11.","DOI":"10.1002\/14651858.CD004902.pub4"},{"key":"2025071202450692000_2025.07.09.25329712v1.37","unstructured":"NICHD. Pregnancy and Perinatology Branch \u2013 Strategic Plan 2005-2010. 2005."},{"key":"2025071202450692000_2025.07.09.25329712v1.38","unstructured":"NICHD. Scientific Vision: The Next Decade (13-7940). Washington, DC: U.S. Government Printing Office. 2012."},{"key":"2025071202450692000_2025.07.09.25329712v1.39","doi-asserted-by":"publisher","DOI":"10.1136\/jamia.1994.95153433"},{"key":"2025071202450692000_2025.07.09.25329712v1.40","doi-asserted-by":"publisher","DOI":"10.1097\/00006199-200111000-00003"},{"key":"2025071202450692000_2025.07.09.25329712v1.41","unstructured":"Courtney KL , Stewart S , Popescu M , Goodwin LK . Predictors of Preterm Birth in Birth Certificate Data. In: MIE; 2008. p. 555\u201360."},{"key":"2025071202450692000_2025.07.09.25329712v1.42","unstructured":"Acog. ACOG Committee Opinion. Use of progesterone to reduce preterm birth. 2008;(419 (Replaces No. 291, November 2003))."},{"key":"2025071202450692000_2025.07.09.25329712v1.43","unstructured":"Ilia V , Salleb-Aouissi A , Radeva A , Raja A , Wapner R , Diab H , et al. Data pre-processing for the preterm prediction study MFMU dataset.; 2013. Available from: http:\/\/www.cs.columbia.edu\/\u00e3nsaf\/cing\/CCLS-13-04.pdf."},{"key":"2025071202450692000_2025.07.09.25329712v1.44","unstructured":"Vovsha I , Salleb-Aouissi A , Raja A , Radeva A , Diab H , Tomar A , et al. Predicting preterm birth is not elusive: machine learning paves the way to individual wellness. In: AAAI Spring Symposium Technical Report \u2013 Big Data Becomes Personal: Knowledge into Meaning For Better Health, Wellness and Well-Being, pp 82\u201389; 2014.."},{"key":"2025071202450692000_2025.07.09.25329712v1.45","unstructured":"Vovsha I , Salleb-Aouissi A , Raja A , Koch T , Rybchuk A , Radeva A , et al. Using Kernel Methods and Model Selection for Prediction of Preterm Birth. In: Doshi-Velez F , Fackler J , Kale D , Wallace B , Wiens J , editors. Proceedings of the 1st Machine Learning for Healthcare Conference. vol. 56 of Proceedings of Machine Learning Research. Children\u2019s Hospital LA, Los Angeles, CA, USA: PMLR; 2016. p. 55\u201372. Available from: http:\/\/proceedings.mlr.press\/v56\/Vovsha16.html."},{"key":"2025071202450692000_2025.07.09.25329712v1.46","first-page":"539.e1","article-title":"A description of the methods of the Nulliparous Pregnancy Outcomes Study: monitoring mothers-to-be (nuMoM2b)","volume":"212 4","year":"2015","journal-title":"American journal of obstetrics and gynecology"},{"key":"2025071202450692000_2025.07.09.25329712v1.47","doi-asserted-by":"crossref","unstructured":"Goretsky A , Dmitrienko A , Tang I , Lari N , Kunhardt O , Khan RR , et al. Data Preparation of the nuMoM2b Dataset. medRxiv. 2021. Available from: https:\/\/www.medrxiv.org\/content\/early\/2021\/08\/26\/2021.08.24.21262142.","DOI":"10.1101\/2021.08.24.21262142"},{"issue":"1","key":"2025071202450692000_2025.07.09.25329712v1.48","doi-asserted-by":"crossref","first-page":"10514","DOI":"10.1038\/s41598-024-61218-9","article-title":"Genetic polymorphisms associated with adverse pregnancy outcomes in nulliparas","volume":"14","year":"2024","journal-title":"Scientific Reports"},{"issue":"2","key":"2025071202450692000_2025.07.09.25329712v1.49","doi-asserted-by":"crossref","first-page":"iyad151","DOI":"10.1093\/genetics\/iyad151","article-title":"Searching and visualizing genetic associations of pregnancy traits by using GnuMoM2b","volume":"225","year":"2023","journal-title":"Genetics"},{"key":"2025071202450692000_2025.07.09.25329712v1.50","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2009.06.042"},{"key":"2025071202450692000_2025.07.09.25329712v1.51","unstructured":"Lopez-Paz D , Bottou L , Sch\u00f6lkopf B , Vapnik V. Unifying distillation and privileged information. arXiv preprint arXiv:151103643. 2015."},{"key":"2025071202450692000_2025.07.09.25329712v1.52","unstructured":"Lin YC , Clark-Sevilla A , Ravindranath R , Hassan F , Reyes J , Lombardi J , et al. A LUPI distillation-based approach: Application to predicting Proximal Junctional Kyphosis. In: Deshpande K , Fiterau M , Joshi S , Lipton Z , Ranganath R , Urteaga I , editors. Proceedings of the 9th Machine Learning for Healthcare Conference. vol. 252 of Proceedings of Machine Learning Research. Toronto, Canada: PMLR; 2024. Available from: https:\/\/proceedings.mlr.press\/v252\/lin24a.html."},{"key":"2025071202450692000_2025.07.09.25329712v1.53","unstructured":"Hinton G , Vinyals O , Dean J. Distilling the knowledge in a neural network. arXiv preprint arXiv:150302531. 2015."},{"key":"2025071202450692000_2025.07.09.25329712v1.54","unstructured":"Nogueira F. Bayesian Optimization: Open source constrained global optimization tool for Python; 2014\u2013. Available from: https:\/\/github.com\/fmfn\/BayesianOptimization."},{"key":"2025071202450692000_2025.07.09.25329712v1.55","doi-asserted-by":"publisher","DOI":"10.1016\/j.ajog.2015.06.036"},{"key":"2025071202450692000_2025.07.09.25329712v1.56","unstructured":"Catov, M J , Parker, B C , Gibbs, BB. Patterns of leisure-time physical activity across pregnancy and adverse pregnancy outcomes. International Journal of Behavioral Nutrition and Physical Activity. 2018;15(68). Available from: https:\/\/www.sciencedirect.com\/science\/article\/pii\/S0002937816002179."},{"key":"2025071202450692000_2025.07.09.25329712v1.57","unstructured":"Lundberg S. A unified approach to interpreting model predictions. arXiv preprint arXiv:170507874. 2017."},{"issue":"1","key":"2025071202450692000_2025.07.09.25329712v1.58","doi-asserted-by":"crossref","first-page":"853","DOI":"10.1186\/s12884-024-06988-w","article-title":"A comprehensive and bias-free machine learning approach for risk prediction of preeclampsia with severe features in a nulliparous study cohort","volume":"24","year":"2024","journal-title":"BMC Pregnancy and Childbirth"},{"key":"2025071202450692000_2025.07.09.25329712v1.59","unstructured":"NICHD. Decoding Maternal Morbidity Data Challenge; 2024. Available from: https:\/\/www.nichd.nih.gov\/research\/supported\/challenges\/decoding-maternal-morbidity."},{"key":"2025071202450692000_2025.07.09.25329712v1.60","unstructured":"Loodaricheh MA , Majmudar N , Raja A , Salleb-Aouissi A. Handling Uncertainty in Health Data using Generative Algorithms; 2025. Available from: https:\/\/arxiv.org\/abs\/2503.03715."}],"container-title":[],"original-title":[],"link":[{"URL":"https:\/\/syndication.highwire.org\/content\/doi\/10.1101\/2025.07.09.25329712","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,15]],"date-time":"2026-01-15T20:40:18Z","timestamp":1768509618000},"score":1,"resource":{"primary":{"URL":"http:\/\/medrxiv.org\/lookup\/doi\/10.1101\/2025.07.09.25329712"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7,10]]},"references-count":60,"URL":"https:\/\/doi.org\/10.1101\/2025.07.09.25329712","relation":{},"subject":[],"published":{"date-parts":[[2025,7,10]]},"subtype":"preprint"}}