{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,29]],"date-time":"2026-08-29T10:48:09Z","timestamp":1788000489175,"version":"build-2784847793"},"reference-count":52,"publisher":"Public Library of Science (PLoS)","issue":"12","license":[{"start":{"date-parts":[[2023,12,27]],"date-time":"2023-12-27T00:00:00Z","timestamp":1703635200000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100020896","name":"Zayed Bin Sultan Center for Health Sciences, United Arab Emirates University","doi-asserted-by":"publisher","award":["31R239"],"award-info":[{"award-number":["31R239"]}],"id":[{"id":"10.13039\/501100020896","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["www.plosone.org"],"crossmark-restriction":false},"short-container-title":["PLoS ONE"],"abstract":"<jats:p>Preterm birth (PTB) presents a complex challenge in pregnancy, often leading to significant perinatal and long-term morbidities. \u201cWhile machine learning (ML) algorithms have shown promise in PTB prediction, the lack of interpretability in existing models hinders their clinical utility. This study aimed to predict PTB in a pregnant population using ML models, identify the key risk factors associated with PTB through the SHapley Additive exPlanations (SHAP) algorithm, and provide comprehensive explanations for these predictions to assist clinicians in providing appropriate care. This study analyzed a dataset of 3509 pregnant women in the United Arab Emirates and selected 35 risk factors associated with PTB based on the existing medical and artificial intelligence literature. Six ML algorithms were tested, wherein the XGBoost model exhibited the best performance, with an area under the operator receiving curves of 0.735 and 0.723 for parous and nulliparous women, respectively. The SHAP feature attribution framework was employed to identify the most significant risk factors linked to PTB. Additionally, individual patient analysis was performed using the SHAP and the local interpretable model-agnostic explanation algorithms (LIME). The overall incidence of PTB was 11.23% (11 and 12.1% in parous and nulliparous women, respectively). The main risk factors associated with PTB in parous women are previous PTB, previous cesarean section, preeclampsia during pregnancy, and maternal age. In nulliparous women, body mass index at delivery, maternal age, and the presence of amniotic infection were the most relevant risk factors. The trained ML prediction model developed in this study holds promise as a valuable screening tool for predicting PTB within this specific population. Furthermore, SHAP and LIME analyses can assist clinicians in understanding the individualized impact of each risk factor on their patients and provide appropriate care to reduce morbidity and mortality related to PTB.<\/jats:p>","DOI":"10.1371\/journal.pone.0293925","type":"journal-article","created":{"date-parts":[[2023,12,27]],"date-time":"2023-12-27T13:27:13Z","timestamp":1703683633000},"page":"e0293925","update-policy":"https:\/\/doi.org\/10.1371\/journal.pone.corrections_policy","source":"Crossref","is-referenced-by-count":31,"title":["Predicting preterm birth using explainable machine learning in a prospective cohort of nulliparous and multiparous pregnant women"],"prefix":"10.1371","volume":"18","author":[{"given":"Wasif","family":"Khan","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Nazar","family":"Zaki","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0897-2587","authenticated-orcid":true,"given":"Nadirah","family":"Ghenimi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Amir","family":"Ahmad","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiang","family":"Bian","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mohammad M.","family":"Masud","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Nasloon","family":"Ali","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Romona","family":"Govender","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Luai A.","family":"Ahmed","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"340","published-online":{"date-parts":[[2023,12,27]]},"reference":[{"issue":"10063","key":"pone.0293925.ref001","doi-asserted-by":"crossref","first-page":"3027","DOI":"10.1016\/S0140-6736(16)31593-8","article-title":"Global, regional, and national causes of under-5 mortality in 2000\u201315: an updated systematic analysis with implications for the Sustainable Development Goals","volume":"388","author":"L Liu","year":"2016","journal-title":"Lancet"},{"issue":"Suppl 1","key":"pone.0293925.ref002","doi-asserted-by":"crossref","first-page":"S2","DOI":"10.1186\/1742-4755-10-S1-S2","article-title":"Born too soon: the global epidemiology of 15 million preterm births","volume":"10","author":"H Blencowe","year":"2013","journal-title":"Reprod Health"},{"issue":"4","key":"pone.0293925.ref003","doi-asserted-by":"crossref","DOI":"10.3390\/ijerph17041382","article-title":"Factors Associated with Preterm Birth and Low Birth Weight in Abu Dhabi, the United Arab Emirates","volume":"17","author":"Z Taha","year":"2020","journal-title":"International journal of environmental research and public health"},{"key":"pone.0293925.ref004","unstructured":"Lipton ZC. The Mythos of Model Interpretability [Internet]. arXiv; 2017 [cited 2022 May 27]. http:\/\/arxiv.org\/abs\/1606.03490"},{"issue":"1","key":"pone.0293925.ref005","doi-asserted-by":"crossref","first-page":"3852","DOI":"10.1038\/s41467-020-17431-x","article-title":"Explainable artificial intelligence model to predict acute critical illness from electronic health records","volume":"11","author":"SM Lauritsen","year":"2020","journal-title":"Nat Commun"},{"issue":"2","key":"pone.0293925.ref006","doi-asserted-by":"crossref","first-page":"228","DOI":"10.1007\/s41666-022-00114-1","article-title":"Explainable Artificial Intelligence for Predictive Modeling in Healthcare","volume":"6","author":"CC Yang","year":"2022","journal-title":"J Healthc Inform Res"},{"key":"pone.0293925.ref007","unstructured":"What is GDPR, the EU\u2019s new data protection law? [Internet]. GDPR.eu. 2018 [cited 2022 May 27]. https:\/\/gdpr.eu\/what-is-gdpr\/"},{"issue":"7","key":"pone.0293925.ref008","doi-asserted-by":"crossref","first-page":"1173","DOI":"10.1093\/jamia\/ocaa053","article-title":"Explainable artificial intelligence models using real-world electronic health record data: a systematic scoping review","volume":"27","author":"SN Payrovnaziri","year":"2020","journal-title":"Journal of the American Medical Informatics Association"},{"issue":"11","key":"pone.0293925.ref009","doi-asserted-by":"crossref","first-page":"4793","DOI":"10.1109\/TNNLS.2020.3027314","article-title":"A Survey on Explainable Artificial Intelligence (XAI): Toward Medical XAI","volume":"32","author":"E Tjoa","year":"2021","journal-title":"IEEE Transactions on Neural Networks and Learning Systems"},{"key":"pone.0293925.ref010","article-title":"A supervised machine learning-based methodology for analyzing dysregulation in splicing machinery: An application in cancer diagnosis","journal-title":"ScienceDirect"},{"key":"pone.0293925.ref011","article-title":"Explainable artificial intelligence for breast cancer: A visual case-based reasoning approach","journal-title":"ScienceDirect"},{"issue":"8","key":"pone.0293925.ref012","doi-asserted-by":"crossref","first-page":"e030937","DOI":"10.1136\/bmjopen-2019-030937","article-title":"Mutaba\u2019ah\u2014Mother and Child Health Study: protocol for a prospective cohort study investigating the maternal and early life determinants of infant, child, adolescent and maternal health in the United Arab Emirates","volume":"9","author":"A Al Haddad","year":"2019","journal-title":"BMJ Open"},{"issue":"6","key":"pone.0293925.ref013","doi-asserted-by":"crossref","first-page":"1885","DOI":"10.1016\/S0002-9378(96)70225-9","article-title":"The preterm prediction study: A clinical risk assessment system","volume":"174","author":"BM Mercer","year":"1996","journal-title":"American Journal of Obstetrics and Gynecology"},{"issue":"16","key":"pone.0293925.ref014","article-title":"Artificial Neural Network Analysis of Spontaneous Preterm Labor and Birth and Its Major Determinants","volume":"34","author":"KS Lee","year":"2019","journal-title":"Journal of Korean Medical Science"},{"key":"pone.0293925.ref015","unstructured":"Tran T, Luo W, Phung D, Morris J, Rickard K, Venkatesh S. Preterm Birth Prediction: Deriving Stable and Interpretable Rules from High Dimensional Data. 2016 Jul 28 [cited 2022 May 25]; https:\/\/arxiv.org\/abs\/1607.08310v1"},{"key":"pone.0293925.ref016","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1155\/2022\/9635526","article-title":"Machine Learning-Based Prediction Model of Preterm Birth Using Electronic Health Record","volume":"2022","author":"Q Sun","year":"2022","journal-title":"Journal of Healthcare Engineering"},{"issue":"1","key":"pone.0293925.ref017","doi-asserted-by":"crossref","first-page":"14","DOI":"10.1007\/s13755-020-00105-9","article-title":"Predicting risk of stillbirth and preterm pregnancies with machine learning","volume":"8","author":"A Koivu","year":"2020","journal-title":"Health Information Science and Systems"},{"key":"pone.0293925.ref018","doi-asserted-by":"crossref","DOI":"10.1155\/2021\/6665573","article-title":"A Machine Learning-Based Prediction Model for Preterm Birth in Rural India","volume":"2021","author":"R Raja","year":"2021","journal-title":"Journal of Healthcare Engineering"},{"issue":"6","key":"pone.0293925.ref019","doi-asserted-by":"crossref","first-page":"e0252025","DOI":"10.1371\/journal.pone.0252025","article-title":"Prediction of preterm birth in nulliparous women using logistic regression and machine learning","volume":"16","author":"RA Belaghi","year":"2021","journal-title":"PLOS ONE"},{"issue":"9","key":"pone.0293925.ref020","doi-asserted-by":"crossref","first-page":"2173","DOI":"10.1038\/s41372-021-01109-3","article-title":"Clinical risk models for preterm birth less than 28 weeks and less than 32 weeks of gestation using a large retrospective cohort","volume":"41","author":"R Arabi Belaghi","year":"2021","journal-title":"Journal of Perinatology"},{"issue":"1","key":"pone.0293925.ref021","doi-asserted-by":"crossref","first-page":"381","DOI":"10.1007\/s12652-021-02906-6","article-title":"Machine learning as a tool to study the influence of chronodisruption in preterm births","volume":"13","author":"E D\u00edaz","year":"2021","journal-title":"Journal of Ambient Intelligence and Humanized Computing"},{"issue":"3","key":"pone.0293925.ref022","doi-asserted-by":"crossref","first-page":"555","DOI":"10.3390\/diagnostics11030555","article-title":"Association of Preterm Birth with Depression and Particulate Matter: Machine Learning Analysis Using National Health Insurance Data","volume":"11","author":"KS Lee","year":"2021","journal-title":"Diagnostics"},{"key":"pone.0293925.ref023","doi-asserted-by":"crossref","first-page":"41S","DOI":"10.1097\/01.AOG.0000558957.93957.8d","article-title":"Predictive Modeling of Spontaneous Preterm Birth Using Machine Learning [36C]","volume":"133","author":"S Guang","year":"2019","journal-title":"Obstetrics & Gynecology"},{"issue":"3","key":"pone.0293925.ref024","doi-asserted-by":"crossref","first-page":"540","DOI":"10.1109\/TITB.2006.872069","article-title":"Predicting High-Risk Preterm Birth Using Artificial Neural Networks","volume":"10","author":"C Catley","year":"2006","journal-title":"IEEE Transactions on Information Technology in Biomedicine"},{"issue":"6","key":"pone.0293925.ref025","doi-asserted-by":"crossref","first-page":"1565","DOI":"10.1007\/s00404-019-05325-3","article-title":"Analysis of big data for prediction of provider-initiated preterm birth and spontaneous premature deliveries and ranking the predictive features","volume":"300","author":"T Khatibi","year":"2019","journal-title":"Arch Gynecol Obstet"},{"key":"pone.0293925.ref026","doi-asserted-by":"crossref","first-page":"1128","DOI":"10.1016\/j.envint.2018.10.025","article-title":"Effect of airborne particulate matter of 2.5 \u03bcm or less on preterm birth: A national birth cohort study in China","volume":"121","author":"Q Li","year":"2018","journal-title":"Environment International"},{"issue":"2","key":"pone.0293925.ref027","doi-asserted-by":"crossref","first-page":"e0198919","DOI":"10.1371\/journal.pone.0198919","article-title":"Improving preterm newborn identification in low-resource settings with machine learning","volume":"14","author":"KJ Rittenhouse","year":"2019","journal-title":"PLoS One"},{"issue":"5","key":"pone.0293925.ref028","doi-asserted-by":"crossref","first-page":"5384","DOI":"10.1016\/j.eswa.2010.10.017","article-title":"Exploring the risk factors of preterm birth using data mining","volume":"38","author":"HY Chen","year":"2011","journal-title":"Expert Systems with Applications"},{"key":"pone.0293925.ref029","doi-asserted-by":"crossref","first-page":"581","DOI":"10.1007\/978-981-13-5802-9_52","volume-title":"Emerging Research in Electronics, Computer Science and Technology","author":"NS Prema","year":"2019"},{"key":"pone.0293925.ref030","doi-asserted-by":"crossref","unstructured":"Moreira MWL, Rodrigues JJPC, Marcondes GAB, Neto AJV, Kumar N, De La Torre Diez I. A Preterm Birth Risk Prediction System for Mobile Health Applications Based on the Support Vector Machine Algorithm. In: 2018 IEEE International Conference on Communications (ICC). 2018. p. 1\u20135.","DOI":"10.1109\/ICC.2018.8422616"},{"issue":"1","key":"pone.0293925.ref031","doi-asserted-by":"crossref","first-page":"17049","DOI":"10.1038\/s41598-019-53448-z","article-title":"Prediction and associations of preterm birth and its subtypes with eicosanoid enzymatic pathways and inflammatory markers","volume":"9","author":"MT Aung","year":"2019","journal-title":"Sci Rep"},{"key":"pone.0293925.ref032","first-page":"340","volume-title":"The Nature of Statistical Learning Theory","author":"V. Vapnik","year":"1999"},{"issue":"1","key":"pone.0293925.ref033","doi-asserted-by":"crossref","first-page":"5","DOI":"10.1023\/A:1010933404324","article-title":"Random Forests","volume":"45","author":"L. Breiman","year":"2001","journal-title":"Machine Learning"},{"key":"pone.0293925.ref034","first-page":"528","volume-title":"Applied Logistic Regression","author":"DW H","year":"2013"},{"key":"pone.0293925.ref035","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1007\/978-1-4419-1742-3","volume-title":"Logistic Regression: A Self-Learning Text","author":"DG Kleinbaum","year":"2010"},{"key":"pone.0293925.ref036","first-page":"546","volume-title":"Fundamentals of Artificial Neural Networks","author":"MH Hassoun","year":"1995"},{"issue":"5","key":"pone.0293925.ref037","doi-asserted-by":"crossref","first-page":"1189","DOI":"10.1214\/aos\/1013203451","article-title":"Greedy Function Approximation: A Gradient Boosting Machine","volume":"29","author":"JH Friedman","year":"2001","journal-title":"The Annals of Statistics"},{"key":"pone.0293925.ref038","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 [Internet]. San Francisco California USA: ACM; 2016 [cited 2022 May 28]. p. 785\u201394. https:\/\/dl.acm.org\/doi\/10.1145\/2939672.2939785","DOI":"10.1145\/2939672.2939785"},{"key":"pone.0293925.ref039","unstructured":"Lundberg S, Lee SI. A Unified Approach to Interpreting Model Predictions [Internet]. arXiv; 2017 Nov [cited 2022 May 27]. Report No.: arXiv:1705.07874. http:\/\/arxiv.org\/abs\/1705.07874"},{"key":"pone.0293925.ref040","doi-asserted-by":"crossref","unstructured":"Ribeiro MT, Singh S, Guestrin C. \u201cWhy Should I Trust You?\u201d: Explaining the Predictions of Any Classifier [Internet]. arXiv; 2016 Aug [cited 2022 May 27]. Report No.: arXiv:1602.04938. http:\/\/arxiv.org\/abs\/1602.04938","DOI":"10.1145\/2939672.2939778"},{"key":"pone.0293925.ref041","doi-asserted-by":"crossref","first-page":"103677","DOI":"10.1016\/j.scs.2022.103677","article-title":"Explainable heat-related mortality with random forest and SHapley Additive exPlanations (SHAP) models","volume":"79","author":"Y Kim","year":"2022","journal-title":"Sustainable Cities and Society"},{"issue":"1","key":"pone.0293925.ref042","doi-asserted-by":"crossref","first-page":"56","DOI":"10.1038\/s42256-019-0138-9","article-title":"From local explanations to global understanding with explainable AI for trees","volume":"2","author":"SM Lundberg","year":"2020","journal-title":"Nat Mach Intell"},{"issue":"1","key":"pone.0293925.ref043","doi-asserted-by":"crossref","first-page":"112","DOI":"10.1093\/bioinformatics\/btr597","article-title":"MissForest\u2014non-parametric missing value imputation for mixed-type data","volume":"28","author":"DJ Stekhoven","year":"2012","journal-title":"Bioinformatics"},{"issue":"1","key":"pone.0293925.ref044","doi-asserted-by":"crossref","first-page":"e37","DOI":"10.1016\/S2214-109X(18)30451-0","article-title":"Global, regional, and national estimates of levels of preterm birth in 2014: a systematic review and modelling analysis","volume":"7","author":"S Chawanpaiboon","year":"2019","journal-title":"The Lancet Global Health"},{"issue":"1","key":"pone.0293925.ref045","doi-asserted-by":"crossref","first-page":"17","DOI":"10.1002\/ijgo.13184","article-title":"Risk factors for spontaneous preterm delivery","volume":"150","author":"T Cobo","year":"2020","journal-title":"Int J Gynaecol Obstet"},{"issue":"9","key":"pone.0293925.ref046","article-title":"Application of Artificial Intelligence in Early Diagnosis of Spontaneous Preterm Labor and Birth","volume":"10","author":"KS Lee","year":"2020","journal-title":"Diagnostics (Basel)"},{"issue":"5","key":"pone.0293925.ref047","doi-asserted-by":"crossref","first-page":"352","DOI":"10.1038\/jp.2012.130","article-title":"Screening for fetal growth disorders by clinical exam in the era of obesity","volume":"33","author":"KR Goetzinger","year":"2013","journal-title":"J Perinatol"},{"issue":"1","key":"pone.0293925.ref048","doi-asserted-by":"crossref","first-page":"21","DOI":"10.1002\/ijgo.12697","article-title":"Maternal serum uric acid concentration and pregnancy outcomes in women with pre-eclampsia\/eclampsia","volume":"144","author":"TM Le","year":"2019","journal-title":"Int J Gynaecol Obstet"},{"issue":"8","key":"pone.0293925.ref049","doi-asserted-by":"crossref","first-page":"907","DOI":"10.1111\/aogs.13358","article-title":"Prediction models for the risk of spontaneous preterm birth based on maternal characteristics: a systematic review and independent external validation","volume":"97","author":"LJE Meertens","year":"2018","journal-title":"Acta Obstetricia et Gynecologica Scandinavica"},{"issue":"11","key":"pone.0293925.ref050","article-title":"Original research: Predictive model and risk analysis for diabetic retinopathy using machine learning: a retrospective cohort study in China","volume":"11","author":"W Li","year":"2021","journal-title":"BMJ Open"},{"issue":"7","key":"pone.0293925.ref051","doi-asserted-by":"crossref","first-page":"1504","DOI":"10.2337\/dc19-1743","article-title":"Predicting the Risk of Inpatient Hypoglycemia With Machine Learning Using Electronic Health Records","volume":"43","author":"Y Ruan","year":"2020","journal-title":"Diabetes Care"},{"issue":"2","key":"pone.0293925.ref052","doi-asserted-by":"crossref","first-page":"e65","DOI":"10.1097\/AOG.0000000000004479","article-title":"Prediction and Prevention of Spontaneous Preterm Birth: ACOG Practice Bulletin, Number 234","volume":"138","author":"American College of Obstetricians and Gynecologists\u2019 Committee on Practice Bulletins\u2014Obstetrics","year":"2021","journal-title":"Obstet Gynecol"}],"container-title":["PLOS ONE"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0293925","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,12,27]],"date-time":"2023-12-27T13:27:41Z","timestamp":1703683661000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0293925"}},"subtitle":[],"editor":[{"given":"Burak","family":"Bayraktar","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2023,12,27]]},"references-count":52,"journal-issue":{"issue":"12","published-online":{"date-parts":[[2023,12,27]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pone.0293925","relation":{},"ISSN":["1932-6203"],"issn-type":[{"value":"1932-6203","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,12,27]]}}}