{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,20]],"date-time":"2026-08-20T18:24:57Z","timestamp":1787250297604,"version":"build-2736575974"},"reference-count":42,"publisher":"Public Library of Science (PLoS)","issue":"8","license":[{"start":{"date-parts":[[2026,8,20]],"date-time":"2026-08-20T00:00:00Z","timestamp":1787184000000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["www.plosone.org"],"crossmark-restriction":false},"short-container-title":["PLoS One"],"abstract":"<jats:p>Childbirth occurring at high-risk maternal ages (\u226418 years or \u226540 years) remains an important public health concern in Bangladesh and is influenced by a range of socio-demographic and behavioral factors. We conducted a cross-sectional secondary analysis of 15,386 ever married women from the BDHS 2022 dataset. After cleaning and removing duplicates and missing values, data were split into training 80 percent and testing 20 percent sets. Three feature selection methods Lasso with 12 features, Chi Square with 13 features, and Boruta with 10 features were applied. Machine learning models including non-ensemble models CART, SVM, KNN, Naive Bayes and ensemble models Random Forest, GBM, AdaBoost, XGB were trained using 10-fold stratified cross validation with SMOTE applied to balance classes. Model performance was evaluated using accuracy, precision, recall, F1 score, Area Under the Receiver Operating Characteristic Curve (AUROC), and Area Under the Precision-Recall Curve (AUPRC).. Among the evaluated machine learning models, CART achieved the best overall performance for the Lasso-selected features (Accuracy\u2009=\u20090.77, F1-score\u2009=\u20090.69, AUROC\u2009=\u20090.74, AUPRC\u2009=\u20090.54), while GBM performed best for the Chi-square-selected features (Accuracy\u2009=\u20090.80, F1-score\u2009=\u20090.71, AUROC\u2009=\u20090.79, AUPRC\u2009=\u20090.64) and Boruta-selected features (Accuracy\u2009=\u20090.75, F1-score\u2009=\u20090.64, AUROC\u2009=\u20090.69). Overall, the GBM model with Chi-square-selected features demonstrated the strongest predictive performance, achieving the highest AUROC (0.79) and F1-score (0.71). Key predictors of high-risk age at childbirth included maternal age, early marriage, current contraceptive use, husband occupation, number of children, husband age and education, respondent age, and regional disparities. Findings were consistent with prior South Asian and LMIC studies while highlighting the added relevance of partner education and media exposure. Machine learning approaches identified the most influential socio demographic and behavioral determinants of high-risk age at childbirth in Bangladesh. The results provide an evidence-based framework to guide policymakers in designing interventions such as delaying age at first birth, expanding female education, and targeting high risk districts to improve maternal and child health outcomes.<\/jats:p>","DOI":"10.1371\/journal.pone.0356362","type":"journal-article","created":{"date-parts":[[2026,8,20]],"date-time":"2026-08-20T17:42:28Z","timestamp":1787247748000},"page":"e0356362","update-policy":"https:\/\/doi.org\/10.1371\/journal.pone.corrections_policy","source":"Crossref","is-referenced-by-count":0,"title":["Uncovering the determinants of high-risk age at childbirth in Bangladesh: A machine learning analysis of the BDHS 2022 data"],"prefix":"10.1371","volume":"21","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-2877-9412","authenticated-orcid":true,"given":"A. T. M. Ahsanul Kyum","family":"Siam","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tanzila Tanjim","family":"Tusra","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Md. Abul","family":"Hossain","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"340","published-online":{"date-parts":[[2026,8,20]]},"reference":[{"issue":"3","key":"pone.0356362.ref001","doi-asserted-by":"crossref","DOI":"10.1016\/j.heliyon.2021.e06547","article-title":"Factors associated with age of mother at first birth in Albania: application of quantile regression model","volume":"7","author":"A Talukder","year":"2021","journal-title":"Heliyon"},{"issue":"5","key":"pone.0356362.ref002","doi-asserted-by":"crossref","DOI":"10.3390\/ijerph20054113","article-title":"Adolescent Pregnancy Outcomes and Risk Factors","volume":"20","author":"J Diabelkov\u00e1","year":"2023","journal-title":"Int J Environ Res Public Health"},{"issue":"5","key":"pone.0356362.ref003","doi-asserted-by":"crossref","DOI":"10.3390\/ijerph20054113","article-title":"Adolescent Pregnancy Outcomes and Risk Factors","volume":"20","author":"J Diabelkov\u00e1","year":"2023","journal-title":"Int J Environ Res Public Health"},{"key":"pone.0356362.ref004","doi-asserted-by":"crossref","DOI":"10.3389\/frph.2023.1165204","article-title":"Time to first childbirth and its predictors among reproductive-age women in Ethiopia: survival analysis of recent evidence from the EDHS 2019","volume":"5","author":"TA Kitaw","year":"2023","journal-title":"Frontiers in Reproductive Health"},{"issue":"6","key":"pone.0356362.ref005","doi-asserted-by":"crossref","DOI":"10.1007\/s13524-018-0730-3","article-title":"Maternal Age and Child Development","volume":"55","author":"GJ Duncan","year":"2018","journal-title":"Demography"},{"issue":"6","key":"pone.0356362.ref006","doi-asserted-by":"crossref","DOI":"10.1007\/s13524-018-0730-3","article-title":"Maternal Age and Child Development","volume":"55","author":"GJ Duncan","year":"2018","journal-title":"Demography"},{"issue":"11","key":"pone.0356362.ref007","doi-asserted-by":"crossref","first-page":"1328","DOI":"10.1080\/00016340701657209","article-title":"First time mothers\u2019 pregnancy and birth experiences varying by age","volume":"86","author":"E Zasloff","year":"2007","journal-title":"Acta Obstet Gynecol Scand"},{"issue":"11","key":"pone.0356362.ref008","doi-asserted-by":"crossref","first-page":"1328","DOI":"10.1080\/00016340701657209","article-title":"First time mothers\u2019 pregnancy and birth experiences varying by age","volume":"86","author":"E Zasloff","year":"2007","journal-title":"Acta Obstet Gynecol Scand"},{"key":"pone.0356362.ref009","unstructured":"K. I n d i c a t o r s. Bangladesh demographic and health survey 2017-18. 2019. http:\/\/www.niport.gov.bd"},{"key":"pone.0356362.ref010","unstructured":"Bangladesh Demographic and Health Survey 2017-18. 2019."},{"key":"pone.0356362.ref011","doi-asserted-by":"crossref","first-page":"602","DOI":"10.25133\/JPSSv302022.034","article-title":"Assessing the Determinants of Women\u2019s Age at First Marriage in Rural and Urban Areas of Bangladesh: Insights From Quantile Regression (QR) Approaches","volume":"30","author":"S Hossain","year":"2022","journal-title":"JPSS"},{"issue":"3","key":"pone.0356362.ref012","doi-asserted-by":"crossref","DOI":"10.1016\/j.heliyon.2021.e06547","article-title":"Factors associated with age of mother at first birth in Albania: application of quantile regression model","volume":"7","author":"A Talukder","year":"2021","journal-title":"Heliyon"},{"issue":"11","key":"pone.0356362.ref013","doi-asserted-by":"crossref","first-page":"1328","DOI":"10.1080\/00016340701657209","article-title":"First time mothers\u2019 pregnancy and birth experiences varying by age","volume":"86","author":"E Zasloff","year":"2007","journal-title":"Acta Obstet Gynecol Scand"},{"key":"pone.0356362.ref014","doi-asserted-by":"crossref","DOI":"10.3389\/frph.2023.1165204","article-title":"Time to first childbirth and its predictors among reproductive-age women in Ethiopia: survival analysis of recent evidence from the EDHS 2019","volume":"5","author":"TA Kitaw","year":"2023","journal-title":"Frontiers in Reproductive Health"},{"issue":"11","key":"pone.0356362.ref015","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pgph.0005494","article-title":"Identifying determinants and predicting cesarean section delivery among Bangladeshi women using machine learning: Insight from BDHS 2022 data","volume":"5","author":"S Zoha","year":"2025","journal-title":"PLOS Global Public Health"},{"issue":"1","key":"pone.0356362.ref016","doi-asserted-by":"crossref","DOI":"10.1186\/1471-2458-14-293","article-title":"Early maternal age at first birth is associated with chronic diseases and poor physical performance in older age: Cross-sectional analysis from the International Mobility in Aging Study","volume":"14","author":"CM Pirkle","year":"2014","journal-title":"BMC Public Health"},{"issue":"15","key":"pone.0356362.ref017","doi-asserted-by":"crossref","DOI":"10.3390\/jcm14155387","article-title":"The Impact of Advanced Maternal Age on Pregnancy Complications and Neonatal Outcomes","volume":"14","author":"FK Yaman","year":"2025","journal-title":"J Clin Med"},{"key":"pone.0356362.ref018","doi-asserted-by":"crossref","unstructured":"Muthukrishnan R, Rohini R. LASSO: A feature selection technique in predictive modeling for machine learning. In: 2016 IEEE International Conference on Advances in Computer Applications (ICACA), 2016. 18\u201320. https:\/\/doi.org\/10.1109\/icaca.2016.7887916","DOI":"10.1109\/ICACA.2016.7887916"},{"key":"pone.0356362.ref019","first-page":"143","article-title":"The chi-square test of independence.","author":"ML McHugh"},{"issue":"11","key":"pone.0356362.ref020","doi-asserted-by":"crossref","DOI":"10.18637\/jss.v036.i11","article-title":"Feature selection with the boruta package","volume":"36","author":"MB Kursa","year":"2010","journal-title":"J Stat Softw"},{"key":"pone.0356362.ref021","author":"L Breiman","journal-title":"Classification and regression trees"},{"issue":"2","key":"pone.0356362.ref022","article-title":"Machine Learning Applications based on SVM Classification: A Review","volume":"1","author":"DM Abdullah","year":"2021","journal-title":"Qubahan Academic Journal"},{"issue":"3","key":"pone.0356362.ref023","doi-asserted-by":"crossref","first-page":"273","DOI":"10.1023\/A:1022627411411","article-title":"Support-vector networks","volume":"20","author":"C Cortes","journal-title":"Mach Learn"},{"key":"pone.0356362.ref024","doi-asserted-by":"crossref","first-page":"105361","DOI":"10.1016\/j.knosys.2019.105361","article-title":"A novel selective na\u00efve Bayes algorithm","volume":"192","author":"S Chen","year":"2020","journal-title":"Knowledge-Based Systems"},{"key":"pone.0356362.ref025","doi-asserted-by":"crossref","first-page":"44","DOI":"10.1016\/j.patrec.2017.09.036","article-title":"A novel kNN algorithm with data-driven k parameter computation","volume":"109","author":"S Zhang","year":"2018","journal-title":"Pattern Recognit Lett"},{"issue":"3","key":"pone.0356362.ref026","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/2990508","article-title":"Learning k for kNN Classification","volume":"8","author":"S Zhang","year":"2017","journal-title":"ACM Trans Intell Syst Technol"},{"issue":"1","key":"pone.0356362.ref027","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"},{"issue":"1","key":"pone.0356362.ref028","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.0356362.ref029","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, 2016. 785\u201394. https:\/\/doi.org\/10.1145\/2939672.2939785","DOI":"10.1145\/2939672.2939785"},{"key":"pone.0356362.ref030","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, 2016. 785\u201394. https:\/\/doi.org\/10.1145\/2939672.2939785","DOI":"10.1145\/2939672.2939785"},{"issue":"3","key":"pone.0356362.ref031","doi-asserted-by":"crossref","DOI":"10.1007\/s10462-020-09896-5","article-title":"A comparative analysis of gradient boosting algorithms","volume":"54","author":"C Bent\u00e9jac","year":"2021","journal-title":"Artificial Intelligence Review"},{"key":"pone.0356362.ref032","doi-asserted-by":"crossref","first-page":"37","DOI":"10.1007\/978-3-642-41136-6_5","article-title":"Explaining AdaBoost","author":"RE Schapire","year":"2013","journal-title":"Empirical Inference: Festschrift in Honor of Vladimir N. Vapnik"},{"issue":"1","key":"pone.0356362.ref033","first-page":"5979","article-title":"On evaluation metrics for medical applications of artificial intelligence","volume":"12","author":"SA Hicks"},{"issue":"3","key":"pone.0356362.ref034","doi-asserted-by":"crossref","DOI":"10.1007\/s12065-021-00565-2","article-title":"Precision\u2013recall curve (PRC) classification trees","volume":"15","author":"J Miao","year":"2022","journal-title":"Evol Intell"},{"key":"pone.0356362.ref035","doi-asserted-by":"crossref","DOI":"10.1162\/neco_a_01362","article-title":"The effect of class imbalance on precision-recall curves","author":"CKI Williams","year":"2021"},{"issue":"1","key":"pone.0356362.ref036","doi-asserted-by":"crossref","first-page":"142","DOI":"10.1177\/0962280214541852","article-title":"Does McNemar\u2019s test compare the sensitivities and specificities of two diagnostic tests?","volume":"26","author":"S Kim","year":"2017","journal-title":"Stat Methods Med Res"},{"issue":"9","key":"pone.0356362.ref037","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pgph.0005187","article-title":"Machine learning based prediction of low birth weight and its associated risk factors: Insights from the Bangladesh Demographic and Health Survey 2022","volume":"5","author":"N Sultana","year":"2025","journal-title":"PLOS Glob Public Health"},{"issue":"1","key":"pone.0356362.ref038","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pgph.0005745","article-title":"Unveiling socio-demographic determinants of low birth weight using machine learning techniques","volume":"6","author":"MS Uddin","year":"2026","journal-title":"PLOS Global Public Health"},{"issue":"11","key":"pone.0356362.ref039","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pgph.0005494","article-title":"Identifying determinants and predicting cesarean section delivery among Bangladeshi women using machine learning: Insight from BDHS 2022 data","volume":"5","author":"S Zoha","year":"2025","journal-title":"PLOS Global Public Health"},{"key":"pone.0356362.ref040","article-title":"A comparative study of ordinal logistic regression and machine learning models for predicting women\u2019s malnutrition in bangladesh: evidence from BDHS 2022","author":"U Kulsum","year":"2026","journal-title":"J Health Popul Nutr"},{"issue":"1","key":"pone.0356362.ref041","doi-asserted-by":"crossref","DOI":"10.1186\/s12889-024-19355-3","article-title":"Understanding the socio-demographic and programmatic factors associated with adolescent motherhood and its association with child undernutrition in Bangladesh","volume":"24","author":"MA Hossain","year":"2024","journal-title":"BMC Public Health"},{"issue":"5","key":"pone.0356362.ref042","doi-asserted-by":"crossref","DOI":"10.1136\/bmjopen-2022-069265","article-title":"Exploring the factors behind the shift in unwanted childbearing rate in Bangladesh between 2007 and 2017\/2018: a cross-sectional study","volume":"13","author":"MM Rahman","year":"2023","journal-title":"BMJ Open"}],"container-title":["PLOS One"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0356362","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,20]],"date-time":"2026-08-20T17:42:42Z","timestamp":1787247762000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0356362"}},"subtitle":[],"editor":[{"given":"Ammal Mokhtar","family":"Metwally","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2026,8,20]]},"references-count":42,"journal-issue":{"issue":"8","published-online":{"date-parts":[[2026,8,20]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pone.0356362","relation":{},"ISSN":["1932-6203"],"issn-type":[{"value":"1932-6203","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8,20]]}}}