{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,19]],"date-time":"2026-10-19T16:31:17Z","timestamp":1792427477270,"version":"4.5.0"},"reference-count":40,"publisher":"Public Library of Science (PLoS)","issue":"5","license":[{"start":{"date-parts":[[2026,5,26]],"date-time":"2026-05-26T00:00:00Z","timestamp":1779753600000},"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>Postnatal care (PNC) plays a crucial role in minimizing maternal and neonatal morbidity and mortality, but the uptake of services in Bangladesh remains below the recommended level. Although logistic regression has been widely used, it may miss complex nonlinear interactions among social, economic, and healthcare factors. This study contributes to the body of knowledge by using machine learning (ML) to identify the most significant determinants of PNC and to enhance prediction accuracy. We compared logistic regression to several ML models, including Random Forest, XGBoost, CatBoost, Support Vector Machine, AdaBoost, and Gradient Boosting, using nationally representative data from the 2022 Bangladesh Demographic and Health Survey (BDHS) with ADASYN oversampling to correct class imbalance. Among all models, Random Forest achieved the highest AUC (0.9050), closely followed by XGBoost (0.9036) and CatBoost (0.9028), all of which substantially outperformed logistic regression (AUC\u2009=\u20090.8470). SHAP analysis of the Random Forest model indicated that delivery place, husband\u2019s occupation, rural residence, wealth index, and media exposure were the most influential predictors of PNC utilization, alongside maternal education, women\u2019s occupation, and age-related factors. The results indicate that ML is more effective than classical procedures for revealing latent patterns and making accurate predictions. Policy implications include encouraging facility-based deliveries, improving maternal education, reducing wealth disparities, and enhancing media coverage of health, particularly among rural and low-income groups. This paper not only identifies key drivers of PNC in Bangladesh but also demonstrates how ML can supplement traditional methods to reinforce maternal health policy and interventions.<\/jats:p>","DOI":"10.1371\/journal.pone.0350188","type":"journal-article","created":{"date-parts":[[2026,5,26]],"date-time":"2026-05-26T17:23:07Z","timestamp":1779816187000},"page":"e0350188","update-policy":"https:\/\/doi.org\/10.1371\/journal.pone.corrections_policy","source":"Crossref","is-referenced-by-count":1,"title":["Determinants of maternal postnatal care utilization in Bangladesh: A machine learning and SHAP-based analysis of BDHS 2022 data"],"prefix":"10.1371","volume":"21","author":[{"given":"Amartay Kumar","family":"Dhar","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-6664-5932","authenticated-orcid":true,"given":"Sharmin","family":"Akther","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Farhana Akter","family":"Bina","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"340","published-online":{"date-parts":[[2026,5,26]]},"reference":[{"issue":"1","key":"pone.0350188.ref001","doi-asserted-by":"crossref","first-page":"642","DOI":"10.1186\/s12889-023-15286-7","article-title":"Trend analysis of multi-level determinants of maternal and newborn postnatal care utilization in Pakistan from 2006 to 2018: Evidence from Pakistan Demographic and Health Surveys","volume":"23","author":"S Iqbal","year":"2023","journal-title":"BMC Public Health"},{"issue":"1","key":"pone.0350188.ref002","doi-asserted-by":"crossref","first-page":"39","DOI":"10.1186\/s12884-023-05350-w","article-title":"Postnatal care services in rural Zambia: a qualitative exploration of user, provider, and community perspectives on quality of care","volume":"23","author":"C Sialubanje","year":"2023","journal-title":"BMC Pregnancy Childbirth"},{"key":"pone.0350188.ref003","doi-asserted-by":"crossref","DOI":"10.1136\/bmjgh-2022-010992","article-title":"WHO recommendations on maternal and newborn care for a positive postnatal experience: strengthening the maternal and newborn care continuum","volume":"8","author":"AM Wojcieszek","year":"2023","journal-title":"BMJ Glob Health"},{"issue":"1","key":"pone.0350188.ref004","doi-asserted-by":"crossref","first-page":"010505","DOI":"10.7189\/jogh.10.010505","article-title":"Discordance in postnatal care between mothers and newborns: measurement artifact or missed opportunity?","volume":"10","author":"A Amouzou","year":"2020","journal-title":"J Glob Health"},{"issue":"5","key":"pone.0350188.ref005","doi-asserted-by":"crossref","first-page":"1453","DOI":"10.1007\/s11625-018-0572-3","article-title":"Initial progress in implementing the Sustainable Development Goals (SDGs): a review of evidence from countries","volume":"13","author":"C Allen","year":"2018","journal-title":"Sustain Sci"},{"key":"pone.0350188.ref006","author":"National Institute of Population Research and Training","year":"2024"},{"issue":"1","key":"pone.0350188.ref007","doi-asserted-by":"crossref","first-page":"509","DOI":"10.1186\/s12884-025-07591-3","article-title":"Dominant predictors of postnatal care utilization among ever-married mothers of reproductive age in Bangladesh","volume":"25","author":"ZR Shabuz","year":"2025","journal-title":"BMC Pregnancy Childbirth"},{"issue":"1","key":"pone.0350188.ref008","doi-asserted-by":"crossref","first-page":"2747","DOI":"10.1038\/s41598-022-06672-z","article-title":"Inequalities in women\u2019s utilization of postnatal care services in Bangladesh from 2004 to 2017","volume":"12","author":"S Aziz","year":"2022","journal-title":"Sci Rep"},{"issue":"4","key":"pone.0350188.ref009","doi-asserted-by":"crossref","first-page":"141","DOI":"10.1363\/43e5017","article-title":"A deviance approach to understanding use of maternal health care services in Bangladesh","volume":"43","author":"T Goldenberg","year":"2017","journal-title":"Int Perspect Sex Reprod Health"},{"key":"pone.0350188.ref010","doi-asserted-by":"crossref","first-page":"111268","DOI":"10.1016\/j.buildenv.2024.111268","article-title":"A comparative analysis of machine learning and statistical methods for evaluating building performance: a systematic review and future benchmarking framework","volume":"252","author":"A Ali","year":"2024","journal-title":"Build Environ"},{"issue":"3","key":"pone.0350188.ref011","doi-asserted-by":"crossref","first-page":"441","DOI":"10.1016\/j.surg.2023.06.011","article-title":"Invited commentary: machine learning versus logistic regression for the prediction of complications after pancreatoduodenectomy","volume":"174","author":"P Kambakamba","year":"2023","journal-title":"Surgery"},{"issue":"1","key":"pone.0350188.ref012","article-title":"Performance evaluation and comparative analysis of different machine learning algorithms in predicting postnatal care utilization: evidence from the ethiopian demographic and health survey 2016","volume":"4","author":"DN Mamo","year":"2025","journal-title":"PLOS Digit Health"},{"key":"pone.0350188.ref013","author":"A Bhardwaj","year":"2025"},{"key":"pone.0350188.ref014","doi-asserted-by":"crossref","first-page":"109168","DOI":"10.1016\/j.compbiomed.2024.109168","article-title":"Polynomial-SHAP analysis of liver disease markers for capturing of complex feature interactions in machine learning models","volume":"182","author":"CJ Ejiyi","year":"2024","journal-title":"Comput Biol Med"},{"issue":"1","key":"pone.0350188.ref015","doi-asserted-by":"crossref","first-page":"348","DOI":"10.1137\/19M1261717","article-title":"An efficient stochastic newton algorithm for parameter estimation in logistic regressions","volume":"58","author":"B Bercu","year":"2020","journal-title":"SIAM J Control Optim"},{"issue":"20","key":"pone.0350188.ref016","doi-asserted-by":"crossref","first-page":"7547","DOI":"10.3390\/en15207547","article-title":"A comprehensive study of random forest for short-term load forecasting","volume":"15","author":"G Dudek","year":"2022","journal-title":"Energies"},{"issue":"4","key":"pone.0350188.ref017","doi-asserted-by":"crossref","first-page":"2523","DOI":"10.1109\/TIT.2022.3222767","article-title":"Density-convoluted support vector machines for high-dimensional classification","volume":"69","author":"B Wang","year":"2023","journal-title":"IEEE Trans Inform Theory"},{"issue":"5","key":"pone.0350188.ref018","doi-asserted-by":"crossref","first-page":"1304","DOI":"10.1109\/TCSS.2020.3017013","article-title":"Improved TrAdaBoost and its application to transaction fraud detection","volume":"7","author":"L Zheng","year":"2020","journal-title":"IEEE Trans Comput Soc Syst"},{"key":"pone.0350188.ref019","article-title":"Sequential training of neural networks with gradient boosting","author":"G Mart\u00ednez-Mu\u00f1oz"},{"issue":"2","key":"pone.0350188.ref020","article-title":"Particle swarm optimization\u2010XGBoost\u2010based modeling of radio\u2010frequency power amplifier under different temperatures","volume":"37","author":"J Wang","year":"2023","journal-title":"Int J Numer Model: Electron Netw Devices Fields"},{"issue":"2","key":"pone.0350188.ref021","first-page":"2269","article-title":"A novel SSA-CatBoost machine learning model for credit rating","volume":"44","author":"R Yang","year":"2022","journal-title":"J Intell Fuzzy Syst"},{"key":"pone.0350188.ref022","doi-asserted-by":"crossref","first-page":"52588","DOI":"10.1109\/ACCESS.2020.2981072","article-title":"Basic enhancement strategies when using Bayesian optimization for hyperparameter tuning of deep neural networks","volume":"8","author":"H Cho","year":"2020","journal-title":"IEEE Access"},{"key":"pone.0350188.ref023","article-title":"Practical Bayesian optimization of machine learning algorithms.","volume-title":"Advances in neural information processing systems","author":"J Snoek","year":"2012"},{"issue":"1","key":"pone.0350188.ref024","doi-asserted-by":"crossref","first-page":"820","DOI":"10.1186\/s12884-024-07030-9","article-title":"Predicting maternal risk level using machine learning models","volume":"24","author":"SS Al Mashrafi","year":"2024","journal-title":"BMC Pregnancy Childbirth"},{"issue":"4","key":"pone.0350188.ref025","doi-asserted-by":"crossref","first-page":"427","DOI":"10.1016\/j.ipm.2009.03.002","article-title":"A systematic analysis of performance measures for classification tasks","volume":"45","author":"M Sokolova","year":"2009","journal-title":"Inf Process Manag"},{"issue":"1","key":"pone.0350188.ref026","doi-asserted-by":"crossref","DOI":"10.1186\/s12864-019-6413-7","article-title":"The advantages of the Matthews correlation coefficient (MCC) over F1 score and accuracy in binary classification evaluation","volume":"21","author":"D Chicco","year":"2020","journal-title":"BMC Genom"},{"key":"pone.0350188.ref027","unstructured":"Powers DMW. Evaluation: from precision, recall and F-measure to roc, informedness, markedness & correlation."},{"issue":"3","key":"pone.0350188.ref028","doi-asserted-by":"crossref","first-page":"359","DOI":"10.3390\/ijerph21030359","article-title":"Assessing the quality and coverage of maternal postnatal care in Bangladesh: a comparative analysis of quality postnatal care among home and facility births","volume":"21","author":"SS Priyanka","year":"2024","journal-title":"Int J Environ Res Public Health"},{"key":"pone.0350188.ref029","article-title":"Factors associated with post-natal care utilization among the women of reproductive age group: evidence from Bangladesh demographic and health survey 2017\u201318","volume":"9","author":"IT Sheba","year":"2022","journal-title":"Health Serv Res Manag Epidemiol"},{"issue":"1","key":"pone.0350188.ref030","doi-asserted-by":"crossref","first-page":"2747","DOI":"10.1038\/s41598-022-06672-z","article-title":"Inequalities in women\u2019s utilization of postnatal care services in Bangladesh from 2004 to 2017","volume":"12","author":"S Aziz","year":"2022","journal-title":"Sci Rep"},{"issue":"1","key":"pone.0350188.ref031","doi-asserted-by":"crossref","DOI":"10.1186\/s12884-016-0970-4","article-title":"Progress in the utilization of antenatal and delivery care services in Bangladesh: Where does the equity gap lie?","volume":"16","author":"MH Pulok","year":"2016","journal-title":"BMC Pregnancy Childbirth"},{"issue":"4","key":"pone.0350188.ref032","doi-asserted-by":"crossref","first-page":"929","DOI":"10.1111\/mcn.12178","article-title":"The role of maternal education in the 15-year trajectory of malnutrition in children under 5 years of age in Bangladesh","volume":"12","author":"MT Hasan","year":"2016","journal-title":"Matern Child Nutr"},{"key":"pone.0350188.ref033","doi-asserted-by":"crossref","article-title":"Determinants of antenatal and postnatal care visits among Indigenous people in Bangladesh: a study of the Mru Community.","author":"MR Islam","DOI":"10.22605\/RRH1672"},{"issue":"2","key":"pone.0350188.ref034","doi-asserted-by":"crossref","first-page":"153","DOI":"10.1080\/17441730902992075","article-title":"Factors affecting utilization of skilled maternity care services among married adolescents in Bangladesh","volume":"5","author":"SMM Kamal","year":"2009","journal-title":"Asian Popul Stud"},{"issue":"11","key":"pone.0350188.ref035","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pone.0313424","article-title":"Determining the influential factors of postnatal care in Bangladesh using multilevel logistic regression","volume":"19","author":"IH Sumon","year":"2024","journal-title":"PLoS One"},{"issue":"1","key":"pone.0350188.ref036","doi-asserted-by":"crossref","first-page":"21483","DOI":"10.1038\/s41598-024-71934-x","article-title":"Ensemble machine learning framework for predicting maternal health risk during pregnancy","volume":"14","author":"AO Khadidos","year":"2024","journal-title":"Sci Rep"},{"key":"pone.0350188.ref037","doi-asserted-by":"crossref","first-page":"100285","DOI":"10.1016\/j.health.2023.100285","article-title":"A Medical Cyber-physical system for predicting maternal health in developing countries using machine learning","volume":"5","author":"MM Hossain","year":"2024","journal-title":"Healthc Anal"},{"issue":"6","key":"pone.0350188.ref038","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pone.0011190","article-title":"Economic status, education and empowerment: implications for maternal health service utilization in developing countries","volume":"5","author":"S Ahmed","year":"2010","journal-title":"PLoS One"},{"key":"pone.0350188.ref039","doi-asserted-by":"crossref","first-page":"100252","DOI":"10.1016\/j.ibmed.2025.100252","article-title":"Machine learning approach in predicting early antenatal care initiation at first trimester among reproductive women in Somalia: an analysis with SHAP explanations","volume":"11","author":"J Sani","year":"2025","journal-title":"Intell Based Med"},{"issue":"1","key":"pone.0350188.ref040","doi-asserted-by":"crossref","DOI":"10.1186\/s12884-024-07030-9","article-title":"Predicting maternal risk level using machine learning models","volume":"24","author":"SS Al Mashrafi","year":"2024","journal-title":"BMC Pregnancy Childbirth"}],"container-title":["PLOS One"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0350188","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,26]],"date-time":"2026-05-26T17:23:13Z","timestamp":1779816193000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0350188"}},"subtitle":[],"editor":[{"given":"Jayanta Kumar","family":"Bora","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2026,5,26]]},"references-count":40,"journal-issue":{"issue":"5","published-online":{"date-parts":[[2026,5,26]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pone.0350188","relation":{},"ISSN":["1932-6203"],"issn-type":[{"value":"1932-6203","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,5,26]]}}}