{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,22]],"date-time":"2026-10-22T17:43:42Z","timestamp":1792691022336,"version":"4.5.0"},"reference-count":25,"publisher":"Public Library of Science (PLoS)","issue":"10","license":[{"start":{"date-parts":[[2026,10,22]],"date-time":"2026-10-22T00:00:00Z","timestamp":1792627200000},"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":"\n Background<\/jats:title>\n In sub-Saharan Africa, child mortality remains a critical public health challenge, with Zambia exhibiting some of the highest rates in the region. While survival analysis has identified key risk factors, these methods often fail to capture complex non-linear interactions and the dynamic, time-varying nature of longitudinal markers like birth intervals. This study aimed to develop and compare predictive survival models to improve risk stratification for under-five mortality using the 2024 Zambia Demographic and Health Survey (ZDHS).<\/jats:p>\n <\/jats:sec>\n \n Methods<\/jats:title>\n A cohort of 35,610 live births was initially identified, with a final analytic sample of 9,362 singleton births and 1,236 mortality events (13.2%) after applying exclusion criteria for maternal age and data completeness. We compared four modeling frameworks for predictive comparison: Cox Proportional Hazards (Cox PH), Lasso Cox regression, Random Survival Forests (RSF), and Gradient Boosting Machines (GBM), alongside a Bayesian Joint Model for inference on the birth interval and mortality association. The proportional hazards assumption was assessed using Schoenfeld residuals, and stratified Cox models were employed to address time-varying effects. Model performance was evaluated using nested cross-validation with mother-level outer folds and time-dependent Concordance Indices (C-index) and Area Under the Curve (AUC) metrics across a 48-month follow-up period.<\/jats:p>\n <\/jats:sec>\n \n Results<\/jats:title>\n \n Under nested cross-validation, the four survival models demonstrated comparable predictive performance, with C-indices ranging from 0.745 (Cox PH) to 0.750 (Gradient Boosting Machine) and Integrated Brier Scores ranging from 0.095 to 0.096; pairwise comparisons across models were not statistically significant (DeLong\u2019s test: all\n p<\/jats:italic>\n \u2009>\u20090.05). The Bayesian Joint Model revealed a significant association between the longitudinal birth interval process and the hazard of death (\n \n \n \n \n \n \u03b1<\/mml:mi>\n =<\/mml:mo>\n 0.035<\/mml:mn>\n <\/mml:mrow>\n <\/mml:math>\n <\/jats:alternatives>\n <\/jats:inline-formula>\n , 95% CI: 0.023\u20130.048,\n p<\/jats:italic>\n \u2009<\u20090.001), supporting the maternal depletion hypothesis. Variable importance analysis identified birth interval and maternal age as the most influential predictors of child survival, followed by previous child deaths. Stratified analysis of the Cox model revealed significant effects for maternal education (Secondary: HR\u2009=\u20090.426, 95% CI: 0.318\u20130.570) and previous child deaths (HR\u2009=\u20091.648, 95% CI: 1.529\u20131.777).\n <\/jats:p>\n <\/jats:sec>\n \n Conclusion<\/jats:title>\n Advanced survival modeling using joint modeling techniques provides deeper biological insights into child mortality dynamics, and machine learning and traditional survival models offered equivalent predictive discrimination and calibration in this analysis. These findings support targeted public health interventions focusing on birth spacing, maternal age, and enhanced monitoring for high-risk families as critical strategies for reducing under-five mortality in Zambia.<\/jats:p>\n <\/jats:sec>","DOI":"10.1371\/journal.pone.0361197","type":"journal-article","created":{"date-parts":[[2026,10,22]],"date-time":"2026-10-22T17:32:03Z","timestamp":1792690323000},"page":"e0361197","update-policy":"https:\/\/doi.org\/10.1371\/journal.pone.corrections_policy","source":"Crossref","is-referenced-by-count":0,"title":["Predicting under-five child mortality in Zambia: Machine learning versus parametric survival models"],"prefix":"10.1371","volume":"21","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9819-6579","authenticated-orcid":true,"given":"Kassaye Getaneh","family":"Arge","sequence":"first","affiliation":[{"name":"College of Natural and Computational Sciences, Samara University","place":["Samara, Ethiopia"],"department":["Department of Statistics"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"340","published-online":{"date-parts":[[2026,10,22]]},"reference":[{"key":"pone.0361197.ref001","volume-title":"Levels and trends in child mortality: Report 2024","author":"UNICEF, WHO, World Bank Group, United Nations Population Division","year":"2024"},{"issue":"1","key":"pone.0361197.ref002","doi-asserted-by":"crossref","first-page":"341","DOI":"10.1186\/s12887-022-03362-7","article-title":"Trends of under-five mortality and associated risk factors in Zambia: A multi survey analysis between 2007 and 2018","volume":"22","author":"AK Andegiorgish","year":"2022","journal-title":"BMC Pediatr"},{"key":"pone.0361197.ref003","doi-asserted-by":"crossref","DOI":"10.1007\/978-1-4757-3294-8","volume-title":"Modeling survival data: Extending the Cox model","author":"TM Therneau","year":"2000"},{"issue":"6","key":"pone.0361197.ref004","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3214306","article-title":"Machine learning for survival analysis","volume":"51","author":"P Wang","year":"2019","journal-title":"ACM Comput Surv"},{"issue":"5","key":"pone.0361197.ref005","first-page":"421","article-title":"Birth spacing and child mortality: an analysis of sequential pregnancies in matlab, Bangladesh","volume":"25","author":"LJ Smits","year":"2011","journal-title":"Paed Perinatal Epidemiol"},{"key":"pone.0361197.ref006","unstructured":"Zambia Statistics Agency (ZamStats), ICF. Zambia Demographic and Health Survey 2024. FR397. 2024. https:\/\/dhsprogram.com\/publications\/publication-FR397-DHS-Final-Reports.cfm"},{"issue":"2","key":"pone.0361197.ref007","doi-asserted-by":"crossref","first-page":"187","DOI":"10.1111\/j.2517-6161.1972.tb00899.x","article-title":"Regression models and life-tables","volume":"34","author":"DR Cox","year":"1972","journal-title":"J Royal Stat Soc Series B: Stat Methodol"},{"issue":"3","key":"pone.0361197.ref008","doi-asserted-by":"crossref","first-page":"841","DOI":"10.1214\/08-AOAS169","article-title":"Random survival forests","volume":"2","author":"H Ishwaran","year":"2008","journal-title":"Ann Appl Stat"},{"issue":"5","key":"pone.0361197.ref009","doi-asserted-by":"crossref","DOI":"10.1214\/aos\/1013203451","article-title":"Greedy function approximation: A gradient boosting machine","volume":"29","author":"JH Friedman","year":"2001","journal-title":"Ann Statist"},{"key":"pone.0361197.ref010","doi-asserted-by":"crossref","first-page":"873595","DOI":"10.1155\/2013\/873595","article-title":"A gradient boosting algorithm for survival analysis via direct optimization of concordance index","volume":"2013","author":"Y Chen","year":"2013","journal-title":"Comput Math Methods Med"},{"issue":"4","key":"pone.0361197.ref011","doi-asserted-by":"crossref","first-page":"385","DOI":"10.1002\/(SICI)1097-0258(19970228)16:4<385::AID-SIM380>3.0.CO;2-3","article-title":"The lasso method for variable selection in the Cox model","volume":"16","author":"R Tibshirani","year":"1997","journal-title":"Stat Med"},{"issue":"5","key":"pone.0361197.ref012","doi-asserted-by":"crossref","first-page":"1","DOI":"10.18637\/jss.v039.i05","article-title":"Regularization paths for cox\u2019s proportional hazards model via coordinate descent","volume":"39","author":"N Simon","year":"2011","journal-title":"J Stat Softw"},{"key":"pone.0361197.ref013","doi-asserted-by":"crossref","first-page":"27265","DOI":"10.3402\/gha.v8.27265","article-title":"Cost and impact of scaling up interventions to save lives of mothers and children: Taking South Africa closer to MDGs 4 and 5","volume":"8","author":"L Chola","year":"2015","journal-title":"Glob Health Action"},{"key":"pone.0361197.ref014","doi-asserted-by":"crossref","DOI":"10.1201\/b12208","volume-title":"Joint models for longitudinal and time-to-event data: With applications in R","author":"D Rizopoulos","year":"2012"},{"issue":"2","key":"pone.0361197.ref015","doi-asserted-by":"crossref","first-page":"337","DOI":"10.1111\/j.0006-341X.2000.00337.x","article-title":"Time-dependent ROC curves for censored survival data and a diagnostic marker","volume":"56","author":"PJ Heagerty","year":"2000","journal-title":"Biometrics"},{"issue":"9378","key":"pone.0361197.ref016","first-page":"204","article-title":"Child survival IV: Child survival in developing countries: What can we learn from the past?","volume":"362","author":"CG Victora","year":"2003","journal-title":"The Lancet"},{"key":"pone.0361197.ref017","doi-asserted-by":"crossref","first-page":"137","DOI":"10.1186\/1471-2288-14-137","article-title":"Modern modelling techniques are data hungry: A simulation study for predicting dichotomous endpoints","volume":"14","author":"T van der Ploeg","year":"2014","journal-title":"BMC Med Res Methodol"},{"key":"pone.0361197.ref018","doi-asserted-by":"crossref","first-page":"12","DOI":"10.1016\/j.jclinepi.2019.02.004","article-title":"A systematic review shows no performance benefit of machine learning over logistic regression for clinical prediction models","volume":"110","author":"E Christodoulou","year":"2019","journal-title":"J Clin Epidemiol"},{"issue":"2","key":"pone.0361197.ref019","doi-asserted-by":"crossref","first-page":"139","DOI":"10.1080\/00324728.2018.1439180","article-title":"New evidence about effects of reproductive variables on child mortality in sub-Saharan Africa","volume":"72","author":"\u00d8 Kravdal","year":"2018","journal-title":"Popul Stud (Camb)"},{"issue":"3","key":"pone.0361197.ref020","doi-asserted-by":"crossref","DOI":"10.34172\/jrhs.9033","article-title":"Survival machine-learning approach for predicting under-five mortality in low sociodemographic index states of India","volume":"25","author":"M Vishwakarma","year":"2025","journal-title":"J Res Health Sci"},{"issue":"5","key":"pone.0361197.ref021","doi-asserted-by":"crossref","first-page":"026150079","DOI":"10.36922\/IJPS026150079","article-title":"The enduring burden of short birth intervals on child survival: A 28-year trend analysis in Burkina Faso","volume":"12","author":"H Bassinga","year":"2026","journal-title":"IJPS"},{"issue":"1","key":"pone.0361197.ref022","doi-asserted-by":"crossref","first-page":"247","DOI":"10.1086\/713768","article-title":"Harmonizing longitudinal and survival data using a joint-modeling framework: An efficient approach to assessing social interventions","volume":"12","author":"D-G Chen","year":"2021","journal-title":"J Soc Soc Work and Res"},{"key":"pone.0361197.ref023","doi-asserted-by":"crossref","unstructured":"Mulenga JN, Bwalya BB, Mapoma CC, Siyoto E, Banda J. Under-five child survival and associated risk factors in Zambia. 2022.","DOI":"10.21203\/rs.3.rs-1225252\/v1"},{"issue":"7","key":"pone.0361197.ref024","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pgph.0003331","article-title":"Spatial variations and predictors of neonatal mortality among births to HIV-infected and non-infected mothers in rural Zambia","volume":"5","author":"S Shumba","year":"2025","journal-title":"PLOS Glob Public Health"},{"issue":"7","key":"pone.0361197.ref025","article-title":"Women\u2019s education and health inequalities in under-five mortality in selected sub-Saharan African countries, 1990\u20132015","volume":"11","author":"AR Bado","year":"2016","journal-title":"PLoS One"}],"container-title":["PLOS One"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0361197","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,10,22]],"date-time":"2026-10-22T17:32:12Z","timestamp":1792690332000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0361197"}},"subtitle":[],"editor":[{"given":"Jos\u00e9 Antonio","family":"Ortega","sequence":"first","affiliation":[{"name":"University of Salamanca","place":["SPAIN"]}],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2026,10,22]]},"references-count":25,"journal-issue":{"issue":"10","published-online":{"date-parts":[[2026,10,22]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pone.0361197","relation":{},"ISSN":["1932-6203"],"issn-type":[{"value":"1932-6203","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,10,22]]}}}