{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,26]],"date-time":"2026-06-26T17:52:10Z","timestamp":1782496330467,"version":"3.54.5"},"reference-count":26,"publisher":"Public Library of Science (PLoS)","issue":"6","license":[{"start":{"date-parts":[[2026,6,26]],"date-time":"2026-06-26T00:00:00Z","timestamp":1782432000000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["www.plosglobalpublichealth.org"],"crossmark-restriction":false},"short-container-title":["PLOS Glob Public Health"],"abstract":"<jats:p>Cesarean section (CS) delivery is an important surgical intervention for reducing maternal and neonatal morbidity and mortality when medically indicated; however, substantial inequalities in its utilization persist across Sub-Saharan Africa (SSA). This study evaluated the performance of explainable machine learning (ML) algorithms in classifying cesarean section delivery patterns using Demographic and Health Survey (DHS) data from ten SSA countries collected between 2016 and 2024. A weighted sample of 388,015 women aged 15\u201349 years was included, among whom 7,369 (1.82%) had undergone cesarean section delivery. Data preprocessing included handling missing values, feature encoding, normalization, and balancing the minority class using the Synthetic Minority Over-sampling Technique (SMOTE). Multiple ML classifiers, including LightGBM, XGBoost, Random Forest, Decision Tree, Logistic Regression, Na\u00efve Bayes, K-Nearest Neighbor, AdaBoost, and Artificial Neural Networks, were trained and evaluated using repeated 10-fold cross-validation. Model performance was assessed using accuracy, recall, F1-score, and area under the receiver operating characteristic curve (AUC). LightGBM achieved the best classification performance with an AUC of 0.89 (95% CI: 0.887\u20130.893), accuracy of 85% (95% CI: 83.7\u201386.3%), and recall of 91% (95% CI: 89.8\u201392.2%), significantly outperforming logistic regression. SHapley Additive exPlanations (SHAP) identified maternal age, child size at birth, maternal education, wealth index, antenatal care visits, and media exposure as the most influential features associated with cesarean section classification outcomes. The findings demonstrate that explainable ML approaches, particularly LightGBM, improve classification performance compared with conventional regression models when applied to large population-based DHS datasets. However, because the study used cross-sectional survey data without external validation or detailed clinical predictors, the findings should be interpreted as associative classification patterns rather than tools for prospective clinical prediction.<\/jats:p>","DOI":"10.1371\/journal.pgph.0006613","type":"journal-article","created":{"date-parts":[[2026,6,26]],"date-time":"2026-06-26T17:24:13Z","timestamp":1782494653000},"page":"e0006613","update-policy":"https:\/\/doi.org\/10.1371\/journal.pgph.corrections_policy","source":"Crossref","is-referenced-by-count":0,"title":["Use of explainable machine learning in risk classification of Cesarean section delivery: A cross-sectional analysis of Demographic and Health Surveys from ten Sub-Saharan African countries (2016\u20132024)"],"prefix":"10.1371","volume":"6","author":[{"given":"Walle Addis","family":"Birhanu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Binyam","family":"Tilahun","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tirualem Zeleke","family":"Yehuala","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tadele Chekol","family":"Maru","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-3445-341X","authenticated-orcid":true,"given":"Tilalem Biresaw","family":"Ayalaw","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Nebebe Demis","family":"Baykemagn","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-7195-1278","authenticated-orcid":true,"given":"Andualem Enyew","family":"Gedefaw","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"340","published-online":{"date-parts":[[2026,6,26]]},"reference":[{"issue":"6","key":"pgph.0006613.ref001","doi-asserted-by":"crossref","DOI":"10.1136\/bmjgh-2021-005671","article-title":"Trends and projections of caesarean section rates: global and regional estimates","volume":"6","author":"AP Betran","year":"2021","journal-title":"BMJ Glob Health"},{"issue":"10155","key":"pgph.0006613.ref002","doi-asserted-by":"crossref","first-page":"1341","DOI":"10.1016\/S0140-6736(18)31928-7","article-title":"Global epidemiology of use of and disparities in caesarean sections","volume":"392","author":"T Boerma","year":"2018","journal-title":"Lancet"},{"issue":"10155","key":"pgph.0006613.ref003","doi-asserted-by":"crossref","first-page":"1349","DOI":"10.1016\/S0140-6736(18)31930-5","article-title":"Short-term and long-term effects of caesarean section on the health of women and children","volume":"392","author":"J Sandall","year":"2018","journal-title":"Lancet"},{"issue":"1","key":"pgph.0006613.ref004","article-title":"Long-term risks and benefits associated with cesarean delivery for mother, baby, and subsequent pregnancies: Systematic review and meta-analysis","volume":"15","author":"OE Keag","year":"2018","journal-title":"PLoS Med"},{"issue":"21","key":"pgph.0006613.ref005","doi-asserted-by":"crossref","first-page":"2263","DOI":"10.1001\/jama.2015.15553","article-title":"Relationship Between Cesarean Delivery Rate and Maternal and Neonatal Mortality","volume":"314","author":"G Molina","year":"2015","journal-title":"JAMA"},{"issue":"5","key":"pgph.0006613.ref006","doi-asserted-by":"crossref","DOI":"10.1016\/S2214-109X(15)70094-X","article-title":"Use of the Robson classification to assess caesarean section trends in 21 countries: a secondary analysis of two WHO multicountry surveys","volume":"3","author":"JP Vogel","year":"2015","journal-title":"Lancet Glob Health"},{"issue":"1","key":"pgph.0006613.ref007","doi-asserted-by":"crossref","first-page":"106","DOI":"10.1016\/j.ijgo.2011.07.011","article-title":"A national review of cesarean delivery in Ethiopia","volume":"115","author":"N Fesseha","year":"2011","journal-title":"Int J Gynaecol Obstet"},{"issue":"9","key":"pgph.0006613.ref008","doi-asserted-by":"crossref","DOI":"10.1136\/bmjopen-2018-024216","article-title":"Caesarean section provision and readiness in Tanzania: analysis of cross-sectional surveys of women and health facilities over time","volume":"8","author":"FL Cavallaro","year":"2018","journal-title":"BMJ Open"},{"issue":"14","key":"pgph.0006613.ref009","doi-asserted-by":"crossref","first-page":"1347","DOI":"10.1056\/NEJMra1814259","article-title":"Machine Learning in Medicine","volume":"380","author":"A Rajkomar","year":"2019","journal-title":"N Engl J Med"},{"issue":"13","key":"pgph.0006613.ref010","doi-asserted-by":"crossref","first-page":"1216","DOI":"10.1056\/NEJMp1606181","article-title":"Predicting the Future - Big Data, Machine Learning, and Clinical Medicine","volume":"375","author":"Z Obermeyer","year":"2016","journal-title":"N Engl J Med"},{"key":"pgph.0006613.ref011","doi-asserted-by":"crossref","first-page":"1680","DOI":"10.1109\/ACCESS.2020.3045469","article-title":"Exploring Machine Learning Algorithms to Find the Best Features for Predicting Modes of Childbirth","volume":"9","author":"MN Islam","year":"2021","journal-title":"IEEE Access"},{"issue":"11","key":"pgph.0006613.ref012","doi-asserted-by":"crossref","DOI":"10.2196\/16503","article-title":"Comparison of Multivariable Logistic Regression and Other Machine Learning Algorithms for Prognostic Prediction Studies in Pregnancy Care: Systematic Review and Meta-Analysis","volume":"8","author":"H Sufriyana","year":"2020","journal-title":"JMIR Med Inform"},{"key":"pgph.0006613.ref013","doi-asserted-by":"crossref","first-page":"9917919","DOI":"10.1155\/2021\/9917919","article-title":"A Comparative Analysis of Machine Learning Algorithms to Predict Alzheimer\u2019s Disease","volume":"2021","author":"M Bari Antor","year":"2021","journal-title":"J Healthc Eng"},{"key":"pgph.0006613.ref014","first-page":"100317","article-title":"Performance of advanced machine learning algorithms overlogistic regression in predicting hospital readmissions: A meta-analysis","volume":"11","author":"A Talwar","year":"2023","journal-title":"Explor Res Clin Soc Pharm"},{"key":"pgph.0006613.ref015","article-title":"Lightgbm: A highly efficient gradient boosting decision tree","volume":"30","author":"G Ke","year":"2017","journal-title":"Advances in Neural Information Processing Systems"},{"issue":"5","key":"pgph.0006613.ref016","doi-asserted-by":"crossref","first-page":"275","DOI":"10.3390\/jrfm18050275","article-title":"A Panel Data Analysis of Determinants of Financial Inclusion in Sub-Saharan Africa (SSA) Countries from 1999 to 2024","volume":"18","author":"O Anifowose","year":"2025","journal-title":"JRFM"},{"key":"pgph.0006613.ref017","unstructured":"Manual DPSaHL. 2023. https:\/\/dhsprogram.com"},{"key":"pgph.0006613.ref018","unstructured":"Program. DPTD. https:\/\/dhsprogram.com"},{"issue":"1","key":"pgph.0006613.ref019","doi-asserted-by":"crossref","first-page":"89","DOI":"10.1186\/s12938-017-0378-z","article-title":"Classification of caesarean section and normal vaginal deliveries using foetal heart rate signals and advanced machine learning algorithms","volume":"16","author":"P Fergus","year":"2017","journal-title":"Biomed Eng Online"},{"key":"pgph.0006613.ref020","first-page":"293","article-title":"Risk Prediction with Machine Learning in Cesarean Section: Optimizing Healthcare Operational Decisions","volume-title":"Intelligent Systems Reference Library","author":"S Rahman","year":"2020"},{"key":"pgph.0006613.ref021","doi-asserted-by":"crossref","first-page":"321","DOI":"10.1613\/jair.953","article-title":"SMOTE: Synthetic Minority Over-sampling Technique","volume":"16","author":"NV Chawla","year":"2002","journal-title":"JAIR"},{"key":"pgph.0006613.ref022","unstructured":"Learning Avitm. https:\/\/r2d3.us\/visual-intro-to-machine-learning\/"},{"key":"pgph.0006613.ref023","unstructured":"S-l. Documentation. https:\/\/scikit-learn.org\/stable\/"},{"key":"pgph.0006613.ref024","article-title":"A unified approach to interpreting model predictions","volume":"30","author":"SM Lundberg","year":"2017","journal-title":"Advances in Neural Information Processing Systems"},{"key":"pgph.0006613.ref025","first-page":"292","article-title":"Guide to DHS statistics. Rockville:","volume":"645","author":"TN Croft","year":"2018","journal-title":"ICF"},{"issue":"3","key":"pgph.0006613.ref026","doi-asserted-by":"crossref","DOI":"10.1001\/jamanetworkopen.2023.5436","article-title":"Cesarean Delivery Uptake Trends Associated With Patient Features and Threshold for Labor Anomalies","volume":"6","author":"PI Cavoretto","year":"2023","journal-title":"JAMA Netw Open"}],"container-title":["PLOS Global Public Health"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pgph.0006613","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,26]],"date-time":"2026-06-26T17:24:18Z","timestamp":1782494658000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pgph.0006613"}},"subtitle":[],"editor":[{"given":"Karar Zunaid","family":"Ahsan","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2026,6,26]]},"references-count":26,"journal-issue":{"issue":"6","published-online":{"date-parts":[[2026,6,26]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pgph.0006613","relation":{},"ISSN":["2767-3375"],"issn-type":[{"value":"2767-3375","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,6,26]]}}}