{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,9]],"date-time":"2026-10-09T18:51:06Z","timestamp":1791571866689,"version":"4.3.4"},"reference-count":41,"publisher":"Wiley","issue":"4","license":[{"start":{"date-parts":[[2026,10,9]],"date-time":"2026-10-09T00:00:00Z","timestamp":1791504000000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"},{"start":{"date-parts":[[2026,10,9]],"date-time":"2026-10-09T00:00:00Z","timestamp":1791504000000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/doi.wiley.com\/10.1002\/tdm_license_1.1"}],"content-domain":{"domain":["onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["Public Health Challenges"],"published-print":{"date-parts":[[2026,12]]},"abstract":"<jats:title>ABSTRACT<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>Machine learning (ML) methods are increasingly used for health\u2010related prediction. This study compared logistic regression with five ML algorithms for predicting reported antibiotic treatment following recent fever\/cough among children under five using pooled Demographic and Health Survey (DHS) data.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>\n                      Data from 64 low\u2010 and middle\u2010income countries (LMICs) were analyzed. The final analytic sample included 183,425 children with recent fever\/cough, of whom 56,769 (30.95%) were reported to have received antibiotics. Logistic regression,\n                      <jats:italic>K<\/jats:italic>\n                      \u2010nearest neighbors (\n                      <jats:italic>K<\/jats:italic>\n                      NN), decision tree, random forest (RF), gradient boosting, and XGBoost were evaluated. The data were divided into model\u2010development and common heldout test samples, with 55,028 observations in the test set. Hyperparameters were selected using the same three stratified cross\u2010validation folds for all models, and Synthetic Minority Over\u2010sampling Technique for Nominal and Continuous (SMOTENC) was applied only within training folds. Model performance was assessed using ROC\u2010AUC, area under the precision\u2013recall curve (AUPRC), balanced accuracy, sensitivity, specificity, precision,\n                      <jats:italic>F<\/jats:italic>\n                      1 score, Matthews correlation coefficient (MCC), Brier score, and calibration measures. Primary classification results used a prespecified probability threshold of 0.50.\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>\n                      Overall predictive performance was modest. RF achieved the highest ROC\u2010AUC (0.568, 95% CI: 0.552\u20130.591), whereas\n                      <jats:italic>K<\/jats:italic>\n                      NN achieved the highest AUPRC (0.352, 95% CI: 0.308\u20130.401) and balanced accuracy (0.531, 95% CI: 0.526\u20130.536). At the 0.50 threshold, sensitivity was low across all models, ranging from 0.105 to 0.252, whereas specificity ranged from 0.810 to 0.910. Calibration was also limited, with calibration slopes ranging from 0.021 to 0.328. No model consistently performed best across all evaluation measures.\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusions<\/jats:title>\n                    <jats:p>\n                      ML models did not demonstrate clear overall superiority over logistic regression. Although RF and\n                      <jats:italic>K<\/jats:italic>\n                      NN performed better on selected measures, discrimination and calibration remained limited. ML may be useful as a complementary predictive approach, but stronger validation, additional predictors, and more complete consideration of the DHS complex survey design are needed before practical public\u2010health application.\n                    <\/jats:p>\n                  <\/jats:sec>","DOI":"10.1002\/puh2.70413","type":"journal-article","created":{"date-parts":[[2026,10,9]],"date-time":"2026-10-09T18:07:47Z","timestamp":1791569267000},"update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Comparison of Machine Learning Classifiers for Predicting Reported Antibiotic Treatment After Recent Fever\/Cough Among Under\u2010Five Children: A Pooled Analysis of DHS Data From 64 LMICs"],"prefix":"10.1002","volume":"5","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7216-0925","authenticated-orcid":false,"given":"Md Sabbir","family":"Hossain","sequence":"first","affiliation":[{"name":"Biostatistics, Epidemiology and Public Health Research Team Department of Statistics Shahjalal University of Science and Technology Sylhet Bangladesh"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Prosenjit Basak","family":"Arka","sequence":"additional","affiliation":[{"name":"Biostatistics, Epidemiology and Public Health Research Team Department of Statistics Shahjalal University of Science and Technology Sylhet Bangladesh"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Md Fakrul","family":"Islam","sequence":"additional","affiliation":[{"name":"Biostatistics, Epidemiology and Public Health Research Team Department of Statistics Shahjalal University of Science and Technology Sylhet Bangladesh"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mahfuzer","family":"Rohman","sequence":"additional","affiliation":[{"name":"Biostatistics, Epidemiology and Public Health Research Team Department of Statistics Shahjalal University of Science and Technology Sylhet Bangladesh"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8360-3274","authenticated-orcid":false,"given":"Md Jamal","family":"Uddin","sequence":"additional","affiliation":[{"name":"Biostatistics, Epidemiology and Public Health Research Team Department of Statistics Shahjalal University of Science and Technology Sylhet Bangladesh"},{"name":"Faculty of Graduate Studies Daffodil International University  Dhaka Bangladesh"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"311","published-online":{"date-parts":[[2026,10,9]]},"reference":[{"key":"e_1_2_12_2_1","doi-asserted-by":"crossref","unstructured":"U.Musa M. O.Adebiyi A. A.Adebiyi andA. A.Adebiyi \u201cDevelopment of a Machine Learning Model for Big Data Analytics \u201d inProceedings of the 2023 International Conference on Science Engineering and Business for Sustainable Development Goals SEB\u2010SDG 2023(IEEE 2023)https:\/\/doi.org\/10.1109\/SEB\u2010SDG57117.2023.10124592.","DOI":"10.1109\/SEB-SDG57117.2023.10124592"},{"key":"e_1_2_12_3_1","doi-asserted-by":"publisher","DOI":"10.2174\/1389202922666210705124359"},{"key":"e_1_2_12_4_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.artmed.2020.101822"},{"key":"e_1_2_12_5_1","doi-asserted-by":"crossref","DOI":"10.3389\/fmed.2024.1496869","article-title":"Comparison Between Traditional Logistic Regression and Machine Learning for Predicting Mortality in Adult Sepsis Patients","volume":"11","author":"Wu H.","year":"2025","journal-title":"Frontiers in Medicine"},{"issue":"3","key":"e_1_2_12_6_1","first-page":"451","article-title":"A Review on Machine Learning Techniques","volume":"4","author":"Sandhya N. D.","year":"2016","journal-title":"International Journal on Recent and Innovation Trends in Computing and Communication"},{"key":"e_1_2_12_7_1","doi-asserted-by":"publisher","DOI":"10.20544\/HORIZONS.B.04.1.17.P05"},{"key":"e_1_2_12_8_1","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/btab681"},{"key":"e_1_2_12_9_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.sjbs.2022.02.047"},{"issue":"4","key":"e_1_2_12_10_1","doi-asserted-by":"crossref","first-page":"e00211","DOI":"10.1128\/mSystems.00211-19","article-title":"Identification of Primary Antimicrobial Resistance Drivers in Agricultural Nontyphoidal Salmonella enterica Serovars by Using Machine Learning","volume":"4","author":"Maguire F.","year":"2019","journal-title":"mSystems"},{"key":"e_1_2_12_11_1","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/bty276"},{"key":"e_1_2_12_12_1","doi-asserted-by":"publisher","DOI":"10.15252\/emmm.201910264"},{"key":"e_1_2_12_13_1","doi-asserted-by":"crossref","unstructured":"Ribers MA Ullrich H. \u201cBattling Antibiotic Resistance: Can Machine Learning Improve Prescribing?\u201d CESifo Working Paper No. 7654 2019.https:\/\/doi.org\/10.2139\/ssrn.3422235.","DOI":"10.2139\/ssrn.3422235"},{"key":"e_1_2_12_14_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jiph.2016.08.007"},{"key":"e_1_2_12_15_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.eclinm.2023.102055"},{"key":"e_1_2_12_16_1","doi-asserted-by":"crossref","unstructured":"English BK Gaur AH. The use and abuse of antibiotics and the development of antibiotic resistance. Adv Exp Med Biol. 2010;659:73\u201382. doi:10.1007\/978\u20101\u20104419\u20100981\u20107_6.","DOI":"10.1007\/978-1-4419-0981-7_6"},{"key":"e_1_2_12_17_1","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1717295115"},{"key":"e_1_2_12_18_1","doi-asserted-by":"publisher","DOI":"10.1111\/j.1651-2227.2009.01309.x"},{"key":"e_1_2_12_19_1","doi-asserted-by":"publisher","DOI":"10.1016\/S1473-3099(19)30572-9"},{"key":"e_1_2_12_20_1","doi-asserted-by":"publisher","DOI":"10.1016\/S2542-5196(21)00280-1"},{"issue":"1","key":"e_1_2_12_21_1","doi-asserted-by":"crossref","first-page":"37","DOI":"10.1186\/s12875-017-0619-z","article-title":"Antibiotic Overuse for Acute Respiratory Tract Infections in Sri Lanka: A Qualitative Study of Outpatients and Their Physicians","volume":"18","author":"Tillekeratne L. G.","year":"2017","journal-title":"BMC Family Practice [Electronic Resource]"},{"key":"e_1_2_12_22_1","doi-asserted-by":"publisher","DOI":"10.1002\/9781118548387"},{"key":"e_1_2_12_23_1","doi-asserted-by":"publisher","DOI":"10.1177\/117693510600200030"},{"key":"e_1_2_12_24_1","doi-asserted-by":"publisher","DOI":"10.1023\/A:1010933404324"},{"key":"e_1_2_12_25_1","doi-asserted-by":"publisher","DOI":"10.1145\/3236386.3241340"},{"key":"e_1_2_12_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.1967.1053964"},{"key":"e_1_2_12_27_1","first-page":"771","article-title":"A Short Introduction to Boosting","volume":"14","author":"Freund Y.","year":"1999","journal-title":"Journal of Japanese Society for Artificial Intelligence"},{"key":"e_1_2_12_28_1","doi-asserted-by":"publisher","DOI":"10.1214\/aos\/1013203451"},{"key":"e_1_2_12_29_1","doi-asserted-by":"publisher","DOI":"10.1016\/S0167-9473(01)00065-2"},{"key":"e_1_2_12_30_1","doi-asserted-by":"crossref","unstructured":"T.ChenandC.Guestrin \u201cXGBoost: A Scalable Tree Boosting System\u201d inProceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining(ACM 2016) https:\/\/doi.org\/10.1145\/2939672.2939785.","DOI":"10.1145\/2939672.2939785"},{"key":"e_1_2_12_31_1","doi-asserted-by":"publisher","DOI":"10.1201\/9781315139470"},{"key":"e_1_2_12_32_1","doi-asserted-by":"crossref","DOI":"10.1007\/978-981-33-4604-8","volume-title":"Applications of Artificial Intelligence in Engineering","author":"Gao X.\u2010Z.","year":"2021"},{"key":"e_1_2_12_33_1","doi-asserted-by":"publisher","DOI":"10.1016\/S0893-6080(01)00111-3"},{"key":"e_1_2_12_34_1","doi-asserted-by":"crossref","first-page":"123347","DOI":"10.1109\/ACCESS.2020.3006710","article-title":"Machine Learning Methods for Neonatal Mortality and Morbidity Classification","volume":"8","author":"Jaskari J.","year":"2020","journal-title":"IEEE Access"},{"key":"e_1_2_12_35_1","doi-asserted-by":"publisher","DOI":"10.1111\/tmi.13540"},{"key":"e_1_2_12_36_1","doi-asserted-by":"crossref","first-page":"1153","DOI":"10.3390\/antibiotics10101153","article-title":"Antibiotic Use for Febrile Illness Among Under\u20105 Children in Bangladesh: A Nationally Representative Sample Survey","volume":"10","author":"Samir N.","year":"2021","journal-title":"Antibiotics"},{"key":"e_1_2_12_37_1","doi-asserted-by":"crossref","first-page":"388","DOI":"10.1186\/s12884-022-04699-8","article-title":"Application of Machine Learning Methods for Predicting Infant Mortality in Rwanda: Analysis of Rwanda Demographic Health Survey 2014\u201315 Dataset","volume":"22","author":"Mfateneza E.","year":"2022","journal-title":"BMC Pregnancy Childbirth"},{"key":"e_1_2_12_38_1","doi-asserted-by":"crossref","unstructured":"J.Miah M.Mamun M. M.Rahman M. I.Mahmud S.Ahmad andM. H. B.Nasir \u201cMHfit: Mobile Health Data for Predicting Athletics Fitness Using Machine Learning Models \u201d inProceedings of the 2022 2nd International Seminar on Machine Learning Optimization and Data Science (ISMODE)(IEEE 2022) https:\/\/doi.org\/10.1109\/ISMODE56940.2022.10180967.","DOI":"10.1109\/ISMODE56940.2022.10180967"},{"key":"e_1_2_12_39_1","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0277738"},{"key":"e_1_2_12_40_1","first-page":"94","volume-title":"Artificial Intelligence Trends in Systems. CSOC 2022. Lecture Notes in Networks and Systems","author":"Mbunge E.","year":"2022"},{"key":"e_1_2_12_41_1","doi-asserted-by":"crossref","first-page":"338","DOI":"10.1186\/s12879-024-09195-2","article-title":"Empowering Child Health: Harnessing Machine Learning to Predict Acute Respiratory Infections in Ethiopian Under\u2010Fives Using Demographic and Health Survey Insights","volume":"24","author":"Kalayou M. H.","year":"2024","journal-title":"BMC Infectious Diseases"},{"key":"e_1_2_12_42_1","doi-asserted-by":"publisher","DOI":"10.1063\/5.0203746"}],"container-title":["Public Health Challenges"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/puh2.70413","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/full-xml\/10.1002\/puh2.70413","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/puh2.70413","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,10,9]],"date-time":"2026-10-09T18:07:51Z","timestamp":1791569271000},"score":1,"resource":{"primary":{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/10.1002\/puh2.70413"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,10,9]]},"references-count":41,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2026,12]]}},"alternative-id":["10.1002\/puh2.70413"],"URL":"https:\/\/doi.org\/10.1002\/puh2.70413","archive":["Portico"],"relation":{},"ISSN":["2769-2450","2769-2450"],"issn-type":[{"value":"2769-2450","type":"print"},{"value":"2769-2450","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,10,9]]},"assertion":[{"value":"2026-06-01","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-09-27","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-10-09","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"e70413"}}