{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,9]],"date-time":"2026-10-09T18:53:12Z","timestamp":1791571992713,"version":"4.3.4"},"reference-count":25,"publisher":"Walter de Gruyter GmbH","funder":[{"DOI":"10.13039\/100000865","name":"Bill and Melinda Gates Foundation","doi-asserted-by":"publisher","award":["INV-044317"],"award-info":[{"award-number":["INV-044317"]}],"id":[{"id":"10.13039\/100000865","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000002","name":"NIH\/NIAID","doi-asserted-by":"publisher","award":["R01AI185140"],"award-info":[{"award-number":["R01AI185140"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>Acute diarrheal disease is a leading cause of death in children under age 5, disproportionately impacting children in low-resource settings. Although many cases could respond to antibiotic treatment, the benefits of widely prescribing antibiotics must be weighed against the risks of antimicrobial resistance. These challenges motivate development of individualized treatment guidelines for diarrheal disease. In this study, we utilize a framework for creation and evaluation of individualized treatment rules that leverage diagnostic and clinical information to make treatment recommendations. In contrast to many applications of pipelines for creating and evaluating treatment rules, we (i) explicitly create rules that limit the proportion of children treated based on expected clinical benefit, to limit risks for overtreatment and the emergence of antimicrobial resistance, and (ii) propose methods to compare rules based on different sets of input covariates, allowing for quantification of the impact of measuring additional biomarkers in clinical settings. We use a nested cross-validation procedure with ensemble machine learning and doubly-robust estimation to derive, evaluate, and compare rules. We demonstrate that our proposed method yields appropriate inference in a realistic simulation study and apply our method to data from the AntiBiotics for Children with severe Diarrhea (ABCD) trial.<\/jats:p>","DOI":"10.1515\/ijb-2026-0026","type":"journal-article","created":{"date-parts":[[2026,10,9]],"date-time":"2026-10-09T16:28:55Z","timestamp":1791563335000},"source":"Crossref","is-referenced-by-count":0,"title":["Machine learning for\u00a0estimating and\u00a0comparing clinical rules for\u00a0treating diarrheal illness with\u00a0antibiotics"],"prefix":"10.1515","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6562-607X","authenticated-orcid":false,"given":"Allison","family":"Codi","sequence":"first","affiliation":[{"name":"Department of Biostatistics and Bioinformatics , Emory University , 1518 Clifton Rd NE , Atlanta , GA , 30322 , USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sara","family":"Kim","sequence":"additional","affiliation":[{"name":"Department of Epidemiology , Emory University , 1518 Clifton Rd NE , Atlanta , GA , 30322 , USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Elizabeth","family":"Rogawski McQuade","sequence":"additional","affiliation":[{"name":"Department of Epidemiology , Emory University , 1518 Clifton Rd NE , Atlanta , GA , 30322 , USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1019-8343","authenticated-orcid":false,"given":"David","family":"Benkeser","sequence":"additional","affiliation":[{"name":"Department of Biostatistics and Bioinformatics , Emory University , 1518 Clifton Rd NE , Atlanta , GA , 30322 , USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"374","published-online":{"date-parts":[[2026,10,9]]},"reference":[{"key":"2026100918224753190_j_ijb-2026-0026_ref_001","doi-asserted-by":"crossref","unstructured":"Troeger, C, Blacker, BF, Khalil, IA, Rao, PC, Cao, SA, Zimsen, SR, et al.. Estimates of the global, regional, and national morbidity, mortality, and aetiologies of diarrhoea in 195 countries: a systematic analysis for the global burden of disease study 2016. Lancet Infect Dis 2018;18:1211\u201328. https:\/\/doi.org\/10.1016\/s1473-3099(18)30362-1.","DOI":"10.1016\/S1473-3099(18)30362-1"},{"key":"2026100918224753190_j_ijb-2026-0026_ref_002","unstructured":"Pavlinac, PB, Platts-Mills, JA, Liu, J, Atlas, HE, Gratz, J, Operario, D, et al.. Azithromycin for bacterial watery diarrhea: a reanalysis of the antibiotics for children with severe diarrhea (abcd) trial incorporating molecular diagnostics. J Infect Dis 2023:jiad252. https:\/\/academic.oup.com\/jid\/advance-Article\/doi\/10.1093\/infdis\/jiad252\/7219578."},{"key":"2026100918224753190_j_ijb-2026-0026_ref_003","doi-asserted-by":"crossref","unstructured":"Richard, SA, Black, RE, Gilman, RH, Guerrant, RL, Kang, G, Lanata, CF, et al.. Diarrhea in early childhood: short-term association with weight and long-term association with length. Am J Epidemiol 2013;178:1129\u201338. https:\/\/doi.org\/10.1093\/aje\/kwt094. https:\/\/www.ncbi.nlm.nih.gov\/pmc\/Articles\/PMC3783094\/.","DOI":"10.1093\/aje\/kwt094"},{"key":"2026100918224753190_j_ijb-2026-0026_ref_004","doi-asserted-by":"crossref","unstructured":"Houpt, ER, Ferdous, T, Ara, R, Ibrahim, M, Alam, MM, Kabir, M, et al.. Clinical outcomes of drug-resistant shigellosis treated with azithromycin in Bangladesh. Clin Infect Dis 2021;72:1793\u20138. https:\/\/doi.org\/10.1093\/cid\/ciaa363.","DOI":"10.1093\/cid\/ciaa363"},{"key":"2026100918224753190_j_ijb-2026-0026_ref_005","unstructured":"Nie, X, Wager, S. Learning objectives for treatment effect estimation. arXiv:1712.04912. 2017. http:\/\/arxiv.org\/abs\/1712.04912."},{"key":"2026100918224753190_j_ijb-2026-0026_ref_006","doi-asserted-by":"crossref","unstructured":"K\u00fcnzel, SR, Sekhon, JS, Bickel, PJ, Yu, B. Metalearners for estimating heterogeneous treatment effects using machine learning. Proc Natl Acad Sci 2019;116:4156\u201365. https:\/\/doi.org\/10.1073\/pnas.1804597116.","DOI":"10.1073\/pnas.1804597116"},{"key":"2026100918224753190_j_ijb-2026-0026_ref_011","unstructured":"Kennedy, EH. Towards optimal doubly robust estimation of heterogeneous causal effects. arXiv:2004.14497 [math, stat] 2023. http:\/\/arxiv.org\/abs\/2004.14497."},{"key":"2026100918224753190_j_ijb-2026-0026_ref_008","doi-asserted-by":"crossref","unstructured":"Athey, S, Imbens, G. Recursive partitioning for heterogeneous causal effects. Proc Natl Acad Sci 2016;113:7353\u201360. https:\/\/doi.org\/10.1073\/pnas.1510489113.","DOI":"10.1073\/pnas.1510489113"},{"key":"2026100918224753190_j_ijb-2026-0026_ref_009","doi-asserted-by":"crossref","unstructured":"Wager, S, Athey, S. Estimation and inference of heterogeneous treatment effects using random forests. J Am Stat Assoc 2018;113:1228\u201342. https:\/\/doi.org\/10.1080\/01621459.2017.1319839.","DOI":"10.1080\/01621459.2017.1319839"},{"key":"2026100918224753190_j_ijb-2026-0026_ref_010","doi-asserted-by":"crossref","unstructured":"Nizam, S, Codi, A, Rogawski McQuade, E, Benkeser, D. Highly adaptive lasso for estimation of heterogeneous treatment effects and treatment recommendation. J Causal Inference 2025;13:20230085. https:\/\/doi.org\/10.1515\/jci-2023-0085.","DOI":"10.1515\/jci-2023-0085"},{"key":"2026100918224753190_j_ijb-2026-0026_ref_012","doi-asserted-by":"crossref","unstructured":"van der Laan, M, Polley, E, Hubbard, A. Super learner. Stat Appl Genet Mol Biol 2007;6. https:\/\/doi.org\/10.2202\/1544-6115.1309.","DOI":"10.2202\/1544-6115.1309"},{"key":"2026100918224753190_j_ijb-2026-0026_ref_013","doi-asserted-by":"crossref","unstructured":"Luedtke, AR, Laan, MJVD. Super-learning of an optimal dynamic treatment rule. Int J Biostat 2016b;12:305. https:\/\/doi.org\/10.1515\/ijb-2015-0052. https:\/\/www.ncbi.nlm.nih.gov\/pmc\/Articles\/PMC6056197\/.","DOI":"10.1515\/ijb-2015-0052"},{"key":"2026100918224753190_j_ijb-2026-0026_ref_014","doi-asserted-by":"crossref","unstructured":"Montoya, LM, van der Laan, MJ, Luedtke, AR, Skeem, JL, Coyle, JR, Petersen, ML. The optimal dynamic treatment rule superlearner: considerations, performance, and application to criminal justice interventions. Int J Biostat 2023;19:217\u201338. https:\/\/doi.org\/10.1515\/ijb-2020-0127.","DOI":"10.1515\/ijb-2020-0127"},{"key":"2026100918224753190_j_ijb-2026-0026_ref_015","doi-asserted-by":"crossref","unstructured":"Kim, SS, Codi, A, Platts-Mills, JA, Pavlinac, PB, Manji, K, Sudfeld, CR, et al.. Personalized azithromycin treatment rules for children with watery diarrhea using machine learning. Nat Commun 2025;16:5968. Publisher: Nature Publishing Group. https:\/\/doi.org\/10.1038\/s41467-025-60682-9.","DOI":"10.1038\/s41467-025-60682-9"},{"key":"2026100918224753190_j_ijb-2026-0026_ref_016","unstructured":"Codi, A. Drotr: doubly-robust methods for optimal treatment rules. R package version 0.1.0 2024. https:\/\/github.com\/allicodi\/drotr."},{"key":"2026100918224753190_j_ijb-2026-0026_ref_017","doi-asserted-by":"crossref","unstructured":"The Antibiotics for Children With Diarrhea (ABCD) Study Group, Ahmed, T, Chisti, MJ, Rahman, MW, Alam, TA, Parvin, I, et al.. Effect of 3 days of oral azithromycin on young children with acute diarrhea in low-resource settings: a randomized clinical trial. JAMA Netw Open 2021;4:e2136726. https:\/\/doi.org\/10.1001\/jamanetworkopen.2021.36726.","DOI":"10.1001\/jamanetworkopen.2021.36726"},{"key":"2026100918224753190_j_ijb-2026-0026_ref_018","doi-asserted-by":"crossref","unstructured":"Luedke, AR, van der Laan, MJ. Optimal individualized treatments in resource-limited settings. Int J Biostat 2016.","DOI":"10.1515\/ijb-2015-0007"},{"key":"2026100918224753190_j_ijb-2026-0026_ref_019","doi-asserted-by":"crossref","unstructured":"Hubbard, AE, Kherad-Pajouh, S, Laan, MJvD. Statistical inference for data adaptive target parameters. Int J Biostat 2016;12:3\u201319. https:\/\/doi.org\/10.1515\/ijb-2015-0013.","DOI":"10.1515\/ijb-2015-0013"},{"key":"2026100918224753190_j_ijb-2026-0026_ref_020","doi-asserted-by":"crossref","unstructured":"Luedtke, AR, Laan, MJD. Statistical inference for the mean outcome under a possibly non-unique optimal treatment strategy. Ann Stat 2016a;44:713\u201342. Publisher: Institute of Mathematical Statistics. https:\/\/projecteuclid.org\/journals\/annals-of-statistics\/volume-44\/issue-2\/Statistical-inference-for-the-mean-outcome-under-a-possibly-non\/10.1214\/15-AOS1384.full.","DOI":"10.1214\/15-AOS1384"},{"key":"2026100918224753190_j_ijb-2026-0026_ref_021","doi-asserted-by":"crossref","unstructured":"Pfanzagl, J. Contributions to a general asymptotic statistical theory, lecture notes in statistics, 1 edn. New York, NY: Springer; 1982.","DOI":"10.1007\/978-1-4612-5769-1_1"},{"key":"2026100918224753190_j_ijb-2026-0026_ref_022","doi-asserted-by":"crossref","unstructured":"Chernozhukov, V, Chetverikov, D, Demirer, M, Duflo, E, Hansen, C, Newey, W, et al.. Double\/debiased machine learning for treatment and structural parameters. Econom J 2018;21:C1\u201368. https:\/\/doi.org\/10.1111\/ectj.12097.","DOI":"10.1111\/ectj.12097"},{"key":"2026100918224753190_j_ijb-2026-0026_ref_023","unstructured":"Polley, E, LeDell, E, Kennedy, C, van der Laan, M. SuperLearner: super learner prediction. R package version 2024;2:0\u201329. https:\/\/CRAN.R-project.org\/package=SuperLearner."},{"key":"2026100918224753190_j_ijb-2026-0026_ref_024","doi-asserted-by":"crossref","unstructured":"Anderson, JD, Bagamian, KH, Pecenka, CJ, Muhib, F, Puett, CA, Hausdorff, WP, et al.. Potential impact and cost-effectiveness of Shigella vaccination in 102 low-income and middle-income countries in children aged 5 years or younger: a modelling study. Lancet Global Health 2023;11:e880\u201391. https:\/\/doi.org\/10.1016\/s2214-109x(23)00192-4.","DOI":"10.1016\/S2214-109X(23)00192-4"},{"key":"2026100918224753190_j_ijb-2026-0026_ref_025","doi-asserted-by":"crossref","unstructured":"Schader, L, Song, W, Kempker, R, Benkeser, D. Don\u2019t let your analysis go to seed: on the impact of random seed on machine learning-based causal inference. Epidemiology 2024;35:764\u201378. https:\/\/doi.org\/10.1097\/ede.0000000000001782.","DOI":"10.1097\/EDE.0000000000001782"},{"key":"2026100918224753190_j_ijb-2026-0026_ref_026","doi-asserted-by":"crossref","unstructured":"Lei, L, Cand\u00e8s, EJ. Conformal inference of counterfactuals and individual treatment effects. J Roy Stat Soc B Stat Methodol 2021;83:911\u201338. https:\/\/doi.org\/10.1111\/rssb.12445.","DOI":"10.1111\/rssb.12445"}],"container-title":["The International Journal of Biostatistics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.degruyterbrill.com\/document\/doi\/10.1515\/ijb-2026-0026\/xml","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.degruyterbrill.com\/document\/doi\/10.1515\/ijb-2026-0026\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,10,9]],"date-time":"2026-10-09T18:22:55Z","timestamp":1791570175000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.degruyterbrill.com\/document\/doi\/10.1515\/ijb-2026-0026\/html"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,10,9]]},"references-count":25,"alternative-id":["10.1515\/ijb-2026-0026"],"URL":"https:\/\/doi.org\/10.1515\/ijb-2026-0026","relation":{},"ISSN":["2194-573X","1557-4679"],"issn-type":[{"value":"2194-573X","type":"print"},{"value":"1557-4679","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,10,9]]}}}