{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,8]],"date-time":"2026-02-08T03:34:35Z","timestamp":1770521675233,"version":"3.49.0"},"reference-count":31,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2026,1,26]],"date-time":"2026-01-26T00:00:00Z","timestamp":1769385600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2026,2,7]],"date-time":"2026-02-07T00:00:00Z","timestamp":1770422400000},"content-version":"vor","delay-in-days":12,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/100010269","name":"Wellcome Trust","doi-asserted-by":"publisher","award":["226691\/Z\/22\/Z"],"award-info":[{"award-number":["226691\/Z\/22\/Z"]}],"id":[{"id":"10.13039\/100010269","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100010269","name":"Wellcome Trust","doi-asserted-by":"publisher","award":["226691\/Z\/22\/Z"],"award-info":[{"award-number":["226691\/Z\/22\/Z"]}],"id":[{"id":"10.13039\/100010269","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100010269","name":"Wellcome Trust","doi-asserted-by":"publisher","award":["226691\/Z\/22\/Z"],"award-info":[{"award-number":["226691\/Z\/22\/Z"]}],"id":[{"id":"10.13039\/100010269","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100010269","name":"Wellcome Trust","doi-asserted-by":"publisher","award":["226691\/Z\/22\/Z"],"award-info":[{"award-number":["226691\/Z\/22\/Z"]}],"id":[{"id":"10.13039\/100010269","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["npj Digit. Med."],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>\n                    Predicting antibiotic treatment outcomes could help tackle antibiotic resistance by guiding prescribing decisions. Existing approaches do not quantitatively incorporate the judgment of clinician users. Our antibiotic decision-making algorithm predicted treatment outcomes for 13 antibiotics using clinical prediction models trained on prescribing and urine culture data from 93,906 patients, then weighted outcomes using treatment decisions made by 49 clinicians in an antibiotic choice ranking exercise. In a simulation using Emergency Department data, the algorithm chose more correctly-targeted World Health Organization Access category antibiotics (75.6% of cases versus 11.9%, 95% confidence interval of difference 57.6% to 69.7%,\n                    <jats:italic>p<\/jats:italic>\n                    \u2009&lt;\u20090.001) and oral antibiotics (69% versus 22.6%, 95% confidence interval of difference 39.5% to 53.4%,\n                    <jats:italic>p<\/jats:italic>\n                    \u2009&lt;\u20090.001) than human prescribers, and fewer intravenous antibiotics (31.2% versus 65.8%, 95% confidence interval of difference \u221241.9% to \u221227.1%,\n                    <jats:italic>p<\/jats:italic>\n                    \u2009&lt;\u20090.001). These results show that our algorithm could improve antibiotic prescribing decisions by combining human judgment with data-driven probability predictions.\n                  <\/jats:p>","DOI":"10.1038\/s41746-026-02369-z","type":"journal-article","created":{"date-parts":[[2026,1,26]],"date-time":"2026-01-26T11:53:40Z","timestamp":1769428420000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Algorithmic antibiotic decision-making in urinary tract infection using prescriber-informed prediction of treatment utility"],"prefix":"10.1038","volume":"9","author":[{"given":"Alex","family":"Howard","sequence":"first","affiliation":[]},{"given":"Peter L.","family":"Green","sequence":"additional","affiliation":[]},{"given":"Yinzheng","family":"Zhong","sequence":"additional","affiliation":[]},{"given":"David M.","family":"Hughes","sequence":"additional","affiliation":[]},{"given":"Alessandro","family":"Gerada","sequence":"additional","affiliation":[]},{"given":"Simon","family":"Maskell","sequence":"additional","affiliation":[]},{"given":"Anoop","family":"Velluva","sequence":"additional","affiliation":[]},{"given":"Iain E.","family":"Buchan","sequence":"additional","affiliation":[]},{"given":"William","family":"Hope","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2026,1,26]]},"reference":[{"key":"2369_CR1","doi-asserted-by":"publisher","first-page":"e1004264","DOI":"10.1371\/journal.pmed.1004264","volume":"20","author":"TR Walsh","year":"2023","unstructured":"Walsh, T. R., Gales, A. C., Laxminarayan, R. & Dodd, P. C. Antimicrobial resistance: addressing a global threat to humanity. PLOS Med. 20, e1004264 (2023).","journal-title":"PLOS Med."},{"key":"2369_CR2","unstructured":"United Nations General Assembly. Political declaration on antimicrobial resistance. (The United Nations, 2024)."},{"key":"2369_CR3","doi-asserted-by":"publisher","first-page":"e2418923","DOI":"10.1001\/jamanetworkopen.2024.18923","volume":"7","author":"C Rhee","year":"2024","unstructured":"Rhee, C. et al. Trends in empiric broad-spectrum antibiotic use for suspected community-onset sepsis in US Hospitals. JAMA Network Open 7, e2418923 (2024).","journal-title":"JAMA Network Open"},{"key":"2369_CR4","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/s43856-022-00094-8","volume":"2","author":"CK Corbin","year":"2022","unstructured":"Corbin, C. K. et al. Personalized antibiograms for machine learning driven antibiotic selection. Commun. Med. 2, 1\u201314 (2022).","journal-title":"Commun. Med."},{"key":"2369_CR5","doi-asserted-by":"publisher","first-page":"21","DOI":"10.1007\/s13347-024-00705-3","volume":"37","author":"D Stader","year":"2024","unstructured":"Stader, D. Algorithms don\u2019t have a future: on the relation of judgement and calculation. Philos. Technol. 37, 21 (2024).","journal-title":"Philos. Technol."},{"key":"2369_CR6","doi-asserted-by":"publisher","unstructured":"Walsh, W. E., Tesauro, G., Kephart, J. O. & Das, R. Utility functions in autonomic systems. In International Conference on Autonomic Computing, 2004. Proceedings. 70\u201377, https:\/\/doi.org\/10.1109\/ICAC.2004.1301349 (IEEE, 2004).","DOI":"10.1109\/ICAC.2004.1301349"},{"key":"2369_CR7","doi-asserted-by":"publisher","unstructured":"Johnson, A. et al. MIMIC-IV (version 2.2). https:\/\/doi.org\/10.13026\/6mm1-ek67. (2023)","DOI":"10.13026\/6mm1-ek67"},{"key":"2369_CR8","doi-asserted-by":"crossref","unstructured":"Johnson, A. E. W. et al. MIMIC-IV, a freely accessible electronic health record dataset. Sci. Data 10, 1 (2023).","DOI":"10.1038\/s41597-023-01945-2"},{"key":"2369_CR9","doi-asserted-by":"crossref","unstructured":"Goldberger, A. L. et al. PhysioBank, PhysioToolkit, and PhysioNet: Components of a New Research Resource for Complex Physiologic Signals. Circulation 101, (2000).","DOI":"10.1161\/01.CIR.101.23.e215"},{"key":"2369_CR10","doi-asserted-by":"publisher","first-page":"3141","DOI":"10.2169\/internalmedicine.4664-20","volume":"59","author":"P Li","year":"2020","unstructured":"Li, P., Cheng, Z. Y. & Liu, G. L. Availability bias causes misdiagnoses by physicians: Direct evidence from a randomized controlled trial. Intern. Med. 59, 3141\u20133146 (2020).","journal-title":"Intern. Med."},{"key":"2369_CR11","doi-asserted-by":"publisher","first-page":"1330","DOI":"10.1164\/rccm.202109-2092OC","volume":"205","author":"NC Dean","year":"2022","unstructured":"Dean, N. C. et al. A pragmatic, stepped\u2011wedge, cluster\u2011controlled clinical trial of real\u2011time pneumonia clinical decision support. Am. J. Respir. Critic. Care Med. 205, 1330\u20131336 (2022).","journal-title":"Am. J. Respir. Critic. Care Med."},{"key":"2369_CR12","doi-asserted-by":"publisher","DOI":"10.1038\/s41746-024-01400-5","volume":"8","author":"S Shapiro Ben David","year":"2025","unstructured":"Shapiro Ben David, S. et al. AI driven decision support reduces antibiotic mismatches and inappropriate use in outpatient urinary tract infections. npj Digit. Med. 8, 61 (2025).","journal-title":"npj Digit. Med."},{"key":"2369_CR13","doi-asserted-by":"publisher","first-page":"1493","DOI":"10.1016\/S1473-3099(22)00308-5","volume":"22","author":"G Catho","year":"2022","unstructured":"Catho, G. et al. Impact of interactive computerised decision support for hospital antibiotic use (COMPASS): an open-label, cluster-randomised trial in three swiss hospitals. Lancet Infect. Dis. 22, 1493\u20131502 (2022).","journal-title":"Lancet Infect. Dis."},{"key":"2369_CR14","doi-asserted-by":"publisher","first-page":"1238","DOI":"10.1093\/jac\/dkl372","volume":"58","author":"M Paul","year":"2006","unstructured":"Paul, M. et al. Improving empirical antibiotic treatment using TREAT, a computerized decision support system: cluster randomized trial. J. Antimicrob. Chemother. 58, 1238\u20131245 (2006).","journal-title":"J. Antimicrob. Chemother."},{"key":"2369_CR15","unstructured":"R. Core Team. R: A Language and Environment for Statistical Computing. (R Foundation for Statistical Computing, 2021)."},{"key":"2369_CR16","doi-asserted-by":"publisher","unstructured":"Avoiding Overfitting of Decision Trees. in Principles of Data Mining (ed. Bramer, M.) 119\u2013134. https:\/\/doi.org\/10.1007\/978-1-84628-766-4_8, (Springer, London, 2007)","DOI":"10.1007\/978-1-84628-766-4_8"},{"key":"2369_CR17","unstructured":"U.S. Department of Veterans Affairs (2025) VA National Acquisition Center (NAC) vendor portal https:\/\/www.vendorportal.ecms.va.gov\/nac (Accessed 21 Jan 2025)."},{"key":"2369_CR18","doi-asserted-by":"publisher","first-page":"3384","DOI":"10.1093\/jac\/dkz321","volume":"74","author":"E Budd","year":"2019","unstructured":"Budd, E. et al. Adaptation of the WHO Essential Medicines List for national antibiotic stewardship policy in England: Being AWaRe. J. Antimicrob. Chemother. 74, 3384\u20133389 (2019).","journal-title":"J. Antimicrob. Chemother."},{"key":"2369_CR19","doi-asserted-by":"publisher","first-page":"e078378","DOI":"10.1136\/bmj-2023-078378","volume":"385","author":"GS Collins","year":"2024","unstructured":"Collins, G. S. et al. TRIPOD+AI statement: updated guidance for reporting clinical prediction models that use regression or machine learning methods. BMJ 385, e078378 (2024).","journal-title":"BMJ"},{"key":"2369_CR20","doi-asserted-by":"publisher","first-page":"147","DOI":"10.1089\/sur.2017.282","volume":"19","author":"SA Buckman","year":"2018","unstructured":"Buckman, S. A., Turnbull, I. R. & Mazuski, J. E. Empiric antibiotics for sepsis. Surg. Infect. 19, 147\u2013154 (2018).","journal-title":"Surg. Infect."},{"key":"2369_CR21","unstructured":"British National Formulary Joint Formulary Committee (2025) Appendix 1 interactions. https:\/\/bnf.nice.org.uk\/interactions\/appendix-1-interactions\/ (Accessed 21 Jan 2025)."},{"key":"2369_CR22","doi-asserted-by":"publisher","first-page":"4304","DOI":"10.1111\/bcp.14847","volume":"87","author":"X Kong","year":"2021","unstructured":"Kong, X., Guo, D., Liu, S., Zhu, Y. & Yu, C. Incidence, characteristics and risk factors for drug-induced liver injury in hospitalized patients: a matched case-control study. Br. J. Clin. Pharmacol. 87, 4304\u20134312 (2021).","journal-title":"Br. J. Clin. Pharmacol."},{"key":"2369_CR23","doi-asserted-by":"publisher","first-page":"1308","DOI":"10.1001\/jamainternmed.2017.1938","volume":"177","author":"PD Tamma","year":"2017","unstructured":"Tamma, P. D., Avdic, E., Li, D. X., Dzintars, K. & Cosgrove, S. E. Association of adverse events with antibiotic use in hospitalized patients. JAMA Intern. Med. 177, 1308\u20131315 (2017).","journal-title":"JAMA Intern. Med."},{"key":"2369_CR24","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-024-54192-3","volume":"15","author":"A Howard","year":"2024","unstructured":"Howard, A. et al. Personalised antimicrobial susceptibility testing with clinical prediction modelling informs appropriate antibiotic use. Nat. Commun. 15, 9924 (2024).","journal-title":"Nat. Commun."},{"key":"2369_CR25","doi-asserted-by":"publisher","unstructured":"Chen, T. et al. Xgboost: Extreme Gradient Boosting. 1.7.8.1 https:\/\/doi.org\/10.32614\/CRAN.package.xgboost (2014).","DOI":"10.32614\/CRAN.package.xgboost"},{"key":"2369_CR26","doi-asserted-by":"publisher","unstructured":"Chen, T. & Guestrin, C. XGBoost: A scalable tree boosting system. In Proc. 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining 785\u2013794. https:\/\/doi.org\/10.1145\/2939672.2939785, (Association for Computing Machinery, 2016)","DOI":"10.1145\/2939672.2939785"},{"key":"2369_CR27","doi-asserted-by":"crossref","unstructured":"Winter, E. The shapley value. Handbook of Game Theory with Economic Applications. 3, 2025\u20132054 (2002).","DOI":"10.1016\/S1574-0005(02)03016-3"},{"key":"2369_CR28","doi-asserted-by":"publisher","first-page":"1","DOI":"10.18637\/jss.v095.i11","volume":"95","author":"Y Croissant","year":"2020","unstructured":"Croissant, Y. Estimation of Random Utility Models in R: The mlogit Package. J. Stat. Softw. 95, 1\u201341 (2020).","journal-title":"J. Stat. Softw."},{"key":"2369_CR29","doi-asserted-by":"publisher","first-page":"501","DOI":"10.1007\/s10107-012-0522-2","volume":"138","author":"Y-H Dai","year":"2013","unstructured":"Dai, Y.-H. A perfect example for the BFGS method. Math. Program. 138, 501\u2013530 (2013).","journal-title":"Math. Program."},{"key":"2369_CR30","doi-asserted-by":"publisher","first-page":"10","DOI":"10.1177\/0272989X10369005","volume":"31","author":"CM Rutter","year":"2011","unstructured":"Rutter, C. M., Zaslavsky, A. M. & Feuer, E. J. Dynamic microsimulation models for health outcomes: A review. Med. Decision Mak. 31, 10\u201318 (2011).","journal-title":"Med. Decision Mak."},{"key":"2369_CR31","doi-asserted-by":"crossref","unstructured":"Kranz, J. et al. European association of urology guidelines on urological infections: summary of the 2024 guidelines. European Urology. 86, 27-41 (2024).","DOI":"10.1016\/j.eururo.2024.03.035"}],"container-title":["npj Digital Medicine"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41746-026-02369-z","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41746-026-02369-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41746-026-02369-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,7]],"date-time":"2026-02-07T06:11:04Z","timestamp":1770444664000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41746-026-02369-z"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1,26]]},"references-count":31,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,12]]}},"alternative-id":["2369"],"URL":"https:\/\/doi.org\/10.1038\/s41746-026-02369-z","relation":{},"ISSN":["2398-6352"],"issn-type":[{"value":"2398-6352","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,1,26]]},"assertion":[{"value":"16 May 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"13 January 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"26 January 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"Alex Howard declares personal consulting work for Pfizer outside the submitted work, and a donation from Pfizer to the University of Liverpool for a public and professional engagement project outside the submitted work. Iain Buchan declares consulting fees via University of Liverpool from AstraZeneca outside the submitted work. William Hope holds or has recently held research grants with UKRI, EU (FP7, IMI-1, IMI-2), Wellcome, F2G, Spero Therapeutics, Antabio, Pfizer, Allecra, Bugworks, Phico Therapeutics, BioVersys, Global Antimicrobial Research and Development Partnership (GARDP). He is (or has recently been) a consultant for Appili Therapeutics, F2G, Spero Therapeutics, Pfizer, GSK, Phico Therapeutics, Pulmocide, and Mundipharma Research Ltd. He was a member of the Specialist Advisory Committee for GARDP (2020-2023), a member of the British Society for Antimicrobial Chemotherapy (BSAC) Breakpoint Committee (2020-2023), a member of Health Technology Appraisal (HTA) Prioritization Committee for hospital care and was the Specialty National Co-lead for Infection for the National Institute of Health Research (NIHR) (2020-2024). The other authors declare no competing interests.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"136"}}