{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,19]],"date-time":"2026-01-19T15:13:58Z","timestamp":1768835638788,"version":"3.49.0"},"reference-count":27,"publisher":"Cambridge University Press (CUP)","issue":"4","license":[{"start":{"date-parts":[[2019,3,4]],"date-time":"2019-03-04T00:00:00Z","timestamp":1551657600000},"content-version":"unspecified","delay-in-days":0,"URL":"https:\/\/www.cambridge.org\/core\/terms"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Infect. Control Hosp. Epidemiol."],"published-print":{"date-parts":[[2019,4]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:sec id=\"S0899823X19000175_as1\"><jats:title>Background:<\/jats:title><jats:p>Timely identification of multidrug-resistant gram-negative infections remains an epidemiological challenge. Statistical models for predicting drug resistance can offer utility where rapid diagnostics are unavailable or resource-impractical. Logistic regression\u2013derived risk scores are common in the healthcare epidemiology literature. Machine learning\u2013derived decision trees are an alternative approach for developing decision support tools. Our group previously reported on a decision tree for predicting ESBL bloodstream infections. Our objective in the current study was to develop a risk score from the same ESBL dataset to compare these 2 methods and to offer general guiding principles for using each approach.<\/jats:p><\/jats:sec><jats:sec id=\"S0899823X19000175_as2\"><jats:title>Methods:<\/jats:title><jats:p>Using a dataset of 1,288 patients with<jats:italic>Escherichia coli<\/jats:italic>or<jats:italic>Klebsiella<\/jats:italic>spp bacteremia, we generated a risk score to predict the likelihood that a bacteremic patient was infected with an ESBL-producer. We evaluated discrimination (original and cross-validated models) using receiver operating characteristic curves and C statistics. We compared risk score and decision tree performance, and we reviewed their practical and methodological attributes.<\/jats:p><\/jats:sec><jats:sec id=\"S0899823X19000175_as3\"><jats:title>Results:<\/jats:title><jats:p>In total, 194 patients (15%) were infected with ESBL-producing bacteremia. The clinical risk score included 14 variables, compared to the 5 decision-tree variables. The positive and negative predictive values of the risk score and decision tree were similar (&gt;90%), but the C statistic of the risk score (0.87) was 10% higher.<\/jats:p><\/jats:sec><jats:sec id=\"S0899823X19000175_as4\"><jats:title>Conclusions:<\/jats:title><jats:p>A decision tree and risk score performed similarly for predicting ESBL infection. The decision tree was more user-friendly, with fewer variables for the end user, whereas the risk score offered higher discrimination and greater flexibility for adjusting sensitivity and specificity.<\/jats:p><\/jats:sec>","DOI":"10.1017\/ice.2019.17","type":"journal-article","created":{"date-parts":[[2019,3,4]],"date-time":"2019-03-04T07:17:20Z","timestamp":1551683840000},"page":"400-407","source":"Crossref","is-referenced-by-count":40,"title":["A methodological comparison of risk scores versus decision trees for predicting drug-resistant infections: A case study using extended-spectrum beta-lactamase (ESBL) bacteremia"],"prefix":"10.1017","volume":"40","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2851-775X","authenticated-orcid":false,"given":"Katherine E.","family":"Goodman","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Justin","family":"Lessler","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Anthony D.","family":"Harris","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Aaron M.","family":"Milstone","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Pranita D.","family":"Tamma","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"56","published-online":{"date-parts":[[2019,3,4]]},"reference":[{"key":"S0899823X19000175_ref25","doi-asserted-by":"publisher","DOI":"10.2202\/1544-6115.1309"},{"key":"S0899823X19000175_ref18","doi-asserted-by":"publisher","DOI":"10.1016\/S0895-4356(96)00236-3"},{"key":"S0899823X19000175_ref24","doi-asserted-by":"crossref","first-page":"267","DOI":"10.1111\/j.2517-6161.1996.tb02080.x","article-title":"Regression shrinkage and selection via the lasso","volume":"58","author":"Tibshirani","year":"1996","journal-title":"J Roy Stat Soc B"},{"key":"S0899823X19000175_ref11","doi-asserted-by":"publisher","DOI":"10.1093\/jac\/dkt167"},{"key":"S0899823X19000175_ref23","unstructured":"23. Drummond C , Holte RC . Exploiting the cost (in)sensitivity of decision tree splitting criteria. Proceedings of the Seventeenth International Conference on Machine Learning. Stanford, CA; 2000."},{"key":"S0899823X19000175_ref6","doi-asserted-by":"publisher","DOI":"10.1128\/JCM.00581-15"},{"key":"S0899823X19000175_ref1","doi-asserted-by":"publisher","DOI":"10.1186\/s13756-018-0346-9"},{"key":"S0899823X19000175_ref19","doi-asserted-by":"publisher","DOI":"10.1093\/aje\/kwk052"},{"key":"S0899823X19000175_ref2","doi-asserted-by":"publisher","DOI":"10.1017\/ice.2017.156"},{"key":"S0899823X19000175_ref3","doi-asserted-by":"publisher","DOI":"10.1128\/AAC.00007-18"},{"key":"S0899823X19000175_ref4","doi-asserted-by":"publisher","DOI":"10.1097\/CCM.0000000000001140"},{"key":"S0899823X19000175_ref5","first-page":"2018","volume-title":"Performance Standards for Antimicrobial Susceptibility Testing"},{"key":"S0899823X19000175_ref8","doi-asserted-by":"publisher","DOI":"10.1093\/cid\/ciw425"},{"key":"S0899823X19000175_ref9","unstructured":"9. Antimicrobial resistant phenotype definitions. Centers for Disease Control and Prevention webstie. https:\/\/www.cdc.gov\/nhsn\/pdfs\/ps-analysis-resources\/phenotype_definitions.pdf. Published 2016. Accessed January 15, 2019."},{"key":"S0899823X19000175_ref10","doi-asserted-by":"publisher","DOI":"10.1093\/cid\/ciu957"},{"key":"S0899823X19000175_ref14","doi-asserted-by":"publisher","DOI":"10.1017\/ice.2017.178"},{"key":"S0899823X19000175_ref15","doi-asserted-by":"publisher","DOI":"10.1016\/j.cmi.2018.03.023"},{"key":"S0899823X19000175_ref16","doi-asserted-by":"publisher","DOI":"10.1017\/ice.2016.292"},{"key":"S0899823X19000175_ref17","doi-asserted-by":"publisher","DOI":"10.1136\/bmj.38398.500764.8F"},{"key":"S0899823X19000175_ref20","doi-asserted-by":"publisher","DOI":"10.1145\/212094.212114"},{"key":"S0899823X19000175_ref21","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/bts643"},{"key":"S0899823X19000175_ref22","doi-asserted-by":"publisher","DOI":"10.1037\/a0016973"},{"key":"S0899823X19000175_ref26","first-page":"130","article-title":"Decision tree methods: applications for classification and prediction","volume":"27","author":"Song","year":"2015","journal-title":"Shanghai Arch Psychiatr"},{"key":"S0899823X19000175_ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.1974.1100705"},{"key":"S0899823X19000175_ref13","volume-title":"Classification and Regression Trees","author":"Breiman","year":"1984"},{"key":"S0899823X19000175_ref12","first-page":"2001","volume-title":"Pattern Classification","author":"Duda"},{"key":"S0899823X19000175_ref7","doi-asserted-by":"publisher","DOI":"10.1007\/s10096-014-2252-2"}],"container-title":["Infection Control &amp; Hospital Epidemiology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.cambridge.org\/core\/services\/aop-cambridge-core\/content\/view\/S0899823X19000175","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,7,15]],"date-time":"2024-07-15T09:53:29Z","timestamp":1721037209000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.cambridge.org\/core\/product\/identifier\/S0899823X19000175\/type\/journal_article"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,3,4]]},"references-count":27,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2019,4]]}},"alternative-id":["S0899823X19000175"],"URL":"https:\/\/doi.org\/10.1017\/ice.2019.17","relation":{},"ISSN":["0899-823X","1559-6834"],"issn-type":[{"value":"0899-823X","type":"print"},{"value":"1559-6834","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019,3,4]]}}}