{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T22:36:25Z","timestamp":1793572585469,"version":"4.5.0"},"reference-count":25,"publisher":"Public Library of Science (PLoS)","issue":"6","license":[{"start":{"date-parts":[[2026,6,5]],"date-time":"2026-06-05T00:00:00Z","timestamp":1780617600000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/100017821","name":"School of Medicine, University of Connecticut","doi-asserted-by":"publisher","award":["CRISP Award"],"award-info":[{"award-number":["CRISP Award"]}],"id":[{"id":"10.13039\/100017821","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["www.plosone.org"],"crossmark-restriction":false},"short-container-title":["PLoS One"],"abstract":"<jats:sec id=\"sec001\">\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>Research is needed to develop more accurate readmission prediction models that identify patients at the highest risk of readmission after their initial pneumonia hospitalization. Improving prediction accuracy will support the implementation of more effective, personalized interventions to lower readmission rates. Published models tend to rely on traditional methods or advanced machine learning models that exclude continuous variables, overlooking opportunities to uncover nonlinear relationships and interactions. In response, we used electronic medical record (EMR) data, including continuous variables such as vitals, alongside more advanced machine learning (ML) models.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec id=\"sec002\">\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>Using EMR data from a single academic medical center, we identified adults with initial pneumonia admissions between April 2018 and February 2024. We predicted 30-day readmission using eXtreme Gradient Boosting (XGBoost) and deep neural networks, and compared their performance with that of traditional logistic regression.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec id=\"sec003\">\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>We identified 2,752 patients admitted with pneumonia during the study period (mean age\u2009=\u200970.0 years, 49.1% female). The 30-day readmission rate was 9.9%. The average AUROC for our ML models ranged from 0.62 to 0.64, and AUPRC was 0.15 to 0.16, comparable to traditional logistic regression (0.63 and 0.17, respectively). Previously underemphasized predictors included drug abuse and BUN values.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec id=\"sec004\">\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>Using more advanced machine learning models and continuous variables yielded similar performance to logistic regression models. However, we identified previously understated predictors of readmission after pneumonia hospitalization. Future efforts should focus on gathering important data not readily available in EMR, such as social determinants of health, to potentially enhance the models.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1371\/journal.pone.0349804","type":"journal-article","created":{"date-parts":[[2026,6,5]],"date-time":"2026-06-05T17:37:18Z","timestamp":1780681038000},"page":"e0349804","update-policy":"https:\/\/doi.org\/10.1371\/journal.pone.corrections_policy","source":"Crossref","is-referenced-by-count":2,"title":["Leveraging nonlinear relationships and interactions to improve 30-day pneumonia readmission machine learning models"],"prefix":"10.1371","volume":"21","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3880-5563","authenticated-orcid":true,"given":"Eric M.","family":"Mortensen","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Nkiruka","family":"Atuegwu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shane J.","family":"Sacco","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"340","published-online":{"date-parts":[[2026,6,5]]},"reference":[{"issue":"14","key":"pone.0349804.ref001","doi-asserted-by":"crossref","first-page":"1418","DOI":"10.1056\/NEJMsa0803563","article-title":"Rehospitalizations among patients in the Medicare fee-for-service program","volume":"360","author":"SF Jencks","year":"2009","journal-title":"N Engl J Med"},{"issue":"24","key":"pone.0349804.ref002","doi-asserted-by":"crossref","first-page":"2287","DOI":"10.1056\/NEJMsa1101942","article-title":"The relationship between hospital admission rates and rehospitalizations","volume":"365","author":"AM Epstein","year":"2011","journal-title":"N Engl J Med"},{"issue":"4","key":"pone.0349804.ref003","first-page":"649","article-title":"Pneumonia readmissions: risk factors and implications","volume":"14","author":"I De Alba","year":"2014","journal-title":"Ochsner J"},{"issue":"2","key":"pone.0349804.ref004","doi-asserted-by":"crossref","first-page":"269","DOI":"10.1007\/s11606-012-2235-x","article-title":"Impact of social factors on risk of readmission or mortality in pneumonia and heart failure: systematic review","volume":"28","author":"L Calvillo-King","year":"2013","journal-title":"J Gen Intern Med"},{"issue":"7","key":"pone.0349804.ref005","doi-asserted-by":"crossref","first-page":"675","DOI":"10.1001\/jama.2011.123","article-title":"Thirty-day readmission rates for Medicare beneficiaries by race and site of care","volume":"305","author":"KE Joynt","year":"2011","journal-title":"JAMA"},{"issue":"1","key":"pone.0349804.ref006","doi-asserted-by":"crossref","first-page":"53","DOI":"10.1093\/intqhc\/mzv090","article-title":"Reducing excess readmissions: promising effect of hospital readmissions reduction program in US hospitals","volume":"28","author":"N Lu","year":"2015","journal-title":"Int J Qual Health Care"},{"issue":"17","key":"pone.0349804.ref007","doi-asserted-by":"crossref","first-page":"1716","DOI":"10.1001\/jama.2010.533","article-title":"Relationship between early physician follow-up and 30-day readmission among Medicare beneficiaries hospitalized for heart failure","volume":"303","author":"AF Hernandez","year":"2010","journal-title":"JAMA"},{"issue":"8","key":"pone.0349804.ref008","doi-asserted-by":"crossref","first-page":"520","DOI":"10.7326\/0003-4819-155-8-201110180-00008","article-title":"Interventions to reduce 30-day rehospitalization: a systematic review","volume":"155","author":"LO Hansen","year":"2011","journal-title":"Ann Intern Med"},{"issue":"2","key":"pone.0349804.ref009","first-page":"11","article-title":"Payers benefit when hospitals issue improved discharge orders","volume":"18","author":"T Berberabe","year":"2009","journal-title":"Manag Care"},{"issue":"3","key":"pone.0349804.ref010","doi-asserted-by":"crossref","first-page":"535","DOI":"10.1111\/j.1532-5415.2005.00638.x","article-title":"Isolation of health services research from practice and policy: the example of chronic heart failure management","volume":"54","author":"H Seow","year":"2006","journal-title":"J Am Geriatr Soc"},{"issue":"9","key":"pone.0349804.ref011","doi-asserted-by":"crossref","first-page":"1607","DOI":"10.1513\/AnnalsATS.201602-135SR","article-title":"Predicting the Risk of Readmission in Pneumonia. A Systematic Review of Model Performance","volume":"13","author":"M Weinreich","year":"2016","journal-title":"Ann Am Thorac Soc"},{"key":"pone.0349804.ref012","first-page":"785","volume-title":"XGBoost: A Scalable Tree Boosting System. Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining","author":"T Chen","year":"2016"},{"issue":"5","key":"pone.0349804.ref013","doi-asserted-by":"crossref","first-page":"415","DOI":"10.1056\/NEJMoa1500245","article-title":"Community-Acquired Pneumonia Requiring Hospitalization among U.S. Adults","volume":"373","author":"S Jain","year":"2015","journal-title":"N Engl J Med"},{"issue":"6","key":"pone.0349804.ref014","doi-asserted-by":"crossref","first-page":"573","DOI":"10.1007\/s40258-014-0124-7","article-title":"Using decision trees to manage hospital readmission risk for acute myocardial infarction, heart failure, and pneumonia","volume":"12","author":"JP Hilbert","year":"2014","journal-title":"Appl Health Econ Health Policy"},{"issue":"3","key":"pone.0349804.ref015","doi-asserted-by":"crossref","first-page":"129","DOI":"10.1097\/JHQ.0000000000000080","article-title":"Comparison of Machine Learning Algorithms for the Prediction of Preventable Hospital Readmissions","volume":"40","author":"A Garcia-Arce","year":"2018","journal-title":"J Healthc Qual"},{"issue":"4","key":"pone.0349804.ref016","article-title":"Predicting 30-day hospital readmissions using artificial neural networks with medical code embedding","volume":"15","author":"W Liu","year":"2020","journal-title":"PLoS One"},{"issue":"11","key":"pone.0349804.ref017","doi-asserted-by":"crossref","first-page":"1245","DOI":"10.1016\/0895-4356(94)90129-5","article-title":"Validation of a combined comorbidity index","volume":"47","author":"M Charlson","year":"1994","journal-title":"J Clin Epidemiol"},{"issue":"4","key":"pone.0349804.ref018","first-page":"188","article-title":"Charlson Comorbidity Index: ICD-9 Update and ICD-10 Translation","volume":"12","author":"WP Glasheen","year":"2019","journal-title":"Am Health Drug Benefits"},{"issue":"1","key":"pone.0349804.ref019","doi-asserted-by":"crossref","first-page":"8","DOI":"10.1097\/00005650-199801000-00004","article-title":"Comorbidity measures for use with administrative data","volume":"36","author":"A Elixhauser","year":"1998","journal-title":"Med Care"},{"issue":"1","key":"pone.0349804.ref020","doi-asserted-by":"crossref","first-page":"32","DOI":"10.1002\/1097-0142(1950)3:1<32::AID-CNCR2820030106>3.0.CO;2-3","article-title":"Index for rating diagnostic tests","volume":"3","author":"WJ Youden","year":"1950","journal-title":"Cancer"},{"key":"pone.0349804.ref021","doi-asserted-by":"crossref","first-page":"871768","DOI":"10.3389\/fnut.2022.871768","article-title":"Interaction Analysis Based on Shapley Values and Extreme Gradient Boosting: A Realistic Simulation and Application to a Large Epidemiological Prospective Study","volume":"9","author":"N Orsini","year":"2022","journal-title":"Front Nutr"},{"key":"pone.0349804.ref022","volume-title":"R: A Language and Environment for Statistical Computing","author":"Team RC","year":"2024"},{"key":"pone.0349804.ref023","article-title":"BTS Guidelines for the Management of Community Acquired Pneumonia in Adults","volume":"56","year":"2001","journal-title":"Thorax"},{"issue":"12","key":"pone.0349804.ref024","doi-asserted-by":"crossref","first-page":"2538","DOI":"10.1111\/add.70136","article-title":"Unpacking the link between substance use disorders and 30-day unplanned readmission","volume":"120","author":"AD Rosen","year":"2025","journal-title":"Addiction"},{"issue":"4","key":"pone.0349804.ref025","doi-asserted-by":"crossref","first-page":"550","DOI":"10.1086\/526526","article-title":"Causes and risk factors for rehospitalization of patients hospitalized with community-acquired pneumonia","volume":"46","author":"H Jasti","year":"2008","journal-title":"Clin Infect Dis"}],"container-title":["PLOS One"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0349804","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,5]],"date-time":"2026-06-05T17:37:24Z","timestamp":1780681044000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0349804"}},"subtitle":[],"editor":[{"given":"Oliver","family":"Schildgen","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2026,6,5]]},"references-count":25,"journal-issue":{"issue":"6","published-online":{"date-parts":[[2026,6,5]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pone.0349804","relation":{},"ISSN":["1932-6203"],"issn-type":[{"value":"1932-6203","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,6,5]]}}}