{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,23]],"date-time":"2026-08-23T16:39:28Z","timestamp":1787503168345,"version":"build-2736575974"},"reference-count":32,"publisher":"Oxford University Press (OUP)","issue":"1","license":[{"start":{"date-parts":[[2025,6,11]],"date-time":"2025-06-11T00:00:00Z","timestamp":1749600000000},"content-version":"vor","delay-in-days":167,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,12,26]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Motivation<\/jats:title>\n                    <jats:p>Hospital readmissions represent a major challenge for healthcare systems due to their impact on patient outcomes and associated costs. As many readmissions are considered preventable, predictive modeling offers a valuable tool for early identification and intervention. This study aimed to develop and validate a predictive model for 30-day readmissions in a 200-bed community hospital in Argentina. A retrospective analysis was conducted on 3388 adult admissions. The primary endpoint was readmission within 30\u2009days of discharge. Predictor variables included demographic and clinical factors such as age, length of stay, hypertension, diabetes, heart failure, coronary artery disease, stroke, cancer, dementia, chronic kidney disease, chronic obstructive pulmonary disease, and bedridden status. Three models\u2014Logistic Regression (LR), Random Forest (RF), and LightGBM (LGBM)\u2014were developed, with hyperparameter tuning via Bayesian optimization. Model performance was assessed using calibration, discrimination (C-statistics), and decision curve analysis. Internal validation was performed using 250 bootstrap resamples.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>The readmission rate was 11% (n\u2009=\u2009394). RF outperformed LR and LGBM in discrimination and clinical utility within predictive probability thresholds of 0.05\u20130.25. Optimism-corrected C-statistics were 0.60 (LR, LGBM) and 0.64 (RF); calibration slopes were 0.75 (LR), 1.13 (RF), and 1.76 (LGBM). Machine learning models, particularly RF, can improve readmission risk prediction and inform targeted healthcare interventions.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Availability and implementation<\/jats:title>\n                    <jats:p>The dataset and code used to develop and validate the predictive models are available from the corresponding author upon reasonable request. The implementation was conducted in R using the mlr3verse, pminternal, rms, dcurves, data.table, tidyverse, ranger and lightgbm packages, with Bayesian hyperparameter optimization via mlr3mbo.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1093\/bioadv\/vbaf121","type":"journal-article","created":{"date-parts":[[2025,5,23]],"date-time":"2025-05-23T09:43:30Z","timestamp":1747993410000},"source":"Crossref","is-referenced-by-count":6,"title":["Predictive machine learning model for 30-day hospital readmissions in a tertiary healthcare setting"],"prefix":"10.1093","volume":"5","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-6683-8160","authenticated-orcid":false,"given":"Diego","family":"Halac","sequence":"first","affiliation":[{"name":"Departamento de Medicina Interna, Sanatorio Anchorena de San Martin , Perdriel 4189, CP: 1650. Gral. San Martin, Provincia de Buenos Aires,","place":["Argentina"]},{"name":"Instituto de Efectividad Clinica y Sanitaria (IECS) , Dr. Emilio Ravignani 2024, CP:1414 CABA,","place":["Argentina"]},{"name":"Catedra de Bioestadistica, Hospital universitario Austral , Avenida Juan Domingo Per\u00f3n 1500, Pilar CP: B1629AHJ, Provincia de Buenos Aires,","place":["Argentina"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Cecilia","family":"Cocucci","sequence":"additional","affiliation":[{"name":"Instituto de Efectividad Clinica y Sanitaria (IECS) , Dr. Emilio Ravignani 2024, CP:1414 CABA,","place":["Argentina"]},{"name":"Catedra de Bioestadistica, Hospital universitario Austral , Avenida Juan Domingo Per\u00f3n 1500, Pilar CP: B1629AHJ, Provincia de Buenos Aires,","place":["Argentina"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sebastian","family":"Camerlingo","sequence":"additional","affiliation":[{"name":"Instituto de Efectividad Clinica y Sanitaria (IECS) , Dr. Emilio Ravignani 2024, CP:1414 CABA,","place":["Argentina"]},{"name":"Catedra de Bioestadistica, Hospital universitario Austral , Avenida Juan Domingo Per\u00f3n 1500, Pilar CP: B1629AHJ, Provincia de Buenos Aires,","place":["Argentina"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"286","published-online":{"date-parts":[[2025,5,24]]},"reference":[{"key":"2025061901560247000_vbaf121-B1","doi-asserted-by":"publisher","first-page":"1552","DOI":"10.1136\/bmj.308.6943.1552","article-title":"Diagnostic tests 1: sensitivity and specificity","volume":"308","author":"Altman","year":"1994","journal-title":"BMJ"},{"key":"2025061901560247000_vbaf121-B2","doi-asserted-by":"crossref","first-page":"5","DOI":"10.1023\/A:1010933404324","article-title":"Random forests","volume":"45","author":"Breiman","year":"2001","journal-title":"Mach Learn"},{"key":"2025061901560247000_vbaf121-B3","author":"Centeno","year":"2015"},{"key":"2025061901560247000_vbaf121-B4","doi-asserted-by":"crossref","first-page":"373","DOI":"10.1016\/0021-9681(87)90171-8","article-title":"A new method of classifying prognostic comorbidity in longitudinal studies: development and validation","volume":"40","author":"Charlson","year":"1987","journal-title":"J Chronic Dis"},{"key":"2025061901560247000_vbaf121-B5","doi-asserted-by":"publisher","first-page":"20","DOI":"10.22529\/me.2023.8(1)04","article-title":"Frecuencia y causas de reingresos hospitalarios de pacientes adultos internados","volume":"8","author":"Chavesta Carrillo","year":"2023","journal-title":"Me"},{"key":"2025061901560247000_vbaf121-B6","doi-asserted-by":"crossref","first-page":"e074819","DOI":"10.1136\/bmj-2023-074819","article-title":"Evaluation of clinical prediction models (part 1): from development to external validation","volume":"384","author":"Collins","year":"2024","journal-title":"BMJ"},{"key":"2025061901560247000_vbaf121-B7","article-title":"TRIPOD+ AI statement","volume":"385","author":"Collins","year":"2024","journal-title":"BMJ"},{"key":"2025061901560247000_vbaf121-B8","author":"De Cock","year":"2023"},{"key":"2025061901560247000_vbaf121-B9","doi-asserted-by":"crossref","first-page":"496","DOI":"10.1001\/jamainternmed.2015.8462","article-title":"International validity of the HOSPITAL score","volume":"176","author":"Donz\u00e9","year":"2016","journal-title":"JAMA Intern Med"},{"key":"2025061901560247000_vbaf121-B10","doi-asserted-by":"crossref","first-page":"104236","DOI":"10.1016\/j.ijmedinf.2020.104236","article-title":"Emergency department visits and hospital readmissions in an Argentine health system","volume":"141","author":"Giunta","year":"2020","journal-title":"Int J Med Inform"},{"key":"2025061901560247000_vbaf121-B11","first-page":"30","article-title":"LightGBM: a highly efficient gradient boosting decision tree","author":"Goulin","year":"2017","journal-title":"Adv Neural Inf Process Syst"},{"key":"2025061901560247000_vbaf121-B12"},{"key":"2025061901560247000_vbaf121-B13","doi-asserted-by":"crossref","DOI":"10.1002\/0471722146","volume-title":"Applied Logistic Regression","author":"Hosmer","year":"2000"},{"key":"2025061901560247000_vbaf121-B14","doi-asserted-by":"crossref","first-page":"e0221606","DOI":"10.1371\/journal.pone.0221606","article-title":"Predicting 30-day hospital readmissions","volume":"15","author":"Liu","year":"2020","journal-title":"PLoS One"},{"key":"2025061901560247000_vbaf121-B15","doi-asserted-by":"crossref","first-page":"e020325","DOI":"10.1136\/bmjopen-2017-020325","article-title":"National trends in emergency readmission rates","volume":"8","author":"McIlvennan","year":"2018","journal-title":"BMJ Open"},{"key":"2025061901560247000_vbaf121-B16","volume-title":"Statistical Methods","author":"Mohr","year":"2021."},{"key":"2025061901560247000_vbaf121-B17","first-page":"28","article-title":"Early hospital re-entries and their association with morbi-mortality","volume":"20","author":"Mu\u00f1oz-Cruzado","year":"2010","journal-title":"Revista de la Asociaci\u00f3n M\u00e9dica de Bah\u00eda Blanca"},{"key":"2025061901560247000_vbaf121-B18","author":"Posit Team","year":"2024"},{"key":"2025061901560247000_vbaf121-B19","author":"R Core Team","year":"2023"},{"key":"2025061901560247000_vbaf121-B20","author":"Rhodes","year":"2023"},{"key":"2025061901560247000_vbaf121-B21","doi-asserted-by":"crossref","first-page":"e074820","DOI":"10.1136\/bmj-2023-074820","article-title":"Evaluation of clinical prediction models (part 2)","volume":"384","author":"Riley","year":"2024","journal-title":"BMJ"},{"key":"2025061901560247000_vbaf121-B22","doi-asserted-by":"crossref","first-page":"m441","DOI":"10.1136\/bmj.m441","article-title":"Sample size for prediction models","volume":"368","author":"Riley","year":"2020","journal-title":"BMJ"},{"key":"2025061901560247000_vbaf121-B23","doi-asserted-by":"crossref","first-page":"e3137","DOI":"10.7717\/peerj.3137","article-title":"The HOSPITAL score and LACE index","volume":"5","author":"Robinson","year":"2017","journal-title":"PeerJ"},{"key":"2025061901560247000_vbaf121-B24","author":"Rosso","year":"2021"},{"key":"2025061901560247000_vbaf121-B25","doi-asserted-by":"crossref","first-page":"148","DOI":"10.1109\/JPROC.2015.2494218","article-title":"Bayesian optimization","volume":"104","author":"Shahriari","year":"2016","journal-title":"Proc IEEE"},{"key":"2025061901560247000_vbaf121-B26","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-030-16399-0","volume-title":"Clinical Prediction Models","author":"Steyerberg","year":"2019"},{"key":"2025061901560247000_vbaf121-B28","doi-asserted-by":"crossref","first-page":"47643","DOI":"10.1109\/ACCESS.2022.3169512","article-title":"Stop oversampling for class imbalance learning","volume":"10","author":"Tarawneh","year":"2022","journal-title":"IEEE Access"},{"key":"2025061901560247000_vbaf121-B29","author":"The Health Foundation","year":"2021"},{"key":"2025061901560247000_vbaf121-B30","doi-asserted-by":"crossref","first-page":"230","DOI":"10.1186\/s12916-019-1466-7","article-title":"Calibration: the achilles heel of predictive analytics","volume":"17","author":"Van Calster","year":"2019","journal-title":"BMC Med"},{"key":"2025061901560247000_vbaf121-B31","doi-asserted-by":"crossref","first-page":"1525","DOI":"10.1093\/jamia\/ocac093","article-title":"Harm of class imbalance corrections","volume":"29","author":"van den Goorbergh","year":"2022","journal-title":"J Am Med Inform Assoc"},{"key":"2025061901560247000_vbaf121-B32","doi-asserted-by":"crossref","first-page":"i6","DOI":"10.1136\/bmj.i6","article-title":"Net benefit approaches","volume":"352","author":"Vickers","year":"2016","journal-title":"BMJ"},{"key":"2025061901560247000_vbaf121-B33","doi-asserted-by":"crossref","first-page":"l4563","DOI":"10.1136\/bmj.l4563","article-title":"Hospital revisits within 30 days after discharge","volume":"366","author":"Wadhera","year":"2019","journal-title":"BMJ"}],"container-title":["Bioinformatics Advances"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/bioinformaticsadvances\/article-pdf\/5\/1\/vbaf121\/63472924\/vbaf121.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformaticsadvances\/article-pdf\/5\/1\/vbaf121\/63472924\/vbaf121.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T01:56:10Z","timestamp":1750298170000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bioinformaticsadvances\/article\/doi\/10.1093\/bioadv\/vbaf121\/8145567"}},"subtitle":[],"editor":[{"given":"Michael","family":"DeGiorgio","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2024,12,26]]},"references-count":32,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2024,12,26]]}},"URL":"https:\/\/doi.org\/10.1093\/bioadv\/vbaf121","relation":{},"ISSN":["2635-0041"],"issn-type":[{"value":"2635-0041","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2025]]},"published":{"date-parts":[[2024,12,26]]},"article-number":"vbaf121"}}