{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,9]],"date-time":"2026-06-09T12:05:53Z","timestamp":1781006753422,"version":"3.54.1"},"reference-count":64,"publisher":"BMJ","issue":"6","license":[{"start":{"date-parts":[[2026,6,9]],"date-time":"2026-06-09T00:00:00Z","timestamp":1780963200000},"content-version":"unspecified","delay-in-days":8,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"}],"content-domain":{"domain":["bmj.com"],"crossmark-restriction":true},"short-container-title":["BMJ Open"],"accepted":{"date-parts":[[2026,5,21]]},"published-print":{"date-parts":[[2026,6]]},"abstract":"<jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>Hepatitis, a disease characterised by inflammation of the liver, is a leading global health challenge that contributes to over 1.3\u2009million deaths annually, with hepatitis B and C accounting for many of these fatalities. Intensive care unit (ICU) management of patients is particularly challenging due to the complex clinical care and resource demands. Despite advancements in ICU predictive analytics, limited research has specifically addressed hepatitis patients, creating a gap in optimising care for this population.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>This study focuses on predicting ICU length of stay (LoS), hospital discharge outcomes and discharge location for ICU-admitted viral hepatitis patients using a comparative assessment of machine learning (ML) models. Leveraging data from the Medical Information Mart for Intensive Care-IV database, which includes around 94\u2009500 ICU patient records, this study uses sociodemographic details, clinical characteristics and resource utilisation metrics to develop predictive models such as Random Forest, Logistic Regression, Gradient Boosting Machines and Generalised Additive Model with Negative Binomial Regression.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>Among 3875 ICU-admitted hepatitis patients, Random Forest classification outperformed Logistic Regression in predicting discharge outcomes, achieving higher accuracy (0.87 vs 0.82) and greater discriminative ability (area under the receiver operating characteristic curve 0.95 vs 0.89). For ICU LoS prediction, Random Forest regression applied to log-transformed LoS demonstrated strong performance (R\u00b2 up to 0.82), while the generalised additive model with negative binomial distribution explained approximately 76% of LoS variance. Prediction of discharge location yielded moderate performance across Gradient Boosting and multinomial logistic regression models (accuracy 0.55 and 0.56), reflecting challenges associated with multi-class imbalance. Variable importance analyses across ML models consistently identified medication counts, procedure counts, comorbidity burden, age, race and total LoS as the most influential predictors of discharge outcomes and discharge location.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusions<\/jats:title>\n                    <jats:p>This study demonstrates the value of ML models for predicting clinical outcomes for hepatitis patients, including ICU LOS and hospital discharge status. The results underscore the influence of factors like race and age, revealing disparities that must be addressed in predictive care strategies. While the models show promise, challenges such as variability in prolonged stays and limited multiclass prediction accuracy point to the need for ongoing refinement and research.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1136\/bmjopen-2025-106819","type":"journal-article","created":{"date-parts":[[2026,6,9]],"date-time":"2026-06-09T11:50:15Z","timestamp":1781005815000},"page":"e106819","update-policy":"https:\/\/doi.org\/10.1136\/crossmarkpolicy","source":"Crossref","is-referenced-by-count":0,"title":["Prediction of ICU length of stay, hospital discharge outcomes and discharge location among ICU-admitted patients diagnosed with viral hepatitis using machine learning: a retrospective cohort study of the MIMIC-IV database"],"prefix":"10.1136","volume":"16","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-1399-6972","authenticated-orcid":false,"given":"Dimple Sushma","family":"Alluri","sequence":"first","affiliation":[{"name":"Department of Biomedical Engineering and Informatics, Indiana University Luddy School of Informatics, Computing, and Engineering, Indianapolis, Indiana, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3528-2354","authenticated-orcid":false,"given":"Felix M","family":"Pabon-Rodriguez","sequence":"additional","affiliation":[{"name":"Department of Biomedical Engineering and Informatics, Indiana University Luddy School of Informatics, Computing, and Engineering, Indianapolis, Indiana, USA"},{"name":"Department of Biostatistics and Health Data Science, Indiana University School of Medicine, Indianapolis, Indiana, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"239","published-online":{"date-parts":[[2026,6,9]]},"reference":[{"key":"2026060904500748000_16.6.e106819.1","unstructured":"WHO . Global hepatitis report 2024: action for access in low- and middle-income countries. 2024."},{"key":"2026060904500748000_16.6.e106819.2","unstructured":"WHO . WHO sounds alarm on viral hepatitis infections claiming 3500 lives each day. 2024. Available: https:\/\/www.who.int\/news\/item\/09-04-2024-who-sounds-alarm-on-viral-hepatitis-infections-claiming-3500-lives-each-day"},{"key":"2026060904500748000_16.6.e106819.3","unstructured":"CDC . Viral hepatitis surveillance report. 2022. Available: https:\/\/www.cdc.gov\/hepatitis\/statistics\/2022surveillance\/index.htm"},{"key":"2026060904500748000_16.6.e106819.4","unstructured":"CDC . 2023 Viral hepatitis surveillance report. 2025. Available: https:\/\/www.cdc.gov\/hepatitis-surveillance-2023\/about\/index.html"},{"key":"2026060904500748000_16.6.e106819.5","unstructured":"CDC . Clinical overview of viral hepatitis. 2025. Available: https:\/\/www.cdc.gov\/hepatitis\/hcp\/clinical-overview\/index.html"},{"key":"2026060904500748000_16.6.e106819.6","unstructured":"CDC . Hepatitis B surveillance. 2025. Available: https:\/\/www.cdc.gov\/hepatitis-surveillance-2023\/hepatitis-b\/index.html"},{"key":"2026060904500748000_16.6.e106819.7","unstructured":"CDC . Hepatitis B surveillance. 2025. Available: https:\/\/www.cdc.gov\/hepatitis-surveillance-2023\/hepatitis-c\/index.html"},{"key":"2026060904500748000_16.6.e106819.8","unstructured":"Massachusetts Department of Public Health (DPH) . 2023 viral hepatitis surveillance report. 2025. Available: https:\/\/www.mass.gov\/ lists\/infectious-disease-data-reports-and-requests"},{"key":"2026060904500748000_16.6.e106819.9","unstructured":"WHO . Hepatitis. 2023. Available: https:\/\/www.who.int\/health-topics\/hepatitis\/viral-hepatitis-in-the-world-map#tab=tab_1"},{"key":"2026060904500748000_16.6.e106819.10","doi-asserted-by":"publisher","DOI":"10.1016\/j.jcrc.2020.08.003"},{"key":"2026060904500748000_16.6.e106819.11","doi-asserted-by":"publisher","DOI":"10.1097\/CCM.0000000000001480"},{"key":"2026060904500748000_16.6.e106819.12","unstructured":"Whitcomb W . Choosing location after discharge wisely. 2018. Available: https:\/\/www.the-hospitalist.org\/hospitalist\/article\/155424\/transitions-care\/choosing-location-after-discharge-wisely"},{"key":"2026060904500748000_16.6.e106819.13","doi-asserted-by":"publisher","DOI":"10.1056\/NEJMp1315607"},{"key":"2026060904500748000_16.6.e106819.14","doi-asserted-by":"publisher","DOI":"10.1056\/NEJMp1302981"},{"key":"2026060904500748000_16.6.e106819.15","doi-asserted-by":"publisher","DOI":"10.7326\/0003-4819-155-3-201108020-00005"},{"key":"2026060904500748000_16.6.e106819.16","doi-asserted-by":"crossref","DOI":"10.1097\/MD.0000000000025976","article-title":"Racial\/ethnic and socioeconomic variations in hospital length of stay: A state-based analysis","volume":"100","author":"Ghosh","year":"2021","journal-title":"Medicine (Baltimore)"},{"key":"#cr-split#-2026060904500748000_16.6.e106819.17.1","doi-asserted-by":"crossref","unstructured":"Hayes RM , Carter PR , Gollop ND , et al . 108 The impact of marital status on mortality and length of stay in patients admitted with myocardial infarction. BCS Annual Conference. 'Prediction and Prevention', 6-8 June 2016, Manchester Central, UK","DOI":"10.1136\/heartjnl-2016-309890.108"},{"key":"#cr-split#-2026060904500748000_16.6.e106819.17.2","doi-asserted-by":"crossref","unstructured":"June 2016:1-A77. doi:10.1136\/heartjnl-2016-309890.108","DOI":"10.1136\/heartjnl-2016-309890.108"},{"key":"2026060904500748000_16.6.e106819.18","doi-asserted-by":"crossref","first-page":"75","DOI":"10.1016\/j.arth.2024.07.009","article-title":"The Effect of Insurance Type on Length of Stay Following Total Knee Arthroplasty","volume":"40","author":"Dubin","year":"2025","journal-title":"J Arthroplasty"},{"key":"2026060904500748000_16.6.e106819.19","doi-asserted-by":"crossref","DOI":"10.1186\/s12911-022-02027-w","article-title":"Evaluation of factors that influenced the length of hospital stay using data mining techniques","volume":"22","author":"Eskandari","year":"2022","journal-title":"BMC Med Inform Decis Mak"},{"key":"2026060904500748000_16.6.e106819.20","doi-asserted-by":"crossref","first-page":"3325609","DOI":"10.1155\/2024\/3325609","article-title":"Hepatitis C Virus Infection and Hospital-Related Outcomes: A Systematic Review","volume":"2024","author":"Ng","year":"2024","journal-title":"Can J Gastroenterol Hepatol"},{"key":"2026060904500748000_16.6.e106819.21","doi-asserted-by":"crossref","DOI":"10.3390\/s23094178","article-title":"A Comprehensive Review on Machine Learning in Healthcare Industry: Classification, Restrictions, Opportunities and Challenges","volume":"23","author":"An","year":"2023","journal-title":"Sensors (Basel)"},{"key":"2026060904500748000_16.6.e106819.22","doi-asserted-by":"crossref","DOI":"10.1038\/s41598-022-11226-4","article-title":"Mortality prediction of patients in intensive care units using machine learning algorithms based on electronic health records","volume":"12","author":"Choi","year":"2022","journal-title":"Sci Rep"},{"key":"2026060904500748000_16.6.e106819.23","doi-asserted-by":"publisher","DOI":"10.1136\/bmjinnov-2020-000420"},{"key":"2026060904500748000_16.6.e106819.24","unstructured":"Johnson A , Bulgarelli L , Pollard T , et al . MIMIC-IV (version 3.0). PhysioNet 2024. doi:10.13026\/hxp0-hg59"},{"key":"2026060904500748000_16.6.e106819.25","doi-asserted-by":"crossref","DOI":"10.1038\/s41597-022-01899-x","article-title":"MIMIC-IV, a freely accessible electronic health record dataset","volume":"10","author":"Johnson","year":"2023","journal-title":"Sci Data"},{"key":"2026060904500748000_16.6.e106819.26","doi-asserted-by":"crossref","unstructured":"Goldberger AL , Amaral LAN , Glass L , et al . 2000;101. doi:10.1161\/01.CIR.101.23.e215","DOI":"10.1161\/01.CIR.101.23.e215"},{"key":"2026060904500748000_16.6.e106819.27","unstructured":"Oracle Corporation . MySQL: the world\u2019s most popular open-source database. 2024. Available: https:\/\/www.mysql.com\/"},{"key":"2026060904500748000_16.6.e106819.28","unstructured":"Oracle . What is MySQL?. 2021. Available: https:\/\/www.oracle.com\/mysql\/what-is-mysql\/"},{"key":"2026060904500748000_16.6.e106819.29","doi-asserted-by":"publisher","DOI":"10.1002\/mpr.329"},{"key":"2026060904500748000_16.6.e106819.30","doi-asserted-by":"crossref","unstructured":"Pradipta GA , Wardoyo R , Musdholifah A , et al . SMOTE for handling imbalanced data problem : a review. 2021 Sixth International Conference on Informatics and Computing (ICIC); Jakarta, Indonesia, 2021:1\u20138. doi:10.1109\/ICIC54025.2021.9632912","DOI":"10.1109\/ICIC54025.2021.9632912"},{"key":"2026060904500748000_16.6.e106819.31","doi-asserted-by":"publisher","DOI":"10.1111\/j.1553-2712.2011.01185.x"},{"key":"2026060904500748000_16.6.e106819.32","unstructured":"Wrld AI . Random forest: the ultimate guide to regression and classification. 2024. Available: https:\/\/medium.com\/@adeevmardia\/random-forest-the-ultimate-guide-to-regression-and-classification-33506d6cf865"},{"key":"2026060904500748000_16.6.e106819.33","doi-asserted-by":"crossref","DOI":"10.1186\/s12859-018-2264-5","article-title":"Random forest versus logistic regression: a large-scale benchmark experiment","volume":"19","author":"Couronn\u00e9","year":"2018","journal-title":"BMC Bioinformatics"},{"key":"2026060904500748000_16.6.e106819.34","doi-asserted-by":"crossref","DOI":"10.1186\/s12874-022-01685-8","article-title":"A comparison of statistical methods for modeling count data with an application to hospital length of stay","volume":"22","author":"Fernandez","year":"2022","journal-title":"BMC Med Res Methodol"},{"key":"2026060904500748000_16.6.e106819.35","doi-asserted-by":"crossref","DOI":"10.1186\/s12911-022-01855-0","article-title":"Predicting in-hospital length of stay: a two-stage modeling approach to account for highly skewed data","volume":"22","author":"Xu","year":"2022","journal-title":"BMC Med Inform Decis Mak"},{"key":"2026060904500748000_16.6.e106819.36","doi-asserted-by":"crossref","unstructured":"Zeileis A , Kleiber C , Jackman S . Regression models for count data in r. J Stat Softw 2008;27. doi:10.18637\/jss.v027.i08","DOI":"10.18637\/jss.v027.i08"},{"key":"2026060904500748000_16.6.e106819.37","doi-asserted-by":"crossref","unstructured":"Hastie T , Tibshirani R . Generalized additive models. In: Wiley StatsRef: Statistics Reference Online. Wiley, 2014.","DOI":"10.1002\/9781118445112.stat03141"},{"key":"2026060904500748000_16.6.e106819.38","doi-asserted-by":"crossref","first-page":"152","DOI":"10.21037\/atm.2019.03.29","article-title":"Predictive analytics with gradient boosting in clinical medicine","volume":"7","author":"Zhang","year":"2019","journal-title":"Ann Transl Med"},{"key":"2026060904500748000_16.6.e106819.39","doi-asserted-by":"publisher","DOI":"10.1097\/00006199-200211000-00009"},{"key":"2026060904500748000_16.6.e106819.40","doi-asserted-by":"crossref","unstructured":"Zwanenburg A , Lock S . Familiar: end-to-end automated machine learning and model evaluation. Contributed Packages; 2022.","DOI":"10.32614\/CRAN.package.familiar"},{"key":"2026060904500748000_16.6.e106819.41","doi-asserted-by":"crossref","unstructured":"Verma VK , Saxena K , Banodha U . Analysis Effect of K Values Used in K Fold Cross Validation for Enhancing Performance of Machine Learning Model with Decision Tree.2024:374\u201396.","DOI":"10.1007\/978-3-031-56700-1_30"},{"key":"2026060904500748000_16.6.e106819.42","doi-asserted-by":"crossref","DOI":"10.2196\/49023","article-title":"Practical Considerations and Applied Examples of Cross-Validation for Model Development and Evaluation in Health Care: Tutorial","volume":"2","author":"Wilimitis","year":"2023","journal-title":"JMIR AI"},{"key":"2026060904500748000_16.6.e106819.43","unstructured":"RStudio Team . RStudio: integrated development for R. 2024. Available: https:\/\/www.rstudio.com\/"},{"key":"2026060904500748000_16.6.e106819.44","unstructured":"R Core Team . R: a language and environment for statistical computing. 2024. Available: https:\/\/www.R-project.org\/"},{"key":"2026060904500748000_16.6.e106819.45","doi-asserted-by":"publisher","DOI":"10.21105\/joss.01686"},{"key":"2026060904500748000_16.6.e106819.46","doi-asserted-by":"crossref","unstructured":"Buuren S van , Groothuis-Oudshoorn K . mice: Multivariate Imputation by Chained Equations in R. J Stat Soft 2022;45. doi:10.18637\/jss.v045.i03","DOI":"10.18637\/jss.v045.i03"},{"key":"2026060904500748000_16.6.e106819.47","doi-asserted-by":"crossref","unstructured":"Smith BJ . MachineShop: Machine Learning Models and Tools; CRAN Contributed Packages; 2018.","DOI":"10.32614\/CRAN.package.MachineShop"},{"key":"2026060904500748000_16.6.e106819.48","unstructured":"Torgo L . Data mining with R. In: Chapman and Hall\/CRC. Available: https:\/\/www.taylorfrancis.com\/books\/9781315399096"},{"key":"2026060904500748000_16.6.e106819.49","doi-asserted-by":"crossref","unstructured":"Venables WN , Ripley BD . Modern Applied Statistics with S. New York, NY: Springer, 2002.","DOI":"10.1007\/978-0-387-21706-2"},{"key":"2026060904500748000_16.6.e106819.50","doi-asserted-by":"publisher","DOI":"10.1111\/J.1467-9868.2010.00749.X"},{"key":"2026060904500748000_16.6.e106819.51","unstructured":"Wickham H . Ggplot2. Springer International Publishing; 2016. Available: http:\/\/link.springer.com\/10.1007\/978-3-319-24277-4"},{"key":"2026060904500748000_16.6.e106819.52","unstructured":"Liaw A , Wiener M . Classification and regression by randomforest. 2002."},{"key":"2026060904500748000_16.6.e106819.53","doi-asserted-by":"crossref","unstructured":"Yoshida K , Bartel A . Tableone: create \u201ctable 1\u201d to describe baseline characteristics with or without propensity score weights. CRAN:Contributed Packages; 2014.","DOI":"10.32614\/CRAN.package.tableone"},{"key":"2026060904500748000_16.6.e106819.54","doi-asserted-by":"crossref","first-page":"251","DOI":"10.3961\/jpmph.21.151","article-title":"Trends of the Global Hepatitis C Disease Burden: Strategies to Achieve Elimination","volume":"54","author":"Brunner","year":"2021","journal-title":"J Prev Med Public Health"},{"key":"2026060904500748000_16.6.e106819.55","doi-asserted-by":"publisher","DOI":"10.3748\/wjg.v22.i34.7824"},{"key":"2026060904500748000_16.6.e106819.56","doi-asserted-by":"crossref","first-page":"S34","DOI":"10.1093\/ajhp\/zxy054","article-title":"Development and validation of a medication regimen complexity scoring tool for critically ill patients","volume":"76","author":"Gwynn","year":"2019","journal-title":"Am J Health Syst Pharm"},{"key":"2026060904500748000_16.6.e106819.57","doi-asserted-by":"crossref","DOI":"10.1038\/s41598-024-64911-x","article-title":"Outcomes and factors associated with prolonged stays among patients admitted to adult intensive care unit in a resource-limited setting: a multicenter chart review","volume":"14","author":"Bekele","year":"2024","journal-title":"Sci Rep"},{"key":"2026060904500748000_16.6.e106819.58","doi-asserted-by":"crossref","DOI":"10.1038\/s41598-022-17091-5","article-title":"Prediction algorithm for ICU mortality and length of stay using machine learning","volume":"12","author":"Iwase","year":"2022","journal-title":"Sci Rep"},{"key":"2026060904500748000_16.6.e106819.59","doi-asserted-by":"crossref","DOI":"10.2196\/21347","article-title":"Predicting Intensive Care Unit Length of Stay and Mortality Using Patient Vital Signs: Machine Learning Model Development and Validation","volume":"9","author":"Alghatani","year":"2021","journal-title":"JMIR Med Inform"},{"key":"2026060904500748000_16.6.e106819.60","doi-asserted-by":"crossref","DOI":"10.1186\/s12913-018-2916-1","article-title":"Evaluation of hospital outcomes: the relation between length-of-stay, readmission, and mortality in a large international administrative database","volume":"18","author":"Lingsma","year":"2018","journal-title":"BMC Health Serv Res"},{"key":"2026060904500748000_16.6.e106819.61","first-page":"18","article-title":"Association between race and risk of ICU mortality in mechanically ventilated COVID-19 patients at a safety net hospital","volume":"114","author":"Olanipekun","year":"2022","journal-title":"J Natl Med Assoc"},{"key":"2026060904500748000_16.6.e106819.62","doi-asserted-by":"crossref","first-page":"827","DOI":"10.1109\/JBHI.2020.2995836","article-title":"Predicting Discharge Destination of Critically Ill Patients Using Machine Learning","volume":"25","author":"Abad","year":"2021","journal-title":"IEEE J Biomed Health Inform"},{"key":"2026060904500748000_16.6.e106819.63","doi-asserted-by":"crossref","DOI":"10.1186\/s12913-022-08615-w","article-title":"Early prediction of patient discharge disposition in acute neurological care using machine learning","volume":"22","author":"Mickle","year":"2022","journal-title":"BMC Health Serv Res"}],"container-title":["BMJ Open"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/syndication.highwire.org\/content\/doi\/10.1136\/bmjopen-2025-106819","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,9]],"date-time":"2026-06-09T11:50:48Z","timestamp":1781005848000},"score":1,"resource":{"primary":{"URL":"https:\/\/bmjopen.bmj.com\/lookup\/doi\/10.1136\/bmjopen-2025-106819"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6]]},"references-count":64,"journal-issue":{"issue":"6","published-online":{"date-parts":[[2026,6,9]]},"published-print":{"date-parts":[[2026,6]]}},"alternative-id":["10.1136\/bmjopen-2025-106819"],"URL":"https:\/\/doi.org\/10.1136\/bmjopen-2025-106819","relation":{},"ISSN":["2044-6055","2044-6055"],"issn-type":[{"value":"2044-6055","type":"print"},{"value":"2044-6055","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,6]]}}}