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

Clinical Snapshot

Key Findings

• P Value: Not reported in abstract

• Effect Size: Random Forest achieved accuracy 0.87 vs 0.82 for logistic regression in discharge prediction

• Primary Outcome: ICU length of stay, hospital discharge outcomes, and discharge location prediction

• Nnt Or Sensitivity: AUC 0.95 for Random Forest vs 0.89 for logistic regression; R² up to 0.82 for length of stay prediction

• Confidence Interval: Not specified in abstract

Clinical Application

Requires implementation of ML infrastructure and integration with electronic health records Relevant for Australian ICUs managing hepatitis patients; could inform resource allocation and discharge planning in public hospital systems ICU-admitted patients with viral hepatitis requiring resource planning and discharge coordination

Abstract

BACKGROUND: Hepatitis, a disease characterised by inflammation of the liver, is a leading global health challenge that contributes to over 1.3 million 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. METHODS: 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 94 500 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. RESULTS: 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 (R² 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. CONCLUSIONS: 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.

References

1. 1.Alluri, D. S., & Pabon-Rodriguez, F. M. (2026). 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. BMJ Open. https://doi.org/10.1136/bmjopen-2025-106819