Assessment and Prediction of Clinical Outcomes for ICU-Admitted Patients Diagnosed with Hepatitis: Integrating Sociodemographic and Comorbidity Data

Hepatitis, a leading global health challenge, contributes to over 1.3 million deaths annually, with hepatitis B and C accounting for the majority of these fatalities. Intensive care unit (ICU) management of patients is particularly challenging due to the complex clinical care and resource demands. This study focuses on predicting Length of Stay (LoS) and discharge outcomes for ICU-admitted hepatitis patients using machine learning models. Despite advancements in ICU predictive analytics, limited research has specifically addressed hepatitis patients, creating a gap in optimizing care for this population. Leveraging data from the MIMIC-IV database, which includes around 94,500 ICU patient records, this study uses sociodemographic details, clinical characteristics, and resource utilization metrics to develop predictive models. Using Random Forest, Logistic Regression, Gradient Boosting Machines, and Generalized Additive Model with Negative Binomial Regression, these models identified medications, procedures, comorbidities, age, and race as key predictors. Total LoS emerged as a pivotal factor in predicting discharge outcomes and location. These findings provide actionable insights to improve resource allocation, enhance clinical decision-making, and inform future ICU management strategies for hepatitis patients.