Predictive machine learning model in intensive care unit patients with acute-on-chronic liver failure and two or more organ failures

Background/Aims: Prediction of short-term mortality in patients with acute-on-chronic liver failure (ACLF) admitted to the intensive care unit (ICU) may enhance effective management. Methods: To develop, explain, and validate a predictive machine learning (ML) model for short-term mortality in patients with ACLF with two or more organ failures (OFs). Utilizing a large ICU cohort with detailed clinical information, we identified ACLF patients with two or more OFs according to the EASL-CLIF and NACSELD definitions. ML model was developed for each definition to predict 30-day mortality. The Shapley value was estimated to explain the models. Validation and calibration of these models were performed. Results: Of 5,994 patients with cirrhosis admitted to ICU, 1,511 met NACSELD criteria, and 1,692 met EASL-CLIF grade II or higher criteria. The CatBoost ACLF (CBA) model had the greatest accuracy in the NACSELD cohort (area under curve [AUC] of 0.87), while the Random Forest ACLF (RFA) model performed best in the EASL-CLIF cohort (AUC of 0.83). Both models showed robust calibration. The models were explained by SHAP score analysis, yielding a rank list, and the top twelve predictors were selected. Both simplified models demonstrated similar performance (CBA model: AUC 0.89, RFA model: AUC 0.81) and significantly outperformed contemporary scoring systems, including CLIF-C ACLF and MELD 3.0. The models were validated in both internal and external cohorts. A simple-touse online tool was created to predict mortality rates. Conclusions: We presented explainable, well-validated, and calibrated predictive models for ACLF patients with two or more OFs, which outperformed existing predictive scores.