Predicting Short-Term Mortality in Elderly ICU Patients with Diabetes and Heart Failure: A Distributional Inference Framework

TL;DR

This study introduces a novel probabilistic framework for predicting short-term mortality in elderly ICU patients with diabetes and heart failure, utilizing distributional inference to improve personalized risk assessment.

Contribution

It develops a distribution-aware machine learning model that provides uncertainty estimates, enhancing clinical decision-making for a high-risk, understudied patient group.

Findings

CatBoost achieved AUROC of 0.863 on test data.

19 key variables identified for mortality prediction.

Distributional inference improves risk assessment accuracy.

Abstract

Elderly ICU patients with coexisting diabetes mellitus and heart failure experience markedly elevated short-term mortality, yet few predictive models are tailored to this high-risk group. Diabetes mellitus affects nearly 30% of U.S. adults over 65, and significantly increases the risk of heart failure. When combined, these conditions worsen frailty, renal dysfunction, and hospitalization risk, leading to one-year mortality rates of up to 40%. Despite their clinical burden and complexity, no established models address individualized mortality prediction in elderly ICU patients with both diabetes mellitus and heart failure. We developed and validated a probabilistic mortality prediction framework using the MIMIC-IV database, targeting 65-90-year-old patients with both diabetes mellitus and heart failure. Using a two-stage feature selection pipeline and a cohort of 1,478 patients, we identified 19 clinically significant variables that reflect physiology, comorbidities, and intensity of treatment. Among six ML models benchmarked, CatBoost achieved the highest test AUROC (0.863), balancing performance and interpretability. To enhance clinical relevance, we employed the DREAM algorithm to generate posterior mortality risk distributions rather than point estimates, enabling assessment of both risk magnitude and uncertainty. This distribution-aware approach facilitates individualized triage in complex ICU settings. Interpretability was further supported via ablation and ALE analysis, highlighting key predictors such as APS III, oxygen flow, GCS eye, and Braden Mobility. Our model enables transparent, personalized, and uncertainty-informed decision support for high-risk ICU populations.