Key result
Seven-variable XGBoost model outperforms standard scores for in-hospital mortality with ~0.92 AUC.
Why the study?
Patients with CHF and T2DM admitted to ICUs have elevated in-hospital mortality risk, and conventional scoring systems may not fully capture their clinical complexity.
Does an interpretable machine learning model (XGBoost with SHAP) accurately predict in-hospital mortality in ICU patients with concurrent CHF and T2DM compared to traditional statistical and scoring methods?
Cross-Sectional (n=573)
Yes
Does an interpretable machine learning model (XGBoost with SHAP) accurately predict in-hospital mortality in ICU patients with concurrent CHF and T2DM compared to traditional statistical and scoring methods?
An interpretable XGBoost machine learning model significantly outperformed traditional clinical scoring systems (SOFA, LODS) in accurately predicting in-hospital mortality for critically ill patients with concurrent heart failure and diabetes.
Background Patients with congestive heart failure (CHF) and type 2 diabetes mellitus (T2DM) are at elevated risk of in-hospital mortality, particularly in intensive care units (ICUs). Conventional scoring systems may not fully capture the clinical complexity of such comorbidities. This study aimed to construct an interpretable machine learning model to predict in-hospital mortality in this high-risk group. Methods A retrospective study included 573 ICU patients with CHF and T2DM admitted to three hospitals in Henan, China (Jan 2025–Jun 2026). Seven predictors—body mass index (BMI), myocardial infarction, mild liver disease, SOFA score, LODS score, white blood cell (WBC) count, and serum creatinine—were identified via stepwise logistic regression. XGBoost and four other machine learning algorithms (KNN, SVM, CatBoost, AdaBoost) were trained and evaluated. Model performance was assessed using AUC, accuracy, sensitivity, specificity, and F1-score. SHAP (SHapley Additive exPlanations) was used to interpret XGBoost predictions. Results XGBoost achieved the best performance (AUC 0.917, sensitivity 86.8%, specificity 96.6%, accuracy 74.8%). SHAP analysis indicated that mild liver disease, LODS score, BMI, WBC count, and SOFA score were the top contributors, jointly explaining over 77% of the predictive power. Myocardial infarction, liver disease, elevated WBC, and higher SOFA/LODS scores increased mortality risk, while higher BMI and serum creatinine were protective—supporting the obesity paradox and sarcopenia hypothesis. Conclusion An XGBoost model with SHAP interpretation provides accurate, explainable prediction of in-hospital mortality in ICU patients with CHF and T2DM, offering a valuable tool for early risk stratification and clinical decision-making.
No takes yet. Share an insight, caveat, or question.
Hu et al. (2026) conducted a cross-sectional in Congestive heart failure (CHF) and type 2 diabetes mellitus (T2DM) (n=573). XGBoost machine learning predictive model (seven clinical predictors) vs. Logistic regression and traditional clinical scoring systems (SOFA, LODS) was evaluated on In-hospital mortality. An XGBoost machine learning model incorporating seven clinical predictors achieved an AUC of 0.917 for predicting in-hospital mortality, outperforming traditional logistic regression and scoring systems.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: