Key result
XGBoost model outperforms logistic regression in predicting diuretic resistance with an AUC of ~0.85.
Why the study?
Predicting diuretic resistance in HFpEF patients comorbid with MASLD is challenging and may benefit from machine learning approaches incorporating multi-organ interactions.
Does an XGBoost machine learning model accurately predict diuretic resistance in patients with HFpEF comorbid with MASLD?
Observational (n=586)
No
Does an XGBoost machine learning model accurately predict diuretic resistance in patients with HFpEF comorbid with MASLD?
Absolute Event Rate: 0.85% vs 0.74%
p-value: p=<0.001
An XGBoost machine learning model incorporating cardio-hepato-renal parameters, particularly FIB-4 and serum albumin, accurately predicts diuretic resistance in patients with HFpEF and MASLD.
May aid risk stratification in HFpEF-MASLD; extends regression models but remains hypothesis-generating pending prospective validation.
To explore machine learning models for predicting diuretic resistance (DR) in patients with heart failure with preserved ejection fraction (HFpEF) comorbid with metabolic dysfunction-associated steatotic liver disease (MASLD). In this retrospective study of 586 patients, four predictive algorithms were evaluated. The eXtreme Gradient Boosting (XGBoost) model was further interpreted using SHapley Additive exPlanations (SHAP) to identify non-linear feature interactions. XGBoost achieved the highest predictive performance (AUC: 0.850). SHAP analysis indicated that hepatic parameters, particularly the FIB-4 index and serum albumin, were strongly associated with DR, potentially rivaling traditional cardio-renal indices. Interaction analyses suggested that concurrent hepatic and renal impairment synergistically correlated with elevated DR risk. Patients stratified into the AI-derived high-risk phenotype experienced lower freedom from HF re-hospitalization (Log-rank P < 0.001). The XGBoost model, coupled with SHAP analysis, may serve as a valuable tool for DR risk stratification. Assessing multi-organ crosstalk across the cardio-hepato-renal axes could inform personalized volume management in this complex cohort.
No takes yet. Share an insight, caveat, or question.
Huang et al. (2026) conducted an observational in Heart failure with preserved ejection fraction (HFpEF) comorbid with metabolic dysfunction-associated steatotic liver disease (MASLD) (n=586). XGBoost machine learning model vs. Logistic regression model was evaluated on Prediction of diuretic resistance (Area Under the Curve) (p=<0.001). The XGBoost machine learning model accurately predicted diuretic resistance with an AUC of 0.850, significantly outperforming traditional logistic regression and identifying hepatic parameters as strong predictors.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: