Construction of an inflammatory, nutritional, and metabolic prognostic risk score in patients with heart failure with preserved ejection fraction: a machine learning-based approach

Abstract

Abstract Background Chronic inflammation, malnutrition, and metabolic syndrome contribute to the underlying mechanisms of heart failure with preserved ejection fraction (HFpEF). Inflammatory, nutritional, and metabolic biomarkers often interact with each other and affect the prognosis of patients. Purpose We aimed to identify the most predictive indicators from a pool of 21 biomarkers encompassing inflammation, nutritional status, as well as lipid, glucose, thyroid, and uric acid metabolism. Subsequently, predictive biomarkers were used to develop a risk score to enhance risk prediction for patients with HFpEF. Methods We included patients diagnosed with HFpEF and without infective or systemic disease. The primary outcome was all-cause mortality. We employed the Least Absolute Shrinkage and Selection Operator (LASSO) regression to screen the biomarkers. A machine learning-based approach was utilized to fine-tune the optimal model parameters. Additionally, we generated 1000 bootstrapping datasets to identify biomarkers recurring above a 95% frequency in repetitions, which were then employed to formulate the biomarker risk score. The discrimination of incorporating the risk score into the basic model was evaluated using 100 iterations of 5-fold cross-validation to assess the predictive efficacy. Results Among the 1311 included patients (with a median age of 64 years and 42.6% female), 363 patients (27.7%) experienced mortality over a median follow-up period of 2.7 years. The final risk score model was derived from 5 biomarkers—albumin (ALB), red blood cell distribution width-standard deviation (RDW-SD), lymphocytes, triiodothyronine (T3), and uric acid—each selected in over 95% of 1000 bootstrapping iterations. Integration of this risk score into the basic model notably enhanced discrimination (∆C-index=0.015, 95% CI 0.005-0.023) and reclassification (IDI: 3.3%, 95% CI 1.7%-5.8%; NRI: 15.2%, 95% CI 6.5%-22.5%) for risk stratification. In time-dependent receiver operating characteristic (ROC) analysis, the mean area under the curve (AUC) of the risk score was 0.688, 0.710, and 0.738 at 1, 3, and 5 years post-discharge, respectively, in the cross-validation sets. Incorporating the risk score into the basic model significantly improved the AUC at 1, 3, and 5 years (DeLong test P-value<0.05). Furthermore, in multivariable Cox regression, the risk score demonstrated an independent association with all-cause mortality (HR: 1.81, 95% CI 1.51-2.16, P<0.001 per 1 score increase). Conclusions A risk score derived from 5 commonly used inflammatory, nutritional, thyroid and uric acid metabolic biomarkers can effectively identify high-risk patients with HFpEF. This approach supports the development of potential individualized management strategies for patients with HFpEF.Study population and model constructionPredictive performance of the risk score