Development and validation of a clinical prediction model for in-hospital heart failure risk following PCI in patients with coronary artery disease

Abstract

Objective: Patients with acute coronary syndrome (ACS) are at increased risk of in-hospital heart failure (HF) following percutaneous coronary intervention (PCI), yet understanding of the associated risk factors is limited. This study aims to identify predictors of in-hospital HF after PCI and to develop and validate a clinical prediction model for the early identification of high-risk patients.

Methods: We retrospectively analyzed data from the patients hospitalized for ACS who underwent PCI at Henan Provincial Hospital of Traditional Chinese Medicine from 01/01/2019-01/10/2023. Patients were classified into non-HF and HF groups based on the occurrence of heart failure after PCI. LASSO regression and logistic regression were employed to identify potential predictors. The model's diagnostic efficacy was assessed using receiver operating characteristic curves and calibration curves, while decision curve analysis and clinical impact curve were utilized to evaluate clinical benefits.

Results: A total of 309 patients were included in this study, of whom 79.93% were male, with a mean age of 57.84. Key predictors included New York Heart Association (NYHA) classification, smoking status, right coronary artery occlusion after PCI, left ejection fraction (LVEF), and N-terminal fragment of brain natriuretic peptides. The area under the curve (AUC) was 0.910 (95% CI: 0.868-0.953), indicating strong predictive ability. Decision curve analysis and clinical impact curve demonstrated good clinical applicability of the nomogram.

Conclusion: The identified predictors and the prediction model can be used in identifying high-risk individuals who develop HF hospital admission after PCI, or as a basis for further guiding personalized prevention and treatment.

Fig 1. LASSO regression for variable screening.

(A) LASSO coefficient path; (B) LASSO regularization path.

Fig 2. Receiver operating characteristic curve (A) and calibration curve (B) of clinical prediction model.

Fig 3. Application of clinical prediction model.

(A) Nomogram, where variable levels corresponded to the “Points” axis, with the green line indicating the confidence interval; the “Total Points” reflected the predicted risk on the “Risk” axis; (B) Decision curve analysis, where “None” assumed no patients are treated (net benefit is zero) and “All” assumed all patients are treated (showing net benefit in this extreme case). “Model” represents the benefit from decisions based on the model; (C) Clinical impact curve, where “Number high risk” indicated the total high-risk patients at different thresholds, and “Number high risk with events” indicated those high-risk patients with actual events.