Construction and validation of a nomogram model for cognitive impairment in heart failure patients.

Background: Patients with heart failure face a significantly elevated risk of cognitive impairment, yet clinical recognition remains inadequate-particularly among younger individuals and those with mild symptoms, leading to frequent underdiagnosis. The increasing prevalence among younger patients further worsens prognosis. This study aims to develop a tool to aid clinicians in the early identification of high-risk individuals and support informed clinical decision-making. Methods: Based on evidence-based literature and biopsychosocial holistic model of cardiovascular health, this study included 320 patients with heart failure hospitalized in the Second Hospital of Hebei Medical University from October 2023 to April 2024 to construct the model, and 80 patients from May to July 2024 were selected for temporal validation. MoCA was used to evaluate cognitive function. LASSO regression was used to select variables, Logistic regression was used to construct a nomogram model, and Bootstrap method (1,000 times) was used to evaluate the discrimination, calibration and clinical applicability of the model. Results: The incidence of cognitive impairment was 68.75% in the model group and 56.25% in the validation group. Finally, five variables including age, education level, coronary heart disease, cardiac diastolic function and physical frailty were included. The AUC of internal and temporal validation of the model were 80.2% and 72.44%, respectively, which had good prediction performance. Conclusion: The calibration curve and decision curve of the model showed a high degree of fit, which had strong clinical practicability. This model provides a reliable tool for early identification of cognitive impairment in patients with heart failure.