A novel scoring system for heart failure screening utilizing combined electrocardiogram, phonocardiogram, and radial artery features

Abstract

Heart failure has high prevalence and mortality all over the world, the screening of heart failure still needs improving. This study aimed to construct a risk score of early clinical detection for heart failure based on features associated with electrocardiogram (ECG), phonocardiogram (PCG), and radial artery. This study collected data of 813 participants from the First People’s Hospital of Shangqiu city, between January 2023 and December 2023. All the samples were randomly divided into the training set and the testing set at a ratio of 7:3. Features selected through logistic regression and stepwise regression were included in the construction of the scoring system. The screening values of this scoring system for heart failure were verified in the testing set, with the odds ratio (OR), area under the curve (AUC), sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV) as well as their respective 95% confidence interval (CI) for evaluation. Totally 813 participants were included in this study. Participants with heart failure had higher scores than those without. The elevation of the score was associated with increased risk of heart failure in the training set (OR = 4.461, 95%CI: 3.209–6.200) and testing set (OR = 3.854, 95%CI: 2.364–6.281). The AUC of the risk score for heart failure was 0.802 (95%CI: 0.744–0.859) in the training set and 0.762 (95%CI: 0.669–0.855) in the testing set. The risk score had good screening value for heart failure, which might provide a valuable tool for early identification of patients with heart failure and offer timely interventions for these patients to improve their prognosis.