Abstract
Introduction: Asymptomatic cardiac dysfunction (ACD) has management implications, and been shown to have special cardiac electrical signal features, magnetocardiography (MCG) can be used in a range of cardiovascular diseases by tracing subtle changes of the cardiac electromagnetic activity. Hypothesis: MCG could be used to identify ACD in patients with heart failure (HF) risk factors. Methods: This study was a subcohort of a prospective MCG study (NCT05392712), in which patients hospitalized with ischemic heart disease (IHD) were all underwent MCG examination. Patients with asymptomatic HF, according to the American Heart Association Heart Failure Guideline, were divided into “at risk for HF” (stage A) or “pre-HF” (stage B, namely ACD). Supervised machine-learning were undertaken to select specific MCG features and establish MCG recognition model for pre-HF (MCG-HF model), which was further tested in an independent test set. In the end, we compared the performance of MCG-HF model with N-terminal pro-B-type natriuretic peptide (NT-proBNP) and the optimized Atherosclerosis Risk in Communities (ARIC) HF risk score for identifying pre-HF. Results: A total of 420 inpatients with IHD, of which 111 were in stage A and 309 in stage B, were included in this study. In an independent test set (n= 126), the MCG-HF model for identifying patients at stage B demonstrated 95.7% sensitivity and 66.7% specificity (area under the receiver-operating characteristic curve [AUC]: 0.904; 95% confidence interval [CI]: 0.800 to 0.957). The AUC for optimized ARIC model and NT-proBNP model were 0.631 (95% CI:0.572 to 0.690) and 0.761 (95% CI:0.716 to 0.807), respectively. Conventional methods for pre-HF recognition showed inferior discriminative ability. Conclusions: The MCG based on machine learning shows valuable performance in identifying ACD, the cardiac magnetic signal detection technology provides a rapid and optimized screening tool in patients at risk for HF.
Published Version
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
