A feasibility study evaluating seismocardiography for the detection of heart failure.

Abstract

The study aimed to develop a seismocardiograph (SCG)- based algorithm and assess its diagnostic performance in the detection of heart failure (HF). A total of 218 subjects were included: 198 with suspected HF and 20 with known HF with reduced ejection fraction (HFrEF) were included for testing only. Assessments were conducted using SCG, N-terminal pro b-type natriuretic peptide (NT-proBNP), electrocardiogram, NYHA classification and echocardiography. SCG-based algorithms, "AnyHF score" were developed to identify all subtypes of HF and "HFrEF-score" to identify HFrEF. Diagnostic accuracy was assessed using sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), and the area under the receiver-operating characteristic curve (AUC-ROC). The AnyHF score demonstrated an AUC of 82%, sensitivity of 90.9%, specificity of 43.8%, NPV of 87.5% and PPV of 52.6% in detecting HF versus no HF. A balanced comparative analysis was performed between NT-proBNP and the HFrEF-score for detecting HFrEF versus no HF. NT-proBNP demonstrated an AUC of 94.7%, sensitivity 94.1%, specificity 68.8%, NPV 99%, and PPV 27.1%. The HFrEF-score showed an AUC of 92.9%, sensitivity 88.2%, specificity 92% (p < 0.001), NPV 98.4%, and PPV 57.7% (p = 0.007). The SCG-scores also categorized 71 patients (51%) from the no HF group, referred on suspicion of HF, as minimal risk of HF. This study suggests that SCG has potential to aid in the diagnostic process of HF. The SCG-based algorithms "AnyHF-score" and "HFrEF-score" demonstrated high diagnostic performance in identifying HF.