Background: Heart failure (HF) is a significant global health concern, with limited diagnostic tools for efficient, cost-effective, and non-invasive detection. Transthoracic echocardiography (TTE) is widely used due to its availability and affordability, its accuracy depends on operator skill and re-quires specialist training for accurate results. This study aims to develop and validate seismocardiography (SCG)-based algorithms for HF detection.
Aims:The study aimed to develop an SCG algorithm and assess its diag-nostic performance in detection of heart failure (HF) and SCG's accuracy in identifying HF with preserved ejection fraction (HFpEF).
Methods: The study included 199 subjects with suspected HF and 20 pa-tients with known HF with reduced ejection fraction (HFrEF). Assessments were conducted using SCG, electrocardiogram, NYHA classification and transthoracic echocardiography. The SCG algorithm, "AnyHF-score" was developed to identify all subtypes of HF, including HFrEF, HF with mildly reduced (HFmEF) and HFpEF. Diagnostic accuracy was assessed using sensi-tivity, specificity, positive predictive value (PPV), negative predictive value (NPV), and the area under the receiver-operating characteristic curve (AUC-ROC).
Results: Following exclusion criteria, 208 subjects formed the final study population. The Any-HF score demonstrated an AUC of 82%, sensitivity of 90.9%, NPV of 87.5% and PPV of 52.6% in detecting all HF versus no HF. The AnyHF-score showed an AUC of 78.2 %, with a sensitivity of 88.2%, specificity of 43.8%, NPV of 93.3%, and PPV of 29.4% in detecting HFpEF vs no HF.
Conclusions: This study demonstrates the potential of SCG for identify-ing HF. The Any-HF score showed high diagnostic accuracy in detecting all types of HF and HFpEF. SCG could offer a cost-effective, non-invasive alternative for HF detection.