Key result
AI model combining auscultation and ECG accurately detects severe aortic stenosis with ~0.93 AUC.
Why the study?
Simple sensor-based procedures like auscultation and ECG can facilitate early diagnosis of valvular diseases, but the impact of combining these with machine learning for diagnosing valvular abnormalities and ventricular dysfunction was not established.
Does a machine learning model integrating auscultation and ECG data accurately diagnose severe aortic stenosis, severe mitral regurgitation, and left ventricular dysfunction in patients undergoing echocardiography?
Cross-Sectional (n=1,155)
Does a machine learning model integrating auscultation and ECG data accurately diagnose severe aortic stenosis, severe mitral regurgitation, and left ventricular dysfunction in patients undergoing echocardiography?
Effect estimate: AUC 0.93 for AS, 0.80 for MR, 0.75 for LVD
A multimodal AI approach combining auscultation and ECG data can efficiently detect severe valvular pathologies and left ventricular dysfunction, offering a potential early screening tool prior to echocardiography.
Supports multimodal AI screening for severe valvular disease; leaves open clinical adoption pending prospective validation.
Simple sensor-based procedures, including auscultation and electrocardiography (ECG), can facilitate early diagnosis of valvular diseases, resulting in timely treatment. This study assessed the impact of combining these sensor-based procedures with machine learning on diagnosing valvular abnormalities and ventricular dysfunction. Data from auscultation at three distinct locations and 12-lead ECGs were collected from 1052 patients undergoing echocardiography. An independent cohort of 103 patients was used for clinical validation. These patients were screened for severe aortic stenosis (AS), severe mitral regurgitation (MR), and left ventricular dysfunction (LVD) with ejection fractions ≤ 40%. Optimal neural networks were identified by a fourfold cross-validation training process using heart sounds and various ECG leads, and their outputs were combined using a stacking technique. This composite sensor model had high diagnostic efficiency (area under the receiver operating characteristic curve (AUC) values: AS, 0.93; MR, 0.80; LVD, 0.75). Notably, the contribution of individual sensors to disease detection was found to be disease-specific, underscoring the synergistic potential of the sensor fusion approach. Thus, machine learning models that integrate auscultation and ECG can efficiently detect conditions typically diagnosed via imaging. Moreover, this study highlights the potential of multimodal artificial intelligence applications.
No takes yet. Share an insight, caveat, or question.
Shiraga et al. (2023) conducted a cross-sectional in Valvular abnormalities and ventricular dysfunction (n=1,155). Combined auscultation and electrocardiography with machine learning was evaluated on Diagnostic efficiency (AUC) for severe aortic stenosis, severe mitral regurgitation, and left ventricular dysfunction (AUC 0.93 for AS, 0.80 for MR, 0.75 for LVD). A machine learning model integrating auscultation and ECG showed high diagnostic efficiency for severe aortic stenosis (AUC 0.93), severe mitral regurgitation (AUC 0.80), and LVD (AUC 0.75).
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: