Elephants can detect aortic regurgitation – can you?

Introduction: Early diagnosis of aortic valve regurgitation (AR) and proper follow-up are important in order to avoid left ventricular dilatation. We hypothesized that a novel electronic stethoscope (Voqx™, Sanolla) with subsonic capabilities and an acoustic range of 0-2,000 Hz embedded with a machine-learning algorithm would improve physician’s ability to diagnose AR accurately.

Material and method: Using the Voqx™ stethoscope we recorded heart sounds from 25 patients with severe aortic stenosis referred for echocardiography. Of them, 11 patients also had AR. We used four standard heart auscultation points (2nd right intercostal space, 2nd left intercostal space, left lower sternal border, and apex). We looked for features that might differentiate between the two groups to implement a classifier for AR.

Results and discussion: The heart signals analysis showed that the best features for distinguishing between the AR and non-AR groups were in the subsonic range of 0-20 Hz and were the skewness and kurtosis of the heart infrasound (Figure 1, P<0.05). These features are related to the shape of the wave and the change in the center of gravity due to the occurrence of the AR in addition to the stenosis.

Conclusion: These preliminary results of an ongoing study show the potential of infrasound analysis to detect acoustic signals of aortic regurgitation, and to provide the family physicians with a simple diagnostic tool.

Figure 1. Kurtosis as a function of skewness of the heart’s infrasounds