AI-based stethoscope reliably detects aortic stenosis | Latest news for doctors, nurses and pharmacists | cardiology

A recent study has shown that a stethoscope that uses artificial intelligence (AI) and has infrasound capabilities provides an accurate diagnosis of aortic stenosis (AS).

“AI-based electronic auscultation is a promising new tool for automated screening and diagnosis of valvular heart disease,” said the researchers, led by Tamer Ghanayim of the Department of Cardiology at Lady Davis Carmel Medical Center in Haifa, Israel.

In this two-stage study, Ghanayim and colleagues developed an AI and infrasound-based electronic stethoscope for the diagnosis of AS. The AI-based stethoscope had subsonic capabilities and an acoustic range of 3 to 2,000 Hz.

In the first phase of the study, researchers used VoqX to record heart sounds from 100 patients who were referred for echocardiography (lead group), 50 with moderate or severe AS and 50 without valvular heart disease. They applied an AI-based supervised learning model to the auscultation data from the first 100 patients used for training to construct a diagnostic algorithm that was tested on a validation group consisting of 50 other patients: 25 with AS and 25 without.

The second phase of the study was conducted at a different medical center. Here, researchers tested the device on 106 additional patients referred for echocardiography, including those with other heart valve diseases.

Analysis of the data obtained at the aortic and lung auscultation points from the lead group revealed that the AI-based algorithm accurately identified moderate or severe AS with a sensitivity of 86 percent and a specificity of 100 percent. [Am J Med 2022;135:1124-1133]

When applied to the validation group, the device’s sensitivity and specificity were 84 percent and 92 percent, respectively. In the additional test group, the corresponding values ​​were 90 percent and 84 percent. Sensitivity rates for mild, moderate, and severe AS were 55 percent, 76 percent, and 93 percent, respectively.

“Our first results show that an AI-based stethoscope with infrasound capabilities can accurately diagnose AS,” the researchers said.

Acoustic vs. electronic stethoscopes

According to a report by Marie-Claude Grenier and colleagues, the stethoscope, one of the simplest and most practical diagnostic tools in medicine, is currently available in two different versions on the market, acoustic and electronic. [Am J Cardiol 1998;81:653-656; Circulation 1996;93:1250-1253]

Grenier, who works at the Institut de recherches cliniques de Montréal in Montréal, Canada, explains that acoustic stethoscopes are useful because of their robustness and ergonomic design.

“However, they are not ideal because they attenuate sound transmission proportional to frequency, their frequency response has peaks and valleys at very specific frequencies due to tube resonance effects, and differences in transmission characteristics are observed between different models,” Grenier and her team reported. [J Acoust Soc Am 1992;91:2224-2228;
Bull Europ Physiopathol Respir 1985;21:49-54; J Appl Physiol 1983;54:714-719;
Am Heart J 1982;104:269-275]

“Because the intensity of heart sounds and murmurs is generally weak, with some sounds below the hearing threshold, amplification of the acoustic signal with a smoother frequency response has been introduced in electronic stethoscopes to overcome the major limitations of acoustic stethoscopes,” they added. [Clin Eng 1988;5:355-357;
J Clin Monit 1986;2:151-154]

However, the sensitivity of electronic stethoscopes to tampering artifacts and electronic and environmental noise negates such advantages. In addition, they do not take into account the sensitivity of the human ear, which fluctuates greatly as a function of frequency.

“Consequently, the acoustic stethoscope is still the most widely used today, even though several sophisticated designs for building electronic stethoscopes have been patented over the past 20 years,” the authors noted.