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

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

“Artificial intelligence-based electronic auscultation is a promising new tool for automatic screening and diagnosis of valvular heart disease,” said researchers led by Tamer Ghaneim from the Department of Cardiology, Lady Davis Carmel Medical Center, Haifa, Israel.

In this two-stage study, Ghanayem and colleagues developed an electronic stethoscope, based on artificial intelligence and ultrasound, to diagnose ankylosing spondylitis. The AI-powered speaker has subsonic capabilities and a sound range of 3 to 2000 Hz.

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

The second phase of the study was conducted at a different medical center. Here, the researchers tested the device on an additional 106 patients referred for echocardiography, which included individuals with other valvular diseases.

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

When applied to the validation set, the sensitivity and specificity of the device 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 preliminary findings show that an AI-based stethoscope with infrasound capabilities can accurately diagnose ankylosing spondylitis,” the researchers said.

Audio Headphones vs. Electronic Headphones

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

Grenier, who works at the Montreal Medical Research Institute in Montreal, Canada, says acoustic hearing aids are useful because of their durability and ergonomic design.

“However, it is not ideal because it attenuates the transmission of sound in proportion to frequency, and its frequency response displays a maximum and a minimum at very specific frequencies due to the effects of tubular resonance, and differences in transmission characteristics have also been observed between the 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]

They added: “Because the intensity of heart sounds and murmurs are generally faint with some sounds below the hearing limit, audio signal amplification with a more uniform frequency response was introduced in electronic stethoscopes to solve the major limitations of stethoscopes.” [Clin Eng 1988;5:355-357;
J Clin Monit 1986;2:151-154]

However, the electronic speakers’ sensitivity to handicrafts and ambient electronic noise offset these advantages. In addition, it does not allow the sensitivity of the human ear, which varies greatly as a function of frequency.

As a result, the authors noted, “the stethoscope remains the most widely used today, even if many advanced electronic stethoscope-building designs have been patented over the past 20 years.”