Health clinics in the developing world often are noisy, ill-equipped places that rely on a solitary medic to serve dozens of patients.

Such conditions can make it doubly difficult to detect signs of bacterial pneumonia or other respiratory illnesses that kill nearly 1 million children worldwide each year.

To tackle the problem, engineers, physicians, and public health workers at Johns Hopkins University joined forces to re-engineer an iconic medical device that has changed little since its debut in the early 1800s: the stethoscope.

Funded by the National Heart, Lung, and Blood Institute, NASA, and the Bill & Melinda Gates Foundation, the team create a device that uses digital sensing technology to capture sound, active acoustics for noise cancellation, and artificial intelligence “to help health workers make accurate pneumonia diagnoses.” As the demonstration in the above video  shows, the researchers simulated noisy environment in the lab (70 decibels, according to the sound meter). They then compared the audio heard through a top-notch commercial stethoscope, in which the breathing sounds are mixed with ambient noise, to that heard through the smart stethoscope, which uses active acoustic filtering to isolate the breathing sounds.

The researchers first had to determine just how useful lung sounds could be in diagnosing pneumonia. They started by equipping local health workers with commercially available stethoscopes that the team had augmented with small digital recorders. The clinicians the recorded lung sounds from the children they encountered in rural clinics and urban hospitals, then transmitted the files to expert pulmonologists at Johns Hopkins, who listened to these sounds and offered more informed medical opinions.

The commercial stethoscope’s limitations soon became problematic. To get a decent recording from the lungs, the health worker had to position the device’s chest piece in just the right places on the child’s chest and back. But many typically had only basic training in how to use the tool, and often missed the “sweet spots.” Plus, they usually were making their recordings in noisy settings and not a doctor’s quiet office, and unreliable Internet access meant that it often took many hours or even days to get back an expert diagnosis.

The Johns Hopkins doctors decided they’d have to entirely rethink the stethoscope. So they approached the department of electrical and computer engineering, where two audio engineering specialists were were eager to take up the challenge.

Other Johns Hopkins colleagues founded a start-up called Sonavi Labs to quickly turn the prototype smart stethoscope into a commercially viable product. Their start-ups first products, digital stethoscopes called the Feelix and FeelixPro, are set to launch in early 2019.

This post was drawn from “A Smart Stethoscope Puts AI in Medics’ Ears,” which ran in the February 2019 issue of IEEE Spectrum and was republished by JHU. It was written by Mounya Elhilali, an associate professor of electrical and computer engineering at Johns Hopkins University in Baltimore, Md., where she also directs the Laboratory for Computational Audio Perception, and James E. West, a research professor of electrical and computer engineering and of mechanical engineering at Johns Hopkins, which he joined in 2001 after 40 years as a researcher at Bell Labs.

Filed under: Special Features

Tags: artificial intelligence, Biomedical Engineering, Johns Hopkins University, public health, smart stethoscope