Study: Smartphone app that listens to breathing, determines respiratory diseases is 89 percent accurate

By Jonah Comstock
Share

A smartphone-based system for diagnosing respiratory diseases achieved an accuracy of 89 percent in a recent clinical study of 524 pediatric patients conducted by the company at Joondalup Health Campus (JHC) and Princess Margaret Hospital (PMH) in Perth, Western Australia.

Perth-based ResApp essentially uses the smartphone microphone as a stethoscope to listen to a patient’s breathing. But instead of relying solely on a doctor’s ears to form a diagnosis from those sounds, ResApp has been developing machine-learning algorithms that will automatically determine which respiratory condition a patient might have, including pneumonia, asthma, bronchiolitis and COPD. In the future, the company hopes to integrate those algorithms into telehealth offerings as well as making them available for clinical use.

ResApp released data from this trial previously in November, but that data set included fewer patients. The larger group is starting to show ResApp’s effectiveness in diagnosing less common conditions.

“We are pleased to again report high levels of accuracy on a dataset that is more than 50 percent larger than the previously used dataset,” Dr. Tony Keating, CEO and Managing Director of ResApp, said in a statement. “These updated results reaffirm the algorithm’s clinical accuracy right before we enter the pivotal studies needed for our upcoming premarket submission to the US Food and Drug Administration. In addition, these preliminary results for the separation of bacterial and atypical pneumonia from viral pneumonia are very exciting as they demonstrate the power of ResApp’s algorithm in supporting clinicians in making critical decisions for patient treatment.”

Eighty-nine percent was the overall accuracy in differentiating between lower respiratory tract disease, upper respiratory tract infections, and healthy patients. In particular cases, the accuracy was much higher: for instance, for the differential diagnosis of croup, viral pneumonia, bronchiolitis and upper respiratory tract infections ResApp’s algorithms achieved accuracy levels between 90 and 98 percent. In a subset of patients that had been initially cleared by a doctor but diagnosed with lower respiratory tract disease after additional clinical testing, the ResApp diagnosed them correctly 97 percent of the time.

According to The West Australian, ResApp had its first meeting with the FDA last month to discuss the company’s clearance pathway. 

“Our pre-submission meeting with the FDA was very productive and we were encouraged by the high level of engagement,” Keating said at the time. “We have obtained the clarity required to optimize our clinical and regulatory pathway.”