ResApp Health Limited, a Brisbane, Australia-based digital health company developing smartphone applications for the diagnosis and management of respiratory disease, reports positive results from its prospective, double-blind obstructive sleep apnea (OSA) clinical study. Analysis confirmed that ResApp’s machine-learning algorithms were able to accurately identify OSA from a patient’s overnight breathing and snoring sounds recorded using only a smartphone placed on a bedside table. The company is working with Drs Philip Currie and Ivan Ling of Cardio Respiratory Sleep (CRS), who recruited patients at Hollywood Private Hospital and The Park Private Hospital in Perth, Australia.

Data from 582 adult patients was analyzed, of which 62% were male. The mean age of patients was 53 years (range 18-94) with a mean apnea hypopnea index (AHI) of 26/h (range 0-143).

ResApp’s algorithms achieved 84% sensitivity and 83% specificity for identifying patients with an AHI greater than or equal to 5/h (patients with mild, moderate, or severe OSA) compared to simultaneous gold standard in-laboratory polysomnography scored using the current 2012 American Academy of Sleep Medicine (AASM) scoring criteria. The area under the receiver operating characteristic curve (AUC, a standard measure of how well a test distinguishes between two diagnostic groups, where a value of 1 represents a perfect test) was 0.90. The algorithms were similarly able to identify patients with AHI greater than or equal to 15/h (moderate or severe OSA) and AHI greater than or equal to 30/h (severe OSA).

Currie and Ling say in a release, “The results from the study are excellent and we are one step closer to expanding the set of tools that can help identify people with sleep apnea. Today’s methods of sleep apnea diagnosis, either sleep laboratory polysomnography or home sleep testing, are not able to mass screen patients due to availability and costs, leaving a large unmet clinical and societal need to find a solution to population screen for OSA, especially in patients with existing heart disease, obesity, hypertension, atrial fibrillation, or type 2 diabetes.”

Associate professor Udantha Abeyratne, chief scientist of ResApp, says, “Sleep sound analysis has come of age and these results provide solid confirmation that snoring carries vital information on OSA. This work should provide an excellent platform to build an accurate, low-cost technology that can be used in OSA screening and long-term monitoring applications in a home setting.”

Tony Keating, CEO and managing director of ResApp, says, “By using an off-the-shelf smartphone, we have the opportunity to deliver a highly-scalable, accurate and easy-to-use screening test for OSA. This has the potential to improve the health of a large portion of the population and significantly reduce the economic burden that undiagnosed OSA causes. These clinical study results confirm that our sleep apnea solution works very well and we now look forward to comparing the performance of our algorithms with home sleep testing, which is the final step before we make a regulatory submission.”

The company is currently recruiting patients undergoing home sleep testing and is targeting a regulatory submission for its sleep apnea screening product by the end of this calendar year.