FDA clears pulse ox-analyzing AI from EnsoData to diagnose sleep disorders

A new artificial intelligence algorithm may be able to replace the bulky and often expensive equipment typically used in sleep studies to produce accurate diagnoses of apneas and other disorders.

EnsoData’s algorithm is now cleared by the FDA, the Wisconsin-based company announced Monday. It analyzes data collected during sleep studies by pulse oximeters—which are typically less expensive and more widely accessible than the standard sleep-tracking equipment used in polysomnography.

The new AI tool builds on a previous algorithm developed by EnsoData. Dubbed EnsoSleep, it relied on machine learning AI to analyze readings from typical multi-sensor polysomnography equipment to churn out more accurate sleep disorder diagnoses.

EnsoSleep PPG, meanwhile, looks instead at the light-based measurements collected by the pulse oximetry technology now available in many smartwatches, rings and wearables.

Its deep learning AI can parse through changes in oxygen saturation levels and heart rate to spot sleep-disordered respiratory events, map out a patient’s sleep cycles and track other sleep measures. Doctors then look over the algorithm’s findings and highlight the most important indicators before sharing the results with their patients as a comprehensive sleep report.

“Our interoperable AI tools are democratizing the ability to accurately measure sleep and aid in the diagnosis of sleep disorders broadly—for the existing category of FDA-cleared pulse oximetry devices and sensors that are already widely deployed, in-use clinically, and growing in their adoption daily,” Chris Fernandez, EnsoData’s co-founder and chief research officer, said in the announcement.

“With PPGs among the most commonplace of medical waveforms collected across healthcare settings, from diagnostic tests to bedside monitors and consumer wearables, this will be transformative for patient access and outcomes to achieve better sleep and overall health,” Fernandez said.

EnsoData suggested in the release that its technology could help to close the gap between the nearly 30 million Americans who are estimated to have sleep apnea and the more than 80% of cases that are still undiagnosed—therefore helping to reduce the incidence of cardiovascular, neurodegenerative and metabolic disorders that are often exacerbated by uncontrolled sleep apnea.

“Expanding EnsoData’s capability to collect and analyze PPG signals from simple, wearable pulse ox devices will accelerate the identification, diagnosis and treatment of sleep-disordered breathing events, including sleep apnea,” said CEO Justin Mortara.