Mount Sinai researchers are developing and studying models powered by artificial intelligence (AI) to identify the risk of cardiovascular disease events in patients with obstructive sleep apnea. 

The prediction models, using machine-learning techniques, will also help classify patients who may benefit from continuous positive airway pressure (CPAP).

The researchers say their personalized tools will provide a novel approach to enhancing management by optimizing the best decisions for treatment plans and improving cardiovascular outcomes. The study is supported by a four-year, $3 million grant from the National Heart, Lung, and Blood Institute of the National Institutes of Health (NIH).

Previous studies have established the prevalence of obstructive sleep apnea and its association with cardiovascular disease. However, little research has demonstrated the benefits of continuous CPAP use on the rate of cardiovascular events.

In response to the NIH Sleep Research Plan’s call for further research in critical and high-priority areas, Mount Sinai experts will use machine-learning techniques on comprehensive multi-modal datasets to identify patients at enhanced risk for atherosclerosis progression, or buildup of fats and cholesterol in the artery walls, and heightened risk for cardiovascular events such as heart attack and stroke. 

Researchers say the approach will also predict cardiovascular treatment effectiveness of CPAP therapy for patients with the sleep disorder who scored as “non-sleepy” on a standard clinical test, helping to identify patients who would benefit most from using CPAP as well as patients who should avoid CPAP use.

The foundation of this work is the team’s recently published study which revealed the potential harm of CPAP therapy to non-sleepy patients with obstructive sleep apnea and acute coronary syndrome, such as an increased risk of stroke, heart attack, and cardiovascular death. Those findings underscored the importance of identifying apnea patients who could benefit from CPAP and steered the team toward more personalized treatment strategies, says primary Principal Investigator Neomi Shah, MD, MPH, MSc, associate dean for faculty career advancement, vice chair for faculty affairs in the Mount Sinai Health System Department of Medicine, and professor of medicine (pulmonary, critical care, and sleep medicine) at the Icahn School of Medicine at Mount Sinai.

“Supported by a transformative grant, I’m thrilled to lead a project that stands at the intersection of cutting-edge artificial intelligence and sleep medicine,” says Shah in a release. “Our work will epitomize the wealth of expertise and collaborative effort across the Mount Sinai Health System to both enrich our understanding of the condition and improve patient care, impacting millions in the United States. We are committed to validating our AI tools within Mount Sinai’s clinical dataset to translate our research into real-world practice, thereby effectively bridgnoning the research-to-practice gap.”

The research will use data from two cohorts: the Multi-Ethnic Study of Atherosclerosis cohort of more than 6,000 ethnically diverse, generally healthy non-sleepy participants, and the Sleep Apnea Cardiovascular Endpoints randomized clinical trial of more than 2,500 non-sleepy participants with moderate to severe obstructive sleep apnea and established cardiovascular disease. 

They will use these datasets to identify key variables that predict atherosclerosis progression and cardiovascular events such as heart attack and stroke and to identify subgroups with differential treatment effects with CPAP for cardiovascular events based on demographics or risk characteristics, as well as validate the models within the Mount Sinai Health System using clinical data from the electronic health record.

Photo 133911606 | Ai Heart © Sompong Sriphet |