AI Tool Estimates CPAP Effect on Cardiovascular Risk in Sleep Apnea

Large clinical trials have not shown that continuous positive airway pressure (CPAP) reduces that risk uniformly. Clinicians therefore lack tools to identify who will benefit or be harmed by therapy. Researchers have now developed a machine learning model that predicts individualized cardiovascular risk changes with CPAP.

Developed at the Icahn School of Medicine at Mount Sinai (New York, NY, USA), the analytic tool uses a machine learning algorithm to estimate each patient’s likelihood of benefit or harm from CPAP. It analyzes sleep and health information to generate individualized treatment effect scores. The work, recently published in Communications Medicine, highlights a precision-medicine strategy for tailoring CPAP recommendations.

The model was built using data from the Sleep Apnea Cardiovascular Endpoints (SAVE) trial, the largest clinical cohort evaluating CPAP for cardiovascular disease prevention. The cohort included more than 2,600 participants recruited from 89 sites across seven countries. Investigators considered more than 100 predictors from sleep and health data to derive 23 baseline features that informed the individualized treatment effect estimates.

Treatment response varied substantially across the cohort. A subgroup predicted to benefit from CPAP experienced a 100-fold improvement in future cardiac risk when randomized to CPAP compared with usual care. Conversely, patients in a subgroup predicted to be harmed had a greater than 100-fold increase in cardiovascular disease outcomes, including recurrent strokes and heart attacks, when receiving CPAP compared with usual care.

The study involved collaborators from The George Institute for Global Health and the University of New South Wales in Sydney, the School of Electrical and Mechanical Engineering at the University of Adelaide, and the Adelaide Institute for Sleep Health/Flinders Health and Medical Research Institute Sleep Health at Flinders University in Adelaide. The team noted that such models require careful validation before routine clinical adoption.

“Our findings represent a significant advancement in personalized medicine, moving away from a one-size-fits-all strategy in the treatment of obstructive sleep apnea. This underscores the value of new data-driven approaches like our model to assist clinicians in making informed decisions about CPAP treatment recommendations, enhancing personalized care to meet the individual needs of every patient,” said co-corresponding author Neomi A. Shah, MD, MPH, MSC, Professor of Medicine (Pulmonary, Critical Care and Sleep Medicine) and Associate Chief for Academic Affairs in the Division of Pulmonary, Critical Care and Sleep Medicine at the Icahn School of Medicine at Mount Sinai.

Related Links
Icahn School of Medicine at Mount Sinai