Snoring is the vibration of respiratory structures and the resulting sound caused by the obstruction of air movement during breathing during sleep. — Image by Michael Nutt — CC BY-SA 2.0
Scientists at Mount Sinai have created an analytical tool using machine learning that can predict the risk of cardiovascular disease in millions of people with obstructive sleep apnea. This is a serious sleep disorder.
Apnea is a disorder in which breathing repeatedly stops and starts during sleep, often resulting in low oxygen levels in the blood and fragmented sleep. Each pause can last from a few seconds to more than a minute and can occur multiple times per hour.
Researchers suggest that the study is the first to provide estimates of whether continuous positive airway pressure (CPAP), a widely used treatment for obstructive sleep apnea, increases or decreases an individual’s cardiovascular risk.
Additionally, this study highlights the potential of precision medicine and different approaches to customize clinical care and reduce the risk of cardiovascular disease in vulnerable patients.
Obstructive sleep apnea is a common and serious condition in which breathing repeatedly stops and starts during sleep. It is associated with an increased risk of cardiovascular diseases such as stroke and heart disease. CPAP, which provides a continuous supply of pressurized air through a mask to help eliminate breathing problems during sleep, remains the most effective treatment for sleep apnea. However, previous large studies have not shown that CPAP reduces the risk of cardiovascular disease in patients with cardiovascular disease.
machine learning
The researchers used machine learning algorithms to create an analytical model that predicts how CPAP will affect an individual’s cardiovascular health. It estimates the likelihood of benefit or harm from treatment based on each patient’s sleep and health information.
This discovery represents a major advance in personalized medicine, moving away from a one-size-fits-all strategy for treating obstructive sleep apnea.
The Mount Sinai team analyzed data from the Sleep Apnea Cardiovascular Endpoints (SAVE) trial, the largest clinical cohort evaluating CPAP for cardiovascular disease prevention, which included more than 2,600 participants from 89 sites in seven countries, to estimate individual treatment efficacy scores. They considered more than 100 predictors from sleep and health information to establish 23 key baseline characteristics, such as previous medical conditions and smoking status, in their analytical model.
The researchers found that treatment responses varied widely between cohorts. This model identified subgroups in which CPAP treatment would be expected to improve cardiovascular risk. Participants in this subgroup randomly assigned to receive treatment had a 100-fold improvement in future heart risk compared to patients in this subgroup receiving usual care.
Conversely, people in subgroups predicted to be adversely affected by the therapy had more than 100-fold increased cardiovascular disease outcomes, including recurrent strokes and heart attacks, when they received CPAP compared with usual care.
Research published in a magazine communication medicine, The title is “Individual treatment effects of CPAP on secondary cardiovascular outcomes in non-drowsy patients with obstructive sleep apnea”.
