Why the study?
Due to overlapping clinical risk factors, identifying high-risk patients with obstructive sleep apnea who are likely to develop cardiovascular disease remains challenging.
Can machine learning models using baseline clinical factors predict the future development of cardiovascular disease in patients with obstructive sleep apnea?
Population
967 adults aged 45 to 84 years enrolled in the Multi-Ethnic Study of Atherosclerosis
Comparison
Baseline clinical factors predicting OSA with CVD vs OSA alone
Design
Retrospective analysis of prospectively collected data
Follow-up
10 years
Key result
Machine learning models, such as random forest, predicted the development of cardiovascular disease in patients with obstructive sleep apnea with 84% sensitivity and 99% specificity.
Authors
Loading...
May aid CVD risk stratification in OSA; hypothesis-generating and requires prospective validation before clinical use.
Observational (n=967)
Can machine learning models using baseline clinical factors predict the future development of cardiovascular disease in patients with obstructive sleep apnea?
Machine learning models identified fasting glucose >91 mg/dL, diastolic pressure >73 mm Hg, and age >59 years as the strongest baseline predictors for developing cardiovascular disease in patients with obstructive sleep apnea.
Gourishetti et al. (2021) conducted an observational in Obstructive sleep apnea and cardiovascular disease (n=967). Baseline clinical factors (fasting glucose, diastolic pressure, age) vs. Patients with obstructive sleep apnea alone was evaluated on Prediction of additional risk of cardiovascular disease in obstructive sleep apnea. Machine learning models, such as random forest, predicted the development of cardiovascular disease in patients with obstructive sleep apnea with 84% sensitivity and 99% specificity.