Abstract
BACKGROUND: Life's Essential 8 (LE8) is a framework for assessing cardiovascular health (CVH). Individuals with sleep disorders face an elevated risk of cardiovascular disease (CVD). This study aims to investigate the prognostic value of the LE8 score in predicting mortality among individuals with sleep disorders. METHODS: The prospective cohort study included 1606 adults (aged ≥ 20 years) diagnosed with sleep disorders from the National Health and Nutrition Examination Survey (NHANES) 2005-2014. LE8 scores were categorized into three groups: Low CVH (0-49), Moderate CVH (50-79), and High CVH (80-100). Kaplan-Meier survival curves were used to compare mortality across these groups. Weighted multivariable Cox proportional hazards models were employed to investigate the relationship between LE8 scores with all-cause and CVD mortality. The Boruta algorithm was applied for feature selection, and six machine learning (ML) algorithms were utilized to predict all-cause mortality. RESULTS: During a median follow-up of 103 months, 282 deaths occurred, including 66 CVD-related deaths. The weighted multivariable Cox models revealed that higher LE8 scores were significantly associated with a lower risk for both all-cause mortality (HR = 0.85, 95% CI, 0.73-0.99) and CVD mortality (HR = 0.72, 95% CI, 0.56-0.93). Among the evaluated ML algorithms, the Gradient Boosting Decision Tree (GBDT) model exhibited the highest area under the curve (AUC) for predicting all-cause mortality. CONCLUSION: Higher LE8 scores are independently associated with a decreased risk of all-cause and CVD mortality among patients with sleep disorders. These findings highlight the importance of optimizing overall CVH in the clinical management of sleep disorders.