Xiaojin Li, Licong Cui, Fei Wang, Schulz Paul E, Zhang Guo-Qiang
The University of Texas Health Science Center at Houston, Houston, TX 77030.
Department of Population Health Sciences, Weill Cornell Medicine, New York, NY 10065.
AMIA Annu Symp Proc. 2022 Feb 21;2021:744-753. eCollection 2021.
Disordered sleep is associated with poor cognitive function and cognitive decline. However, little is known regarding the association of sleep-related factors with cognitive function in underrepresented cohorts such as the Hispanic/Latino population. Leveraging the National Sleep Research Resource, one of the most comprehensive collections of sleep studies, we identified a Hispanic/Latino cohort of 1,031 lower cognitive function cases and 2,062 normal controls. We developed a novel dual random forest (DRF) approach to discriminate cases against controls for estimating the potential impact of sleep-related variables related to the decline of cognitive function. Several important sleep-related factors were identified which may be associated with cognitive function in the Hispanics/Latinos cohort, such as heart rate, sleep duration, trouble falling asleep, and apnea/hypopnea index, which are consistent with existing research findings. Our DRF approach is effective in validating the association between disordered sleep and cognitive decline in this unique minority population.
睡眠紊乱与认知功能差和认知能力下降有关。然而,对于西班牙裔/拉丁裔等代表性不足的人群中,睡眠相关因素与认知功能之间的关联却知之甚少。利用国家睡眠研究资源(这是最全面的睡眠研究集合之一),我们确定了一个由1031例认知功能较低病例和2062例正常对照组成的西班牙裔/拉丁裔队列。我们开发了一种新颖的双随机森林(DRF)方法,用于区分病例与对照,以估计与认知功能下降相关的睡眠相关变量的潜在影响。我们确定了几个重要的睡眠相关因素,这些因素可能与西班牙裔/拉丁裔队列中的认知功能有关,如心率、睡眠时间、入睡困难以及呼吸暂停/低通气指数,这与现有研究结果一致。我们的DRF方法有效地验证了这一独特少数群体中睡眠紊乱与认知能力下降之间的关联。