Digital phenotyping of sleep patterns among heterogenous samples of Latinx adults using unsupervised learning.

OBJECTIVE: This study aimed to identify sleep disturbance subtypes ("phenotypes") among Latinx adults based on objective sleep data using a flexible unsupervised machine learning technique. METHODS: This study was an analysis of sleep data from three cross-sectional studies of the Precision in Symptom Self-Management Center at Columbia University. All studies focused on sleep health in Latinx adults at increased risk for sleep disturbance. Data on total sleep time (TST), time in bed (TIB), wake after sleep onset (WASO), sleep efficiency (SE), number of awakenings (NOA) and the mean length of nightly awakenings were collected using wrist-mounted accelerometers. Cluster analysis of the sleep data was conducted using an unsupervised machine learning approach that relies on mixtures of multivariate generalized linear mixed models. RESULTS: The analytic sample included 494 days of data from 118 adults (Ages 19-77). A 3-cluster model provided the best fit based on deviance indices (ie, DΔ∼ -75 and -17 from 1- and 2- to 3-cluster models, respectively) and likelihood ratio (Pdiff âˆ¼ 0.93). Phenotype 1 (n = 64) was associated with greater likelihood of overall adequate SE and less variability in SE and WASO. Phenotype 2 (n = 11) was characterized by higher NOAs, and greater WASO and TIB than the other phenotypes. Phenotype 3 (n = 43) was characterized by greater variability in SE, bed times and awakening times. CONCLUSION: Robust digital data-driven modeling approaches can be useful for detecting sleep phenotypes from heterogenous patient populations, and have implications for designing precision sleep health strategies for management and early detection of sleep problems.

Health Insurance Coverage Mandates: Colorectal Cancer Screening in the Post-ACA Era.

Building a culture of precision public health requires research that includes health delivery model with innovative systems, health policies, and programs that support this vision. Health insurance mandates are effective mechanisms that many state policymakers use to increase the utilization of preventive health services, such as colorectal cancer screening. This study estimated the effects of health insurance mandate variations on colorectal cancer screening post Affordable Care Act (ACA) era. The study analyzed secondary data from the Behavioral Risk Factor Surveillance System (BRFSS) and the NCI State Cancer Legislative Database (SCLD) from 1997 to 2014. BRFSS data were merged with SCLD data by state ID. The target population was U.S. adults, age 50 to 74, who lived in states where health insurance was mandated or nonmandated before and after the implementation of ACA. Using a difference-in-differences (DD) approach with a time-series analysis, we evaluated the effects of health insurance mandates on colorectal cancer screening status based on U.S. Preventive Services Task Force guidelines. The adjusted average marginal effects from the DD model indicate that health insurance mandates increased the probability of up-to-date screenings versus noncompliance by 2.8% points, suggesting that an estimated 2.37 million additional age-eligible persons would receive a screening with such health insurance mandates. Compliant participants' mean age was 65 years and 57% were women (n = 32,569). Our findings are robust for various model specifications. Health insurance mandates that lower out-of-pocket expenses constitute an effective approach to increase colorectal cancer screenings for the population, as a whole. PREVENTION RELEVANCE: The value added includes future health care reforms that increase access to preventive services, such as CRC screening, are likely with lower out-of-pocket costs and will increase the number of people who are considered "up-to-date". Such policies have been used historically to improve health outcomes, and they are currently being used as public health strategies to increase access to preventive health services in an effort to improve the nation's health.