Background: Global 12-month psychosis prevalence is estimated at roughly 0.4%, although prevalence of antipsychotic use in the U.S. is estimated at roughly 1.7%. Antipsychotics are frequently prescribed for off label uses, but have also been shown to carry risk factors for certain comorbid conditions and with other prescription medications. The study aims to describe the socio-demographic and health characteristics of U.S. adults taking prescription antipsychotic medications, and to better understand the association of antipsychotic medications and comorbid chronic diseases. Methods: The study pools 2013–2018 data from the National Health and Nutrition Examination Survey (NHANES), a nationally representative cross-sectional survey of non-institutionalized U.S. residents (n = 17,691). Survey staff record prescription medications taken within the past 30 days for each respondent, from which typical and atypical antipsychotic medications were identified. Results: Prevalence of antipsychotic use among U.S. adults was 1.6% (n = 320). Over 90% of individuals taking antipsychotics reported having health insurance and a usual place for care, significantly more than their counterparts not taking antipsychotics. Further, those taking antipsychotics reported higher prevalence of comorbid chronic diseases and took an average of 2.3 prescription medications more than individuals not taking antipsychotics. Individuals taking antipsychotics were more likely to sleep 9 or more hours per night, be a current smoker, and have a body mass index greater than 30 kg/m². Conclusions: U.S. adults who take antipsychotic medications report more consistent health care access and higher prevalence of comorbid chronic diseases compared to those not taking antipsychotics. The higher comorbidity prevalence and number of total prescriptions highlight the need for careful assessment and monitoring of existing comorbidities and potential drug-drug interactions among adults taking antipsychotics in the U.S.

Childhood obesity is a public health concern in the United States. Consequences of childhood obesity include metabolic disease and heart, lung, kidney, and other health-related comorbidities. Therefore, the early determination of obesity risk is needed and predicting the trend of a child’s body mass index (BMI) at an early age is crucial. Early identification of obesity can lead to early prevention. Multiple methods have been tested and evaluated to assess obesity trends in children. Available growth charts help determine a child’s current obesity level but do not predict future obesity risk. The present methods of predicting obesity include regression analysis and machine learning-based classifications and risk factor (threshold)-based categorizations based on specific criteria. All the present techniques, especially current machine learning-based methods, require longitudinal data and information on a large number of variables related to a child’s growth (e.g., socioeconomic, family-related factors) in order to predict future obesity-risk. In this paper, we propose three different techniques for three different scenarios to predict childhood obesity based on machine learning approaches and apply them to real data. Our proposed methods predict obesity for children at five years of age using the following three data sets: (1) a single well-child visit, (2) multiple well-child visits under the age of two, and (3) multiple random well-child visits under the age of five. Our models are especially important for situations where only the current patient information is available rather than having multiple data points from regular spaced well-child visits. Our models predict obesity using basic information such as birth BMI, gestational age, BMI measures from well-child visits, and gender. Our models can predict a child’s obesity category (normal, overweight, or obese) at five years of age with an accuracy of 89%, 77%, and 89%, for the three application scenarios, respectively. Therefore, our proposed models can assist healthcare professionals by acting as a decision support tool to aid in predicting childhood obesity early in order to reduce obesity-related complications, and in turn, improve healthcare.

Recent advances in informatics technology has made it possible to integrate, manipulate, and analyze variables from a wide range of scientific disciplines allowing for the examination of complex social problems such as health disparities. This study used 589 county-level variables to identify and compare geographical variation of high and low preterm birth rates. Data were collected from a number of publically available sources, bringing together natality outcomes with attributes of the natural, built, social, and policy environments. Singleton early premature county birth rate, in counties with population size over 100,000 persons provided the dependent variable. Graph theoretical techniques were used to identify a wide range of predictor variables from various domains, including black proportion, obesity and diabetes, sexually transmitted infection rates, mother’s age, income, marriage rates, pollution and temperature among others. Dense subgraphs (paracliques) representing groups of highly correlated variables were resolved into latent factors, which were then used to build a regression model explaining prematurity (R-squared = 76.7%). Two lists of counties with large positive and large negative residuals, indicating unusual prematurity rates given their circumstances, may serve as a starting point for ways to intervene and reduce health disparities for preterm births.