Harmonized US National Health and Nutrition Examination Survey 1988-2018 for high throughput exposome-health discovery.

The National Health and Nutrition Examination Survey (NHANES) provides data on the health and environmental exposure of the non-institutionalized US population. Such data have considerable potential to understand how the environment and behaviors impact human health. These data are also currently leveraged to answer public health questions such as prevalence of disease. However, these data need to first be processed before new insights can be derived through large-scale analyses. NHANES data are stored across hundreds of files with multiple inconsistencies. Correcting such inconsistencies takes systematic cross examination and considerable efforts but is required for accurately and reproducibly characterizing the associations between the exposome and diseases. Thus, we developed a set of curated and unified datasets and accompanied code by merging 614 separate files and harmonizing unrestricted data across NHANES III (1988-1994) and Continuous (1999-2018), totaling 134,310 participants and 4,740 variables. The variables convey 1) demographic information, 2) dietary consumption, 3) physical examination results, 4) occupation, 5) questionnaire items (e.g., physical activity, general health status, medical conditions), 6) medications, 7) mortality status linked from the National Death Index, 8) survey weights, 9) environmental exposure biomarker measurements, and 10) chemical comments that indicate which measurements are below or above the lower limit of detection. We also provide a data dictionary listing the variables and their descriptions to help researchers browse the data. We also provide R markdown files to show example codes on calculating summary statistics and running regression models to help accelerate high-throughput analysis and secular trends of the exposome. [Table: see text].

Predicting suicidal thoughts and behavior among adolescents using the risk and protective factor framework: A large-scale machine learning approach.

INTRODUCTION: Addressing the problem of suicidal thoughts and behavior (STB) in adolescents requires understanding the associated risk factors. While previous research has identified individual risk and protective factors associated with many adolescent social morbidities, modern machine learning approaches can help identify risk and protective factors that interact (group) to provide predictive power for STB. This study aims to develop a prediction algorithm for STB among adolescents using the risk and protective factor framework and social determinants of health. METHODS: The sample population consisted of more than 179,000 high school students living in Utah and participating in the Communities That Care (CTC) Youth Survey from 2011-2017. The dataset includes responses to 300+ questions from the CTC and 8000+ demographic factors from the American Census Survey for a total of 1.2 billion values. Machine learning techniques were employed to extract the survey questions that were best able to predict answers indicative of STB, using recent work in interpretable machine learning. RESULTS: Analysis showed strong predictive power, with the ability to predict individuals with STB with 91% accuracy. After extracting the top ten questions that most affected model predictions, questions fell into four main categories: familial life, drug consumption, demographics, and peer acceptance at school. CONCLUSIONS: Modern machine learning approaches provide new methods for understanding the interaction between root causes and outcomes, such as STB. The model developed in this study showed significant improvement in predictive accuracy compared to previous research. Results indicate that certain risk and protective factors, such as adolescents being threatened or harassed through digital media or bullied at school, and exposure or involvement in serious arguments and yelling at home are the leading predictors of STB and can help narrow and reaffirm priority prevention programming and areas of focused policymaking.

Prediction of chronological and biological age from laboratory data.

Aging has pronounced effects on blood laboratory biomarkers used in the clinic. Prior studies have largely investigated one biomarker or population at a time, limiting a comprehensive view of biomarker variation and aging across different populations. Here we develop a supervised machine learning approach to study aging using 356 blood biomarkers measured in 67,563 individuals across diverse populations. Our model predicts age with a mean absolute error (MAE), or average magnitude of prediction errors, in held-out data of 4.76 years and an R2 value of 0.92. Age prediction was highly accurate for the pediatric cohort (MAE = 0.87, R2 = 0.94) but inaccurate for ages 65+ (MAE = 4.30, R2 = 0.25). Variability was observed in which biomarkers carry predictive power across age groups, genders, and race/ethnicity groups, and novel candidate biomarkers of aging were identified for specific age ranges (e.g. Vitamin E, ages 18-44). We show that predictors for one age group may fail to generalize to other groups and investigate non-linearity in biomarkers near adulthood. As populations worldwide undergo major demographic changes, it is increasingly important to catalogue biomarker variation across age groups and discover new biomarkers to distinguish chronological and biological aging.