A comprehensive youth diabetes epidemiological dataset and web portal: Resource Development and Case Studies.

BACKGROUND: The prevalence of Type 2 diabetes (DM) and prediabetes (preDM) has been increasing among youth in recent decades in the United States, prompting an urgent need for understanding and identifying their associated risk factors. Such efforts, however, have been hindered by the lack of easily accessible youth preDM/DM data.

OBJECTIVE: We aimed to first build a high quality, comprehensive epidemiological dataset focused on youth preDM/DM. Subsequently, we aimed to make this data accessible by creating a user-friendly web portal to share it and corresponding codes. Through this, we hope to address this significant gap and facilitate youth preDM/DM research.

METHODS: Building on data from the National Health and Nutrition Examination Survey (NHANES) from 1999 to 2018, we cleaned and harmonized hundreds of variables relevant to preDM/DM (fasting plasma glucose level ≥100 mg/dL and/or HbA1C ≥5.7%) for youth aged 12-19 years (n=15,149). We identified individual factors associated with preDM/DM risk using bivariate statistical analyses and predicted preDM/DM status using our Ensemble Integration (EI) framework for multi-domain machine learning. We then developed a user-friendly web portal named Prediabetes/diabetes in youth ONline Dashboard (POND) to share the data and codes.

RESULTS: We extracted 95 variables potentially relevant to preDM/DM risk organized into 4 domains (sociodemographic, health status, diet, and other lifestyle behaviors). The bivariate analyses identified 27 significant correlates of preDM/DM (P ≤0.0005, Bonferroni adjusted), including race/ethnicity, health insurance, BMI, added sugar intake, and screen time. Sixteen of these factors were also identified based on the EI methodology (Fisher's P of overlap=7.06x10^-6). In addition to those, the EI approach identified 11 additional predictive variables, including some known (e.g., meat and fruit intake and family income) and less recognized factors (e.g., number of rooms in homes). The factors identified in both analyses spanned over all 4 of the domains mentioned. These data and results, as well as other exploratory tools, can be accessed on POND (https://rstudio-connect.hpc.mssm.edu/POND/).

CONCLUSIONS: Using NHANES data, we built one of the largest public epidemiological datasets for studying youth preDM/DM and identified potential risk factors using complementary analytical approaches. Our results align with the multifactorial nature of preDM/DM with correlates across several domains. Also, our data-sharing platform, POND, facilitates a wide range of applications to inform future youth preDM/DM studies.