Predicting youth diabetes risk using NHANES data and machine learning

Abstract

Prediabetes and diabetes mellitus (preDM/DM) have become alarmingly prevalent among youth in recent years. However, simple questionnaire-based screening tools to reliably assess diabetes risk are only available for adults, not youth. As a first step in developing such a tool, we used a large-scale dataset from the National Health and Nutritional Examination Survey (NHANES) to examine the performance of a published pediatric clinical screening guideline in identifying youth with preDM/DM based on American Diabetes Association diagnostic biomarkers. We assessed the agreement between the clinical guideline and biomarker criteria using established evaluation measures (sensitivity, specificity, positive/negative predictive value, F-measure for the positive/negative preDM/DM classes, and Kappa). We also compared the performance of the guideline to those of machine learning (ML) based preDM/DM classifiers derived from the NHANES dataset. Approximately 29% of the 2858 youth in our study population had preDM/DM based on biomarker criteria. The clinical guideline had a sensitivity of 43.1% and specificity of 67.6%, positive/negative predictive values of 35.2%/74.5%, positive/negative F-measures of 38.8%/70.9%, and Kappa of 0.1 (95%CI: 0.06-0.14). The performance of the guideline varied across demographic subgroups. Some ML-based classifiers performed comparably to or better than the screening guideline, especially in identifying preDM/DM youth (p = 5.23 × 10^-5).We demonstrated that a recommended pediatric clinical screening guideline did not perform well in identifying preDM/DM status among youth. Additional work is needed to develop a simple yet accurate screener for youth diabetes risk, potentially by using advanced ML methods and a wider range of clinical and behavioral health data.

Figure 1

Variations in the performance of the American Diabetes Association pediatric screening guidelines in identifying youth with prediabetes/diabetes (preDM/DM) based on biomarker measurements across subgroups stratified by age group (12–14, 15–17, and 18–19), race/ethnicity (Hispanic, non-Hispanic Black, non-Hispanic White, other), and sex (female, male). Red lines denote the value of the corresponding evaluation measure obtained from the full study population (youth ages 12–19, National Health and Nutrition Examination Survey data, 2005–2016). preDM prediabetes; DM diabetes; F female; M male; Hisp Hispanic; NHB non-Hispanic Black; NHW non-Hispanic White; PPV positive predictive value; NPV negative predictive value. Results based on unweighted data.

Figure 2

Performance of machine learning algorithms in classifying individuals into prediabetes/diabetes (preDM/DM) and non-preDM/DM classes, evaluated in terms of predictive value, sensitivity/specificity and F-measures for both classes. The variables used in this classification were the same as those used in the American Diabetes Association pediatric screening guidelines, whose performance in terms of each measure is shown by a horizontal red line in the corresponding subplot. preDM prediabetes; DM diabetes; PPV positive predictive value; NPV negative predictive value.