To identify predictors of prediabetes using feature selection and machine learning on a nationally representative sample of the US population. We analyzed n = 6346 men and women enrolled in the National Health and Nutrition Examination Survey 2013–2014. Prediabetes was defined using American Diabetes Association guidelines. The sample was randomly partitioned to training (n = 3174) and internal validation (n = 3172) sets. Feature selection algorithms were run on training data containing 156 preselected exposure variables. Four machine learning algorithms were applied on 46 exposure variables in original and resampled training datasets built using 4 resampling methods. Predictive models were tested on internal validation data (n = 3172) and external validation data (n = 3000) prepared from National Health and Nutrition Examination Survey 2011–2012. Model performance was evaluated using area under the receiver operating characteristic curve (AUROC). Predictors were assessed by odds ratios in logistic models and variable importance in others. The Centers for Disease Control (CDC) prediabetes screening tool was the benchmark to compare model performance. Prediabetes prevalence was 23.43%. The CDC prediabetes screening tool produced 64.40% AUROC. Seven optimal (≥ 70% AUROC) models identified 25 predictors including 4 potentially novel associations; 20 by both logistic and other nonlinear/ensemble models and 5 solely by the latter. All optimal models outperformed the CDC prediabetes screening tool (P < 0.05). Combined use of feature selection and machine learning increased predictive performance outperforming the recommended screening tool. A range of predictors of prediabetes was identified. This work demonstrated the value of combining feature selection with machine learning to identify a wide range of predictors that could enhance prediabetes prediction and clinical decision-making.

Introduction: Using body mass index (BMI) as a proxy, previous Mendelian randomization (MR) studies found total causal effects of general obesity on polycystic ovarian syndrome (PCOS). Hitherto, total and direct causal effects of general- and central obesity on PCOS have not been comprehensively analyzed. Objectives: To investigate the causality of central- and general obesity on PCOS using surrogate anthropometric markers. Methods: Summary GWAS data of female-only, large-sample cohorts of European ancestry were retrieved for anthropometric markers of central obesity (waist circumference (WC), hip circumference (HC), waist-to-hip ratio (WHR)) and general obesity (BMI and its constituent variables–weight and height), from the IEU Open GWAS Project. As the outcome, we acquired summary data from a large-sample GWAS (118870 samples; 642 cases and 118228 controls) within the FinnGen cohort. Total causal effects were assessed via univariable two-sample Mendelian randomization (2SMR). Genetic architectures underlying causal associations were explored. Direct causal effects were analyzed by multivariable MR modelling. Results: Instrumental variables demonstrated no weak instrument bias (F > 10). Four anthropometric exposures, namely, weight (2.69–77.05), BMI (OR: 2.90–4.06), WC (OR: 6.22–20.27), and HC (OR: 6.22–20.27) demonstrated total causal effects as per univariable 2SMR models. We uncovered shared and non-shared genetic architectures underlying causal associations. Direct causal effects of WC and HC on PCOS were revealed by two multivariable MR models containing exclusively the anthropometric markers of central obesity. Other multivariable MR models containing anthropometric markers of both central- and general obesity showed no direct causal effects on PCOS. Conclusions: Both and general- and central obesity yield total causal effects on PCOS. Findings also indicated potential direct causal effects of normal weight-central obesity and more complex causal mechanisms when both central- and general obesity are present. Results underscore the importance of addressing both central- and general obesity for optimizing PCOS care.

Objectives: Using a nationally-representative, cross-sectional cohort, we examined nutritional markers of undiagnosed type 2 diabetes in adults via machine learning. Methods: A total of 16429 men and non-pregnant women ≥ 20 years of age were analysed from five consecutive cycles of the National Health and Nutrition Examination Survey. Cohorts from years 2013–2016 (n = 6673) was used for external validation. Undiagnosed type 2 diabetes was determined by a negative response to the question “Have you ever been told by a doctor that you have diabetes?” and a positive glycaemic response to one or more of the three diagnostic tests (HbA1c > 6.4% or FPG >125 mg/dl or 2-hr post-OGTT glucose > 200mg/dl). Following comprehensive literature search, 114 potential nutritional markers were modelled with 13 behavioural and 12 socio-economic variables. We tested three machine learning algorithms on original and resampled training datasets built using three resampling methods. From this, the derived 12 predictive models were validated on internal- and external validation cohorts. Magnitudes of associations were gauged through odds ratios in logistic models and variable importance in others. Models were benchmarked against the ADA diabetes risk test. Results: The prevalence of undiagnosed type 2 diabetes was 5.26%. Four best-performing models (AUROC range: 74.9%-75.7%) classified 39 markers of undiagnosed type 2 diabetes; 28 via one or more of the three best-performing non-linear/ensemble models and 11 uniquely by the logistic model. They comprised 14 nutrient-based, 12 anthropometry-based, 9 socio-behavioural, and 4 diet-associated markers. AUROC of all models were on a par with ADA diabetes risk test on both internal and external validation cohorts (p>0.05). Conclusions: Models performed comparably to the chosen benchmark. Novel behavioural markers such as the number of meals not prepared from home were revealed. This approach may be useful in nutritional epidemiology to unravel new associations with type 2 diabetes.