Exploration of Machine Learning and Statistical Techniques in Development of a Low-Cost Screening Method Featuring the Global Diet Quality Score for Detecting Prediabetes in Rural India.

BACKGROUND: The prevalence of type 2 diabetes has increased substantially in India over the past 3 decades. Undiagnosed diabetes presents a public health challenge, especially in rural areas, where access to laboratory testing for diagnosis may not be readily available. OBJECTIVES: The present work explores the use of several machine learning and statistical methods in the development of a predictive tool to screen for prediabetes using survey data from an FFQ to compute the Global Diet Quality Score (GDQS). METHODS: The outcome variable prediabetes status (yes/no) used throughout this study was determined based upon a fasting blood glucose measurement ≥100 mg/dL. The algorithms utilized included the generalized linear model (GLM), random forest, least absolute shrinkage and selection operator (LASSO), elastic net (EN), and generalized linear mixed model (GLMM) with family unit as a (cluster) random (intercept) effect to account for intrafamily correlation. Model performance was assessed on held-out test data, and comparisons made with respect to area under the receiver operating characteristic curve (AUC), sensitivity, and specificity. RESULTS: The GLMM, GLM, LASSO, and random forest modeling techniques each performed quite well (AUCs >0.70) and included the GDQS food groups and age, among other predictors. The fully adjusted GLMM, which included a random intercept for family unit, achieved slightly superior results (AUC of 0.72) in classifying the prediabetes outcome in these cluster-correlated data. CONCLUSIONS: The models presented in the current work show promise in identifying individuals at risk of developing diabetes, although further studies are necessary to assess other potentially impactful predictors, as well as the consistency and generalizability of model performance. In addition, future studies to examine the utility of the GDQS in screening for other noncommunicable diseases are recommended.

Distinct cytokine profiles in late pregnancy in Ugandan people with HIV.

During pregnancy, multiple immune regulatory mechanisms establish an immune-tolerant environment for the allogeneic fetus, including cellular signals called cytokines that modify immune responses. However, the impact of maternal HIV infection on these responses is incompletely characterized. We analyzed paired maternal and umbilical cord plasma collected during labor from 147 people with HIV taking antiretroviral therapy and 142 HIV-uninfected comparators. Though cytokine concentrations were overall similar between groups, using Partial Least Squares Discriminant Analysis we identified distinct cytokine profiles in each group, driven by higher IL-5 and lower IL-8 and MIP-1α levels in pregnant people with HIV and higher RANTES and E-selectin in HIV-unexposed umbilical cord plasma (P-value < 0.01). Furthermore, maternal RANTES, SDF-α, gro α -KC, IL-6, and IP-10 levels differed significantly by HIV serostatus (P < 0.01). Although global maternal and umbilical cord cytokine profiles differed significantly (P < 0.01), umbilical cord plasma profiles were similar by maternal HIV serostatus. We demonstrate that HIV infection is associated with a distinct maternal plasma cytokine profile which is not transferred across the placenta, indicating a placental role in coordinating local inflammatory response. Furthermore, maternal cytokine profiles in people with HIV suggest an incomplete shift from Th2 to Th1 immune phenotype at the end of pregnancy.