Search

Postprandial blood glucose prediction is a crucial part of diabetes management. Recently, this topic has been of great interest, resulting in many research projects and published papers. Although different input parameters that might be beneficial for blood glucose prediction models were comprehensively discussed, specific data preprocessing, feature engineering and model tuning steps were not explained in detail in many of these papers. In this work, we developed and comprehensively described a data-driven blood glucose model based on a decision tree gradient boosting algorithm to predict different characteristics of postprandial glycemic responses; the model utilized meal-related data derived from a mobile app diary (including information on the glycemic index), food context (information on previous meals), characteristics of the individual patients and patient behavioral questionnaires. A set of rules was defined and implemented to detect incorrect meal records and to filter faulty data, and analyses were conducted on the overall food diary data and in particular, the data on the current meal for which the postprandial blood glucose response was calculated. Different gradient boosting models were trained and evaluated with parameters selected via random search cross-validation. The best models for the prediction of the incremental area under the blood glucose curve two hours after food intake had the following characteristics: R = 0.631, MAE = 0.373 mmol/L*h for the model not using data on current blood glucose; R = 0.644, MAE = 0.371 mmol/L*h for the model using data on the current blood glucose levels; and R = 0.704, MAE = 0.341 mmol/L*h for the model utilizing data on the continuous blood glucose trends before the meal. The impact of features was evaluated using Shapley values. The meal glycemic load, amount of carbohydrates in the meal, type of meal (e.g., breakfast), amount of starch and amount of food consumed 6 hours before the current meal were the most important contributors in the models.

Obesity and type 2 diabetes mellitus (T2DM) are often combined and pathologically affect many tissues due to changes in circulating bioactive molecules. In this work, we evaluated the effect of blood plasma from obese (OB) patients or from obese patients comorbid with diabetes (OBD) on skeletal muscle function and metabolic state. We employed the mouse myoblasts C2C12 differentiation model to test the regulatory effect of plasma exposure at several levels: (1) cell morphology, (2) functional activity of mitochondria, (3) expression levels of several mitochondria regulators, i.e., Atgl, Pgc1b, and miR-378a-3p. Existing databases were used to computationally predict and analyze mir-378a-3p potential targets. We show that short-term exposure to OB or OBD patients’ plasma is sufficient to affect C2C12 properties. In fact, the expression of genes that regulate skeletal muscle differentiation and growth was downregulated in both OB- and OBD-treated cells, maximal mitochondrial respiration rate was downregulated in the OBD group, while in the OB group, a metabolic switch to glycolysis was detected. These alterations correlated with a decrease in ATGL and Pgc1b expression in the OB group and with an increase of miR-378a-3p levels in the OBD group.

ObjectiveWe aimed to explore the associations between common genetic risk variants with gestational diabetes mellitus (GDM) risk in Russian women and to assess their utility in the identification of GDM cases.MethodsWe conducted a case-control study including 1,142 pregnant women (688 GDM cases and 454 controls) enrolled at Almazov National Medical Research Centre. The International Association of Diabetes and Pregnancy Study Groups criteria were used to diagnose GDM. A total of 11 single- nucleotide polymorphisms (SNPs), including those in HKDC1 (rs10762264), GCK (rs1799884), MTNR1B (rs10830963 and rs1387153), TCF7L2 (rs7903146 and rs12255372), KCNJ11 (rs5219), IGF2BP2 (rs4402960), IRS1 (rs1801278), FTO (rs9939609), and CDKAL1 (rs7754840) were genotyped using Taqman assays. A logistic regression model was used to calculate odds ratios (ORs) and their confidence intervals (CIs). A simple-count genetic risk score (GRS) was calculated using 6 SNPs. The area under the receiver operating characteristic curve (c-statistic) was calculated for the logistic regression model predicting the risk of GDM using clinical covariates, SNPs that had shown a significant association with GDM in our study, GRS, and their combinations.ResultsTwo variants in MTNR1B (rs1387153 and rs10830963) demonstrated a significant association with an increased risk of GDM. The association remained significant after adjustment for age, pre-gestational BMI, arterial hypertension, GDM in history, impaired glucose tolerance, polycystic ovary syndrome, family history of diabetes, and parity (P = 0.001 and P < 0.001, respectively). After being conditioned by each other, the effect of rs1387153 on GDM predisposition weakened while the effect of rs10830963 remained significant (P = 0.004). The risk of GDM was predicted by clinical variables (c-statistic 0.712, 95 % CI: 0.675 – 0.749), and the accuracy of prediction was modestly improved by adding GRS to the model (0.719, 95 % CI 0.682 – 0.755), and more by adding only rs10830963 (0.729, 95 % CI 0.693 – 0.764).ConclusionAmong 11 SNPs associated with T2D and/or GDM in other populations, we confirmed significant association with GDM for two variants in MTNR1B in Russian women. However, these variants showed limited value in the identification of GDM cases.

The incorporation of glycemic index (GI) and glycemic load (GL) is a promising way to improve the accuracy of postprandial glycemic response (PPGR) prediction for personalized treatment of gestational diabetes (GDM). Our aim was to assess the prediction accuracy for PPGR prediction models with and without GI data in women with GDM and healthy pregnant women. The GI values were sourced from University of Sydney&rsquo, s database and assigned to a food database used in the mobile app DiaCompanion. Weekly continuous glucose monitoring (CGM) data for 124 pregnant women (90 GDM and 34 control) were analyzed together with records of 1489 food intakes. Pearson correlation (R) was used to quantify the accuracy of predicted PPGRs from the model relative to those obtained from CGM. The final model for incremental area under glucose curve (iAUC120) prediction chosen by stepwise multiple linear regression had an R of 0.705 when GI/GL was included among input variables and an R of 0.700 when GI/GL was not included. In linear regression with coefficients acquired using regularization methods, which was tested on the data of new patients, R was 0.584 for both models (with and without inclusion of GI/GL). In conclusion, the incorporation of GI and GL only slightly improved the accuracy of PPGR prediction models when used in remote monitoring.

Background. Subclinical hypothyroidism during pregnancy and gestational diabetes mellitus (GDM) is known to be associated with maternal and child morbidity. The concept of subclinical dysfunction of the thyroid gland in pregnant women depends on the population-specific and trimester-specific reference values so fixed universal cutoff concentrations for thyroid-stimulating hormone (TSH) that were recommended earlier now are put under the question. Population-specific and trimester-specific reference values have not been defined for pregnant women residing in Saint Petersburg. The data concerning the association of maternal thyroid status with GDM development are controversial. Aims. The aim of the study was to determine the reference values of TSH and free thyroxin (fT4) in the first trimester of pregnancy in women living in St. Petersburg, and to assess the relationship between thyroid status and the risk of subsequent development of GDM. Materials and methods. The levels of TSH, fT4 and thyroid peroxidase antibodies (TPO-Ab) were analyzed in 503 pregnant women before the 14th week of gestation. The women underwent oral glucose tolerance test (OGTT) at 2428 weeks to find out those with GDM. The association between thyroid function, thyroid autoimmunity and the risk of GDM we estimated. Results. The reference values for TSH were 0.07 4.40 mU /L, and for fT4 11.7 20.3 pmol/L. The prevalence of subclinical hypothyroidism in the 503 pregnant women was 16.9% according to the diagnostic criteria of TSH 2.5 mIU / L and 3.8% using our calculated reference interval. Hypothyroxinemia was registered in 5,3% using reference values recommended by diagnostic tests manufacturer and in 2,8% according to our calculated reference interval for fT4. GDM was diagnosed in 23% of women. Logistic regression analysis showed associations of hypothyroxinemia and TPO-Ab-positivity with the increased risk of GDM that remained significant after adjustments on age and body mass index (BMI) [adjusted OR (95% CI) = 7.39 (1.2742.93) for hypothyroxinemia, p=0.026; and adjusted OR (95% CI) = 2.02 (1.014.04) for TPO-Ab-positivity, p=0.047). Conclusions. Reference intervals for first trimester TSH and fT4 have been established for pregnant women living in St. Petersburg. Hypothyroxinemia and TPO-Ab-positivity were associated with the increased risk of GDM.