Development and validation of risk prediction models for large for gestational age infants using logistic regression and two machine learning algorithms.

BACKGROUND: Large for gestational age (LGA) is one of the adverse outcomes during pregnancy that endangers the life and health of mothers and offspring. We aimed to establish prediction models for LGA at late pregnancy. METHODS: Data were obtained from an established Chinese pregnant women cohort of 1285 pregnant women. LGA was diagnosed as >90th percentile of birth weight distribution of Chinese corresponding to gestational age of the same-sex newborns. Women with gestational diabetes mellitus (GDM) were classified into three subtypes according to the indexes of insulin sensitivity and insulin secretion. Models were established by logistic regression and decision tree/random forest algorithms, and validated by the data. RESULTS: A total of 139 newborns were diagnosed as LGA after birth. The area under the curve (AUC) for the training set is 0.760 (95% confidence interval [CI] 0.706-0.815), and 0.748 (95% CI 0.659-0.837) for the internal validation set of the logistic regression model, which consisted of eight commonly used clinical indicators (including lipid profile) and GDM subtypes. For the prediction models established by the two machine learning algorithms, which included all the variables, the training set and the internal validation set had AUCs of 0.813 (95% CI 0.786-0.839) and 0.779 (95% CI 0.735-0.824) for the decision tree model, and 0.854 (95% CI 0.831-0.877) and 0.808 (95% CI 0.766-0.850) for the random forest model. CONCLUSION: We established and validated three LGA risk prediction models to screen out the pregnant women with high risk of LGA at the early stage of the third trimester, which showed good prediction power and could guide early prevention strategies.

Efficacy and safety of hypoglycemic agents on gestational diabetes mellitus in women: A Bayesian network analysis of randomized controlled trials.

Objective: To compare the efficacy and safety of metformin, glyburide, and insulin for GDM, we conducted a subgroup analysis of outcomes for women with GDM according to the International Association of Diabetes and Pregnancy Study Groups (IADPSG) diagnostic criteria. Methods: We searched the NCBI, Embase, and Web of Science databases from inception to March 2022. Randomized controlled trials (RCTs) that compared the outcomes of hypoglycemic agents in women with GDM were included. Bayesian network analysis was employed. Results: A total of 29 RCTs were included. Metformin was estimated to lead to a slight improvement in total gestational weight gain (WMD - 1.24 kg, 95% CI -2.38, -0.09), a risk of unmet treatment target in the sensitivity analysis (OR 34.50, 95% CI 1.18-791.37) than insulin. The estimated effect of metformin showed improvements in birth weight than insulin (WMD - 102.58 g, 95% CI -180.45 to -25.49) and glyburide (WMD - 137.84 g, 95% CI -255.31 to -25.45), for hypoglycemia within 1 h of birth than insulin (OR 0.65, 95% CI 0.47 to 0.84). The improvement in the estimated effect of metformin for hypoglycemia within 1 h of birth still existed when compared with glyburide (OR 0.41, 95% CI 0.26 to 0.66), whether in the IADPSG group (OR 0.33, 95% CI 0.12 to 0.92) or not (OR 0.43, 95% CI 0.20 to 0.98). Conclusion: Metformin is beneficial for GDM women to control total GWG compared with insulin, regulate fetal birth weight more than insulin and glyburide, and increase the risk of unmet treatment targets compared with insulin. Compared to metformin, glyburide is associated with neonatal hypoglycemia.

Development and Validation of Risk Prediction Models for Gestational Diabetes Mellitus Using Four Different Methods.

Gestational diabetes mellitus (GDM), a common perinatal disease, is related to increased risks of maternal and neonatal adverse perinatal outcomes. We aimed to establish GDM risk prediction models that can be widely used in the first trimester using four different methods, including a score-scaled model derived from a meta-analysis using 42 studies, a logistic regression model, and two machine learning models (decision tree and random forest algorithms). The score-scaled model (seven variables) was established via a meta-analysis and a stratified cohort of 1075 Chinese pregnant women from the Northwest Women's and Children's Hospital (NWCH) and showed an area under the curve (AUC) of 0.772. The logistic regression model (seven variables) was established and validated using the above cohort and showed AUCs of 0.799 and 0.834 for the training and validation sets, respectively. Another two models were established using the decision tree (DT) and random forest (RF) algorithms and showed corresponding AUCs of 0.825 and 0.823 for the training set, and 0.816 and 0.827 for the validation set. The validation of the developed models suggested good performance in a cohort derived from another period. The score-scaled GDM prediction model, the logistic regression GDM prediction model, and the two machine learning GDM prediction models could be employed to identify pregnant women with a high risk of GDM using common clinical indicators, and interventions can be sought promptly.

Association of Elevated Plasma FGF21 and Activated FGF21 Signaling in Visceral White Adipose Tissue and Improved Insulin Sensitivity in Gestational Diabetes Mellitus Subtype: A Case-Control Study.

Objective: To study the discrepancy of the insulin sensitivity alteration pattern, circulating fibroblast growth factor (FGF21) levels and FGF21 signaling in visceral white adipose tissue (vWAT) of gestational diabetes mellitus (GDM) subtypes. Methods: 26 GDM women with either a predominant of insulin-secretion defect (GDM-dysfunction, n = 9) or insulin-sensitivity defect (GDM-resistance, n = 17) and 13 normal glucose tolerance (NGT) women scheduled for caesarean-section at term were studied. Blood and vWAT samples were collected at delivery. Results: The insulin sensitivity was improved from the 2nd trimester to delivery in the GDM-resistance group. Elevated circulating FGF21 concentration at delivery, increased FGF receptor 1c and decreased klotho beta gene expression, enhanced ERK1/2 phosphorylation, and increased GLUT1, IR-B, PPAR-γ gene expression in vWAT were found in the GDM-resistance group as compared with the NGT group. The circulating FGF21 concentration was negatively correlated with fasting blood glucose (r = -0.574, P < 0.001), and associated with the GDM-resistance group (r = 0.574, P < 0.001) in pregnant women at delivery. However, we observed no insulin sensitivity alteration in GDM-dysfunction and NGT groups during pregnancy. No differences of plasma FGF21 level and FGF21 signaling in vWAT at delivery were found between women in the GDM-dysfunction and the NGT group. Conclusions: Women with GDM heterogeneity exhibited different insulin sensitivity alteration patterns. The improvement of insulin sensitivity may relate to the elevated circulating FGF21 concentration and activated FGF21 signaling in vWAT at delivery in the GDM-resistance group.