Machine Learning-Based Prediction of Large-for-Gestational Age Infants in Mothers with Gestational Diabetes Mellitus.

CONTEXT: Large-for-gestational-age (LGA), one of the most common complications of gestational diabetes mellitus (GDM), has become a global concern. The predictive performance of common continuous glucose monitoring (CGM) metrics for LGA is limited. OBJECTIVE: We aimed to develop and validate an artificial intelligence (AI) based model to determine the probability of women with GDM giving birth to LGA infants during pregnancy using CGM measurements together with demographic data and metabolic indicators. METHODS: A total of 371 women with GDM from a prospective cohort at a university hospital were included. CGM was performed during 20-34 gestational weeks, and glycemic fluctuations were evaluated and visualized in women with GDM who gave birth to LGA and non-LGA infants. A convolutional neural network (CNN)-based fusion model was developed to predict LGA. Comparisons among the novel fusion model and three conventional models were made using the area under the receiver-operating characteristic curve (AUCROC) and accuracy. RESULTS: Overall, 76 (20.5%) out of 371 GDM women developed LGA neonates. The visualized 24-h glucose profiles differed at midmorning. This difference was consistent among subgroups categorized by pregestational BMI, therapeutic protocol and CGM administration period. The AI based fusion prediction model using 24-h CGM data and 15 clinical variables for LGA prediction (AUCROC 0.852, 95% CI 0.680-0.966, accuracy 84.4%) showed superior discriminative power compared with the three classic models. CONCLUSIONS: We demonstrated better performance in predicting LGA infants among women with GDM using the AI based fusion model. The characteristics of the CGM profiles allowed us to determine the appropriate window for intervention.

Factors associated with progression of different prediabetic status to Diabetes: A Community-based cohort study.

AIMS: To examine the predictive factors associated with the progression of different prediabetic status to diabetes. METHODS: A two-year retrospective cohort study was conducted on 5741 participants aged 40 years or older. Finally, 1685 participants with prediabetes defined by IFG (impaired fasting glucose), IGT (impaired glucose tolerance) and CGI (combined IFG and IGT) were included. Logistic regression model was used to evaluate the risk of prediabetes progression to diabetes. RESULTS: Of the 1685 subjects with prediabetes at baseline, 212 (12.6%) subjects progressed to diabetes and 1473 (87.4%) subjects did not. Logistic regression analysis demonstrated that people with CGI were associated with an increased risk of progressing to diabetes compared to those with IFG (OR, 95% CI: 3.127, 2.047-4.776). Moreover, males, obese people, people with increased BMI and WHR (Waist/ Hip ratio), and hypertension were positively associated with the progression to diabetes, while HOMA-ß was negatively associated with the progression to diabetes. CONCLUSIONS: Subjects with CGI are prone to progressed to diabetes compared to those with IFG or IGT in middle-aged and older person in China. More attention should be paid to male and obese prediabetic subjects, and measures should be taken to control the increase in their BMI and WHR.