Models Predicting Postpartum Glucose Intolerance Among Women with a History of Gestational Diabetes Mellitus: a Systematic Review

Prediction of pre-eclampsia with machine learning approaches: Leveraging important information from routinely collected data

BACKGROUND

Globally, pre-eclampsia (PE) is a leading cause of maternal and perinatal morbidity and mortality. PE prediction using routinely collected data has the advantage of being widely applicable, particularly in low-resource settings. Early intervention for high-risk women might reduce PE incidence and related complications. We aimed to replicate our machine learning (ML) published work predicting another maternal condition (gestational diabetes) to (1) predict PE using routine health data, (2) identify the optimal ML model, and (3) compare it with logistic regression approach.

METHODS

Data were from a large health service network with 48,250 singleton pregnancies between January 2016 and June 2021. Supervised ML models were employed. Maternal clinical and medical characteristics were the feature variables (predictors), and a 70/30 data split was used for training and testing the model. Predictive performance was assessed using area under the curve (AUC) and calibration plots. Shapley value analysis assessed the contribution of feature variables.

RESULTS

The random forest approach provided excellent discrimination with an AUC of 0.84 (95% CI: 0.82-0.86) and highest prediction accuracy (0.79); however, the calibration curve (slope of 1.21, 95% CI 1.13-1.30) was acceptable only for a threshold of 0.3 or less. The next best approach was extreme gradient boosting, which provided an AUC of 0.77 (95% CI: 0.76-0.79) and well-calibrated (slope of 0.93, 95% CI 0.85-1.01). Logistic regression provided good discrimination performance with an AUC of 0.75 (95% CI: 0.74-0.76) and perfect calibration. Nulliparous, pre-pregnancy body mass index, previous pregnancy with prior PE, maternal age, family history of hypertension, and pre-existing hypertension and diabetes were the top-ranked features in Shapley value analysis.

CONCLUSION

Two ML models created the highest-performing prediction using routinely collected data to identify women at high risk of PE, with acceptable discrimination. However, to confirm this result and also examine model generalisability, external validation studies are needed in other settings, utilising standardised prognostic factors.

Dietary inflammatory index as a predictor of prediabetes in women with previous gestational diabetes mellitus

INTRODUCTION

Gestational diabetes mellitus (GDM) is associated with an increased risk of developing type 2 diabetes mellitus (T2DM). The inflammatory potential of diet is crucial in GDM development. This study compares dietary inflammatory indices (DII) in females with and without a history of GDM and constructs a predictive model for prediabetes risk.

METHODS

Cross-sectional data from NHANES cycles (2011-2014) were analyzed using the DII. Independent t tests, chi-square test, and Mann-Whitney U test examined DII scores in relation to GDM history. Multivariate logistic regression assessed DII's association with prediabetes in females with GDM history. Restricted cubic spline (RCS) and LASSO regression modeled non-linear relationships and predicted prediabetes risk.

RESULTS

971 female participants were included. Those with GDM history had lower DII scores (1.62 (0.58, 2.93) vs. 2.05 (0.91, 2.93)). Higher DII scores in females with GDM were linked to prediabetes, remaining significant after adjusting for confounders. RCS analysis found no non-linear correlation (non-linear p = 0.617). The prediabetes model for GDM history had strong predictive performance (AUC = 88.6%, 95% CI: 79.9-97.4%).

CONCLUSION

Females with GDM history show lower DII levels, potentially reflecting improved diet and health awareness. Higher DII scores correlate with increased prediabetes risk in this group, emphasizing diet's role in diabetes risk. Further studies are needed to confirm these findings.

Development of a risk prediction model for postpartum onset of type 2 diabetes mellitus, following gestational diabetes; the lifestyle InterVention in gestational diabetes (LIVING) study

AIMS

This study aimed to develop a prediction model for identifying a woman with gestational diabetes mellitus (GDM) at high risk of type 2 diabetes (T2DM) post-birth.

METHODS

Utilising data from 1299 women in the Lifestyle Intervention IN Gestational Diabetes (LIVING) study, two models were developed: one for pregnancy and another for postpartum. Key predictors included glucose test results, medical history, and biometric indicators.

RESULTS

Of the initial cohort, 124 women developed T2DM within three years. The study identified seven predictors for the antenatal T2DM risk prediction model and four for the postnatal one. The models demonstrated good to excellent predictive ability, with Area under the ROC Curve (AUC) values of 0.76 (95% CI: 0.72 to 0.80) and 0.85 (95% CI: 0.81 to 0.88) for the antenatal and postnatal models, respectively. Both models underwent rigorous validation, showing minimal optimism in predictive capability. Antenatal model, considering the Youden index optimal cut-off point of 0.096, sensitivity, specificity, and accuracy were measured as 70.97%, 70.81%, and 70.82%, respectively. For the postnatal model, considering the cut-off point 0.086, sensitivity, specificity, and accuracy were measured as 81.40%, 75.60%, and 76.10%, respectively.

CONCLUSIONS

These models are effective for predicting T2DM risk in women with GDM, although external validation is recommended before widespread application.

Association between exposure to outdoor artificial light at night during pregnancy and glucose homeostasis: A prospective cohort study

BACKGROUND

Outdoor artificial light at night (ALAN) has been linked to an elevated risk of diabetes, but the available literature on the relationships between ALAN and glucose homeostasis in pregnancy is limited.

METHODS

A prospective cohort study of 6730 pregnant women was conducted in Hefei, China. Outdoor ALAN exposure was estimated using satellite data with individual addresses at a spatial resolution of approximately 1 km, and the average ALAN intensity was calculated. Gestational diabetes mellitus (GDM) was diagnosed based on a standard 75-g oral glucose tolerance test. Multivariable linear regression and logistic regression were used to estimate the relationships between ALAN and glucose homeostasis.

RESULTS

Outdoor ALAN was associated with elevated glucose homeostasis markers in the first trimester, but not GDM risk. An increase in the interquartile range of outdoor ALAN values was related to a 0.02 (95% confidence interval [CI]: 0.00, 0.03) mmol/L higher fasting plasma glucose, a 0.42 (95% CI: 0.30, 0.54) μU/mL increase in insulin and a 0.09 (95% CI: 0.07, 0.12) increase in homeostatic model assessment of insulin resistance (HOMA-IR) during the first trimester. Subgroup analyses showed that the associations between outdoor ALAN exposure and fasting plasma glucose, insulin, and HOMA-IR were more pronounced among pregnant women who conceived in summer and autumn.

CONCLUSIONS

The results provided evidence that brighter outdoor ALAN in the first trimester was related to elevated glucose intolerance in pregnancy, especially in pregnant women conceived in summer and autumn, and effective strategies are needed to prevent and manage light pollution.