Project Summary

Gestational diabetes mellitus (GDM) is a common pregnancy complication that can significantly affect both maternal and fetal outcomes. While established risk factors include advanced maternal age, obesity, and genetic predisposition, emerging evidence suggests that environmental pollutants such as air pollution may also contribute to its development. This retrospective chart review study will examine the association between exposure to ambient air pollution from preconception through pregnancy and the risk of developing GDM using electronic medical records of women who delivered at KFSHRC between 2010 and 2023. Air quality data, including AQI, PM2.5, PM10, NO2, SO2, O3, CO, and CO2, will be obtained from the Presidency of Meteorology and Environment. Exposure windows will include preconception and each trimester. The analysis will be conducted using both traditional logistic regression models and advanced machine learning algorithms, particularly Random Forests, to predict GDM risk and identify the most critical exposure windows. The study aims to evaluate the predictive accuracy of various methods and enhance the early identification of at-risk women, thereby contributing to enhanced maternal-fetal health and informed preventive strategies in air-polluted environments.

Collaborators

Maha Alnemar, Gamal Mohamed, Luluah Altukhaifi.

Figure

Figure01 - A Machine Learning Approach in Predicting the Risk of Gestational Diabetes Mellitus
Beta Version