Using Machine Learning Models to Determine Medical Features Most Indicative of Gestational Diabetes

With the recent overruling of Roe v. Wade, pregnancies have become especially dangerous since many females who previously abort fetuses no longer can. By doing this research project, I can help figure out what medical factors may lead to gestational diabetes, and hopefully from there, the results can be used to counteract those features.

Since not all females in America have access to abortions, my research is important because it can lead to ways to minimize dangerous and potentially fatal risks in pregnancies. Gestational diabetes is a type of diabetes that develops during pregnancy that can lead to many health concerns for both the mother and fetus. Machine learning classification can take many different features or inputs to guess what the output should be, so in the case of gestational diabetes, in a ML were given many medical features and had to predict what the outcome could be, someone could figure out what the ML thought was most important, and that could be an indicator of what medical factors are closely connected with a disease. I used four different machine learning models to each predict if a patient given a list of their medical features had gestational diabetes. I then found out which features the models relied on to make their guess in order to determine the most indicative medical factors. All models agreed that glucose was a medical factor that they relied on to make their predictions. Two different models had the exact same three features: glucose, BMI, and age. In conclusion, if medical professionals know that these three factors are most indicative of someone developing gestational diabetes, then these areas can be targeted when someone is trying to get pregnant to minimize the likelihood of developing gestational diabetes.