Exploring the Performance of Machine Learning Models and Predictive Factors for Fetal Death: Preliminary Results

This study investigates the effectiveness of machine learning models in predicting fetal death and identifying significant predictive factors. The study utilized a dataset from the Programa Mãe Coruja Pernambucana (PMCP) that includes socio-demographic, prenatal, maternal, and family health history data. The data underwent pre-processing and was explored using four tree-based machine learning models, each of which was evaluated based on their performance and feature importance. The attributes that significantly impacted the learning process were the first prenatal week, maternal age, and months between pregnancies. The application of predictive models for fetal deaths in this context can enhance the ability to detect such occurrences thus representing a pivotal support tool for the PMCP to identify mothers with high risk of adverse outcomes and promote targeted interventions of monitoring during pregnancy, and ultimately increase the likelihood of positive outcomes for mothers and babies.