Multistage Training of Fuzzy Cognitive Maps to Predict Preeclampsia and Fetal Growth Restriction

Abstract

Preeclampsia (PE) and fetal growth restriction (FGR) are pregancy complications related to placental dysfunction that pose significant challenges in terms of morbidity and mortality worldwide. Addressing these challenges involves early identification of the disease, which could reduce both the burden on healthcare systems and associated morbidity rates. In this study, we propose an innovative strategy using multistage training of fuzzy cognitive maps (FCM) to predict specific pregnancy disorders such as PE and FGR. The objective was to develop a predictive approach as a result of multistage training to simulate disease progression in a human individual. The models were rigorously evaluated for their predictive ability using datasets containing characteristics related to the mother, fetus, signs, symptoms, Doppler studies, and laboratory tests. The results conclusively reveal that multistage training better uncovers patterns in the data, leading to significantly improved predictive performance for these disorders. Convergence analysis demonstrated the stability of the FCM generated during the training stages. Also, the comparison with other machine learning models demonstrates that our approach is competitive to predict PE and FGR. The application of these models in healthcare settings holds promise as a valuable tool for the early detection of PE and FGR, contributing to the reduction of morbidity and mortality rates.