NeuroFetalNet: Advancing Remote Electronic Fetal Monitoring with a New Dataset and Comparative Analysis of FHR and UCP Impact

This study explores the evolution of electronic fetal monitoring (EFM) and introduces remote electronic fetal monitoring (REFM). A new REFM dataset is constructed to address gaps in existing datasets. The study compares the impact of fetal heart rate (FHR), uterine contraction pressure (UCP), and their simultaneous presence on prediction accuracy. By leveraging deep learning techniques, our study introduces NeuroFetalNet, which has shown the best performance in our proposed REFM datasets. The results emphasize the multi-scale feature extractor’s potential in NeuroFetalNet to improve the accuracy and efficiency of remote fetal monitoring. These findings have implications for enhancing pregnant and fetal healthcare.