AUTHOR=Rao Lin , Lu Jia , Wu Hai-Rong , Zhao Shu , Lu Bang-Chun , Li Hong 

TITLE=Automatic classification of fetal heart rate based on a multi-scale LSTM network

JOURNAL=Frontiers in Physiology

VOLUME=Volume 15 - 2024

YEAR=2024

URL=https://www.frontiersin.org/journals/physiology/articles/10.3389/fphys.2024.1398735

DOI=10.3389/fphys.2024.1398735

ISSN=1664-042X

ABSTRACT=Fetal heart rate monitoring during labor can aid healthcare professionals in identifying alterations in the heart rate pattern. Nevertheless, discrepanicies in guidelines and obstetricians expertise present chanllenge in interpreting fetal heart rate, including failure to acknowledge findings or misinterpretation. The advancement of computer technology has the potential to support obstetricians in diagnosing abnormal fetal heart rate through the use of artificial intelligence. In this study, we introduce a multi-scale long short-term memory neural network for the automatic classification of fetal heart rae. Preprocessing techniques are employed to mitigate the effects of missing signals and artifacts on the model, while data augmentation methods are utilized to address data imbalance. The multi-scale model is trained using a variety of timescale data. The model achieves an accuracy of 85.73%, specificity of 85.32%, and precision of 85.53%. Furthermore, the area under the receiver operating curve of 0.918, suggests that our model demonstrates a high level of credibility. In Comparison to prior research, our methodology exhibits superior performance across various evaluation metrics.