Does the DeepFHR convolutional neural network model improve the prediction of fetal acidemia using fetal heart rate signals compared to other methods?
The DeepFHR convolutional neural network model demonstrates high accuracy and AUC for predicting fetal acidemia from fetal heart rate signals, suggesting potential utility as a computer-aided diagnosis tool.
Based on the test open-access database (CTU-UHB), after comprehensive experimentation, we achieved better classification performance using the optimal CNN configuration compared to other state-of-the-art methods: the averaged ten-fold cross-validation of the accuracy, sensitivity, specificity, quality index defined as the geometric mean of the sensitivity and specificity, and the area under the curve yielded results of 98.34, 98.22, 94.87, 96.53 and 97.82%, respectively CONCLUSIONS: Once the proposed CNN model is successfully trained, the corresponding CAD system can be served as an effective tool to predict fetal asphyxia objectively and accurately.
Zhao et al. (Sun,) studied this question.