Fetal Health Diagnosis Based on Adaptive Dynamic Weighting with Main-Auxiliary Correction Network
Open Access
Abstract
Maternal and child health during pregnancy is an important issue in global public health, and the classification accuracy of fetal cardiotocography (CTG), as a key tool for monitoring fetal health during pregnancy, is directly related to the effectiveness of early diagnosis and intervention. Due to the serious category imbalance problem of CTG data, traditional models find it challenging to take into account a small number of categories of samples, increasing the risk of leakage and misdiagnosis. To solve this problem, this paper proposes a two-step innovation: firstly, we design a method of adaptive adjustment of misclassification loss function weights (MAAL), which dynamically identifies and increases the focus on misclassified samples based on misclassification rates. Secondly, a primary and secondary correction network model (MAC-NET) is constructed to carry out secondary correction for the misclassified samples of the primary model. Experimental results show that the method proposed in this paper achieves 99.39% accuracy on the UCI publicly available fetal health dataset, and also obtains excellent performance on other domain imbalance datasets. This demonstrates that the model is not only effective in alleviating the problem of category imbalance, but also has very high clinical utility.Keywords
Funding Information
- the Jilin Province Science and Technology Development Plan Project (YDZJ202201ZYTS549, YDZJ202301ZYTS496, 21ZGM30)
- Changchun City Science and Technology Development Project (YDZJ202201ZYTS549, YDZJ202301ZYTS496, 21ZGM30)
This publication has 40 references indexed in Scilit:
- Machine learning-enabled risk prediction of chronic obstructive pulmonary disease with unbalanced dataComputer Methods and Programs in Biomedicine, 2023
- Cardiac arrhythmia classification by time–frequency features inputted to the designed convolutional neural networksBiomedical Signal Processing and Control, 2022
- Handling Class-Imbalance with KNN (Neighbourhood) Under-Sampling for Software Defect PredictionArtificial Intelligence Review, 2021
- A hybrid method with dynamic weighted entropy for handling the problem of class imbalance with overlap in credit card fraud detectionExpert Systems with Applications, 2021
- Intelligent classification of antepartum cardiotocography model based on deep forestBiomedical Signal Processing and Control, 2021
- Recognition of imbalanced underwater acoustic datasets with exponentially weighted cross-entropy lossApplied Acoustics, 2021
- Fetal health status prediction based on maternal clinical history using machine learning techniquesComputer Methods and Programs in Biomedicine, 2018
- Technical characteristics of current cardiotocographic monitorsBest Practice & Research Clinical Obstetrics & Gynaecology, 2016
- FIGO consensus guidelines on intrapartum fetal monitoring: CardiotocographyInternational Journal of Gynecology & Obstetrics, 2015
- Classification of the cardiotocogram data for anticipation of fetal risks using machine learning techniquesApplied Soft Computing, 2015