Key points are not available for this paper at this time.
Cardiotocography (CTG) is the widely used tool for recording fetal heart rate (FHR) signal and uterine contraction (UC) activity at the same time during pregnancy and delivery. CTG is frequently used for assisting the obstetricians to obtain detailed physiological information of fetal and pregnant woman as a technique of diagnosing fetal well-being. However, the visual analysis of the CTG traces requires a high level of expertise of the obstetricians and can cause inter- and intra-observer variability. Therefore, this research aimed at realizing a clinical decision support system for diagnosing fetal risk through advanced machine learning method applied to relevant features extracted from CTG recordings. In this paper, a CTG dataset consisting of 2126 recordings and 21 features obtained from UCI Machine Learning Repository is used for classification. After selecting more relevant features from total features based on Principle Component Analysis (PCA), data are trained and tested through Adaptive Boosting (AdaBoost) algorithm integrated with Support Vector Machine (SVM) to obtain a strong classifier for classifying the unknown CTG data and predicting the fetal state. Fetal state is divided into two classes as normal and pathological. Based on ten-fold cross-validation, according to the results of this study, a good overall classification accuracy of total and selected features using AdaBoost approach were obtained as 93.0% and 98.6%, computation time of 11.6s and 2.4s, respectively. So this research shows the success of hybrid PCA and AdaBoost for classifying CTG data and assessing fetal state. Furthermore, some criterias of classification performance measure were taken into consideration, including sensitivity, specificity, AUC, etc.
Zhang et al. (Sun,) studied this question.