Decision tree to analyze the cardiotocogram data for fetal distress determination

One of the most commonly used techniques for recording changes in Uterine Contractions (UC) and Fetal Heart Rate (FHR) is cardiotocography (CTG). Cardiotocographic assessment is very important in identifying oxygen-deficient fetuses, i.e. hypoxia. The situation is defined as fetal distress requiring fetal intervention, since hypoxia causes neurological diseases or fetus death. The proposed method in this paper is decision tree to analyze the Cardiotocogram data for Fetal Distress Determination. The main purpose of this classification method is to classify the fetal state class code consisting of normal, suspicious or pathologic. Fetal state class code or FHR pattern class can be classified by using pruned decision tree with the minimum misclassification error of classification confusion matrix. The misclassification error (0.184383) is the result of the experimental decision tree for analyzing cardiotogram data in determining fetal distress using a pruned decision tree. By pruning the decision tree, promising results have been obtained, 1593 + 130 + 11 = 1734 of 2126 samples were perfectly predicted. 138 samples were predicted as "pathologic", 165 samples as "suspicious", and 1593 as the actual values of "normal". 27 "pathologic", 62 "normal", and 130 as the actual values of "suspicious". Additionally, 0 "suspicious", 0 "normal", and 11 as the actual values of "pathologic".