Classification of Cardiotocography Data with WEKA

Cardiotocography (CTG) records fetal heart rate (FHR) and uterine contractions (UC) simultaneously. Cardiotocography trace patterns help doctors to understand the state of the fetus. Even after the introduction of cardiotocograph, the capacity to predict is still inaccurate. This paper evaluates some commonly used classification methods using WEKA. Precision, Recall, F-Measrue and ROC curve have been used as the metric to evaluate the performance of classifiers. As opposed to some of the earlier research works that were unable to identify Suspicious and Pathologic patterns, the results obtained from the study in this paper could precisely identify pathologic and Suspicious cases. Best results were obtained from J48, Random Forest and Classification via Regression.