Data mining approach for prediction umbilical cord wrapping around the fetus and investigating effective factors

Today, in the field of medical science, data collection on various diseases is very important. Baby’s birth and its related issues are the vital subject. Nuchal cord is the term used by medical professionals when baby has their umbilical cord wrapped around their neck. In this article, using data mining methods, the occurrence of nuchal cord is predicted. Also some influence factors in this event are investigated. For achieve this aim, in the first stage, based on the literature review and consultation with gynecologists, the new and comprehensive questionnaire for effective factors on the nuchal cord, was designed. ( 31 features that were completed by 140 samples of pregnant mothers). Then, the questionnaire was evaluated by Cronbach’s Alpha. In the next stage, since the obtained dataset was imbalanced, some techniques are applied to balance it. We compared different classification methods such as SVM, cost-sensitive SVM, Random Forest, KNN, Naïve Base, and neural network for prediction, which bootstrap resampling method in combination with KNN and random forest gain the best accuracy (84%). Also, KNN classifier with smote balance handling method achieves best recall (94%). Finally, to extract effective factors some association rule mining methods such as Predictive Apriori, FP-growth were applied. The results show nutrition, blood pressure, diabetes, fetus number, and Internet usage can have more influence on wrapping the umbilical cord around the fetus.