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

Today, in medical knowledge, data collection on various diseases is very important. one of the important issues in the medical world is the baby’s birth and its related issues. the relationship between mother and fetus is by the umbilical cord which is responsible for the development of the fetus. in this article, using data mining methods, the occurrence of umbilical cord torsion around the fetus is predicted, we also investigated some factors that can affect this event. based on the studying articles on fetus birth and its factors, and consultation with gynecologists, the new and comprehensive questionnaire was designed on factors affecting the wrapping of the umbilical cord around the fetus, including 31 features that were completed by 140 samples of pregnant mothers. then, the questionnaire was evaluated by cronbach’s alpha. since the obtained dataset was imbalanced it was balanced with smote technique. we compared different classification methods, including svm, random forest, knn, and naïve base for prediction, which knn had the best result accuracy of 81%. finally, to extract effective factors some association rule mining methods such as predictive apriori, and fp-growth were applied. the results show nutrition, blood pressure, diabetes, fetus number, and internet usage can have more impact on wrapping the umbilical cord around the fetus.