Uterine fibroid risk prediction using data analytics and support vector machines in data mining

In healthcare, the amount and sensitivity of data is huge. The information must be handled with considerable caution, and no shortcuts should be made. A variety of data mining categorization approaches have been used to estimate the quality of healthcare services. On the basis of 150 patient records, this study describes and evaluates the experience of applying a data mining approach and methods. Using data mining techniques, this unique approach to determining the correctness of a product was devised. Data mining employs a number of techniques, including Decision Tree, Naive Bayes, KNN, Radom Tree Set, Rule Model, ZeroR, and J48 or C 4.5. Using the fibroid data set, I applied the Support Vector Machine data mining classification to estimate the Precision. Our goal is to make a conclusion by analyzing the Precision and other indicator values such as RMSE, Recall, and so on.