INFERTILITY PREDICTIVE ANALYSIS ON IVF BASED ON SIGNIFICANT FEATURE SELECTION USING DATA MINING TECHNIQUES

Abstract

This paper elucidates the process by applying clustering and classification technique to spot major procedures for the infertility couples to decide the success rate of In-vitro Fertilization treatment. There are factors which lead to infertility like age, education, economical backlog, body mass index (BMI) and obesity which cause changes in hormonal levels and heredity etc., for infertility couples. The constraints with high sway factor can be well-known by apply the proper decrease/unrelated algorithm, which destroy the parameters that has a less important role in determining the success rate of particular patients. Data mining plays vital roles in its pre-processing techniques to increase prediction accuracy and find which treatment will be perfect for the patient.

A FAST_FOIL algorithm, First becomes the construction of minimum spanning tree, after that the partition the data into each tree by clustering the similar features. Selected features are represented into clusters. Thus, the proposed paper will determine the accuracy of IVF treatment compared with ZIFT and GIFT using MATLAB.