An Efficient Framework for Prediction in Healthcare Data Using Soft Computing Techniques

摘要: Healthcare organizations aim at deriving valuable insights employing data mining and soft computing techniques on the vast stores that have been accumulated over years. This however, might consist of missing, incorrect most time, incomplete instances can a detrimental effect predictive analytics healthcare data. Preprocessing this data, specifically imputation missing values offers challenge for reliable modeling. work presents novel preprocessing phase with value both numerical categorical A hybrid combination Classification Regression Trees (CART) Genetic Algorithms to impute continuous Self Organizing Feature Maps (SOFM) is adapted in work. Further, Artificial Neural Networks (ANN) used validate improved accuracy prediction after imputation. To evaluate model, we use PIMA Indians Diabetes Data set (PIDD), Mammographic Mass (MMD). The proposed model emphasizes shown be superior existing techniques. approach simple, easy implement practically reliable.