Application of Entropy-Based Attribute Reduction and an Artificial Neural Network in Medicine: A Case Study of Estimating Medical Care Costs Associated with Myocardial Infarction

摘要: In medicine, artificial neural networks (ANN) have been extensively applied in many fields to model the nonlinear relationship of multivariate data. Due difficulty selecting input variables, attribute reduction techniques were widely used reduce data get a smaller set attributes. However, compute reductions from heterogeneous data, discretizing algorithm was often introduced dimensionality methods, which may cause information loss. this study, we developed an integrated method for estimating medical care costs, obtained 798 cases, associated with myocardial infarction disease. The subset attributes selected as variables ANN by using entropy-based measure, fuzzy entropy, can deal both categorical and numerical without discretization. Then, correction Akaike criterion (ΑICc) compare networks. results revealed that entropy capable ANN, proposed procedure study provided reasonable estimation be adopted other science.