OPTIMIZATION OF EVALUATION OF THE INFORMATIVITY OF MEDICAL INDICATORS ON THE BASIS OF THE HYBRID APPROACH

Feature Selection task is one of most complicated and actual in Data Mining area. Any approaches for it solving are based on non-mathematical and presentative hypothesis. New approach for evaluation of medical features information quantity, based on optimal combination of Feature Selection and Feature Extraction methods. This approach permits to produce optimal reduced number of features with linguistic interpreting of each ones. Hybrid system of Feature Selection/Extraction is proposed. This system is numerically simple, can produce Feature Selection/Extraction with any number of features using standard method of principal component analysis and calculating distance between first principal component and all medical features.