Абстрактный

EVALUATION OF CLASSIFICATION ALGORITHMS FOR DISEASE DIAGNOSIS

Tamije Selvy P, Palanisamy V, Elakkiya S

Data classification is the categorization of data for its most effective and efficient use. Data can be classified according to any criteria, not only relative importance or frequency of use. Classification plays a major role in disease diagnosis. The paper contains brief discussion of various classification methods that includes Case Based Reasoning, decision trees, K-nearest neighbour classifier, naïve bayes classifier and neural network. The paper also discusses some applications of classification model. The performance of the classification methods are observed where the CBR classification model results in 90.7% of specificity, 92.3% of sensitivity and 95.5% of prediction accuracy