Classification of Liver Disorders Diagnosis using Naïve Bayes Method

Abstract

Liver diseases pose a significant health challenge, necessitating robust predictive tools for early diagnosis. This study aims to determine the predictive performance of Naive Bayes classifier, one of the data mining algorithms, in the classification of liver patients. The study applied 2, 5, 10 and 20-fold cross-validation method. Trying to determine the effect of the cross-validation (CV) method used on the classification performance, this study used the "BUPA" dataset in the UCI Machine Learning Repository database for this purpose. The dataset consists of 6 variables and 345 examples. Orange program was used for data analysis. As a result of the analysis, the accuracy for the Naive Bayes method was determined to be 62.9%, 63.5%, 63.8%, and 64.3%, respectively. The AUC values were 0.68, 0.66, 0.66, and 0.67, respectively; the F1 scores were 0.56, 0.57, 0.58, and 0.58, respectively. On the other hand, the precision values were 0.60, 0.60, 0.60, and 0.62, respectively, while the recall values were determined to be 0.52, 0.53, 0.55, and 0.54. Additionally, the MCC values were determined to be 0.24, 0.26, 0.26, and 0.27, respectively. The analysis results indicate that the 20-fold CV method demonstrates marginally superior performance. The use of the free and easy-to-use program is recommended.