Application of kernel logistic regression to the prediction of liver fibrosis stages in chronic hepatitis C

Conventional studies for predicting the stage of liver fibrosis in patients with hepatitis C used classifiers such as multivariate linear regression (MLR), logistic regression (LOGR), or kernel support vector machine (KSVM). However, the prediction performance of both MLR and LOGR was not high, and KSVM does not provide the posterior probabilities of classes, nor is it easily applicable to multiclass problems. This study proposes and evaluates the use of kernel logistic regression (KLOGR), which has the advantages of LOGR and KSVM. Our experimental results showed that KLOGR achieved a higher prediction performance than the other conventional classifiers. Additionally, KLOGR can provide posterior probabilities of classes and is easily applicable to multiclass problems. Therefore, the effectiveness of KLOGR was confirmed.