医療データ解析へのサポートベクトルマシン(SVM)の応用

概要

論文の詳細を見る
In our previous papers we proposed a novel screening methodbthat assists the diagnosis of Grave's hyperthyrodism via two types of neural networks by making use of routine test data.This method can be applied by non-specialists during physical check-ups at a low cost and is expected to lead to rapid referrals for examination and treatment by thyroid specialists, that is,toimprove patient'QOL. In this report,we apply the support vector machine,which is a novel learning method building on kernels, to the classification problems of madical data such as Wisconsin breast cancer data or our screening of hyperthyroid.It turned out that the support vector machine ,after best turning of parameters based on the grid-search method,works quite well to correctly the lacated in the bordering area between two classes.Our results suggest that the SVM would work as a useful methods in our screening in addition to previous two types of neural networks.