Effective liver cancer diagnosis method based on machine learning algorithm
Sangman Kim, Seungpyo Jung, Youngju Park, Jihoon Lee, Jusung Park · 2014
In this paper, we introduce a method to find useful markers from sensor arrays which have massive sensing points and diagnose liver cancer based on machine learning algorithms which are neural network and fuzzy neural network. We obtain reliable results by using a learning ability and n-fold cross validation. For the verification of the proposed method, raw data of serums from 314 normal and 81 patients reacted to 1,142 aptamers are used. According to the results, we can detect liver cancer with the accuracy of 99.19 % by average use of 132 aptamers based on neural network and 98.19 % by average use of 226 aptamers based on fuzzy neural network.