Effective liver cancer diagnosis method based on machine learning algorithm

Author

Sangman Kim ; Seungpyo Jung ; Youngju Park ; Jihoon Lee ; Jusung Park

Author_Institution

Dept. of Electron. & Electr. Eng., Pusan Nat. Univ., Pusan, South Korea

fYear

2014

fDate

14-16 Oct. 2014

Firstpage

714

Lastpage

718

Abstract

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.

Keywords

cancer; fuzzy neural nets; learning (artificial intelligence); liver; medical diagnostic computing; molecular biophysics; patient diagnosis; proteins; sensor arrays; aptamers; fuzzy neural network; learning; liver cancer detection; liver cancer diagnose; machine learning algorithms; n-fold cross validation; neural network; sensor arrays; serums; Accuracy; Artificial neural networks; Cancer; Diseases; Fuzzy neural networks; Liver; diagnosis; feature; fuzzy neural network; machine learning; neural network; select-drop;

fLanguage

English

Publisher

ieee

Conference_Titel

Biomedical Engineering and Informatics (BMEI), 2014 7th International Conference on

Conference_Location

Dalian

Print_ISBN

978-1-4799-5837-5

Type

conf

DOI

10.1109/BMEI.2014.7002866

Filename

7002866