J Korean Soc Med Inform.  1998 Jun;4(1):83-87.

Development of Breast Cancer Predication Model Using Neural Networks

Affiliations
  • 1Medical Information Center, Seoul National University Hospital, Korea. jwchoi@shinbiro.com

Abstract

This paper describes the developing a neural network breast cancer prediction model using neural network. Neural Networks are nonparametric, pattern recognition techniques that can be used to complex biological relationships. The applicability of multilayer perceptron (MLP) was accessed using the data of 1143 patients who had breast cancer or visited hospital for the treatment of other disease. The MLP prediction model consists of one-hidden layer and 4 to 10 hidden nodes and it is trained by back propagation algorithm. The overall prediction performance of the model was 76% as evaluated with test data sets. Principal Component Analysis(PCA) was done for featuring the input data. The performance of PCA neural networks which had 7 transformed input nodes was 72% as it was tested on the unknown data.

Keyword

Neural Network; Breast Cancer; Prediction Model; Back Propagation; Principal Component Analysis

MeSH Terms

Breast Neoplasms*
Breast*
Dataset
Humans
Neural Networks (Computer)
Passive Cutaneous Anaphylaxis
Principal Component Analysis
Full Text Links
  • JKSMI
Actions
Cited
CITED
export Copy
Close
Share
  • Twitter
  • Facebook
Similar articles
Copyright © 2024 by Korean Association of Medical Journal Editors. All rights reserved.     E-mail: koreamed@kamje.or.kr