J Korean Soc Med Inform Search


Healthc Inform Res > Volume 4(1); 1998 > Article
Journal of Korean Society of Medical Informatics 1998;4(1):83-87.
DOI: https://doi.org/10.4258/jksmi.1998.4.1.83    Published online June 30, 1998.
Development of Breast Cancer Predication Model Using Neural Networks
Jin Wook Choi
Medical Information Center, Seoul National University Hospital, Korea.

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.

Key Words: Neural Network, Breast Cancer, Prediction Model, Back Propagation, Principal Component Analysis


Browse all articles >

Editorial Office
1618 Kyungheegung Achim Bldg 3, 34, Sajik-ro 8-gil, Jongno-gu, Seoul 03174, Korea
Tel: +82-2-733-7637, +82-2-734-7637    E-mail: hir@kosmi.org                

Copyright © 2024 by Korean Society of Medical Informatics.

Developed in M2community

Close layer
prev next