Searching for risk factors using multilayer neural network as a classifier

H Xue; N Tatsumi; K Park; M Shimizu; T Kyojima; Y Sumiya; S Kawabata; N Maeda; D Sakano

doi:10.3109/14639239609025360

Searching for risk factors using multilayer neural network as a classifier

Med Inform (Lond). 1996 Jul-Sep;21(3):229-32. doi: 10.3109/14639239609025360.

Authors

H Xue¹, N Tatsumi, K Park, M Shimizu, T Kyojima, Y Sumiya, S Kawabata, N Maeda, D Sakano

Affiliation

¹ Department of Statistics, Chinese Academy of Preventive Medicine, Beijing, China.

PMID: 9062885
DOI: 10.3109/14639239609025360

Abstract

A method to determine risk factors for particular outcomes using trained multilayer neural networks is proposed. The basic idea is to measure the partial differentials of the output with respect to input variables of the network. Differentiable activation functions and continuity of input variables is assumed.

Publication types

Research Support, Non-U.S. Gov't

MeSH terms

Algorithms
Anemia, Macrocytic / classification
Diagnosis, Computer-Assisted*
Humans
Mathematical Computing
Neural Networks, Computer*
Random Allocation
Risk Factors
Treatment Outcome