Paper: On using feedforward neural networks for clinical diagnostic tasks

Authors:
Georg Dorffner;Gerold Porenta
Affiliations:
Austrian Research Institute for Artificial Intelligence, Schottengasse 3, A-1010 Vienna, Austria and Dept. of Medical Cybernetics and Artificial Intelligence, University of Vienna Austria;Dept. of Cardiology, 2nd Clinic of Internal Medicine, University of Vienna Medical School, Waehriger Guertel 18-20, A-1090 Vienna, Austria
Venue:
Artificial Intelligence in Medicine
Year:
1994

Citing 7
Cited 2

Self-organization and associative memory: 3rd edition

Self-organization and associative memory: 3rd edition
Learning internal representations by error propagation

Parallel distributed processing: explorations in the microstructure of cognition, vol. 1
Generalization properties of radial basis functions

NIPS-3 Proceedings of the 1990 conference on Advances in neural information processing systems 3
Learning by combining memorization and gradient descent

NIPS-3 Proceedings of the 1990 conference on Advances in neural information processing systems 3
Initializing back propagation networks with prototypes

Neural Networks
A neural network that learns to interpret myocardial planar thallium scintigrams

Neural Computation
Designing multilayer perceptrons from nearest-neighbor systems

IEEE Transactions on Neural Networks

Automated assessment of myocardial SPECT perfusion scintigraphy: A comparison of different approaches of case-based reasoning

Artificial Intelligence in Medicine
Data mining for the diagnosis of type II diabetes from three-dimensional body surface anthropometrical scanning data

Computers & Mathematics with Applications

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this paper we present an extensive comparison between several feedforward neural network types in the context of a clinical diagnostic task, namely the detection of coronary artery disease (CAD) using planar thallium-201 dipyridamole stress-redistribution scintigrams. We introduce results from well-known (e.g. multilayer perceptrons or MLPs, and radial basis function networks or RBFNs) as well as novel neural network techniques (e.g. conic section function networks) which demonstrate promising new routes for future applications of neural networks in medicine, and elsewhere. In particular we show that initializations of MLPs and conic section function networks - which can learn to behave more like an MLP or more like an RBFN - can lead to much improved results in rather difficult diagnostic tasks.