Predicting Risk of an Adverse Event in Complex Medical Data Sets Using the Fuzzy ARTMAP Network

N. Markuzon, S. Gaehde, A. Ash, G. Carpenter, and M. Moskowitz

Fuzzy ARTMAP is a supervised learning system which includes nonlinear dynamics in the learning process. We introduce a new testing procedure which allows the system to estimate the probability of an outcome. Simulations illustrate the system performance in estimating risk in medical procedures. The results are compared to the performance of the logistic regression model. It is shown that both models have similar explanatory power.

This page is copyrighted by AAAI. All rights reserved. Your use of this site constitutes acceptance of all of AAAI's terms and conditions and privacy policy.