ARTMAP-IC and Medical Diagnosis: Instance Counting and Inconsistent Cases
OA Version
Citation
Abstract
For complex database prediction problems such as medical diagnosis, the ARTMAP-IC neural network adds distributed prediction and category instance counting to the basic fuzzy ARTMAP system. For the ARTMAP match tracking algorithm, which controls search following a predictive error, a new version facilitates prediction with sparse or inconsistent data. Compared to the original match tracking algorithm (MT+), the new algorithm (MT-) better approximates the real-time network differential equations and further compresses memory without loss of performance. Simulations examine predictive accuracy on four medical databases: Pima Indian diabetes, breast cancer, heart disease, and gall bladder removal. ARTMAP-IC results arc equal to or better than those of logistic regression, K nearest neighbor (KNN), the ADAP perceptron, multisurface pattern separation, CLASSIT, instance-based (IBL), and C4. ARTMAP dynamics are fast, stable, and scalable. A voting strategy improves prediction by training the system several times on different orderings of an input set. Voting, instance counting, and distributed representations combine to form confidence estimates for competing predictions.
Description
License
Copyright 1996 Boston University. Permission to copy without fee all or part of this material is granted provided that: 1. The copies are not made or distributed for direct commercial advantage; 2. the report title, author, document number, and release date appear, and notice is given that copying is by permission of BOSTON UNIVERSITY TRUSTEES. To copy otherwise, or to republish, requires a fee and / or special permission.