A Study on Rule Extraction from Neural Networks Applied to Medical Databases

The inherent black-box nature of neural networks is an important drawback with respect to the problem of knowledge discovery from databases. In this work our aim is to extract rules from multi-layer perceptrons. This is a starting point to explain the basis of neural network solutions for knowledge discovery to experts of domain applications. Our approach consists in characterizing discriminant hyper-plane frontiers built by a special neural network model denoted to as Discretized Interpretable Multi Layer Perceptron (DIMLP). Rules are extracted in polynomial time with respect to the size of the problem and the size of the network. Further, the degree of matching between extracted rules and neural network responses is 100%. We apply DIMLP to 9 databases related to the medical diagnosis domain in which for some of them it gives better average predictive accuracy than standard multi-layer perceptrons and C4.5 decision trees. Finally, the quality of rules generated from DIMLP networks is compared to those related to decision trees.