Diagnosis of hepatobiliary disorders using rules extracted from artificial neural networks

Neural networks have been widely used as tools for prediction in medical diagnosis. We expect to see even more applications of neural networks as recently developed neural network rule extraction algorithms make it possible for the decision process of a trained network to be expressed as classification rules. These rules are more comprehensible to a human user than the classification process of the original network which involves complex nonlinear mapping of the input data. We apply NeuroRule, an algorithm that extracts rules from neural networks to the problem of diagnosing hepatobiliary disorders. The results of our study show that NeuroRule produces a compact set of rules with predictive accuracy rates that are higher those that obtained from linear discriminant analysis and fuzzy neural networks.