A Prototype Neural Network Decision-Support Tool for the Early Diagnosis of Acute Myocardial Infarction

摘要

An application of the ARTMAP neural network model to the early diagnosis of acute myocardial infarction is described. Performance results are given for 10 individual ARTMAP networks and for combinations of the networks using "pooled" decision making (the so-called voting strategy). Category nodes are pruned from the trained networks in different ways so as to improve accuracy, sensitivity and specificity respectively. The differently pruned networks are employed in a novel "cascaded" variation of the voting strategy. This allows a partitioning of the test data into predictions with a high and lower certainty of being correct, providing the diagnosing clinician with an indication of the reliability of an individual prediction. Additionally, symbolic rule extraction is performed upon the networks, allowing a domain expert to verify the networks have learned autonomously a valid set of predictive rules for the domain.