A. Hamilton-Wright and D.W. Stashuk (Canada)
biomedical computing, fuzzy rule based classification sys tems, pattern discovery, decision support
A framework for a decision support system (DSS) is intro duced. This framework supports the exploration of quan titative electromyographic (QEMG) data acquired using a concentric needle electrode and decomposed using the DQEMG program. This DSS has been constructed by marrying a statistically based fuzzy inference system (FIS) with a user interface, allowing drill-down exploration of the underlying statistical support, providing an exceptionally transparent access to both the rule based inference as well as the underlying statistical basis for the rules. The FIS is constructed through a “Pattern Discovery” based analysis of training data. Such an analysis yields a rule base charac terized by simple explanations for any rule or data division in the extracted knowledge base. The reliability of a fuzzy inference is well predicted by a confidence measure that de termines the probability of a correct suggestion by exami nation of values produced during the inference calculation. The combination of these components provides a means of supporting the characterization of neuromuscular disorders in a clinical environment, providing the transparent support required to allow a clinical user to confidently incorporate the automatic suggestions provided by this framework into a larger decision context. Specific data examples based on the characterization of QEMG data are used to demonstrate the principles of the system.
Important Links:
Go Back
