Medical Data Mining using Particle Swarm Optimization for Temporal Lobe Epilepsy

In clinical problems, numerous factors are usually involved in a medical syndrome. New advances in medicine provide a broad range of diagnosis methods to cover all aspects of a disease. However, huge amounts of raw information may confuse clinicians and decrease decision accuracy. Computerized knowledge extraction is an active area of research in medical informatics. This paper suggests a new medical data mining approach using an advanced swarm intelligence data mining algorithm. Considering medical knowledge discovery difficulties, this approach addresses common issues such as missing value management and interactive rule extraction. Here, surgery candidate selection in temporal lobe epilepsy is the main target application. However, the general idea can be applied to other medical knowledge discovery problems. Experimental results show noticeable performance improvement in the final rule-set quality while the method is flexible and fast.