A. Ouali, A. Ramdane-Cherif, and M.O. Krebs (France)
Data mining, Bio-informatics, clinical data, Schizophreniaand neural networks
Despite the large amount of information gathered in the clinical database concerning patients suffering of schizophrenia, there are many unanswered questions regarding the associated features and boundaries of this heterogeneous disease. The patterns within these data could provide new medical knowledge. In this study, the techniques of data mining are used to search for relationships between clinical variables in a large database. We use an artificial neural networks (ANN) approach in order to predict attributes related to subtypes of schizophrenia. The results are encouraging, and indicate that data mining can play a useful role in large scale medical problem solving.
Important Links:
Go Back
