Intelligent classification techniques for mining temporal patterns from clinical datasets

Abstract

Representation of temporal knowledge and analysis of temporal data are essential for effective temporal reasoning in medical diagnosis systems which are gaining importance recently These temporal representation models provide features for temporal rules extraction through association rule mining which are necessary to perform detective inference in medical expert systems Most of the existing temporal mining systems focus on mining clinical data assumes instant stamping of tuples as the time stamping method In such systems database is created using a series of observations taken at different time points and the mining algorithm classifies newlinethe data based on the time instants recorded in the database How eve the analysis techniques need to consider data performing to a time interval Hence it is necessary to propose new representation and reasoning methods for the effective analysis of medical data newline