engleski

Data analysis based on subgroup discovery: Experiments in brain ischaemia domain

This paper presents insightful analysis of medical data collected in regular hospital practice. The domain consists of patients suffering from brain ischaemia, either permanent as brain attack (stroke) with positive computer tomography (CT) or reversible ischaemia with normal brain CT test. The goal of the analysis is the extraction of useful knowledge that can help in diagnosis, prevention and better understanding of vascular brain disease. The work demonstrates the applicability of subgroup rule induction as the basis for insightful data analysis and describes intellectual process of converting rules into reasonable medical concepts. Detection of coexisting risk factors, selection of relevant discriminative points for numerical descriptors, as well detection and description of characteristic patient subpopulations are important results of the analysis. Graphical representation is extensively used to illustrate the detected regularities.

Intelligent data analysis; brain ischemia; subgroup discovery

nije evidentirano