In this paper, we propose a method which removes exceptional patients in a spiral manner for obtaining a definition of a disease in the form of a table of conditional probabilities and we describe its application to chronic hepatitis data. The removal is based on a risk-ratio-based criterion and can be supported by our previously developed data mining methods and medical experts. A series of experiments in which two domain experts decided exceptional patients to be removed show that our proposed method is effective and promising from various viewpoints such as obtaining new hypotheses and improving skills of domain experts. Another series of experiments in which exceptional patients were removed automatically led us to a rediscovery of a piece of knowledge, which had been reported in an article of a medical journal as the main result of the article.
All Science Journal Classification (ASJC) codes
- Theoretical Computer Science
- Hardware and Architecture
- Computer Networks and Communications