Applying clustering based on rules on WHO-DAS II for knowledge discovery on functional disabilities

Abstract

The senior citizens represent a fast growing proportion of the population in Europe and other developed areas. This increases the proportion of persons with disability and reducing quality of life. The concept of disability itself is not always precise and quantifiable. To improve agreement on the concept of disability, the World Health Organization (WHO) developed a clinical test WHO Disability Assessment Schedule, (WHO-DASII) that is understood to include physical, mental, and social well-being, as a generic measure of functioning. From the medical point of view, the purpose of this work is to extract knowledge on the performance of the test WHO-DASII on the basis of a sample of neurological patients from an Italian hospital. This Knowledge Discovery problem has been faced by using clustering based on rules, a technique stablished on 1994 by Gibert which combines some Inductive Learning (from AI) methods with Statistics to extract knowledge on ill-structured domains (that is complex domains where consensus is not achieved, like is the case). So, in this paper, the results of applying this technique to the WHO-DASII results is presented.