Knowledge discovery on functional disabilities using clustering based on rules on WHO-DAS II

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 reduced 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-DAS II) - 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 WHO-DAS II on the basis of a sample of neurological patients from an Italian hospital. This knowledge discovery problem has been faced 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 (complex domains where consensus is not achieved). The results of applying this technique to the WHO-DAS II results is presented.