Advantages of combining AI and statistic for knowledge discovery on functional disability: multivariate analysis of assessment scales using clustering based on rules

Abstract

In Europe, and other developed areas, senior citizens are a fast growing part of population. This increases proportion of disabled persons and proportion of persons with 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 the clinical test WHO Disability Assessment Schedule, (WHO-DASII) that includes physical, mental, and social wellbeing, as a generic measure of functioning. From the medical point of view, the purpose of this work is to extract knowledge about the different kinds of disabilities from the responses to the WHO-DAS II of a sample of patients from an Italian hospital. This Knowledge Discovery problem has been faced by using clustering based on rules, an hybrid AI and Statistics technique introduced by Gibert (1994), which combines some Inductive Learning (from AI) with clustering (from Statistics) to extract knowledge from certain complex domains in form of typical profiles. In this paper, the results of applying this technique to the WHODAS II results is presented together with a comparison of other more classical analysis approaches. Four profiles of increasing degree of disability are identified together with the main characteristics associated to them.