Clustering Using Principal Component Analysis: Application of Elderly People Autonomy-disability

The aim of this paper is to find features-patterns relating to the autonomy-disability level of elderly people living in nursing homes. These levels correspond to profiles based on performing activities of daily living, like washing, dressing and transferring... To achieve this aim, an unsupervised approach is used. In the article, we propose a new clustering approach based on the principal component analysis (PCA) to better approximate clusters. We want to automatically find categories or groups of residents based on their autonomy-disability. All residents in a group have similar patterns. The main function of PCA is to explore the links between variables and the similarities between examples (individuals). The proposed algorithm uses the PCA technique to direct the determination of the clusters with self-organizing partitions by using the Euclidian distance. The study has been done in close collaboration with the French mutual benefit organization called “Mutualité Française de la Loire”. The quantitative data arises from databases of four different nursing homes located in Saint-Etienne – France. The study concerns 2,271 observations of dependence evaluations corresponding to 628 residents.