DePicT CLASS is a case-based learning assistant system to detect and predict disease using image classi cation and text information. The main objective of DePicT Dementia CLASS is to develop the DePicT CLASS concept by enrichment of cases with dementia learning materials (e.g. reference images and textbooks). Each case has a word association pro le (DePicT Pro le Matrix) of the main keywords which are de ned based on the International Classi cation of Functioning, Disability, and Health framework of WHO (ICF codes) and medical expressions extracted from the references of dementia and its related diseases. Therefore, DePicT Dementia CLASS uses DePicT Pro le Matrix of WHO-ICF codes and enables caregivers and patients' relatives to nd their learning materials and references which address the problems that they are looking for. This recommender system proposes a combination of references with the highest value of keyword association strength and collaborative recommendation based on ranked references by the user's feedback.