Defining a recommendation system to configure personalized assistance for individuals with cognitive impairments due to a traumatic brain injury

Abstract

Smart assistive technologies are increasingly being used to support independent living. Occupational therapists perceive such technologies as useful to helping their clients become more independent in their everyday activities, particularly individuals having sustained a traumatic brain injury. However, adapting and configuring these technologies to meet each person’s individual needs remain challenging. In this study, occupational therapists and computer scientists collaborate to develop a recommendation system designed to assist in configuring a smart assistive technology that helps people having sustained a traumatic brain injury cook safely. The relevance of the recommendations made by this case-based recommendation system was first evaluated by comparing the recommended assistant options with the selections of an expert occupational therapist. Then, we questioned the final users, i.e. occupational therapists, about the usefulness of such a system. This first prototype demonstrated promising results, with about 80% correct recommendations for selection (with an average percentage ranging from 77.0% to 86.2% depending on the threshold set for recommended functionalities, using a database of 16 cases). Additionally, the system was found to be robust against an unbalanced database and has been estimated as useful and relevant by end-users, who remain the final decision-makers. The latter also expressed concerns and suggested improvements, which were incorporated early in the development process to enhance acceptance and facilitate the tool’s integration into clinical practice. As a result, the tools and methods used by the multidisciplinary team led to the successful development of a generic human-centered recommendation system that can be used to personalize smart assistive technologies to each unique person’s needs.