A framework for AI-driven neurorehabilitation training: the profiling challenge

• Autor(a) principal: Rodrigues, Pedro Alexandre Gomes
• Data de Publicação: 2022
• Tipo de documento: Dissertação
• Idioma: eng
• Título da fonte: Repositórios Científicos de Acesso Aberto de Portugal (RCAAP)
• Texto Completo: http://hdl.handle.net/10400.13/4890
• topic: Driven neurorehabilitation training; Neurorehabilitation training; Cognitive decline; Cognitive rehabilitation; Declínio cognitivo; Reabilitação cognitiva; Informatics Engineering; .; Faculdade de Ciências Exatas e da Engenharia

Cognitive decline is a common sign that a person is ageing. However, abnormal cases can lead to dementia, affecting daily living activities and independent functioning. It is a leading cause of disability and death. Its prevention is a global health priority. One way to address cognitive decline is to undergo cognitive rehabilitation. Cognitive rehabilitation aims to restore or mitigate the symptoms of a cognitive disability, increasing the quality of life for the patient. However, cognitive rehabilitation is stuck to clinical environments and logistics, leading to a suboptimal set of expansive tools that is hard to accommodate every patient’s needs. The BRaNT project aims to create a tool that mitigates this problem. The NeuroAIreh@b is a rehabilitation tool developed within a framework that combines neuropsychological assessments, neurorehabilitation procedures, artificial intelligence and game design, composing a tool that is easy to set up in a clinical environment and accessible to adapt to every patient’s needs. Among all the challenges within NeuroAlreh@b, one focuses on representing a cognitive profile through the aggregation of multiple neuropsychological assessments. To test this possibility, we will need data from patients currently unavailable. In the first part of this master’s project, study the possibility of aggregating neuropsychological assessments for the case of Alzheimer’s disease using the Alzheimer’s Disease Neuroimaging Initiative database. This database contains a vast collection of images and neuropsychological assessments that will serve as a baseline for the NeuroAlreh@b when the time comes. In the second part of this project, we set up a computational system to run all the artificial intelligence models and simulations required for the BRaNT project. The system allocates a database and a webserver to serve all the required pages for the project.