Browsing by Author "Paulino, Teresa da Conceição Madureira"
Now showing 1 - 1 of 1
Results Per Page
Sort Options
- From design to evaluation: a human-centered approach to AI-powered remote cognitive training for stroke patientsPublication . Paulino, Teresa da Conceição Madureira; Cameirão, Mónica da SilvaStroke is a leading cause of long-term disability worldwide, often resulting in cognitive impairments that significantly impact patients' quality of life and independence. This doctoral thesis presents the design, development of the client-side modules, and evaluation of the NeuroAIreh@b platform, a remote cognitive training system specifically tailored for stroke survivors. The focus of this thesis is dual. First, a focus on a comprehensive human-centered design approach was used to design the modular platform that addresses the specific needs of stroke patients and healthcare professionals. Second, the automation of cognitive training through the development of the software module Reh@Sync allows the training to be performed remotely with reduced need for therapist intervention. The system integrates a set of cognitive training apps that incorporate activities of daily living, enhancing ecological validity and potential skill transfer to real-life situations. One of the key innovations of the Reh@Sync is the implementation of personalization and difficulty adaptation features, which use cognitive profiles and machine learning models to tailor interventions to the individual patient's needs and abilities. Moreover, the engineered system can universally integrate independent apps beyond the cognition dimension, making it a multipurpose system for multidimensional training. The design process involved multiple stakeholders and employed various techniques, including requirements engineering, ideation sessions, prototyping, and iterative usability evaluations. The development phase resulted in a modular system capable of integrating multiple cognitive training apps while maintaining customizability for individual users. The results of a feasibility study with 10 chronic stroke survivors who used the system for 4 weeks showed high levels of adherence, usability, and user satisfaction, indicating the potential for widespread adoption in home based rehabilitation settings. Regarding clinical outcomes after the intervention, we observed significant improvements for a subgroup that showed baseline cognition below the norm. Evaluation of the automation process revealed that the system efficiently personalized and adapted the training to each participant's profile. This research contributes to the fields of cognitive rehabilitation, informatics engineering, and human-computer interaction by providing a detailed account of the design, engineering, and development process of an automated remote cognitive training system for stroke survivors. The findings support the feasibility of self-administered digital cognitive training and highlight areas for future improvements, including expanding the difficulty range to accommodate higher-functioning individuals and incorporating a wider variety of content to enhance engagement.