The use of Computational Intelligence in healthcare, explored in this thesis, has greatly advanced the digitization of medical services. Computational Intelligence enables computers to perform tasks that typically require human intelligence. In healthcare, it has led to significant innovations, such as improved drug development and better screening of patients for clinical trials. One of its main applications is in disease diagnostics, where it has shown high efficiency and accuracy, particularly in fields like medical imaging, neurology, cardiology, diabetes, movement disorders, and mental health. However, despite its benefits, there are still ethical challenges and uncertainties about how to validate its use effectively. Computational Intelligence has the potential to revolutionize patient care, especially in diagnosing diseases. It leverages the vast amounts of healthcare data available and the advancements in computer technology to provide quick and accurate results. The work focuses on exploring the literature surrounding Computational Intelligence in healthcare diagnostics and examining how patients perceive its use. It divides patients into two groups: those who don't use wearable devices and those who do. Through qualitative research methods like snowball sampling and thematic analysis, the study aims to identify common applications of Computational Intelligence in diagnostic healthcare, understand patients' attitudes towards it, investigate what motivates them to adopt diagnostic wearables, and uncover any concerns they may have.
Keywords
Computational Intelligence, artificial neural networks, atrial fibrillation, Big Data, data protection, deep learning, diabetes, machine learning, movement disorder, neurology, Oura ring.
