The project aims to develop a deep learning model for the prediction of Parkinson’s disease through the use of signal processing, medical images and oculometry, leveraging the interplay between visual tracking metrics and neurological markings. By identifying complex patterns in data, an increase in accuracy of Parkinson’s disease is expected, as well as new opportunities for the early diagnosis which is of vital importance. This project will, by means of integrating state-of-the-art machine learning techniques with signal processing computational approaches, contribute to the advancement of signal and medical image processing algorithms. The outcome of this research is anticipated to offer a novel, non-invasive early diagnostic approach, so that medical professionals can detect and manage Parkinson’s disease more effectively, ultimately improving patients’ quality of life.