Early detection of Parkinson’s disease using deep learning approaches.

Abstract

Parkinson’s disease (PD), a progressive neurodegenerative disorder, often presents subtle early symptoms such as speech impairments that are challenging to detect with traditional methods. This Master’s thesis proposes deep learning models to assist health care professionals in the early diagnosis of Parkinson’s disease through speech analysis. Our approach combines voice records processing and artificial intelligence, utilizing ad vanced deep learning models. Various techniques were implemented to enhance model robustness and generalization. Multiple models were evaluated, yielding promising re sults. This system aims to improve the accuracy and speed of PD diagnosis, offering a valuable tool for early intervention and better patient care.