This paper presents a state-of-the-art review of the applications of deep learning in the study of principal neurodegenerative diseases, including Parkinson’s disease, Alzheimer’s disease, and Multiple Sclerosis. These diseases pose significant challenges in terms of early diagnosis and treatment due to their complex nature and progression. The aim of this review is to explore and highlight the main applications of deep learning techniques, including Convolutional Neural Networks (CNNs) in the classification and prediction of these neurodegenerative conditions. The review identifies and discusses the multimodal data employed in the experimentation, including medical imaging (MRI, PET), electrophysiological data (EEG), genetic data, and clinical assessments. We also address the challenges of integrating these diverse data modalities to enhance prediction accuracy and disease progression modeling. This review highlights the potential of deep learning models and their application in the area of ​​neurodegenerative diseases, as well as identifying key areas for future research.