Implementation of an Early Detection System for Neurodegenerative Diseases Through the use of Artificial Intelligence

Neurodegenerative diseases such as Alzheimer's, Parkinson's, and ALS pose a significant challenge to global health, especially due to the aging population, which significantly increases their prevalence. In this context, Artificial Intelligence (AI) has emerged as a promising approach to address the problem at an early stage. Therefore, this article presents an innovative AI-based system for early detection of neurodegenerative diseases. The combination of machine learning algorithms with clinical data, cognitive assessments, and specific test outcomes has enabled the identification of early disease patterns, facilitating timely intervention and better outcomes for patients. The study utilized the OASIS dataset, which includes magnetic resonance scans from 150 individuals, and evaluated three predictive models (Decision Tree, Random Forest, and AdaBoost) for dementia detection. It was found that the Random Forest model achieved the best metrics, with 86.84% accuracy, 80% recall, and 87.22% AUC. In conclusion, this research highlights the potential of AI in early detection of neurodegenerative diseases, providing hope for improving diagnostic approaches and treatments in neurodegenerative conditions.