Parkinson's disease (PD) is a progressive neurodegenerative disorder characterized by motor and cognitive impairments. Early diagnosis is crucial for improving the quality of life and slowing disease progression. In recent years, the integration of advanced imaging techniques and neuropsychological data has opened new avenues for automated diagnostic methods. This study presents an innovative approach that combines magnetic resonance imaging (MRI) with neuropsychological test data to develop a machine learning model capable of accurately identifying PD in its early stages. The dataset consists of high-resolution MRI scans alongside detailed neuropsychological assessments, enabling a comprehensive analysis of both structural brain alterations and cognitive deficits associated with the disease. Using state-of-the-art algorithms for feature extraction and classification, we achieved high diagnostic accuracy compared to traditional methods. Our results demonstrate the potential of integrating neuroimaging and cognitive profiling for automated, non-invasive PD diagnosis, paving the way for more efficient and accessible diagnostic practices in clinical settings.