This study presents an AI-based system for the early detection of Parkinson’s disease using deep learning models, InceptionV3 and Xception, with an Attention Mechanism. The system analyzes hand-drawn spiral images, which act as biomarkers for Parkinson’s symptoms like tremors and micrographia. The proposed model extracts critical features from these images using pre-trained convolutional neural networks (CNNs) enhanced with attention layers, ensuring effective classification. The dataset consists of spiral drawings from both healthy individuals and Parkinson’s patients, enabling the model to learn distinguishing features. The InceptionV3 model achieved 100% accuracy, while Xception attained 88% accuracy in Parkinson’s detection. To evaluate performance, accuracy vs. epoch and loss vs. epoch graphs were plotted to track learning trends, a confusion matrix was generated to analyze misclassifications, and a classification report provided insights into precision, recall, and F1-score. A comparative bar chart further highlighted the performance difference between the InceptionV3 and Xception models. This AI-driven approach offers a non-invasive, cost-effective, and automated diagnostic tool, improving early diagnosis and assisting healthcare professionals in timely intervention.