<![CDATA[Multiple System Atrophy (MSA) is a progressive neurodegenerative disorder that presents significant challenges in early and accurate diagnosis. Advances in machine learning algorithms offer promising solutions for improving diagnostic support in medical fields, particularly in complex disorders such as MSA. This study compares the performance of two widely used classification algorithms Decision Tree (DT) and Support Vector Machine (SVM) in detecting MSA using clinical datasets consisting of 300 patient records. Supervised learning techniques with cross-validation were employed, and key performance metrics including accuracy, precision, recall, and F1-score were evaluated. SVM achieved an accuracy of 88.1% and F1-score of 87.1%, outperforming Decision Tree, which recorded 85.4% accuracy and an F1-score of 83.9%. The novelty of this study lies in its direct comparative benchmark using standardized clinical features for MSA detection, offering practical insights into model selection for neurodegenerative disease screening. The SVM model’s superior performance indicates its suitability for reliable early detection of MSA from clinical data. This research contributes to the development of machine learning-based decision support tools in neurology.]]>
Copyrights © 2025
