<![CDATA[Lyme Disease is a zoonotic infection caused by the bacterium Borrelia burgdorferi, transmitted to humans through bites from ticks of the Ixodes genus. This disease can lead to serious complications affecting the nervous system, joints, skin, and heart if not diagnosed and treated early. However, early diagnosis remains a major challenge due to the non-specific nature of its initial symptoms, which often resemble other common illnesses. In this context, artificial intelligence approaches particularly classification methods in machine learning can assist in achieving faster and more accurate diagnosis and medical decision-making. This study aims to compare the performance of two classification algorithms, Support Vector Machine (SVM) and Decision Tree, in classifying the spread level of Lyme Disease cases using historical data from the United States. The dataset includes temporal and geographic attributes spanning the years 1992 to 2011. Model performance is evaluated using accuracy, precision, recall, and F1-score. The results indicate that the Decision Tree algorithm outperforms SVM in terms of classification accuracy and interpretability. This finding suggests that Decision Tree may be more suitable for integration into clinical decision support systems for Lyme Disease diagnosis.]]>
Copyrights © 2025
