Enhancing Glaucoma Diagnosis: A Comparative Analysis of SVM and Logistic Regression for Clinical Decision Support

The early diagnosis of diseases such as glaucoma is crucial for effective treatment and prevention of severe outcomes. Machine learning models, particularly Logistic Regression (LR) and Support Vector Machines (SVM), are widely used for classification tasks in clinical settings. This study compares the performance of Logistic Regression (LR) and Support Vector Machines (SVM) in classifying glaucoma cases, using clinical features such as the Cup-to-Disc Ratio (CDR), Optic Disc Diameter (ODD), and demographic risk factors. While SVM outperforms LR in accuracy, F1-score, and AUC-ROC, LR is more interpretable, making it suitable for transparent clinical use. This comparison highlights the trade-off between model interpretability and performance and provides insights into their clinical applicability.