Leveraging Logistic Regression and K-Nearest Neighbors for Accurate Detection of Multiple Sclerosis from MRI and Clinical Features

Multiple sclerosis (MS), a common demyelinating disease of the central nervous system, produces a spectrum of symptoms including visual loss, muscle weakness, and coordination difficulties. Good control and treatment depend on correct and quick diagnosis. This paper evaluates Logistic Regression and K-Nearest Neighbors (KNN) classifiers for MS identification using a dataset comprising several clinical and MRI features. The dataset offers a complete basis for classification including age, gender, early symptoms, and MRI findings. For both groups, logistic regression exceeded KNN in terms of precision, recall, and F1-score. Logistic Regression specifically attained a precision of 0.75 and recall of 0.88 for Class 1 and a precision of 0.89 and recall of 0.77 for Class 2, therefore producing greater F1-scores and total accuracy of 0.82. With an overall accuracy of 0.78, KNN displayed lesser performance with respect to precision, recall, and F1-scores for Class 1 and Class 2 being 0.71, 0.83, 0.77, and 0.85, respectively, with an overall accuracy of 0.74, These results emphasise Logistic Regression as a more efficient model for MS identification, thereby offering a strong instrument for early diagnosis and maybe enhancing patient outcomes.