Computer-Aided Diagnosis of Multiple Sclerosis Using a Support Vector Machine and Optical Coherence Tomography...

Area of Science:

• Ophthalmology
• Neurology
• Biomedical Engineering

Background:

• Multiple sclerosis (MS) is a chronic neurological disease affecting the central nervous system.
• Early diagnosis and monitoring of MS progression are crucial for effective management.
• Optical coherence tomography (OCT) offers high-resolution cross-sectional imaging of retinal layers.

Purpose of the Study:

• To evaluate the feasibility of diagnosing MS using optical coherence tomography (OCT) data.
• To employ a support vector machine (SVM) as an automatic classifier for MS detection.
• To assess the potential of OCT in identifying structural neurodegeneration in the retina of MS patients without optic neuritis.

Main Methods:

• Forty-eight MS patients and 48 healthy controls were recruited.
• Swept-source OCT (SS-OCT) was used to acquire macular and peripapillary measurements.
• A support vector machine (SVM) classifier was trained and validated using leave-one-out cross-validation.

Main Results:

• Key discriminant variables included total ganglion cell layer (GCL++) thickness and macular retinal thickness.
• The SVM classifier achieved high performance: MCC = 0.81, sensitivity = 0.89, specificity = 0.92, accuracy = 0.91, AUC_CLASSIFIER = 0.97.
• The study successfully differentiated MS patients from healthy controls, even in the absence of optic neuritis symptoms.

Conclusions:

• Machine learning techniques applied to OCT data can accurately classify MS patients.
• OCT can detect subtle retinal structural changes indicative of neurodegeneration in MS.
• This approach shows promise for non-invasive MS diagnosis and monitoring.