Exploration of machine learning techniques in predicting multiple sclerosis disease course
Healy, Brian C.
Guttmann, Charles R. G.
Weiner, Howard L.
Brodley, Carla E.
- Publisher: Public Library of Science
(issn: 1932-6203, eissn: 1932-6203)
Magnetic Resonance Imaging | Research Article | Diagnostic Medicine | Lesions | Mathematics | Signs and Symptoms | Pathology and Laboratory Medicine | Diagnostic Radiology | Mathematical and Statistical Techniques | Radiology and Imaging | Artificial Intelligence | Clinical Medicine | Neurodegenerative Diseases | Physical Sciences | People and Places | Demography | Immunology | Neurology | Autoimmune Diseases | Demyelinating Disorders | Statistics (Mathematics) | Support Vector Machines | Biology and Life Sciences | Computer and Information Sciences | Multiple Sclerosis | Neuroscience | Forecasting | Research and Analysis Methods | Medicine | Machine Learning | Neuroimaging | Q | R | Imaging Techniques | Clinical Immunology | Science | Medicine and Health Sciences | Statistical Methods
OBJECTIVE:To explore the value of machine learning methods for predicting multiple sclerosis disease course. METHODS:1693 CLIMB study patients were classified as increased EDSS≥1.5 (worsening) or not (non-worsening) at up to five years after baseline visit. Support vector machines (SVM) were used to build the classifier, and compared to logistic regression (LR) using demographic, clinical and MRI data obtained at years one and two to predict EDSS at five years follow-up. RESULTS:Baseline data alone provided little predictive value. Clinical observation for one year improved overall SVM sensitivity to 62% and specificity to 65% in predicting worsening cases. The addition of one year MRI data improved sensitivity to 71% and specificity to 68%. Use of non-uniform misclassification costs in the SVM model, weighting towards increased sensitivity, improved predictions (up to 86%). Sensitivity, specificity, and overall accuracy improved minimally with additional follow-up data. Predictions improved within specific groups defined by baseline EDSS. LR performed more poorly than SVM in most cases. Race, family history of MS, and brain parenchymal fraction, ranked highly as predictors of the non-worsening group. Brain T2 lesion volume ranked highly as predictive of the worsening group. INTERPRETATION:SVM incorporating short-term clinical and brain MRI data, class imbalance corrective measures, and classification costs may be a promising means to predict MS disease course, and for selection of patients suitable for more aggressive treatment regimens.