Abstract
ObjectiveTo explore the value of machine learning methods for predicting multiple sclerosis disease course.Methods1693 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.ResultsBaseline 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.InterpretationSVM 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.
Highlights
A critical component in the management of patients with multiple sclerosis (MS) is correctly predicting which patients will experience worsening disease over the short term
Using a sample of 1352 patients, 525 of whom were progressive at 5 years, we attained an overall accuracy rate for logistic regression of 62% and for linear Support Vector Machine (SVM) of 64% (SVM with a non-linear kernel fared no better (Table 3))
The issue with these baseline methods is that they are heavily weighted toward always saying a patient is non-progressive
Summary
A critical component in the management of patients with multiple sclerosis (MS) is correctly predicting which patients will experience worsening disease over the short term. This is relevant given the expanding array of disease-modifying medications, and the importance of identifying the patients who may benefit from more potent or aggressive treatment or closer monitoring. In this paper we explore both logistic regression and machine-learning techniques in predicting disease course and their relative performance using baseline data or longitudinal data. Logistic regression is a statistical method for finding the best fitting linear relationship between the log odds of a binary variable (“worsening” versus “non-worsening” in our case) and a group of independent explanatory variables (patients’ longitudinal records in our case). Support Vector Machine (SVM) is a widely used machine-learning classification method where the algorithm maximizes the margin that separates the two classes of data
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
