Accurate classification of secondary progression in multiple sclerosis
Authors:
- Ryan RamanujamRRRyan Ramanujam
- Feng ZhuFZFeng Zhu
- Katharina FinkKFKatharina Fink
- Virginija Danylaitė KarrenbauerVirginija Danylaitė Karrenbauer
- Johannes LorscheiderJLJohannes Lorscheider
- Pascal BenkertPBPascal Benkert
- Elaine KingwellEKElaine Kingwell
- Helen TremlettHTHelen Tremlett
- Jan HillertJHJan Hillert
- Ali ManouchehriniaAMAli Manouchehrinia
Preprint
Abstract
Transition from a relapsing-remitting to the secondary progressive phenotype is an important milestone in the clinical evolution of multiple sclerosis. In the absence of reliable imaging or biological markers of phenotype transition, assignment of current phenotype status relies on retrospective evaluation of the medical history of an individual. Here, we sought to determine if demographic and clinical information from multiple sclerosis patients can be used to accurately assign current disease phenotypes: either relapsing-remitting or secondary progressive status. Data from the most recent clinical visit of 14,387 multiple sclerosis patients were extracted from the Swedish Multiple Sclerosis Registry. Decision trees based on sex, symptom onset age, Expanded Disability Scale Status score, and age & disease duration at the most recent clinic visit, were examined to build a classifier to determine disease phenotype. Validation was conducted using an independent cohort of multiple sclerosis patients from British Columbia, Canada, and a previously published classifier to assign phenotype was also tested. Clinical records of 100 randomly selected patients were used to manually categorize phenotype by three independent neurologists. A decision tree (the classifier) containing only most recently available disability score and age obtained 89.3% (95% confidence intervals (CI): 88.8% to 89.8%) classification accuracy, defined as concordance with the latest reported status in the registry. Replication in an independent cohort from British Columbia resulted in 82.0% (95%CI: 81.0% to 83.1%) accuracy. A previously published classification algorithm with slight modifications achieved 77.8% (95%CI: 77.1% to 78.4%) accuracy when assigning disease phenotype. With complete patient history data, three neurologists obtained 84.7% accuracy on average compared with 85 for the classifier using the same data. The model is easily interpretable and could allow research studies and randomized clinical trials to estimate the probability of patients having already reached the secondary progressive stage when they have not yet been retrospectively assigned this status, and to standardize definitions of disease phenotype across different cohorts. Clinically, this model could assist neurologists by providing additional information about the probability of having secondary progressive disease. This could also benefit patients who may be introduced to new therapies targeting progressive multiple sclerosis.Keywords
All Related Versions
- Published version: Multiple Sclerosis Journal, 27 (8), 1240.
This publication has 11 references indexed in Scilit:
- Meta-analysis of the Age-Dependent Efficacy of Multiple Sclerosis TreatmentsFrontiers in Neurology, 2017
- Defining secondary progressive multiple sclerosisBrain, 2016
- Defining the clinical course of multiple sclerosisNeurology, 2014
- Onset of secondary progressive phase and long-term evolution of multiple sclerosisJournal of Neurology, Neurosurgery & Psychiatry, 2013
- From the Gothenburg cohort to the Swedish multiple sclerosis registryActa Neurologica Scandinavica, 2012
- New perspectives in the natural history of multiple sclerosisNeurology, 2010
- Rituximab in patients with primary progressive multiple sclerosis: Results of a randomized double‐blind placebo‐controlled multicenter trialAnnals of Neurology, 2009
- Natural history of secondary-progressive multiple sclerosisMultiple Sclerosis Journal, 2008
- Defining the clinical course of multiple sclerosisNeurology, 1996
- Rating neurologic impairment in multiple sclerosisNeurology, 1983