Predicting conversion from clinically isolated syndrome to multiple sclerosis–An imaging-based machine learning approach

Abstract

Magnetic resonance imaging (MRI) scans play a pivotal role in the evaluation of patients presenting with a clinically isolated syndrome (CIS), as these may depict brain lesions suggestive of an inflammatory cause. We hypothesized that it is possible to predict the conversion from CIS to multiple sclerosis (MS) based on the baseline MRI scan by studying image features of these lesions. We analyzed 84 patients diagnosed with CIS from a prospective observational single center cohort. The patients were followed up for at least three years. Conversion to MS was defined according to the 2010 McDonald criteria. Brain lesions were segmented based on 3D FLAIR and 3D T1 images. We generated brain lesion masks by a computer assisted manual segmentation. We also generated a set of automated segmentations using the Lesion Segmentation Toolbox for SPM to assess the influence of different segmentation methods. Shape and brightness features were automatically calculated from the segmented masks and used as input data to train an oblique random forest classifier. Prediction accuracies of the resulting model were validated through a three-fold cross-validation. Conversion from CIS to MS occurred in 66 of 84 patients (79%). The conversion or non-conversion was predicted correctly in 71 patients based on shape features derived from the computer assisted manual segmentation masks (84.5% accuracy). This predictor was more accurate than predicting conversion using dissemination in space at baseline according to the 2010 McDonald criteria (75% accuracy). While shape features strongly contributed to the accuracy of the predictor, including intensity features did not further improve performance. As patients who convert to definite MS benefit from early treatment, an early classification model is highly desirable. Our study shows that shape parameters of lesions can contribute to predicting the future course of CIS patients more accurately.

Considering patient clinical history impacts performance of machine learning models in predicting course of multiple sclerosis

“…For support to patient counseling, prognosis, and therapy, attention has increasingly been turned to artificial intelligence, exploiting the ability of Machine learning (ML) approaches to extract complex relations among existing data without requiring a priori models linking input and output variables [18]. Different problems have been addressed, such as the classification of disease phase at the time of analysis [19][20][21] or evaluation of the probability of transition from Clinically Isolated Syndrome (CIS) to definite multiple sclerosis within 1 to 3 years [22][23][24]. Others have attempted to derive predictions on the course of individual patients or have investigated the variables that best predict disease evolution in time [25][26][27][28].…”

Machine learning in secondary progressive multiple sclerosis: an improved predictive model for short-term disability progression

“…In MS, the application of ML thus far has mainly been for classifying participants into the different disease stages (e.g. clinically isolated syndrome (CIS), relapsing–remitting multiple sclerosis (RRMS), and SPMS), 2–4 or for predicting transition from CIS to clinically definite MS, 5–7 and less for predicting disability progression. One study showed that an ensemble of 10 support vector machines (SVMs) outperformed logistic regression (LR) for predicting disability progression (defined by an Expanded Disability Status Scale (EDSS) increase of 1.0) within 5 years in individuals with EDSS <4.…”

Machine learning for classification and prediction of brain diseases: recent advances and upcoming challenges

“…Predictive studies in other neurological disorders are less frequent. Zhang et al [13] predicted progression from clinically isolated syndrome to multiple sclerosis using characteristics of MRI white matter lesions with a balanced accuracy of 72%. Instead of predicting the future, one can also use ML to go back in time and estimate the date at which the disease started.…”

“…Computer-aided diagnosis has moved from the discrimination between a single disease and controls to differential diagnosis [4*-8]. In addition to diagnosis, models for predicting the subsequent evolution of patients have been developed [9][10][11][12][13]. Most of the initial work focused on neuroimaging as the data source, because it is inherently digital and databases are easy to access.…”