Predicting disease severity in multiple sclerosis using multimodal data and machine learning

Abstract

Background: Multiple sclerosis patients would benefit from machine learning algorithms that integrates clinical, imaging and multimodal biomarkers to define the risk of disease activity.

Methods: We have analysed a prospective multi-centric cohort of 322 MS patients and 98 healthy controls from four MS centres, collecting disability scales at baseline and 2 years later. Imaging data included brain MRI and optical coherence tomography, and omics included genotyping, cytomics and phosphoproteomic data from peripheral blood mononuclear cells. Predictors of clinical outcomes were searched using Random Forest algorithms. Assessment of the algorithm performance was conducted in an independent prospective cohort of 271 MS patients from a single centre.

Results: We found algorithms for predicting confirmed disability accumulation for the different scales, no evidence of disease activity (NEDA), onset of immunotherapy and the escalation from low- to high-efficacy therapy with intermediate to high-accuracy. This accuracy was achieved for most of the predictors using clinical data alone or in combination with imaging data. Still, in some cases, the addition of omics data slightly increased algorithm performance. Accuracies were comparable in both cohorts.

Conclusion: Combining clinical, imaging and omics data with machine learning helps identify MS patients at risk of disability worsening.

Keywords: Imaging; Machine learning; Multiple sclerosis; Omics; Precision medicine.

Fig. 1

Performance of random forest algorithm for predicting the EDSS at 2-year follow-up. A ROC curve showing 6-month confirmed EDSS accumulation at the end of follow-up using: (1) clinical features (blue); (2) clinical and imaging (MRI and OCT) features (orange); or (3) clinical, imaging and omics features (green); the random classification is shown in red. B Representative tree of the random forest for predicting 6-month confirmed EDSS accumulation. Each box of the decision trees shows the following information: (1) feature of the tree: based on the result, it either follows the true or the false path; (2) entropy, a measure of disorder or uncertainty that is reduced by the algorithm; (3) samples: percentage of samples that fall in that node; (4) value: the proportion of samples that falls in each category (class); and (5) class. C discriminatory features by order of relevance (top to down) for the best predictors of EDSS-CDA based on the AUC using: a clinical, b clinical and imaging, c clinical, imaging and genetics, and d Clinical, imaging, genetics and omics features

Fig. 2

Performance of random forest algorithm for predicting confirmed disability accumulation disability scales at 2-year follow-up. The figure shows the ROC curves on the left and the feature importance ranking (top 10) for the best predictor (Table 2) on the right. A 9HPT; B T25WT; C SDMT; D SL25

Fig. 3

Performance of random forest algorithm for predicting NEDA and change on therapy during follow-up. The figure shows the ROC curves on the left and the feature importance ranking (top 10) for the best predictor (Table 2) on the right. A staying on NEDA after 2 years follow-up; B starting DMDs during follow-up; C change from the first line to high-efficacy DMDs during follow-up