Predicting disease severity in Multiple Sclerosis using multimodal data and machine learning

Abstract

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 analyzed a prospective multi-centric cohort of 322 MS patients and 98 healthy controls from four MS centers, 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. Validation was conducted in an independent prospective cohort of 271 MS patients from a single center. 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 by 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 the discovery and validation cohorts. Conclusion Combining clinical, imaging, and omics data with machine learning helps to identify MS patients at risk of disability worsening.