Predicting disease severity in multiple sclerosis using multimodal data and machine learning
Magí Andorrà, Ana Freire, Irati Zubizarreta, Nicole Kerlero de Rosbo, Steffan D. Bos, Melanie Rinas, Einar August Høgestøl, Sigrid A. de Rodez Benavent, Tone Berge, Synne Brune-Ingebretse, Federico Ivaldi, Maria Cellerino, Matteo Pardini, Gemma Vila, Irene Pulido-Valdeolivas, Elena H. Martínez‐Lapiscina, Sara Llufriú, Albert Saiz, Yolanda Blanco, Eloy Martínez‐Heras, Elisabeth Solana, Priscilla Bäcker‐Koduah, Janina Behrens, Joseph Kuchling, Susanna Asseyer, Michael Scheel, Claudia Chien, Hanna Zimmermann, Seyedamirhosein Motamedi, Josef Kauer-Bonin, Alex Brandt, Julio Sáez-Rodríguez, Leonidas G. Alexopoulos, Friedemann Paul, Hanne F. Harbo, Hengameh Shams, Jorge R. Oksenberg, Antonio Uccelli, Ricardo Baeza‐Yates, Pablo Villoslada
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.