Predicting disease severity in multiple sclerosis using multimodal data and machine learning
-
Published:2023-12-22
Issue:
Volume:
Page:
-
ISSN:0340-5354
-
Container-title:Journal of Neurology
-
language:en
-
Short-container-title:J Neurol
Author:
Andorra Magi, Freire Ana, Zubizarreta Irati, de Rosbo Nicole Kerlero, Bos Steffan D., Rinas Melanie, Høgestøl Einar A., de Rodez Benavent Sigrid A., Berge Tone, Brune-Ingebretse Synne, Ivaldi Federico, Cellerino Maria, Pardini Matteo, Vila Gemma, Pulido-Valdeolivas Irene, Martinez-Lapiscina Elena H., Llufriu Sara, Saiz Albert, Blanco Yolanda, Martinez-Heras Eloy, Solana Elisabeth, Bäcker-Koduah Priscilla, Behrens Janina, Kuchling Joseph, Asseyer Susanna, Scheel Michael, Chien Claudia, Zimmermann Hanna, Motamedi Seyedamirhosein, Kauer-Bonin Josef, Brandt Alex, Saez-Rodriguez Julio, Alexopoulos Leonidas G., Paul Friedemann, Harbo Hanne F., Shams Hengameh, Oksenberg Jorge, Uccelli Antonio, Baeza-Yates Ricardo, Villoslada PabloORCID
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 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.
Funder
Directorate-General for Research and Innovation Instituto de Salud Carlos III Universitat Pompeu Fabra
Publisher
Springer Science and Business Media LLC
Subject
Neurology (clinical),Neurology
Reference64 articles.
1. Kotelnikova E, Kiani NA, Abad E et al (2017) Dynamics and heterogeneity of brain damage in multiple sclerosis. PLoS Comput Biol 13:e1005757 2. Pulido-Valdeolivas I, Zubizarreta I, Martinez-Lapiscina E, Villoslada P (2017) Precision medicine for multiple sclerosis: an update of the available biomarkers and their use in therapeutic decision making. Expert Rev Precis Med Drug Dev 2:1–17 3. Villoslada P (2021) Personalized medicine for multiple sclerosis: How to integrate neurofilament light chain levels in the decision? Mult Scler 2021:13524585211049552 4. Pitt D, Lo CH, Gauthier SA et al (2022) Toward precision phenotyping of multiple sclerosis. Neurology(R) Neuroimmunol Neuroinflammat 2022:9 5. Giovannoni G, Bermel R, Phillips T, Rudick R (2018) A brief history of NEDA. Multiple Sclerosis Related Disord 20:228–230
Cited by
2 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献
|
|