![[feed]](/style/images/feed-icon-14x14.png){kind=icon}
|
PDF (Original Article)
- Requires a PDF viewer such as GSview, Xpdf or Adobe Acrobat Reader
1MB | |
![[img]](http://edoc.mdc-berlin.de/style/images/fileicons/other.png) |
Other (Supporting Information)
61kB |
| Item Type: | Article |
|---|---|
| Title: | Predicting disease severity in multiple sclerosis using multimodal data and machine learning |
| Creators Name: | Andorra, M. and Freire, A. and Zubizarreta, I. and de Rosbo, N.K. and Bos, S.D. and Rinas, M. and Høgestøl, E.A. and de Rodez Benavent, S.A. and Berge, T. and Brune-Ingebretse, S. and Ivaldi, F. and Cellerino, M. and Pardini, M. and Vila, G. and Pulido-Valdeolivas, I. and Martinez-Lapiscina, E.H. and Llufriu, S. and Saiz, A. and Blanco, Y. and Martinez-Heras, E. and Solana, E. and Bäcker-Koduah, P. and Behrens, J. and Kuchling, J. and Asseyer, S. and Scheel, M. and Chien, C. and Zimmermann, H. and Motamedi, S. and Kauer-Bonin, J. and Brandt, A. and Saez-Rodriguez, J. and Alexopoulos, L.G. and Paul, F. and Harbo, H.F. and Shams, H. and Oksenberg, J. and Uccelli, A. and Baeza-Yates, R. and Villoslada, P. |
| 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: | Multiple Sclerosis, Omics, Imaging, Machine Learning, Precision Medicine |
| Source: | Journal of Neurology |
| ISSN: | 0340-5354 |
| Publisher: | Springer |
| Volume: | 271 |
| Number: | 3 |
| Page Range: | 1133-1149 |
| Date: | March 2024 |
| Official Publication: | https://doi.org/10.1007/s00415-023-12132-z |
| PubMed: | View item in PubMed |
Repository Staff Only: item control page
Download Statistics
Download Statistics
