[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-123904-en":3,"doc-seo-123904-105":30,"detail-sidebar-cat-0-en-105":91},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":4,"is_deleted":4,"is_public":20,"is_downloadable":20,"audit_status":20,"page_count":21,"language":22,"language_code":23,"site_id":24,"html_lang":23,"table_of_contents":25,"faqs":26,"seo_title":27,"seo_description":14,"update_tm":28,"read_time":29},123904,4398048950312,"Violet","https://ap-avatar.wpscdn.com/avatar/400002538284de19e3c?_k=1778320343897328908",7,"Healthcare","Predicting disease severity in multiple sclerosis using multimodal data and machine learning","Machine learning approaches are proposed to integrate clinical variables, brain imaging, and multimodal biomarkers to estimate the risk of disease activity in multiple sclerosis. A prospective multi-center cohort of 322 MS patients and 98 healthy controls was analyzed using baseline and 2-year disability assessments, with predictors searched via Random Forest models. Performance was validated in an independent prospective cohort of 271 MS patients. Algorithms predicted confirmed disability accumulation across scales, NEDA, immunotherapy onset, and therapy escalation, achieving high accuracy largely with clinical and imaging data, with omics adding modest improvements in some cases. Combining multimodal inputs identifies patients at risk of disability worsening.","Journal of Neurology  \n[https://doi.org/10.1007/s00415-023-12132-z](https://doi.org/10.1007/s00415-023-12132-z)  \nPredicting disease severity in multiple sclerosis using multimodal data and machine learning  \nMagi Andorra1 · Ana Freire2,18 · Irati Zubizarreta1 · Nicole Kerlero de Rosbo3,4 · Steffan D. Bos5,6 · Melanie Rinas7 ·  \nEinar A. Høgestøl5,6 · Sigrid A. de Rodez Benavent5,6 · Tone Berge6,8 · Synne Brune‑Ingebretse5,6 · Federico Ivaldi9 · Maria Cellerino3 · Matteo Pardini3,4 · Gemma Vila1 · Irene Pulido‑Valdeolivas1 · Elena H. Martinez‑Lapiscina1 · Sara Llufriu1 · Albert Saiz1 · Yolanda Blanco1 · Eloy Martinez‑Heras1 · Elisabeth Solana1 · Priscilla Bäcker‑Koduah10 ·  \nJanina Behrens10 · Joseph Kuchling10 · Susanna Asseyer10,11 · Michael Scheel10 · Claudia Chien10,11 · Hanna Zimmermann10,11 · Seyedamirhosein Motamedi10 · Josef Kauer‑Bonin10 · Alex Brandt10 ·  \nJulio Saez‑Rodriguez7 · Leonidas G. Alexopoulos12,13 · Friedemann Paul10,11 · Hanne F. Harbo5,6 · Hengameh Shams14 · Jorge Oksenberg14 · Antonio Uccelli3,4 · Ricardo Baeza‑Yates15 · Pablo Villoslada16,17  \nReceived: 24 June 2023 / Revised: 28 October 2023 / Accepted: 22 November 2023 © The Author(s) 2023  \nAbstract  \nBackground Multiple sclerosis patients would benefit from machine learning algorithms that integrates clinical, imaging and multimodal biomarkers to define the risk of disease activity.  \nMethods 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.  \nResults 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 highaccuracy. 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.  \nConclusion Combining clinical, imaging and omics data with machine learning helps identify MS patients at risk of disability worsening.  \nKeywords Multiple sclerosis · Omics · Imaging · Machine learning · Precision medicine  \nIntroduction  \nDeveloping personalised health care for people with multiple sclerosis (MS) is hindered by our limited understanding of the biological processes underlying the disease, by the lack of validated prognostic or predictive biomarkers and by the clinical heterogeneity between patients [1–4] . At present, clinical decisions are taken based on outcomes identified in  \nMagi Andorra and Ana Freire have contributed equally as first authors.  \nExtended author information available on the last page of the article  \nnatural history cohort studies and randomised clinical trials, such as the disease subtype (relapsing [vs. progressive](vs. progressive)[ ](vs. progressive)course); age (above ~ 45 years old); the time to reach disability milestones like the expanded disability status scale (EDSS) 4.0 or 6.0; the Evidence of Disease Activity (EDA)  \n[5]; lesion activity (presence of gadolinium-enhancing lesions) and lesion load (presence of new or enlarging T2 lesions and T2 lesion volume) [6] . Indeed, retinal atrophy monitored by optical coherence tomography (OCT) is able to predict the risk of disability worsening [7, 8] . Moreover, the use of disease-modifying drugs (DMDs) and, specifically, high-efficacy therapies, is also associated with amore severe disease course, not the least becaus","cbCaioEyAUUP6I5m","https://ap.wps.com/l/cbCaioEyAUUP6I5m","pdf",1427003,1,17,"English","en",105,"# Abstract\n# Introduction\n## Biomarkers and unmet need for personalized prognosis\n## Aim: stratify patients using clinical, imaging, and omics\n# Materials and methods\n## Ethical approval and cohorts","[{\"question\":\"What data types were used to predict multiple sclerosis disease severity?\",\"answer\":\"The study combined clinical disability assessments, brain MRI and optical coherence tomography, and omics data including genotyping, cytomics, and phosphoproteomics from peripheral blood cells.\"},{\"question\":\"How were predictive models developed and validated?\",\"answer\":\"Random Forest algorithms were used to search predictors in a prospective multi-center cohort, and algorithm performance was evaluated in an independent prospective cohort from a single center.\"},{\"question\":\"Which clinical outcomes could the algorithms predict?\",\"answer\":\"The models predicted confirmed disability accumulation across different scales, absence of disease activity (NEDA), onset of immunotherapy, and escalation from low- to high-efficacy therapy.\"}]","Predicting disease severity in multiple sclerosis using multimodal data and machine learning | PDF",1785819170,43,{"code":4,"msg":31,"data":32},"ok",{"site_id":24,"language":23,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":86,"head_meta":88,"extra_data":90,"updated_unix":28},"predicting-disease-severity-in-multiple-sclerosis-using-multimodal-data-and-machine-learning","",{"@graph":36,"@context":85},[37,54,68],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,51],{"item":41,"name":42,"@type":43,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":47},"https://docshare.wps.com/document/","Document",2,{"item":49,"name":12,"@type":43,"position":50},"https://docshare.wps.com/document/healthcare/",3,{"item":52,"name":13,"@type":43,"position":53},"https://docshare.wps.com/document/predicting-disease-severity-in-multiple-sclerosis-using-multimodal-data-and-machine-learning/123904/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":23,"description":14,"dateModified":62,"datePublished":62,"encodingFormat":61,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-04",true,{"@type":65,"interactionType":66,"userInteractionCount":4},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"What data types were used to predict multiple sclerosis disease severity?","Question",{"text":75,"@type":76},"The study combined clinical disability assessments, brain MRI and optical coherence tomography, and omics data including genotyping, cytomics, and phosphoproteomics from peripheral blood cells.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How were predictive models developed and validated?",{"text":80,"@type":76},"Random Forest algorithms were used to search predictors in a prospective multi-center cohort, and algorithm performance was evaluated in an independent prospective cohort from a single center.",{"name":82,"@type":73,"acceptedAnswer":83},"Which clinical outcomes could the algorithms predict?",{"text":84,"@type":76},"The models predicted confirmed disability accumulation across different scales, absence of disease activity (NEDA), onset of immunotherapy, and escalation from low- to high-efficacy therapy.","https://schema.org",{"og:url":52,"og:type":87,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":89,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":92},[93,97,101,105,110,115,118,123,128,131,135],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":46,"category_name":107,"show_sort_weight":108,"slug":109},5,"Comic",60,"comic",{"id":111,"doc_module":4,"doc_module_name":46,"category_name":112,"show_sort_weight":113,"slug":114},6,"Technology",50,"technology",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":116,"slug":117},40,"healthcare",{"id":119,"doc_module":4,"doc_module_name":46,"category_name":120,"show_sort_weight":121,"slug":122},8,"Research & Report",30,"research-report",{"id":124,"doc_module":4,"doc_module_name":46,"category_name":125,"show_sort_weight":126,"slug":127},9,"Religion & Spirituality",20,"religion-spirituality",{"id":126,"doc_module":4,"doc_module_name":46,"category_name":129,"show_sort_weight":126,"slug":130},"World Cup","world-cup",{"id":132,"doc_module":4,"doc_module_name":46,"category_name":133,"show_sort_weight":132,"slug":134},10,"Lifestyle","lifestyle",{"id":136,"doc_module":4,"doc_module_name":46,"category_name":137,"show_sort_weight":106,"slug":138},19,"General","general"]