{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,5]],"date-time":"2026-09-05T00:14:38Z","timestamp":1788567278865,"version":"build-2803163510"},"reference-count":36,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,1,15]],"date-time":"2026-01-15T00:00:00Z","timestamp":1768435200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Neurol."],"abstract":"<jats:sec>\n                    <jats:title>Introduction<\/jats:title>\n                    <jats:p>Accurate prediction of disease progression in multiple sclerosis (MS) remains a critical challenge in clinical management. This study investigates the utility of supervised machine learning (ML) models in predicting clinical disability, as measured by the Expanded Disability Status Scale (EDSS), and radiological activity based on MRI lesion changes in patients with relapsing-remitting MS (RRMS).<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>Using peripheral cytokine profiles (IL-12, TNF-\u03b1, IFN-\u03b3, IL-4, IL-10) along with patient metadata (e.g., sex, family history, relapse status), 43 ML classifiers were trained and evaluated for their ability to discriminate between mild and moderate disability (EDSS &amp;lt;1 vs &amp;gt;1, and &amp;lt;2.5 vs &amp;gt;2.5), and to predict new MRI lesions in 15 MS patients.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>Ensemble models consistently outperformed simpler algorithms. For EDSS prediction, Random Forest achieved 90.1% sensitivity and 89.7% specificity, while Simple Logistic Regression reached 92.6% for both metrics when patient ID was included. In predicting new MRI lesions, Random Subspace classifiers performed best, with 82.4% sensitivity and specificity.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Discussion<\/jats:title>\n                    <jats:p>These findings suggest that combining cytokine-based immune signatures with machine learning strategies can provide clinically meaningful predictions of both functional disability and radiological progression. Such tools may support more proactive patient monitoring, informed therapeutic decision-making, and risk stratification in the care of RRMS. Further validation in prospective cohorts is warranted to support clinical implementation.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/fneur.2025.1712953","type":"journal-article","created":{"date-parts":[[2026,1,15]],"date-time":"2026-01-15T08:43:47Z","timestamp":1768466627000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["Predicting multiple sclerosis prognosis using AI and machine learning: integrating clinical, immunological, and radiological variables"],"prefix":"10.3389","volume":"16","author":[{"given":"Suhail","family":"Al-Shammri","sequence":"first","affiliation":[{"name":"Department of Medicine, College of Medicine, Kuwait University","place":["Safat, Kuwait"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ahmet","family":"\u00d6zdil","sequence":"additional","affiliation":[{"name":"Department of Computer Engineering, OST\u0130M Technical University","place":["Ankara, T\u00fcrkiye"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Amro","family":"Aboukoura","sequence":"additional","affiliation":[{"name":"Division of Neurology, Mubarak Al-Kabeer Hospital, Ministry of Health","place":["Jabriya, Kuwait"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fawaz","family":"Azizieh","sequence":"additional","affiliation":[{"name":"College of Integrative Studies, Abdullah Al Salem University","place":["Khaldiya, Kuwait"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bulent","family":"Yilmaz","sequence":"additional","affiliation":[{"name":"Department of Electrical Engineering, Gulf University for Science and Technology","place":["Hawally, Kuwait"]},{"name":"GUST Engineering and Applied Innovation Research (GEAR) Center, Gulf University for Science and Technology","place":["Hawally, Kuwait"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Raj","family":"Raghupathy","sequence":"additional","affiliation":[{"name":"Department of Microbiology, College of Medicine, Kuwait University","place":["Safat, Kuwait"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,1,15]]},"reference":[{"key":"ref1","doi-asserted-by":"publisher","first-page":"169","DOI":"10.1056\/NEJMra1401483","article-title":"Multiple Sclerosis","volume":"378","author":"Reich","year":"2018","journal-title":"N Engl J Med"},{"key":"ref2","doi-asserted-by":"publisher","first-page":"977","DOI":"10.1016\/j.lanepe.2024.100977","article-title":"Multiple sclerosis: emerging epidemiological trends and redefining the clinical course","volume":"44","author":"Portaccio","year":"2024","journal-title":"Lancet Reg Health Europe"},{"key":"ref3","doi-asserted-by":"publisher","first-page":"342","DOI":"10.1212\/CPJ.0000000000001045","article-title":"Multiple sclerosis phenotypes as a continuum: the role of neurologic reserve","volume":"11","author":"Vollmer","year":"2021","journal-title":"Neurol Clin Pract"},{"key":"ref4","doi-asserted-by":"publisher","first-page":"102242","DOI":"10.1016\/j.msard.2020.102242","article-title":"The transitional phase of multiple sclerosis: characterization and conceptual framework","volume":"44","author":"Kleiter","year":"2020","journal-title":"Mult Scler Relat Disord"},{"key":"ref5","doi-asserted-by":"publisher","first-page":"247","DOI":"10.1177\/1756285617708911","article-title":"MRI in the assessment and monitoring of multiple sclerosis: an update on best practice","volume":"10","author":"Kaunzner","year":"2017","journal-title":"Ther Adv Neurol Disord"},{"key":"ref6","doi-asserted-by":"publisher","first-page":"1444","DOI":"10.1212\/WNL.33.11.1444","article-title":"Rating neurologic impairment in multiple sclerosis","volume":"33","author":"Kurtzke","year":"1983","journal-title":"Neurology"},{"key":"ref7","doi-asserted-by":"publisher","first-page":"561","DOI":"10.1177\/13524585211031801","article-title":"MRI brain volume loss, lesion burden, and clinical outcome in secondary progressive multiple sclerosis","volume":"28","author":"Koch","year":"2022","journal-title":"Mult Scler"},{"key":"ref8","doi-asserted-by":"publisher","first-page":"1132","DOI":"10.1001\/jamaneurol.2020.1568","article-title":"Contribution of relapse-independent progression vs relapse-associated worsening to overall confirmed disability accumulation in typical relapsing multiple sclerosis in a pooled analysis of 2 randomized clinical trials","volume":"77","author":"Kappos","year":"2020","journal-title":"JAMA Neurol"},{"key":"ref9","doi-asserted-by":"publisher","first-page":"841","DOI":"10.1001\/archneurol.2009.119","article-title":"Association between clinical conversion to multiple sclerosis in radiologically isolated syndrome and magnetic resonance imaging, cerebrospinal fluid, and visual evoked potential: follow-up of 70 patients","volume":"66","author":"Lebrun","year":"2009","journal-title":"Arch Neurol"},{"key":"ref10","doi-asserted-by":"publisher","first-page":"292","DOI":"10.1002\/ana.22366","article-title":"Diagnostic criteria for multiple sclerosis: 2010 revisions to the McDonald criteria","volume":"69","author":"Polman","year":"2011","journal-title":"Ann Neurol"},{"key":"ref11","doi-asserted-by":"publisher","first-page":"88","DOI":"10.1016\/S0165-5728(01)00431-3","article-title":"Single-cell analysis of cytokine production shows different immune profiles in multiple sclerosis patients with active or quiescent disease","volume":"121","author":"Clerici","year":"2001","journal-title":"J Neuroimmunol"},{"key":"ref12","doi-asserted-by":"publisher","first-page":"e37297","DOI":"10.1097\/MD.0000000000037297","article-title":"Review of multiple sclerosis: epidemiology, etiology, pathophysiology, and treatment","volume":"103","author":"Haki","year":"2024","journal-title":"Medicine (Baltimore)"},{"key":"ref13","doi-asserted-by":"publisher","first-page":"10","DOI":"10.3389\/fneur.2019.00781","article-title":"Computational intelligence technique for prediction of multiple sclerosis based on serum cytokines","volume":"10","author":"Goyal","year":"2019","journal-title":"Front Neurol"},{"key":"ref14","doi-asserted-by":"publisher","first-page":"2950","DOI":"10.1007\/s12035-016-9846-x","article-title":"Cytokine profile in patients with progressive multiple sclerosis and its association with disease progression and disability","volume":"54","author":"Kallaur","year":"2017","journal-title":"Mol Neurobiol"},{"key":"ref15","doi-asserted-by":"publisher","first-page":"145","DOI":"10.1007\/s11481-023-10059-w","article-title":"Inflammatory cytokines associated with multiple sclerosis directly induce alterations of neuronal Cytoarchitecture in human neurons","volume":"18","author":"Meyer-Arndt","year":"2023","journal-title":"J NeuroImmune Pharmacol"},{"key":"ref16","doi-asserted-by":"publisher","first-page":"2078","DOI":"10.1038\/s41467-021-22265-2","article-title":"Identifying multiple sclerosis subtypes using unsupervised machine learning and MRI data","volume":"12","author":"Eshaghi","year":"2021","journal-title":"Nat Commun"},{"key":"ref17","doi-asserted-by":"publisher","first-page":"700582","DOI":"10.3389\/fimmu.2021.700582","article-title":"Machine learning approaches in study of multiple sclerosis disease through magnetic resonance images","volume":"12","author":"Moazami","year":"2021","journal-title":"Front Immunol"},{"key":"ref18","doi-asserted-by":"publisher","first-page":"345","DOI":"10.1186\/s12880-024-01528-6","article-title":"Enhancing classification of active and non-active lesions in multiple sclerosis: machine learning models and feature selection techniques","volume":"24","author":"Rostami","year":"2024","journal-title":"BMC Med Imaging"},{"key":"ref19","doi-asserted-by":"publisher","first-page":"6543","DOI":"10.1007\/s00415-024-12651-3","article-title":"Predicting multiple sclerosis disease progression and outcomes with machine learning and MRI-based biomarkers: a review","volume":"271","author":"Yousef","year":"2024","journal-title":"J Neurol"},{"key":"ref20","doi-asserted-by":"publisher","first-page":"300","DOI":"10.1034\/j.1600-0404.2002.1o199.x","article-title":"Serum cytokine levels do not correlate with disease activity and severity assessed by brain MRI in multiple sclerosis","volume":"105","author":"Kraus","year":"2002","journal-title":"Acta Neurol Scand"},{"key":"ref21","doi-asserted-by":"publisher","first-page":"385","DOI":"10.1111\/j.1600-0404.2004.00246.x","article-title":"Diagnosis of multiple sclerosis: comparison of the poser criteria and the new McDonald criteria","volume":"109","author":"Fangerau","year":"2004","journal-title":"Acta Neurol Scand"},{"key":"ref22","doi-asserted-by":"publisher","first-page":"76","DOI":"10.1145\/507338.507355","article-title":"Data mining: practical machine learning tools and techniques with Java implementations","volume":"31","author":"Witten","year":"2002","journal-title":"SIGMOD Rec"},{"key":"ref23","doi-asserted-by":"publisher","first-page":"545493","DOI":"10.1155\/2014\/545493","article-title":"Cytokines as biomarkers in rheumatoid arthritis","volume":"2014","author":"Burska","year":"2014","journal-title":"Mediat Inflamm"},{"key":"ref24","doi-asserted-by":"publisher","first-page":"1057","DOI":"10.1097\/GME.0000000000000885","article-title":"Cytokine profiles in osteoporosis suggest a proresorptive bias","volume":"24","author":"Azizieh","year":"2017","journal-title":"Menopause"},{"key":"ref25","doi-asserted-by":"publisher","first-page":"7297","DOI":"10.4049\/jimmunol.0904180","article-title":"Analysis of complex biomarkers for human immune-mediated disorders based on cytokine responsiveness of peripheral blood cells","volume":"184","author":"Davis","year":"2010","journal-title":"J Immunol"},{"key":"ref26","doi-asserted-by":"publisher","first-page":"1161849","DOI":"10.3389\/fimmu.2023.1161849","article-title":"The value of interferon \u03b2 in multiple sclerosis and novel opportunities for its anti-viral activity: a narrative literature review","volume":"14","author":"Bellucci","year":"2023","journal-title":"Front Immunol"},{"key":"ref27","doi-asserted-by":"publisher","first-page":"1188750","DOI":"10.3389\/fimmu.2023.1188750","article-title":"Under the influence: environmental factors as modulators of neuroinflammation through the IL-10\/IL-10R axis","volume":"14","author":"Bugbee","year":"2023","journal-title":"Front Immunol"},{"key":"ref28","doi-asserted-by":"publisher","first-page":"1663526","DOI":"10.3389\/fimmu.2025.1663526","article-title":"Aging-dependent immunological changes in multiple sclerosis","volume":"16","author":"Iribarren-L\u00f3pez","year":"2025","journal-title":"Front Immunol"},{"key":"ref29","doi-asserted-by":"publisher","first-page":"9684","DOI":"10.1038\/s41598-019-46097-9","article-title":"Establishing a many-cytokine signature via multivariate anomaly detection","volume":"9","author":"Dingle","year":"2019","journal-title":"Sci Rep"},{"key":"ref30","doi-asserted-by":"publisher","first-page":"20140428","DOI":"10.1098\/rsif.2014.0428","article-title":"A computational method to differentiate normal individuals, osteoarthritis and rheumatoid arthritis patients using serum biomarkers","volume":"11","author":"Heard","year":"2014","journal-title":"J R Soc Interface"},{"key":"ref31","doi-asserted-by":"publisher","first-page":"56","DOI":"10.1136\/jitc-2024-SITC2024.0056","article-title":"56 intracellular cytokine profiling and specific immune cell characterization using CyTOF in whole blood for antibody-based cancer immunotherapies","volume":"12","author":"Boute","year":"2024","journal-title":"J Immunother Cancer"},{"key":"ref32","doi-asserted-by":"publisher","first-page":"e006788","DOI":"10.1136\/jitc-2023-006788","article-title":"Machine learning for prediction of immunotherapeutic outcome in non-small-cell lung cancer based on circulating cytokine signatures","volume":"11","author":"Wei","year":"2023","journal-title":"J Immunother Cancer"},{"key":"ref33","doi-asserted-by":"publisher","first-page":"103116","DOI":"10.1016\/j.artmed.2025.103116","article-title":"Machine learning and clinical EEG data for multiple sclerosis: a systematic review","volume":"166","author":"Mouazen","year":"2025","journal-title":"Artif Intell Med"},{"key":"ref34","first-page":"117","volume-title":"Harnessing cytokine signatures and AI for early disease detection and predictive medicine. Intersecting AI and medicine for improved care and administrative efficiency","author":"Azizieh","year":"2026"},{"key":"ref35","doi-asserted-by":"publisher","first-page":"102335","DOI":"10.1016\/j.nicl.2020.102335","article-title":"Multiple sclerosis cortical and WM lesion segmentation at 3T MRI: a deep learning method based on FLAIR and MP2RAGE","volume":"27","author":"La Rosa","year":"2020","journal-title":"NeuroImage Clin"},{"key":"ref36","doi-asserted-by":"publisher","first-page":"183","DOI":"10.1016\/S1474-4422(14)70256-X","article-title":"Pathological mechanisms in progressive multiple sclerosis","volume":"14","author":"Mahad","year":"2015","journal-title":"Lancet Neurol"}],"container-title":["Frontiers in Neurology"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fneur.2025.1712953\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,15]],"date-time":"2026-01-15T08:43:51Z","timestamp":1768466631000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fneur.2025.1712953\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1,15]]},"references-count":36,"alternative-id":["10.3389\/fneur.2025.1712953"],"URL":"https:\/\/doi.org\/10.3389\/fneur.2025.1712953","relation":{},"ISSN":["1664-2295"],"issn-type":[{"value":"1664-2295","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,1,15]]},"article-number":"1712953"}}