{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,14]],"date-time":"2026-08-14T23:28:24Z","timestamp":1786750104320,"version":"build-2736575974"},"reference-count":21,"publisher":"SAGE Publications","license":[{"start":{"date-parts":[[2026,2,1]],"date-time":"2026-02-01T00:00:00Z","timestamp":1769904000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"},{"start":{"date-parts":[[2026,2,1]],"date-time":"2026-02-01T00:00:00Z","timestamp":1769904000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/journals.sagepub.com\/page\/policies\/text-and-data-mining-license"}],"content-domain":{"domain":["journals.sagepub.com"],"crossmark-restriction":true},"short-container-title":["DIGITAL HEALTH"],"published-print":{"date-parts":[[2026,2]]},"abstract":"<jats:p>This study evaluates a genetic algorithm\u2013assisted support vector machine (GA-SVM) framework for multiple sclerosis (MS) diagnosis using a publicly available dataset (n=709; 370 MS, 339 controls) comprising five pre-extracted white matter lesion features. Model performance was assessed using repeated nested stratified 10\u00d75 cross-validation, with hyperparameter optimization confined to inner training folds and results reported from aggregated out-of-fold predictions. The tuned RBF-SVM achieved AUC=0.993, accuracy=0.987, sensitivity=1.000, specificity=0.973, precision=0.976, and F1-score=0.988 at a probability threshold of 0.5. Precision\u2013recall (AP\u22480.99) and calibration analysis (Brier=0.012) confirmed strong discrimination and reliable probability estimates. Comparative benchmarking showed competitive performance while preserving model simplicity and interpretability. These findings support the feasibility of compact radiomics combined with rigorously validated classical machine learning for MS classification. External multi-site validation is required to confirm generalizability.<\/jats:p>","DOI":"10.1177\/20552076261471332","type":"journal-article","created":{"date-parts":[[2026,8,12]],"date-time":"2026-08-12T21:29:04Z","timestamp":1786570144000},"update-policy":"https:\/\/doi.org\/10.1177\/sage-journals-update-policy","source":"Crossref","is-referenced-by-count":0,"title":["Genetic Algorithm\u2013Optimized support vector machine for MRI-based multiple sclerosis diagnosis from white matter lesion features"],"prefix":"10.1177","volume":"12","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-4095-7589","authenticated-orcid":false,"given":"Raha Sadat","family":"Hosseiny","sequence":"first","affiliation":[{"name":"Islamic Azad University, Central Tehran Branch (IAUCTB)"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Touraj","family":"BaniRostam","sequence":"additional","affiliation":[{"name":"University of Niagara Falls Canada (UNFC)"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"179","published-online":{"date-parts":[[2026,8,12]]},"reference":[{"issue":"2","key":"e_1_3_7_2_2","first-page":"e13049","article-title":"The immunopathology of multiple sclerosis: an overview","volume":"32","author":"Lassmann H","year":"2022","unstructured":"Lassmann H, Br\u00fcck W, Lucchinetti CF. The immunopathology of multiple sclerosis: an overview. Brain Pathol 2022; 32(2): e13049.","journal-title":"Brain Pathol"},{"issue":"3","key":"e_1_3_7_3_2","first-page":"211","article-title":"MRI in multiple sclerosis: a core resource for diagnosis, prognosis and treatment","volume":"22","author":"Filippi M","year":"2023","unstructured":"Filippi M, Preziosa P, Banwell BL, et al. MRI in multiple sclerosis: a core resource for diagnosis, prognosis and treatment. Lancet Neurol 2023; 22(3): 211\u2013226.","journal-title":"Lancet Neurol"},{"key":"e_1_3_7_4_2","first-page":"103212","article-title":"Radiomics for brain lesions: principles and applications in multiple sclerosis","volume":"36","author":"Sudre CH","year":"2022","unstructured":"Sudre CH, Cardoso MJ, et al. Radiomics for brain lesions: principles and applications in multiple sclerosis. Neuroimage Clin 2022; 36: 103212.","journal-title":"Neuroimage Clin"},{"issue":"1","key":"e_1_3_7_5_2","first-page":"54","article-title":"Harmonization of MRI radiomics across scanners for MS lesion analysis","volume":"90","author":"Raji A","year":"2023","unstructured":"Raji A, et al. Harmonization of MRI radiomics across scanners for MS lesion analysis. Magn Reson Med 2023; 90(1): 54\u201367.","journal-title":"Magn Reson Med"},{"key":"e_1_3_7_6_2","first-page":"1376542","article-title":"Compact radiomics for multiple sclerosis diagnosis using MRI","volume":"15","author":"Zhang Y","year":"2024","unstructured":"Zhang Y, et al. Compact radiomics for multiple sclerosis diagnosis using MRI. Front Neurol 2024; 15: 1376542.","journal-title":"Front Neurol"},{"key":"e_1_3_7_7_2","first-page":"105123","article-title":"Machine learning for prognosis in multiple sclerosis: recent advances","volume":"82","author":"Zhou H","year":"2024","unstructured":"Zhou H, et al. Machine learning for prognosis in multiple sclerosis: recent advances. Mult Scler Relat Disord 2024; 82: 105123.","journal-title":"Mult Scler Relat Disord"},{"key":"e_1_3_7_8_2","first-page":"107851","article-title":"Evolutionary optimization and AI in clinical diagnosis: a review","volume":"170","author":"BaniRostam T","year":"2024","unstructured":"BaniRostam T, et al. Evolutionary optimization and AI in clinical diagnosis: a review. Comput Biol Med 2024; 170: 107851.","journal-title":"Comput Biol Med"},{"key":"e_1_3_7_9_2","first-page":"102693","article-title":"Autoencoder-based leukemia diagnosis with interpretable AI","volume":"144","author":"BaniRostam T","year":"2023","unstructured":"BaniRostam T, et al. Autoencoder-based leukemia diagnosis with interpretable AI. Artif Intell Med 2023; 144: 102693.","journal-title":"Artif Intell Med"},{"key":"e_1_3_7_10_2","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-024-61876-9"},{"issue":"7","key":"e_1_3_7_11_2","first-page":"124","article-title":"Implementation of neuro-fuzzy system for diagnosis of multiple sclerosis","volume":"4","author":"Reddy AR","year":"2016","unstructured":"Reddy AR, Vidyavathi C. Implementation of neuro-fuzzy system for diagnosis of multiple sclerosis. Int J Comput Sci Eng 2016; 4(7): 124\u2013128.","journal-title":"Int J Comput Sci Eng"},{"issue":"7","key":"e_1_3_7_12_2","first-page":"150","article-title":"An efficient data mining technique for the diagnosis of multiple sclerosis","volume":"5","author":"Reddy AR","year":"2016","unstructured":"Reddy AR, Vidyavathi C. An efficient data mining technique for the diagnosis of multiple sclerosis. Int J Adv Res Comput Commun Eng 2016; 5(7): 150\u2013154.","journal-title":"Int J Adv Res Comput Commun Eng"},{"key":"e_1_3_7_13_2","first-page":"1","article-title":"Hyperparameter optimization using GA for SVM","volume":"11","author":"Upadhyay S","year":"2025","unstructured":"Upadhyay S, et al. Hyperparameter optimization using GA for SVM. Open Bioinform J 2025; 11: 1\u201310.","journal-title":"Open Bioinform J"},{"issue":"5","key":"e_1_3_7_14_2","first-page":"587","article-title":"Integrated neural network and evolutionary algorithm approach for liver fibrosis staging: Can artificial intelligence reduce patient costs?","volume":"8","author":"BaniRostam T","year":"2024","unstructured":"BaniRostam T, Ghojazadeh M, Hashemzadeh K, et al. Integrated neural network and evolutionary algorithm approach for liver fibrosis staging: Can artificial intelligence reduce patient costs? JGH Open 2024; 8(5): 587\u2013595. https:\/\/doi.org\/10.1002\/jgh3.13075","journal-title":"JGH Open"},{"key":"e_1_3_7_15_2","first-page":"1","article-title":"Magnetic resonance radiomics-based deep learning model for clinical decision support","volume":"11","author":"Yuan Z","year":"2025","unstructured":"Yuan Z, et al. Magnetic resonance radiomics-based deep learning model for clinical decision support. Digit Health 2025; 11: 1\u201318. https:\/\/doi.org\/10.1177\/20552076251337183","journal-title":"Digit Health"},{"key":"e_1_3_7_16_2","first-page":"73","article-title":"Nested cross-validation for robust performance estimation in medical AI","volume":"157","author":"Chawla NV","year":"2022","unstructured":"Chawla NV, et al. Nested cross-validation for robust performance estimation in medical AI. Pattern Recognit Lett 2022; 157: 73\u201381.","journal-title":"Pattern Recognit Lett"},{"key":"e_1_3_7_17_2","doi-asserted-by":"publisher","DOI":"10.2307\/2531595"},{"key":"e_1_3_7_18_2","doi-asserted-by":"publisher","DOI":"10.1162\/089976698300017197"},{"key":"e_1_3_7_19_2","first-page":"1","article-title":"MRI Delta-Radiomics and morphological feature-driven modeling for clinical prediction","volume":"11","author":"Li Y","year":"2025","unstructured":"Li Y, et al. MRI Delta-Radiomics and morphological feature-driven modeling for clinical prediction. Digit Health 2025; 11: 1\u201310. https:\/\/doi.org\/10.1177\/15330338251362050","journal-title":"Digit Health"},{"key":"e_1_3_7_20_2","first-page":"1","article-title":"Cost-effectiveness of the Floodlight\u00ae MS app in Austria","volume":"11","author":"Walter E","year":"2025","unstructured":"Walter E, et al. Cost-effectiveness of the Floodlight\u00ae MS app in Austria. Digit Health 2025; 11: 1\u201312. https:\/\/doi.org\/10.1177\/20552076251314550","journal-title":"Digit Health"},{"key":"e_1_3_7_21_2","first-page":"997","article-title":"Explainable AI in healthcare: recent progress and future directions","volume":"4","author":"Samek W","year":"2022","unstructured":"Samek W, Montavon G, Lapuschkin S, et al. Explainable AI in healthcare: recent progress and future directions. Nat Mach Intell 2022; 4: 997\u20131009.","journal-title":"Nat Mach Intell"},{"key":"e_1_3_7_22_2","first-page":"1","article-title":"Interpretable machine learning for health: challenges and opportunities","volume":"9","author":"Holzinger A","year":"2023","unstructured":"Holzinger A, Biemann C, Pattichis CS, et al. Interpretable machine learning for health: challenges and opportunities. Digit Health 2023; 9: 1-21. 20552076231123456.","journal-title":"Digit Health"}],"container-title":["DIGITAL HEALTH"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/journals.sagepub.com\/doi\/pdf\/10.1177\/20552076261471332","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/journals.sagepub.com\/doi\/full-xml\/10.1177\/20552076261471332","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/journals.sagepub.com\/doi\/pdf\/10.1177\/20552076261471332","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,14]],"date-time":"2026-08-14T23:24:15Z","timestamp":1786749855000},"score":1,"resource":{"primary":{"URL":"https:\/\/journals.sagepub.com\/doi\/10.1177\/20552076261471332"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,2]]},"references-count":21,"alternative-id":["10.1177\/20552076261471332"],"URL":"https:\/\/doi.org\/10.1177\/20552076261471332","relation":{},"ISSN":["2055-2076","2055-2076"],"issn-type":[{"value":"2055-2076","type":"print"},{"value":"2055-2076","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,2]]},"article-number":"20552076261471332"}}