{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,20]],"date-time":"2026-04-20T10:33:43Z","timestamp":1776681223663,"version":"3.51.2"},"reference-count":42,"publisher":"MDPI AG","issue":"5","license":[{"start":{"date-parts":[[2025,4,24]],"date-time":"2025-04-24T00:00:00Z","timestamp":1745452800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["JPM"],"abstract":"<jats:p>Background: Multiple Sclerosis (MS) is a chronic autoimmune disease of the central nervous system with a propensity to inflict severe neurological disability. Accurate and early prediction of MS progression is extremely crucial for its management and treatment. Methods: In this paper, we compare a number of self-labeled semi-supervised learning methods used to predict MS from labeled and unlabeled medical data. Specifically, we compare the performance of Self-Training, SETRED, Co-Training, Co-Training by Committee, Democratic Co-Learning, RASCO, RelRASCO, CoForest, and TriTraining in different labeled ratios. The data contain clinical, imaging, and demographic features, allowing for a detailed comparison of each method\u2019s predictive ability. Results and Conclusions: The experimental results demonstrate that several self-labeling semi-supervised learning (SSL) algorithms perform competitively in the task of Multiple Sclerosis (MS) prediction, even when trained on as little as 30\u201340% of the labeled data. Notably, Co-Training by Committee, CoForest, and TriTraining consistently deliver high performance across all metrics (accuracy, F1-score, and MCC).<\/jats:p>","DOI":"10.3390\/jpm15050167","type":"journal-article","created":{"date-parts":[[2025,4,24]],"date-time":"2025-04-24T06:18:02Z","timestamp":1745475482000},"page":"167","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Semi-Supervised Learning for Predicting Multiple Sclerosis"],"prefix":"10.3390","volume":"15","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2247-3082","authenticated-orcid":false,"given":"Sotiris","family":"Kotsiantis","sequence":"first","affiliation":[{"name":"Department of Mathematics, University of Patras, 26504 Patras, Greece"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7547-2342","authenticated-orcid":false,"given":"Georgia","family":"Melagraki","sequence":"additional","affiliation":[{"name":"Department of Military Sciences, Hellenic Army Academy, 16673 Athens, Greece"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9758-0819","authenticated-orcid":false,"given":"Vassilios","family":"Verykios","sequence":"additional","affiliation":[{"name":"School of Science and Technology, Hellenic Open University, 26335 Patras, Greece"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3199-9158","authenticated-orcid":false,"given":"Aikaterini","family":"Sakagianni","sequence":"additional","affiliation":[{"name":"Intensive Care Unit, Sismanogleio General Hospital, 15126 Marousi, Greece"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5554-2964","authenticated-orcid":false,"given":"John","family":"Matsoukas","sequence":"additional","affiliation":[{"name":"Department of Chemistry, University of Patras, 26504 Patras, Greece"},{"name":"Department of Physiology and Pharmacology, Cumming School of Medicine, University of Calgary, Calgary, AB T2N 1N3, Canada"},{"name":"Immunology and Translational Research Group, Institution for Health and Sport, Victoria University, Werribee, VIC 3030, Australia"},{"name":"NewDrug PC, Patras Science Park, 26504 Patras, Greece"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2025,4,24]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","unstructured":"Apostolopoulos, V., Rostami, A., and Matsoukas, J. (2020). The Long Road of Immunotherapeutics against Multiple Sclerosis. Brain Sci., 10.","DOI":"10.3390\/brainsci10050288"},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"2910","DOI":"10.1016\/j.acra.2024.01.032","article-title":"Interpretable and Intuitive Machine Learning Approaches for Predicting Disability Progression in Relapsing-Remitting Multiple Sclerosis Based on Clinical and Gray Matter Atrophy Indicators","volume":"31","author":"Yan","year":"2024","journal-title":"Acad. Radiol."},{"key":"ref_3","doi-asserted-by":"crossref","unstructured":"Gaetani, L., Bellomo, G., Di Sabatino, E., Sperandei, S., Mancini, A., Blennow, K., Zetterberg, H., Parnetti, L., and Di Filippo, M. (2023). The Immune Signature of CSF in Multiple Sclerosis with and without Oligoclonal Bands: A Machine Learning Approach to Proximity Extension Assay Analysis. Int. J. Mol. Sci., 25.","DOI":"10.3390\/ijms25010139"},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"128904","DOI":"10.1016\/j.neucom.2024.128904","article-title":"Self-training: A survey","volume":"616","author":"Amini","year":"2025","journal-title":"Neurocomputing"},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"241052","DOI":"10.1098\/rsos.241052","article-title":"Machine learning for refining interpretation of magnetic resonance imaging scans in the management of multiple sclerosis: A narrative review","volume":"12","author":"Castellani","year":"2025","journal-title":"R. Soc. Open Sci."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"fcae427","DOI":"10.1093\/braincomms\/fcae427","article-title":"Machine learning\u2013based prediction of disease progression in primary progressive multiple sclerosis","volume":"7","author":"Gurevich","year":"2025","journal-title":"Brain Commun."},{"key":"ref_7","doi-asserted-by":"crossref","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":"ref_8","doi-asserted-by":"crossref","unstructured":"Moazami, F., Lefevre-Utile, A., Papaloukas, C., and Soumelis, V. (2021). Machine Learning Approaches in Study of Multiple Sclerosis Disease Through Magnetic Resonance Images. Front. Immunol., 12.","DOI":"10.3389\/fimmu.2021.700582"},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"520","DOI":"10.1016\/j.jmoldx.2024.03.003","article-title":"Machine Learning Analysis Using RNA Sequencing to Distinguish Neuromyelitis Optica from Multiple Sclerosis and Identify Therapeutic Candidates","volume":"26","author":"Wylezinski","year":"2024","journal-title":"J. Mol. Diagn."},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Balaceanu, A., Puertas, I., Alonso de Leciana, M., Talln, A., Gutirrez-Tenorio, \u00c3., Vargas, P., Torres, G., and Gutirrez, \u00c3. (2024). Automatic evaluation of the Nine-Hole Peg Test in multiple sclerosis patients using machine learning models. Biomed. Signal Process. Control, 92.","DOI":"10.1016\/j.bspc.2024.106128"},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"1133","DOI":"10.1007\/s00415-023-12132-z","article-title":"Predicting disease severity in multiple sclerosis using multimodal data and machine learning","volume":"271","author":"Andorra","year":"2023","journal-title":"J. Neurol."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"4278","DOI":"10.1109\/TNSRE.2023.3321874","article-title":"Disease Delineation for Multiple Sclerosis, Friedreich Ataxia, and Healthy Controls Using Supervised Machine Learning on Speech Acoustics","volume":"31","author":"Schultz","year":"2023","journal-title":"IEEE Trans. Neural Syst. Rehabil. Eng."},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Tayyab, M., Metz, L.M., Li, D.K.B., Kolind, S., Carruthers, R., Traboulsee, A., and Tam, R.C. (2023). Accounting for uncertainty in training data to improve machine learning performance in predicting new disease activity in early multiple sclerosis. Front. Neurol., 14.","DOI":"10.3389\/fneur.2023.1165267"},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"119787","DOI":"10.1016\/j.neuroimage.2022.119787","article-title":"Single-timepoint low-dimensional characterization and classification of acute versus chronic multiple sclerosis lesions using machine learning","volume":"265","author":"Caba","year":"2023","journal-title":"NeuroImage"},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"186","DOI":"10.1002\/hbm.26106","article-title":"Prediction of the information processing speed performance in multiple sclerosis using a machine learning approach in a large multicenter magnetic resonance imaging data set","volume":"44","author":"Marzi","year":"2022","journal-title":"Hum. Brain Mapp."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"2253","DOI":"10.1177\/13524585221112605","article-title":"Machine learning classification of multiple sclerosis in children using optical coherence tomography","volume":"28","author":"Erdman","year":"2022","journal-title":"Mult. Scler. J."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"e1100","DOI":"10.1212\/WNL.0000000000200883","article-title":"The Role of Optical Coherence Tomography Criteria and Machine Learning in Multiple Sclerosis and Optic Neuritis Diagnosis","volume":"99","author":"Kenney","year":"2022","journal-title":"Neurology"},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"453","DOI":"10.1212\/WNL.0000000000200862","article-title":"Machine Learning Utility for Optical Coherence Tomography in Multiple Sclerosis","volume":"99","author":"Toosy","year":"2022","journal-title":"Neurology"},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"El Khoury, Y., Gebelin, M., de S\u00e8ze, J., Patte-Mensah, C., Marcou, G., Varnek, A., Mensah-Nyagan, A.-G., Hellwig, P., and Collongues, N. (2022). Rapid Discrimination of Neuromyelitis Optica Spectrum Disorder and Multiple Sclerosis Using Machine Learning on Infrared Spectra of Sera. Int. J. Mol. Sci., 23.","DOI":"10.3390\/ijms23052791"},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"4834","DOI":"10.1007\/s00415-021-10605-7","article-title":"Machine learning classifier to identify clinical and radiological features relevant to disability progression in multiple sclerosis","volume":"268","author":"Tommasin","year":"2021","journal-title":"J. Neurol."},{"key":"ref_21","doi-asserted-by":"crossref","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":"ref_22","doi-asserted-by":"crossref","first-page":"1927","DOI":"10.3174\/ajnr.A7274","article-title":"A Combined Radiomics and Machine Learning Approach to Overcome the Clinicoradiologic Paradox in Multiple Sclerosis","volume":"42","author":"Pontillo","year":"2021","journal-title":"Am. J. Neuroradiol."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"2666","DOI":"10.1109\/TBME.2020.3048142","article-title":"Predicting Multiple Sclerosis From Gait Dynamics Using an Instrumented Treadmill: A Machine Learning Approach","volume":"68","author":"Kaur","year":"2021","journal-title":"IEEE Trans. Biomed. Eng."},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Montolo, A., Mart n-Gallego, A., Cegoino, J., Orduna, E., Vilades, E., Garcia-Martin, E., and del Palomar, A.P. (2021). Machine learning in diagnosis and disability prediction of multiple sclerosis using optical coherence tomography. Comput. Biol. Med., 133.","DOI":"10.1016\/j.compbiomed.2021.104416"},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"107","DOI":"10.1177\/1352458520958362","article-title":"Classifying multiple sclerosis patients on the basis of SDMT performance using machine learning","volume":"27","author":"Buyukturkoglu","year":"2020","journal-title":"Mult. Scler. J."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"100053","DOI":"10.1016\/j.xcrm.2020.100053","article-title":"Inferring Multiple Sclerosis Stages from the Blood Transcriptome via Machine Learning","volume":"1","author":"Acquaviva","year":"2020","journal-title":"Cell Rep. Med."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"102843","DOI":"10.1016\/j.arcmed.2023.102843","article-title":"Conversion predictors of Clinically Isolated Syndrome to Multiple Sclerosis in Mexican patients: A prospective study","volume":"54","author":"Pineda","year":"2023","journal-title":"Arch. Med. Res."},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"1189","DOI":"10.1214\/aos\/1013203451","article-title":"Greedy function approximation: A gradient boosting machine","volume":"29","author":"Friedman","year":"2001","journal-title":"Ann. Stat."},{"key":"ref_29","unstructured":"Ho, T.B., Cheung, D., and Liu, H. (2005). SETRED: Self-training with Editing. Advances in Knowledge Discovery and Data Mining, Springer."},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Blum, A., and Mitchell, T. (1998, January 24\u201326). Combining labeled and unlabeled data with co-training. Proceedings of the Eleventh Annual Conference on Computational Learning Theory, Madison, WI, USA.","DOI":"10.1145\/279943.279962"},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"681","DOI":"10.1007\/s11390-010-9357-6","article-title":"Combining Committee-Based Semi-Supervised Learning and Active Learning","volume":"25","author":"Schwenker","year":"2010","journal-title":"J. Comput. Sci. Technol."},{"key":"ref_32","unstructured":"Zhou, Y., and Goldman, S. (2004, January 15\u201317). Democratic co-learning. Proceedings of the 16th IEEE International Conference on Tools with Artificial Intelligence, Boca Raton, FL, USA."},{"key":"ref_33","unstructured":"Wang, J., Luo, S., and Zeng, X. (2008, January 1\u20138). A random subspace method for co-training. Proceedings of the 2008 IEEE International Joint Conference on Neural Networks (IEEE World Congress on Computational Intelligence), Hong Kong, China."},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"1652","DOI":"10.1016\/j.neucom.2010.01.018","article-title":"Co-training with relevant random subspaces","volume":"73","author":"Yaslan","year":"2010","journal-title":"Neurocomputing"},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"1088","DOI":"10.1109\/TSMCA.2007.904745","article-title":"Improve Computer-Aided Diagnosis With Machine Learning Techniques Using Undiagnosed Samples","volume":"37","author":"Li","year":"2007","journal-title":"IEEE Trans. Syst. Man Cybern.-Part A Syst. Humans"},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"1529","DOI":"10.1109\/TKDE.2005.186","article-title":"Tri-training: Exploiting unlabeled data using three classifiers","volume":"17","author":"Zhou","year":"2005","journal-title":"IEEE Trans. Knowl. Data Eng."},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"102024","DOI":"10.1016\/j.softx.2024.102024","article-title":"SSLearn: A Semi-Supervised Learning library for Python","volume":"29","year":"2025","journal-title":"SoftwareX"},{"key":"ref_38","doi-asserted-by":"crossref","unstructured":"Rodi, M., de Lastic, A.-L., Panagoulias, I., Aggeletopoulou, I., Kelaidonis, K., Matsoukas, J., Apostolopoulos, V., and Mouzaki, A. (2024). Myelin Oligodendrocyte Glycoprotein (MOG) 35\u201355 Mannan Conjugate Induces Human T-Cell Tolerance and Can Be Used as a Personalized Therapy for Multiple Sclerosis. Int. J. Mol. Sci., 25.","DOI":"10.3390\/ijms25116092"},{"key":"ref_39","doi-asserted-by":"crossref","unstructured":"Matsoukas, J., Deraos, G., Kelaidonis, K., Hossain, M.K., Feehan, J., Tzakos, A.G., Matsoukas, E., Topoglidis, E., and Apostolopoulos, V. (2021). Myelin Peptide\u2013Mannan Conjugate Multiple Sclerosis Vaccines: Conjugation Efficacy and Stability of Vaccine Ingredient. Vaccines, 9.","DOI":"10.3390\/vaccines9121456"},{"key":"ref_40","doi-asserted-by":"crossref","unstructured":"Dagkonaki, A., Avloniti, M., Evangelidou, M., Papazian, I., Kanistras, I., Tseveleki, V., Lampros, F., Tselios, T., Jensen, L.T., and M\u00f6bius, W. (2020). Mannan-MOG35-55 reverses experimental autoimmune encephalomyelitis, inducing a peripheral type 2 myeloid response, reducing CNS inflammation, and preserving axons in spinal cord lesions. Front. Immunol., 11.","DOI":"10.3389\/fimmu.2020.575451"},{"key":"ref_41","doi-asserted-by":"crossref","first-page":"214","DOI":"10.1021\/jm801250v","article-title":"Design and Synthesis of a Cyclic Double Mutant Peptide (cyclo (87\u201399) [A91, A96] MBP87\u201399) Induces Altered Responses in Mice after Conjugation to Mannan: Implications in the Immunotherapy of Multiple Sclerosis","volume":"52","author":"Katsara","year":"2009","journal-title":"J. Med. Chem."},{"key":"ref_42","doi-asserted-by":"crossref","first-page":"7834","DOI":"10.1021\/jm800891n","article-title":"Citrullination of Linear and Cyclic Altered Peptide Ligands from Myelin Basic Protein (MBP87\u201399) Epitope Elicits a Th1 Polarized Response by T Cells Isolated from Multiple Sclerosis Patients: Implications in Triggering Disease","volume":"51","author":"Deraos","year":"2008","journal-title":"J. Med. Chem."}],"container-title":["Journal of Personalized Medicine"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2075-4426\/15\/5\/167\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,9]],"date-time":"2025-10-09T17:20:36Z","timestamp":1760030436000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2075-4426\/15\/5\/167"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,24]]},"references-count":42,"journal-issue":{"issue":"5","published-online":{"date-parts":[[2025,5]]}},"alternative-id":["jpm15050167"],"URL":"https:\/\/doi.org\/10.3390\/jpm15050167","relation":{},"ISSN":["2075-4426"],"issn-type":[{"value":"2075-4426","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,4,24]]}}}