Unveiling Multiple Sclerosis Predictors: A Proposed Artificial Intelligence Approach Using Associative Classification

Öz

Objective: Although multiple sclerosis (MS) is the leading non-traumatic cause of disability among young adults, the reasons behind its increasing prevalence remain elusive. This study explores the use of artificial intelligence, specifically associative classification, to identify key predictors for the progression of multiple sclerosis (MS). Methods: The study utilized a publicly available dataset to forecast whether individuals have MS based on various personal traits. The relevant dataset originated from a cohort group study conducted on Mexican mestizo individuals recently identified with Clinically Isolated Syndrome (CIS). These individuals had sought care at the National Institute of Neurology and Neurosurgery (NINN) between 2006 and 2010. Associative rule mining was applied to uncover relationships between the variables and the development of Clinical Definite Multiple Sclerosis (CDMS). The effectiveness of the model was assessed using accuracy, balanced accuracy, sensitivity, specificity, positive & negative predictive values, and F1 measure with 95% confidence intervals. Results: Oligoclonal bands, breastfeeding history, education level, and specific MRI results were significant predictors of MS classification. Oligoclonal bands were particularly associated with a higher likelihood of CDMS. The proposed model performed with high accuracy (87.8%), sensitivity (89.6%), and specificity (86.3%), highlighting its effectiveness in predicting MS progression. Conclusions: Artificial intelligence, through associative classification, provides valuable insights into MS progression by identifying significant predictors. These findings can support early diagnosis and contribute to the development of personalized treatment strategies. Future research should incorporate more diverse datasets to validate these results further.

Anahtar Kelimeler

• Artificial intelligence
• Associative Classification
• Diagnostic Predictors
• Clinically Isolated Syndrome
• Clinical Definite Multiple Sclerosis

Multipl Skleroz Öngörücülerinin Açılması: İlişkisel Sınıflandırma Kullanarak Önerilen Yapay Zekâ Yaklaşımı

Öz

Amaç: Multipl skleroz (MS) genç yetişkinler arasında önde gelen travma olmayan sakatlık nedeni olmasına rağmen, artan prevalansının arkasındaki nedenler zordur. Bu çalışma, multipl sklerozun (MS) ilerlemesi için temel öngörücüleri tanımlamak için yapay zekanın, özellikle de ilişkilendirici sınıflandırmanın kullanımını araştırmayı amaçlamaktadır. Yöntemler: Çalışma, bireylerin çeşitli kişisel özelliklere dayalı MS olup olmadığını tahmin etmek için halka açık bir veri kümesi kullanılmıştır. İlgili veri kümesi, yakın zamanda klinik izole sendrom (CIS) ile tanımlanan Meksika mestizo bireyleri üzerinde yapılan bir kohort grubu çalışmasından kaynaklanmıştır. Bu bireyler 2006-2010 yılları arasında Ulusal Nöroloji ve Nöroşirürji Enstitüsü'nde (NINN) bakım aradılar. Değişkenler arasındaki ilişkileri ortaya çıkarmak ve klinik kesin multipl sklerozun (CDMS) gelişimini ortaya çıkarmak için ilişkisel kural madenciliği uygulanmıştır. Modellerin etkinliği doğruluk, dengeli doğruluk, duyarlılık, özgüllük, pozitif ve negatif prediktif değerler ve F1 ölçüsü kullanılarak değerlendirildi. Bulgular: Oligoklonal bantlar, emzirme geçmişi, eğitim seviyesi ve spesifik MRI sonuçları MS sınıflandırmasının önemli belirleyicileriydi. Oligoklonal bantlar özellikle CDMS'nin daha yüksek bir olasılığı ile ilişkiliydi. Önerilen model, yüksek doğruluk (%87,8), duyarlılık (%89,6) ve özgüllük (%86,3) ile gerçekleştirerek MS ilerlemesini tahmin etmede etkinliğini vurgulamaktadır. Sonuçlar: Yapay zeka, ilişkisel sınıflandırma yoluyla, önemli öngörücüler belirleyerek MS ilerlemesine değerli bilgiler sağlar. Bu bulgular erken tanıyı destekleyebilir ve kişiselleştirilmiş tedavi stratejilerinin geliştirilmesine katkıda bulunabilir. Gelecekteki araştırmalar, bu sonuçları daha da doğrulamak için daha çeşitli veri kümeleri içermelidir.

Anahtar Kelimeler

• Yapay zeka
• İlişkisel Sınıflandırma
• tanılama öngörücüler
• klinik olarak izole edilmiş sendrom
• klinik kesin multipl skleroz

Kaynakça

1. Amin M, Martínez-Heras E, Ontaneda D & Prados Carrasco F (2024). Artificial Intelligence and Multiple Sclerosis. Current Neurology and Neuroscience Reports 24, 233-243.
2. Arani LA, Hosseini A, Asadi F, Masoud SA & Nazemi E (2018). Intelligent computer systems for multiple sclerosis diagnosis: a systematic review of reasoning techniques and methods. Acta Informatica Medica 26, 258-264.
3. Arrambide G, Comabella M & Tur C (2024). Big data and artificial intelligence applied to blood and CSF fluid biomarkers in multiple sclerosis. Frontiers in Immunology.
4. Arslan AK, Yaşar Ş, Çolak C & Yoloğlu S (2018). WSSPAS: An interactive web application for sample size and power analysis with R using shiny. Türkiye Klinikleri Biyoistatistik 10, 224-246.
5. Briggs FB & Sept C (2021). Mining complex genetic patterns conferring multiple sclerosis risk. International journal of environmental research and public health 18, 2518.
6. Brownlee WJ, Hardy TA, Fazekas F & Miller DH (2017). Diagnosis of multiple sclerosis: progress and challenges. The lancet 389, 1336-1346.
7. Chavarria V, Espinosa-Ramírez G, Sotelo J, Flores-Rivera J, Anguiano O, Hernández AC, Guzmán-Ríos ED, Salazar A, Ordoñez G & Pineda B (2023). Conversion Predictors of Clinically Isolated Syndrome to Multiple Sclerosis in Mexican Patients: A Prospective Study. Archives of Medical Research, 102843.
8. Coles A (2009). Multiple sclerosis: the bare essentials. Practical neurology 9, 118-126.

9. Dobson R & Giovannoni G (2019). Multiple sclerosis–a review. European Journal of Neurology 26, 27-40.
10. Goyal M, Khanna D, Rana PS, Khaibullin T, Martynova E, Rizvanov AA, Khaiboullina SF & Baranwal M (2019). Computational intelligence technique for prediction of multiple sclerosis based on serum cytokines. Frontiers in neurology 10, 781.
11. Harbo HF, Gold R & Tintoré M (2013). Sex and gender issues in multiple sclerosis. Therapeutic advances in neurological disorders 6, 237-248.
12. Hone L, Jacobs BM, Marshall C, Giovannoni G, Noyce A & Dobson R (2022). Age-specific effects of childhood body mass index on multiple sclerosis risk. Journal of Neurology 269, 5052-5060.
13. Jacobs BM, Giovannoni G, Cuzick J & Dobson R (2020). Systematic review and meta-analysis of the association between Epstein–Barr virus, multiple sclerosis and other risk factors. Multiple sclerosis journal 26, 1281-1297.
14. Kaggle (2024). Predictors of Multiple Sclerosis Disease, vol. 2024, pp. Conversion predictors of Clinically Isolated Syndrome to Multiple Sclerosis in Mexican patients, https://www.kaggle.com/. [Accessed on June 5, 2025]
15. Langer-Gould A, Brara SM, Beaber BE & Koebnick C (2013). Childhood obesity and risk of pediatric multiple sclerosis and clinically isolated syndrome. Neurology 80, 548-552.
16. Link H & Huang Y-M (2006). Oligoclonal bands in multiple sclerosis cerebrospinal fluid: an update on methodology and clinical usefulness. Journal of neuroimmunology 180, 17-28.
17. Liu B, Hsu W & Ma Y (1998). Integrating classification and association rule mining. In Proceedings of the fourth international conference on knowledge discovery and data mining, pp. 80-86.
18. Liu H, Guan J, Li H, Bao Z, Wang Q, Luo X & Xue H (2020). Predicting the disease genes of multiple sclerosis based on network representation learning. Frontiers in Genetics 11, 328.
19. Marrie RA, Elliott L, Marriott J, Cossoy M, Blanchard J, Leung S & Yu N (2015). Effect of comorbidity on mortality in multiple sclerosis. Neurology 85, 240-247.
20. Nicolaou A, Pantzaris M, Loizou CP, Kakas A & Pattichis CS (2023). An Explainable AI model in the assessment of Multiple Sclerosis using clinical data and Brain MRI lesion texture features. In 2023 IEEE EMBS International Conference on Biomedical and Health Informatics (BHI), pp. 1-4. IEEE.
21. Ponce de Leon-Sanchez ER, Dominguez-Ramirez OA, Herrera-Navarro AM, Rodriguez-Resendiz J, Paredes-Orta C & Mendiola-Santibañez JD (2023). A deep learning approach for predicting multiple sclerosis. Micromachines 14, 749.
22. Roca P, Attye A, Colas L, Tucholka A, Rubini P, Cackowski S, Ding J, Budzik J-F, Renard F & Doyle S (2020). Artificial intelligence to predict clinical disability in patients with multiple sclerosis using FLAIR MRI. Diagnostic and Interventional Imaging 101, 795-802.
23. Rocca MA, Amato MP, De Stefano N, Enzinger C, Geurts JJ, Penner I-K, Rovira A, Sumowski JF, Valsasina P & Filippi M (2015). Clinical and imaging assessment of cognitive dysfunction in multiple sclerosis. The Lancet Neurology 14, 302-317.
24. Smith KJ & McDonald W (1999). The pathophysiology of multiple sclerosis⋮ the mechanisms underlying the production of symptoms and the natural history of the disease. Philosophical Transactions of the Royal Society of London. Series B: Biological Sciences 354, 1649-1673.
25. Stern Y (2012). Cognitive reserve in ageing and Alzheimer's disease. The Lancet Neurology 11, 1006-1012.
26. Thompson AJ, Banwell BL, Barkhof F, Carroll WM, Coetzee T, Comi G, Correale J, Fazekas F, Filippi M & Freedman MS (2018). Diagnosis of multiple sclerosis: 2017 revisions of the McDonald criteria. The Lancet Neurology 17, 162-173.
27. Ucuzal H, Colak C & Turtay MG (2024). An optimized deep learning approach for predicting multiple sclerosis conditions from an artificial intelligence perspective In WACEM 2023 World Academic Congress of Emergency Medicine. ed. Galwangar S, pp. 434-438. WACEM23, Antalya/Türkiye.
28. Vandebergh M, Degryse N, Dubois B & Goris A (2022). Environmental risk factors in multiple sclerosis: Bridging Mendelian randomization and observational studies. Journal of Neurology 269, 4565-4574.
29. Walton C, King R, Rechtman L, Kaye W, Leray E, Marrie RA, Robertson N, La Rocca N, Uitdehaag B, van der Mei I, Wallin M, Helme A, Angood Napier C, Rijke N & Baneke P (2020). Rising prevalence of multiple sclerosis worldwide: Insights from the Atlas of MS, third edition. Mult Scler 26, 1816-1821.