Journals / Sağlık Bilimleri Dergisi / 2026 / Cilt: 35 Sayı: 2

Prediction of FMF Symptoms with Deep Learning Using Genetic Mutations and Clinical Findings

FMF Semptomlarının Genetik Mutasyonlar ve Klinik Bulgular Kullanılarak Derin Öğrenme ile Tahmini

Ali Osman Arslan(BOLU ABANT İZZET BAYSAL ÜNİVERSİTESİ, TIP FAKÜLTESİ, TEMEL TIP BİLİMLERİ BÖLÜMÜ, TIBBİ BİYOLOJİ ANABİLİM DALI)0000-0002-5711-0038
Selma Düzenli(BOLU ABANT İZZET BAYSAL ÜNİVERSİTESİ)0000-0001-9589-4091
Güven Akçay(BOLU ABANT İZZET BAYSAL ÜNİVERSİTESİ)0000-0003-3418-8825
Meryem Yalçınkaya(HİTİT ÜNİVERSİTESİ)0000-0003-4255-5656
Pages
413–426
Publication Date
2026-08-25
🏛️Bibliographic metadata and full text access for this article are provided via DergiPark.
DergiPark Record ↗
✨

AI Summary & Key Takeaways

AI Insight
⚡ TL;DR(Too Long; Didn't Read)

These findings suggest that deep learning models could contribute to clarifying the relationships between genetic mutations and Familial Mediterranean Fever clinical manifestations; furthermore, they demonstrate a potential to improve the understanding of genotype–phenotype correlations by predicting symptoms and risks, thereby helping to enhance the clinical utility of personalized Familial Mediterranean Fever management.

📌 3 Key Takeaways

🎯
Objective & Hypothesis:Familial Mediterranean Fever is a hereditary autoinflammatory disorder characterized by recurrent episodes of peritonitis, pleuritis, arthritis, fever, and abdominal pain, with genetic mutations playing a critical role in disease manifestation as well as symptom type and severity.
📊
Key Findings & Data:A total of 1452 individuals diagnosed with Familial Mediterranean Fever at the Department of Medical Genetics, Bolu Abant İzzet Baysal University Training and Research Hospital between 2016 and 2019 were included.
💡
Conclusion & Impact:These findings suggest that deep learning models could contribute to clarifying the relationships between genetic mutations and Familial Mediterranean Fever clinical manifestations; furthermore, they demonstrate a potential to improve the understanding of genotype–phenotype correlations by predicting symptoms and risks, thereby helping to enhance the clinical utility of personalized Familial Mediterranean Fever management.
🔬Design:Modeling & Simulation
📍Scope:2016 Verileri
⚙️Variables:Derin öğrenme · ailevi akdeniz ateşi · mutasyona dayalı fenotip tahmini

Abstract

Familial Mediterranean Fever is a hereditary autoinflammatory disorder characterized by recurrent episodes of peritonitis, pleuritis, arthritis, fever, and abdominal pain, with genetic mutations playing a critical role in disease manifestation as well as symptom type and severity. This study aimed to resolve the genotype–phenotype uncertainty in Familial Mediterranean Fever by integrating genetic mutations, demographic characteristics, and clinical data through deep learning methods, thereby enhancing the predictive understanding of symptom development and disease-related risks. A total of 1452 individuals diagnosed with Familial Mediterranean Fever at the Department of Medical Genetics, Bolu Abant İzzet Baysal University Training and Research Hospital between 2016 and 2019 were included. Genetic testing was performed via Real-Time Polymerase Chain Reaction, and clinical data were analyzed using deep learning approaches. Models applied using convolutional neural network, Residual Blocks, and Multi-Head Attention showed strong potential to predict symptom occurrence with high accuracy; specifically, they achieved the highest accuracy and receiver operating characteristic area under the curve for skin rash/redness (accuracy: 90%, Area Under the Curve: 0.873) and joint swelling (accuracy: 88.6%, Area Under the Curve: 0.871). Prediction for chest pain was also strong (Area Under the Curve 0.827), while abdominal pain, joint pain, and fever demonstrated moderate predictive performance (Area Under the Curve 0.719–0.751). Synthetic Minority Over-sampling Technique enhanced prediction for rare symptoms in imbalanced datasets. These findings suggest that deep learning models could contribute to clarifying the relationships between genetic mutations and Familial Mediterranean Fever clinical manifestations; furthermore, they demonstrate a potential to improve the understanding of genotype–phenotype correlations by predicting symptoms and risks, thereby helping to enhance the clinical utility of personalized Familial Mediterranean Fever management.

Özet

Ailevi Akdeniz Ateşi, peritonit, plevrit, artrit, ateş ve karın ağrısı ile karakterize, tekrarlayan ataklarla seyreden kalıtsal bir otoinflamatuvar hastalıktır ve genetik mutasyonlar hastalığın ortaya çıkışında ve semptomların türü ile şiddetinde kritik rol oynar. Bu çalışma; genetik mutasyon, demografik özellik ve klinik verileri derin öğrenme yöntemleriyle birleştirerek Ailevi Akdeniz Ateşi’ndeki genotip-fenotip belirsizliğini çözmeyi, böylece semptom gelişimini ve hastalığa ilişkin riskleri daha güçlü şekilde öngörmeyi amaçlamıştır. Araştırma, 2016–2019 yılları arasında Bolu Abant İzzet Baysal Üniversitesi Eğitim ve Araştırma Hastanesi Tıbbi Genetik Anabilim Dalı’na başvuran ve Ailevi Akdeniz Ateşi tanısı alan 1452 bireyi kapsamaktadır. Genetik testler gerçek zamanlı polimeraz zincir reaksiyonu yöntemi ile gerçekleştirilmiş, elde edilen klinik veriler ise derin öğrenme algoritmaları kullanılarak analiz edilmiştir. Analizler, genetik mutasyonlar (ör., M694V, M680I G>C, V726A), demografik özellikler ve Ailevi Akdeniz Ateşi semptomları arasında anlamlı ilişkilere işaret etmektedir. Evrişimli Sinir Ağları, Artık Bloklar ve Çok Başlı Dikkat mekanizması kullanılarak geliştirilen modeller semptomları yüksek doğrulukla tahmin etmede güçlü bir potansiyele sahip olmakla beraber; cilt döküntüsü/kızarıklığı ve eklem şişliği sırasıyla %90 ve %88.6 doğruluk ile en yüksek Alıcı İşletim Karakteristiği Eğrisi Altındaki Alan değerlerini (0.873; 0.871) göstermiştir. Göğüs ağrısı öngörüsü güçlü bulunurken (Eğri Altında Kalan Alan 0.827), karın ağrısı, eklem ağrısı ve ateş orta düzeyde tahmin başarısı sergilemiştir (Eğri Altında Kalan Alan 0.719–0.751). Sentetik Azınlık Örnekleme Tekniği yöntemi, dengesiz verilerde nadir semptomların öngörüsünü artırarak derin öğrenmenin Ailevi Akdeniz Ateşi semptom tahmindeki etkinliğini desteklemiştir. Bulgular, genetik mutasyonlar ile Ailevi Akdeniz Ateşi’nin klinik semptomları arasındaki ilişkilerin açıklanmasında derin öğrenme modellerinin katkı sağlayabileceğine işaret etmekte; semptom ve riskleri öngörerek genotip-fenotip ilişkisine dair anlayışı geliştirebileceğini göstermekte ve kişiselleştirilmiş Ailevi Akdeniz Ateşi yönetimini destekleyerek klinik yararlılığın artırılmasına yardımcı olmaktadır.

🔖

Cite This Article

Arslan, A. O., Düzenli, S., Akçay, G., Yalçınkaya, M. (2026). Prediction of FMF Symptoms with Deep Learning Using Genetic Mutations and Clinical Findings. Sağlık Bilimleri Dergisi, Cilt: 35 Sayı: 2, 413–426. https://doi.org/10.34108/eujhs.1834646

📄 Full Text PDF Viewer

📄

PDF görüntüleyici hazırlanıyor...

References (44)

  1. Lancieri M, Bustaffa M, Palmeri S, et al. An update on familial Mediterranean fever. Int J Mol Sci. 2023;24(11):9584. doi:10.3390/ijms24119584
  2. Gezgin Yıldırım D, Gönen S, Fidan K, Söylemezoğlu O. Does age at onset affect the clinical presentation of familial Mediterranean fever in children? J Clin Rheumatol. 2020;28(1):e125-e128. doi:10.1097/RHU.0000000000001637
  3. Yaşar Bilge Ş, Sarı İ, Solmaz D, et al. The distribution of MEFV mutations in Turkish FMF patients: multicenter study representing results of Anatolia. Turk J Med Sci. 2019;49(2):472-477. doi:10.3906/sag-1809-100
  4. Tufan A, Lachmann HJ. Familial Mediterranean fever, from pathogenesis to treatment: a contemporary review. Turk J Med Sci. 2020;50:1591-1610. doi:10.3906/sag-2008-11
  5. Chaaban A, Salman Z, Karam L, Kobeissy P, Ibrahim J. Updates on the role of epigenetics in familial Mediterranean fever (FMF). Orphanet J Rare Dis. 2024;19:3098. doi:10.1186/s13023-024-03098-w
  6. Maggio MC, Corsello G. FMF is not always “fever”: from clinical presentation to “treat to target”. Ital J Pediatr. 2020;46(1):7. doi:10.1186/s13052-019-0766-z
  7. Aydın F, Özçakar ZB, Yalçınkaya F. Çocuklarda ailesel Akdeniz ateşi tanı ve tedavisi. Turk Klin J Rheumatol Spec Top. 2017;10:46-54.
  8. Güngörer V, Yorulmaz A, Arslan Ş. The effect of gene mutations on disease severity scores in pediatric familial Mediterranean fever patients. Gen Tıp Derg. 2022;32(1):19-26.
  9. Yenigun S, Ayla AY, Baspinar SN, et al. POS1378 Arthritis in patients with familial Mediterranean fever. Ann Rheum Dis. 2022;81(Suppl 1):1073. doi:10.1136/annrheumdis-2022-eular.5337
  10. Sunar-Yayla E, Şenol P, Yıldırım D, Söylemezoğlu O. Chest pain in children with familial Mediterranean fever. Turk J Pediatr. 2023;65(6):973-979. doi:10.24953/turkjped.2023.227
  11. Cekin N, Akyurek M, Pinarbasi E, Ozen F. MEFV mutations and their relation to major clinical symptoms of familial Mediterranean fever. Gene. 2017;626:9-13. doi:10.1016/j.gene.2017.05.013
  12. Keleş A. Derin öğrenme ve sağlık alanındaki uygulamaları. J Turk Stud. 2018;13(21):113-127. doi:10.7827/TurkishStudies.14189
  13. Kaya U, Yılmaz A, Dikmen Y. Sağlık alanında kullanılan derin öğrenme yöntemleri. Avr Bilim Teknol Derg. 2019;16:792-808. doi:10.31590/ejosat.573248
  14. Bhalla S, Laganà A. Artificial intelligence for precision oncology. Adv Exp Med Biol. 2022;1361:249–268. doi:10.1007/978-3-030-91836-1_14
  15. Huang X, Rymbekova A, Dolgova O, Lao O, Kuhlwilm M. Harnessing deep learning for population genetic inference. Nat Rev Genet. 2024;25(1):61-78. doi:10.1038/s41576-023-00636-3
  16. Unger M, Kather JN. Deep learning in cancer genomics and histopathology. Genome Med. 2024;16(1):44. doi:10.1186/s13073-024-01315-6
  17. Deng L. Artificial intelligence in the rising wave of deep learning: the historical path and future outlook. IEEE Signal Process Mag. 2018;35:177-180. doi:10.1109/msp.2017.2762725
  18. Tran KA, Kondrashova O, Bradley A, Williams ED, Pearson JV, Waddell N. Deep learning in cancer diagnosis, prognosis and treatment selection. Genome Med. 2021;13(1):152. doi:10.1186/s13073-021-00968-x
  19. Alarfaj FK, Khan NA, Sulaiman M, Alomair AM. Application of a machine learning algorithm for evaluation of stiff fractional modeling of polytropic gas spheres and electric circuits. Symmetry. 2022;14:2482. doi:10.3390/sym14122482
  20. Mnih V, Kavukcuoglu K, Silver D, et al. Human-level control through deep reinforcement learning. Nature. 2015;518:529-533. doi:10.1038/nature14236
  21. Montesinos-López OA, Montesinos-López A, Pérez-Rodríguez P, et al. A review of deep learning applications for genomic selection. BMC Genomics. 2021;22:19. doi:10.1186/s12864-020-07319-x
  22. Dias R, Torkamani A. Artificial intelligence in clinical and genomic diagnostics. Genome Med. 2019;11:70. doi:10.1186/s13073-019-0689-8
  23. Wen B, Zhang G, Zhan C, Chen C, Yi H. The 2024 revision of the Declaration of Helsinki: a modern ethical framework for medical research. Postgrad Med J. 2025;101(1194):371-382. doi:10.1093/postmj/qgae181
  24. Barış S, Yavaş C, Atan Uzun Ç, Kaya Akca U, Eröz R, Doğan M. Ailesel Akdeniz Ateşi hastalarının MEFV gen mutasyon tiplerinin sıklığı ve hastalarda gen mutasyonu ile klinik bulgular arasındaki ilişkilerin değerlendirilmesi. Dicle Med J. 2023;50(4):545-552. doi:10.5798/dicletip.1412077
  25. Gattorno M, Hofer M, Federici S, et al. Classification criteria for autoinflammatory recurrent fevers. Ann Rheum Dis. 2019;78(8):1025-1032. doi:10.1136/annrheumdis-2019-215048
  26. Wekesa JS, Kimwele M. A review of multi-omics data integration through deep learning approaches for disease diagnosis, prognosis, and treatment. Front Genet. 2023;14:1199087. doi:10.3389/fgene.2023.1199087
  27. Ocak T, Görünen A, Coşkun BN, et al. Pan-immune-inflammation value could be a new marker to predict amyloidosis and disease severity in familial Mediterranean fever. Diagnostics (Basel). 2024;14(6):634. doi:10.3390/diagnostics14060634
  28. Çakar A, Saka Baraz L, Yalçın Kehribar D, Özgen M. The evaluation of health status of familial Mediterranean fever patients with homozygous M694V mutation. Rheumatol Q. 2025;3(3):79-83. doi:10.4274/qrheumatol.galenos.2025.58070
  29. Sezer M, Çelikel E, Ekici Tekin Z, et al. The effect of E148Q variant on disease severity in familial Mediterranean fever patients with compound heterozygous mutation. Pediatr Pract Res. 2023;11(3):111-115.
  30. Ito M, Nobata H, Imai H, et al. Familial Mediterranean fever type 2 with heterozygous mutations of E148Q and M694I in a Japanese patient with progressive systemic AA amyloidosis. Mod Rheumatol Case Rep. 2019;3(1):79-85. doi:10.1080/24725625.2018.1527000
  31. Dundar M, Fahrioglu U, Yildiz SH, et al. Clinical and molecular evaluation of MEFV gene variants in the Turkish population: a study by the National Genetics Consortium. Funct Integr Genomics. 2022;22(3):291-315. doi:10.1007/s10142-021-00819-3
  32. Talaat HS, Sheba MF, Mohammed RH, Gomaa MA, Rifaei NE, Ibrahim MFM. Genotype mutations in Egyptian children with familial Mediterranean fever: clinical profile and response to colchicine. Mediterr J Rheumatol. 2020;31(2):206-213. doi:10.31138/mjr.31.2.206
  33. Arpacı A, Doğan S, Erdoğan HF, El Ç, Elmacıoğlu Cura S. Presentation of a new mutation in FMF and evaluating the frequency of distribution of the MEFV gene mutation in our region with clinical findings. Mol Biol Rep. 2021;48(3):2025-2033. doi:10.1007/s11033-020-06040-y
  34. Manna R, Rigante D. Familial Mediterranean fever: assessing the overall clinical impact and formulating treatment plans. Mediterr J Hematol Infect Dis. 2019;11(1):e2019027. doi:10.4084/MJHID.2019.027
  35. Ülgenalp A. DEGETAM’a Yönlendirilen Hastalardaki MEFV Geni Mutasyonlarının Dağılımı. DEU Tıp Derg. 2009;23(2):53-58.
  36. Aksoy R, Us E, Farhoomand Aksoy D, Dumlupınar E, Turgay TM. Molecular analyses of MEFV gene mutation variants in Turkish population. Mol Biol Rep. 2024;51:844. doi:10.1007/s11033-024-09786-x
  37. Demir AY, Admış Ö. MEFV gene mutations in familial Mediterranean fever patients: Erzincan experience. Erzincan Univ J Sci Technol. 2024;17(2):377-384. doi:10.18185/erzifbed.1432743
  38. Mezher N, Mroweh O, Karam L, Ibrahim JN, Kobeissy PH. Experimental models in familial Mediterranean fever (FMF): insights into pathophysiology and therapeutic strategies. Exp Mol Pathol. 2024;135:104883. doi:10.1016/j.yexmp.2024.104883
  39. Ahmed M, Henawy O, Elshennawy E, Mahros A. Clinical and genetic characterization of familial Mediterranean fever among a cohort of Egyptian patients. Prz Gastroenterol. 2022;17:240-244. doi:10.5114/pg.2022.118595
  40. Adato O, Brenner R, Levy A, et al. Determining the origin of different variants associated with familial Mediterranean fever by machine learning. Sci Rep. 2022;12:15206. doi:10.1038/s41598-022-19538-1
  41. Karaer Büberci R, Duranay M, Karahisar S. Ailevi akdeniz ateşi hastalarında klinik gidişatın MEFV gen mutasyonlarıyla olan ilişkisi. Ankara Eğit Arast Hast Tip Derg. 2022;55(1):9-12. doi:10.20492/aeahtd.917017
  42. Urgancı N, Ozgenc F, Kuloğlu Z, et al. Familial Mediterranean Fever mutation analysis in pediatric patients with inflammatory bowel disease: a multicenter study. Turk J Gastroenterol. 2021;32(3):248-250. doi:10.5152/tjg.2021.20057
  43. Yildirim ME, Kurtulgan HK, Ozdemir O, et al. Prevalence of MEFV gene mutations in a large cohort of patients with suspected familial Mediterranean fever in Central Anatolia. Ann Saudi Med. 2019;39(6):382-387. doi:10.5144/0256-4947.2019.382
  44. Özlü SG, Ergüven M, Hamzah ÖY. Genotype and phenotype correlations in children with familial Mediterranean fever. Turk J Pediatr Dis. 2015;3:171-175. doi:10.12956/tjpd.2015.151