CLASSIFICATION OF FIBROMYALGIA SYNDROME WITH SUPPORT VECTOR MACHINES

Year 2017, Volume: 1 Issue: 2, 92 - 98, 29.12.2017

Cemile Zontul Emrullah Hayta , Metin Zontul , Ayça Taş , Yavuz Siliğ

Abstract

Fibromyalgia
syndrome (FMS) is a long-term common body pain and a defined chronic pain
syndrome. Fibromyalgia syndrome is a difficult disease to diagnose. For this
reason, after many unnecessary treatments are applied to the patient, the
diagnosis of FMS is usually delayed by clinical examination and evaluation of
the patient's complaints. In this respect, there is a need for a decision
support system that will facilitate the diagnosis of FMS. In this study, by
using the questions asked 351 respondents, 175 FSM patients and 176 healthy
control subjects and experimental data, FMS classification was performed with
Support Vector Machines which is one of machine learning methods and 85%
success was achieved.

Keywords

Fibromyalgia Syndrome, Support Vector Machines, Classification, Health Decision Support System

DESTEK VEKTÖR MAKİNELERİ İLE FİBROMİYALJİ SENDROMU SINIFLAMASI

Abstract

Fibromiyalji sendromu (FMS), uzun süreli yaygın vücut
ağrısı ve tanımlanmış kronik bir ağrı sendromudur. Fibromiyalji Sendromu tanısı
konulması zor bir hastalıktır. Bu sebeple, genellikle FMS tanısı, hastaya
gereksiz birçok tedavi uygulandıktan sonra, klinik muayene ve hastanın
yakınmalarının değerlendirilmesi ile geçikmeli olarak konulur. Bu açıdan FMS
teşhisini kolaylaştıracak bir karar destek sistemine ihtiyaç vardır. Bu
çalışmada, 175 FSM hastası ve 176 sağlıklı kontrol bireyi olmak üzere toplam
351 bireye sorulan sorular ve deneysel veriler kullanılarak makine öğrenmesi
yöntemlerinden Destek Vektör Makineleri ile FMS sınıflaması yapılmış ve yüzde
85 başarı elde edilmiştir.

Keywords

Fibromiyalji Sendromu, Destek Vektör Makineleri, Sınıflama, Sağlık Karar Destek Sistemi

References

• [1] Adler, G.K. Manfredsdottir V.F., and Creskoff K.W. 2002 "Neuroendocrine abnormalities in fibromyalgia".Current pain and headache reports. 6: 289-298.
• [2] Marcus, DA. A Primary Care Guide to Practical Management. In Chronic Pain pp 15-30. PA Human Pres. Pain Institute, University of Pittsburgh, Pittsburgh.2005 .
• [3] Yılmaz, H. Uğurlu H., and Sallı A. 2007 "Fibromiyalji Sendromlu Hastalarda Kas Performansı".Romatizma/Rheumatism. 22.
• [4] McBeth J. and Jones K. 2007 "Epidemiology of chronic musculoskeletal pain".Best practice & research Clinical rheumatology. 21: 403-425.
• [5] Guleç, H. Sayar K., and Guleç M.Y. 2007 "The Relationship Between Psychological Factors and Health Care-Seeking Behavior in Fibromyalgia Patients".
• [6] Neumann L. and Buskila D. 2003 "Epidemiology of fibromyalgia".Current pain and headache reports. 7: 362-368.
• [7] Buskila, D. et al., Familial aggregation in the fihromyalgia syndrome, in Seminars in arthritis and rheumatism. Elsevier, 1996 605-611.
• [8] Kato, K. et al. 2006 "Importance of genetic influences on chronic widespread pain".Arthritis & Rheumatology. 54: 1682-1686.
• [9] Robinson, M.E. et al. 2015 "Comparison of machine classification algorithms for fibromyalgia: neuroimages versus self-report".The Journal of Pain. 16: 472-477.
• [10] Sevel, L. et al. 2016 "MRI based classification of chronic fatigue, fibromyalgia patients and healthy controls using machine learning algorithms: a comparison study". The Journal of Pain. 17: S60.
• [11] Katz, J.D. et al. 2010 "Gender bias in diagnosing fibromyalgia".Gender medicine. 7: 19-27.
• [12] Stringer, E. et al. 2013 "Daily cytokine fluctuations distinguish high pain from low pain days in women with fibromyalgia". The Journal of Pain. 14: S50.