Medical Informatics III

EnglishTürkçe

CHAPTER


DOI :10.26650/B/ET07.2023.005.18   IUP :10.26650/B/ET07.2023.005.18    Full Text (PDF)

A Clinical Decision Support System for Early Diagnosis of Behçet’s Disease

Leili Nozaddızaji, Feyza Nur Tuncer Kılınç, Bekir Sıddık Binboga Yarman

Behçet’s disease (BD) is an inflammatory disorder that belongs to the primary systemic vasculitic syndromes and affects all types of vessels and sizes. BD in Turkey has the highest incidence among other countries (between 20 up to 420 per 100,000 people). It is identified with four major symptoms: oral and genital ulcers, skin lesions and ocular lesions. Additional symptoms include vascular, gastrointestinal, and neurological involvement. Since no definitive test is available for BD, general basis for detection of this disorder is looking for physical manifestations. As time progresses the symptoms get worse, Therefore, early detection of the disease is important and could make patients’ condition less painful. In the past few decades, with the development of technology, several clinical decision support systems have been introduced for helping physicians in the process of making decisions about a disease. In this study, we aim to create a stationary linear stochastic system model based on Bayes’ theorem and propose a reliable clinical decision support system for early diagnosis of BD. This CDSS-tool is established with relevant historical data gathered from symptoms of patients suffering from Behçet’s syndromes. Symptoms are defined through precise classification of sets of properties, which are mutually exclusive and complete sets in order to define the disease under consideration. By executing the model in MATLAB programming environment, we will create a decision support tool that is able to detect BD cases. The system requires symptoms of suspicious cases. It registers the availability of a symptom by means of yes or 1 and the absence of a symptom via no or 0 as input and compute the chance of the pertinent illness in the subject as output. If the patient matches with a comprehensive CDSS tool, they will have a chance of early detection of their condition and be directed to rheumatologist.


Keywords: Behçet’s disease, symptom, decision support systems, early diagnosis
DOI :10.26650/B/ET07.2023.005.18   IUP :10.26650/B/ET07.2023.005.18    Full Text (PDF)

Behçet Hastalığının Erken Teşhisi İçin Semptoma Dayalı Klinik Karar Destek Sistemi

Leili Nozaddızaji, Feyza Nur Tuncer Kılınç, Bekir Sıddık Binboga Yarman

Behçet hastalığı (BH), primer sistemik vaskülitik sendromlara ait olan ve her tür damarı ve boyutu etkileyen enflamatuar bir hastalıktır. Türkiye’de BH, diğer ülkeler arasında en yüksek insidansa sahiptir (100.000 kişi başına 20 ila 420 vaka). BH, Dört ana semptomla tanımlanır: oral ve genital ülserler, cilt lezyonları ve oküler lezyonlar. Ek semptomlar, vasküler, gastrointestinal ve nörolojik tutulumu içerir. Hastalığın teşhisi için kesin bir test olmadığından, teşhis fiziksel belirtilere dayanmaktadır. Zaman geçtikçe fiziksel semptomlar kötüleşmekte ve şiddetlenmektedir. Bu nedenle, hastalığın erken teşhisi önemlidir ve BH hastalarının yaşam kalitesini artırabilmektedir. Günümüzde çeşitli hastalıkların erken teşhisi için klinik karar destek sistemi (KKDS) geliştirmeye odaklanan çeşitli çalışmalar yapılmaktadır, KKD sistemleri, hastaya özel değerlendirmeler veya öneriler sağlayan hasta verilerini kullanarak tıbbi karar vermeye yardımcı olmaktadırlar. KKDS insan gibi düşünmek üzerine tasarlanmıştır ve karar desteği amacıyla çeşitli hastalıklar için oluşturulmuş birçok klinik destek sistemi vardır. Bu sistemler Diş Eğitimi, Ventilatör tedavisi, Kanser Teşhisi, Kanser Tedavisi, Kalp Hastalıkları ve Kalp Yetmezliği Teşhisi ve daha birçok alanda kullanılmaktadır Bu çalışmada, Behçet hastalığının ön tanısında kullanılmak üzere BH şüphesi olan hastalar için Bayes’ teoremine ve koşullu olasılığa dayalı bir matematiksel model geliştirmeyi amaçladık. Modeli MATLAB programında gerçekleştirerek, BH vakalarını fiziksel semptomlara göre tespit edebilen bir klinik karar destek sistemi oluşturduk. Sistem şüpheli vakaların belirtilerini gerektirir. Girdi olarak evet veya 1 aracılığıyla bir semptomun varlığını ve hayır veya 0 aracılığıyla bir semptomun yokluğunu kaydeder ve çıktı olarak kişinin ilgili hastalığın olasılığını hesaplar. Önerdiğimiz sistemin, BH vakalarını yüksek sıklıkta tespit edebildiğini gösterdik. Bu sistemle, şüpheli hasta durumunu erken tespit etme şansına sahip olacak ve romatoloğa yönlendirilecektir.


Keywords: Behçet hastalığı, karar destek sistemleri, erken tanı

References

  • Al-Hyari, A.Y., Al-Taee, A.M., & Al-Taee, M.A. (2013). Clinical decision support system for diagnosis and management of Chronic Renal Failure. 2013 IEEE Jordan Conference on Applied Electrical Engineering and Computing Technologies (AEECT), 1-6. google scholar
  • Anaya, J. M., Shoenfeld, Y., Rojas-Villarraga, A., Levy, R. A., & Cervera, R. (Eds.) (2013). Autoimmunity: From Bench to Bedside. El Rosario University Press. google scholar
  • Ball G V, Fessler B J, Bridges S L, editor, 2014 Oxford Textbook of Vasculitis, England: Oxford University Press; 2014 google scholar
  • Banos F J, Acute severe ulcerative colitis: Case report and literature review. Rev Col Gastroenterol; 27: 317-322 google scholar
  • Berner ES, La Lande TJ. (2007) Clinical Decision Support Systems: Theory and Practice. 2.Overview of clinical decision support systems; Springer; NewYork: pp. 3-22 google scholar
  • Bishop C. M. (2007) Pattern recognition and machine learning, New York : Springer google scholar
  • Brahim, A., Jennane, R., Riad, R., Janvier, T., Khedher, L., Toumi, H., & Lespessailles, E. (2019). A decision support tool for early detection of knee OsteoArthritis using X-ray imaging and machine learning: Data from the OsteoArthritis Initiative. Computerized medical imaging and graphics : the official journal of the Computerized Medical Imaging Society, 73, 11-18. https://doi.org/10.1016/j.compmedimag.2019.01.007 google scholar
  • Duda RO, Hart PE.(2001). Pattern Classification. New York: Wiley-Interscience google scholar
  • Ferizi, M., Gerqari, A., & Ferizi, M. (2018). Behcet’s Disease - Case Presentation and Review Literature. Open access Macedonian journal of medical sciences, 6(10), 1871-1874. https://doi.org/10.3889/oamjms.2018.393 google scholar
  • G. Parthiban, S.K. Srivatsa.(2011). “Diagnosis of heart disease for diabetic patients using naive bayes method”, Int. J. Comput. Appl; 24(3), pp. 7-11 google scholar
  • Greco, A., De Virgilio, A., Ralli, M., Ciofalo, A., Mancini, P., Attanasio, G., de Vincentiis, M., & Lambiase, A. (2018). Behcet’s disease: New insights into pathophysiology, clinical features and treatment options. Autoimmunity reviews, 17(6), 567-575. https://doi.org/10.1016/j.autrev.2017.12.006 google scholar
  • Hugle M, Omoumi P.(2020) Applied machine learning and artificial intelligence in rheumatology. Rheumatol Adv Pract. 4(1):rkaa005. doi:10.1093/rap/rkaa005 google scholar
  • Jayachandran, N. V., Rajasekhar, L., Chandrasekhara, P. K., Kanchinadham, S., & Narsimulu, G. (2008). Multiple peripheral arterial and aortic aneurysms in Behcet’s syndrome: a case report. Clinical rheumatology, 27(2), 265-267. https://doi.org/10.1007/s10067-007-0713-z google scholar
  • Jennette, J. C., Falk, R. J., Bacon, P. A., Basu, N., Cid, M. C., Ferrario, F., Flores-Suarez, L. F., Gross, W. L., Guillevin, L., Hagen, E. C., Hoffman, G. S., Jayne, D. R., Kallenberg, C. G., Lamprecht, P., Langford, C. A., Luqmani, R. A., Mahr, A. D., Matteson, E. L., Merkel, P. A., Ozen, S., ... Watts, R. A. (2013). 2012 revised International Chapel Hill Consensus Conference Nomenclature of Vasculitides. Arthritis and rheumatism, 65(1), 1-11. https://doi.org/10.1002/art.37715 google scholar
  • Johnson S R, Tomlinson G, et al.(2018) Applied Bayesian Methods in the Rheumatic Diseases. Rheum. Dis. Clin. N. Am. DOI: 10.1016/j.rdc.2018.01.003. google scholar
  • Keltch B, Lin Y, Bayrak C.(2014) Comparison of AI techniques for prediction of liver fibrosis in hepatitis patients. J Med Syst.38(8):60. doi:10.1007/s10916-014-0060-y google scholar
  • Kubben P, Dumontier M, Dekker A.(2019). Fundamentals of Clinical Data Science. Cham (CH): Springer google scholar
  • Kulaber A, Tugal-Tutkun I, Sibel P, Akman-Demir G, Kaneko F, Gul A, Saruhan G.(2007). Proinflammatory cellular immune response in Behcet’s disease. Rheumatol Int. 27:1113-8. doi:10.1007/s00296-007-0367-9 google scholar
  • Lehmann CU, Seroussi B, et al. Troubled waters: navigating unintended consequences of health information technology. Yearb Med Inform. 2016;1:5-6. google scholar
  • Lin, C., Karlson, E. W., Canhao, H., Miller, T. A., Dligach, D., Chen, P. J., Perez, R. N., Shen, Y., Weinblatt, M. E., Shadick, N. A., Plenge, R. M., & Savova, G. K. (2013). Automatic prediction of rheumatoid arthritis disease activity from the electronic medical records. PloS one, 8(8), e69932. https://doi.org/10.1371/journal.pone.0069932 google scholar
  • Magrabi, F., Ammenwerth, E., Hypponen, H., de Keizer, N., Nykanen, P., Rigby, M., Scott, P., Talmon, J., & Georgiou, A. (2016). Improving Evaluation to Address the Unintended Consequences of Health Information Technology:. a Position Paper from the Working Group on Technology Assessment & Quality Development. Yearbook of medical informatics, (1), 61-69. https://doi.org/10.15265/IY-2016-013 google scholar
  • Musen MA, Shahar Y.(2014). Clinical decision-support systems. In: Shortliffe EH, Cimino JJ, editors. Biomedical informatics: computer applications in health care and biomedicine. (4th ed). New York: Springer; pp. 643-674 google scholar
  • Nebeker, J. R., Hoffman, J. M., Weir, C. R., Bennett, C. L., & Hurdle, J. F. (2005). High rates of adverse drug events in a highly computerized hospital. Archives of internal medicine, 165(10), 1111-1116. https://doi. org/10.1001/archinte.165.10.1111. google scholar
  • Pavlidis T, (1977) Structural pattern recognition, New York: Springer google scholar
  • Pawloski, P. A., Brooks, G. A., Nielsen, M. E., & Olson-Bullis, B. A. (2019). A Systematic Review of Clinical Decision Support Systems for Clinical Oncology Practice. Journal of the National Comprehensive Cancer Network : JNCCN, 17(4), 331-338. https://doi.org/10.6004/jnccn.2018.7104 google scholar
  • Pay S, Simsek I, Erdem H, Dinc A. (2007) Immunopathogenesis of Behcet’s disease with special emphasize to the possible role of antigen presenting cells. Rheumatol Int.; 27:417-24. doi:10.1007/s00296-006-0281-6 google scholar
  • Powley L, McIlroy G. (2016) Are online symptoms checkers useful for patients with inflammatory arthritis? BMC Musculoskelet Disord. 17:362 google scholar
  • Subbalakshmi G, Ramesh K, Chinna M.(2011). Decision support in heart disease prediction system using naive bayes. Ind. J. Comput. Sci. Eng. (IJCSE), 2(2), 170-176 google scholar
  • Vodencarevic, A., Goes, M.C., Medina, O., Groot, M.D., Haitjema, S., Solinge, W.W., Hoefer, I.E., Peelen, L.M., Laar, J.M., Zimmermann-Rittereiser, M., Hamans, B.C., & Welsing, P.M. (2018). Predicting Flare Probability in Rheumatoid Arthritis using Machine Learning Methods. International Conference on Data Technologies and Applications. google scholar
  • Gokbay, I, Zileli, Z, Sari, P, Aksoy, T , Yarman, S.B. (2018)., An Intelligent Decision Support Tool for Early Diagnosis of Functional Pituitary Adenomas, TWMS J. of Apl. & Eng. Math. 5: 169-187 google scholar
  • Yazici Y, Hatemi G, Seyahi E, Yazici H. (2020) Behçet Syndrome. second edition, Switzerland: Springer, Cham google scholar
  • Zhou, S-M., Fernandez-Gutierrez, F., Kennedy, J., Cooksey, R., Atkinson, M., Denaxas, S., Siebert, S., Dixon, W. G., O’Neill, T. W., Choy, E., Sudlow, C., UK Biobank Follow-up and Outcomes Group, Brophy, S., & Sullivan, F. (2016). Defining disease phenotypes in primary care electronic health records by a machine learning approach: a case study in identifying rheumatoid arthritis. PLoS One, 11(5), [e0154515]. https:// doi.org/10.1371/journal.pone.0154515 google scholar


SHARE




Istanbul University Press aims to contribute to the dissemination of ever growing scientific knowledge through publication of high quality scientific journals and books in accordance with the international publishing standards and ethics. Istanbul University Press follows an open access, non-commercial, scholarly publishing.