HYPOTHYROIDI AND HYPERTHYROIDI DETECTION FROM THYROID HORMONE PARAMETERS BY USING DECISION TREES

Abstract

In this study a decision support system has been projected from the biochemistry blood parameters which will be very helpful and will make everything easier for the physicians in the diagnosis of Hyperthyroidi and Hypothyroidi. Based on pattern recognition process, the system operation is achieved via the decision trees structure which is related as one of the data mining techniques. The basic characteristic of the thyroid hormone parameters that is, TSH, FT3, FT4, TT3 and TT4 parameters are used in the process of entering the system and finally Hyper(+), Hypo(+) and (-) results have been evaluated at the end of this process. Data of 120 patients are evaluated in the projected system. The results of the decision support system have completely matched with those of the physicians’ decisions.

Keywords

• Pattern Recognition,Data Mining,Decision Trees,Tyhroid Hormones,Expert System

KARAR AĞACI YÖNTEMİNİ KULLANARAK TİROİD HORMON PARAMETRELERİNDEN HİPERTİROİDİ VE HİPOTİROİDİ TEŞHİSİ

Öz

Bu çalışmada, biyokimya test sonuçlarından Hipertiroidi ve Hipotiroidi teşhisinde, hekime yardımcı olacak ve kolaylık sağlayacak bir karar destek sistemi tasarlanmıştır. Örüntü tanıma süreci esas alınmış olup, siste-min işleyişi veri madenciliği tekniklerinden olan karar ağaçları yapısı ile sağlanmaktadır. Sisteme giriş olarak, tiroid hormonlarından temel belirleyiciler olan TSH, FT3, FT4, TT3, TT4 parametreleri kullanılarak, çıkış olarak ta Hiper(+), Hipo(+) ve (-) değerlendirmelerin de bulunulmuştur. Tasarlanan sistemde 120 hasta verisi değerlendirilmiştir. Karar destek sisteminin sonuçları, doktorun verdiği kararlarla tamamen örtüşmüş-tür.

Anahtar Kelimeler

• Örüntü Tanıma,Veri Madenciliği,Karar Ağacı,Tiroid Hormonları,Uzman Sistemler

References

1. 1. H. Kucukyilmaz, Y. Tutuncu, etc. The relation between pulmonary hypertension, hypothyroidism and hyperthyroidism, Journal of Ankara University Faculty of Medicine, 58:3033, (2005).
2. 2. Internet:http://www.hormonlar.com/tiroid1.html, (Mayıs 2006).
3. 3. M. Ozata, Everything about thyroid, Epsilon Press, (2005).
4. 4. Internet:http://www.hormonlar.com/tiroid2.html, (Mayıs 2006).
5. 5. C. M. Dayan, Interpretation of thyroid function tests. Lancet Vol 357; pp 619-624, (2001)
6. 6. D. Aras, O. Maden, etc. Simple electrocardiographic markers for the prediction of paroxysmal atrial fibrillation in hyperthyroidism, International Journal of Cardiology 99, 59– 64, (2005).
7. 7. A.Y.W. Chan, R. Shinde, etc. Platelet Na+,K+-Adenosine Triphosphatase as a Tissue Marker of Hyperthyroidism, Metabolism, Vol 50, No 12 (December), pp 1393-1396, (2001).
8. 8. W. Y. Lee, K. W. Oh, etc. Relationship between Subclinical Thyroid Dysfunction and Femoral Neck Bone Mineral Density in Women, Archives of Medical Research 37, 511–516, (2006).

9. 9. F. Demirel, A. Bideci, etc. Hypothyroidism Developing In Adolescent Girls Who Lost Weight With Inappropriate Diets, Sted 14, No 8, 188–191, (2006).
10. 10. J. Barrera, R.M. Cesar-Jr, etc. An Environment For Knowledge Discovery in Biology, Computers in Biology and Medicine 34, 427–447, (2003).
11. 11. V. Podgorelec, P. Kokol, etc. Knowledge Discovery with Classification Rules in a Cardiovascular Dataset, Computer Methods and Programs in Biomedicine 80 Suppl. 1, S39-S49, (2005).
12. 12. C. C. Bojarczuk, H. S. Lopes, etc. A Constrained-Syntax Genetic Programming System for Discovering Classification Rules: Application to Medical Data Sets, Artificial Intelligence in Medicine 30, 27–48, (2004).
13. 13. Internet:www.hastarehberi.com/article_read.asp?id= 153 9 -40k, (March 2006).
14. 14. M. M. Yin, & J. T. L. Wang, GeneScout: a Data Mining System For Predicting Vertebrate Genes in Genomic DNA Sequences, Information Sciences 163, 201–218, (2003).
15. 15. J. M. Ayub, C. R. Smulski, etc. Protein–Protein İnteraction Map of the Trypanosoma Cruzi Ribosomal P Protein Complex, Gene 357, 129 – 136, (2005).
16. 16. R. J. Shebuski, Utility of Point-of-Care Diagnostic Testing in Patients with Chest Pain and Suspected Acute Myocardial Infarction, Current Opinion in Pharmacology, 2:160–164, (2002).
17. 17. I. Turkoglu, A. Arslan, etc. “An Intelligent System for Diagnosis of Heart Valve Diseases with Wavelet Packet Neural Networks”, Computer in Biology and Medicine, 33(4), 319-331, (2003).
18. 18. K.C. Tan, Q. Yu, etc. Evolutionary Computing for Knowledge Discovery in Medical Diagnosis, Artificial Intelligence in Medicine 27, 129–154, (2002).
19. 19. CD. Cooke, CA. Santana, etc. Validating Expert System Rule Confidences Using Data Mining of Myocardial Perfusion SPECT Databases, Computers in Cardiology, 27: 785–788, (2000).
20. 20. T. Unger, Z. Korade, etc. True and False Discovery in DNA Microarray Experiments: Transcriptome Changes in the Hippocampus of Presenilin 1 Mutant Mice, Methods 37, 261–273, (2005).
21. 21. M. J. Huang, M. Y. Chen, etc. Integrating Data Mining with Case-Based Reasoning for Chronic Diseases Prognosis and Diagnosis, Expert Systems with Applications, (2006).
22. 22. A. Kusiak, C. A. Caldarone, etc. Hypoplastic Left Heart Syndrome: Knowledge Discovery with a Data Mining Approach, Computers in Biology and Medicine 36, 21–40, (2006).
23. 23. I. M. Mullins, M. S. Siadaty, etc. Data Mining and Clinical Data Repositories: Insights from a 667,000 Patient Data Set, Computers in Biology and Medicine (2005).
24. 24. I. Turkoglu, A. Arslan, etc. “An Expert System for Diagnose of The Heart Valve Diseases”, Expert Systems with Applications, 23(3), 229-236, (2002).
25. 25. C.M. Bishop, Neural Networks for Pattern Recognition, Clarendon Press, Oxford, (1996).
26. 26. F. Fischbach, A Manual of Laboratory & Diagnostic Tests, Lippincott, New York, (2000).
27. 27. M. Zaki, Scalable Data Mining for Rules, University of Rochester, New York U.S.A., (1998).
28. 28. F. Alonso, J. P. Caraça-Valente, etc. Combining Expert Knowledge and Data Mining in a Medical Diagnosis Domain, Expert Systems with Applications 23, 367-375, (2002).
29. 29. N. Allahverdi, A artifical intelligence application with expert systems, Satin Publication Distribution, Istanbul, (2002).
30. 30. G. S. Oger, The use of data mining for the diagnosis of osteoporos disease, Firat University, Msc Thesis, (2003).
31. 31. Internet: Data mining, mf.kou.edu.tr/bilgisayar/ nduru/Ch1.doc, (March 2005).
32. 32. R. Agrawal, M. Mehta, etc. The Quest Data Mining System, IBM Almaden Research Center San Jose 6s California, U.S.A., (1996).
33. 33. Information discovery in databases and data mining, I. U. The school of business administration magazine, C:29, S: 1, (April 2000).
34. 34. Internet: Information Management, Data mining and information discovery, http://www.bilgiyonetimi.org/cm/pages/mkl_gos.php?nt=538, (March 2000).
35. 35. SPSS Inc. AnswerTree 2.0 User’s Guide, 1998, ISBN 1-56827-254-5, (1998).
36. 36. O. Hogl, M. Müller, etc. On Supporting Medical Quality with Intelligent Data Mining, Proceedings of the 34th Hawaii International Conference on System Sciences, (2001).
37. 37. A. Kusiak, B. Dixon, etc. Predicting Survival time for Kidney Dialysis Patients: a Data Mining Approach, Computers in Biology and Medicine 35, 311–327, (2005).