Mobile Diagnosis of Thyroid based on Ensemble Classifier

Abstract

The thyroid gland plays a major role in many metabolic activities of the human body. Thyroid disease, which is quite common in humans, affects people's quality of life significantly. Early diagnosis is very important for taking precautions. The mobile diagnostic system can be the solution for early diagnosis especially in rural areas or without going to health institution. This study has been proposed to enable people with mobile devices to obtain quick information about the disease or to seek medical assistance in any matter without going to the hospital. Functional thyroid diagnosis system is designed using mobile device, Android based software application, Database (SQL) and Server (MATLAB based decision algorithms). With the system, functional thyroid disease can be diagnosed using an android based mobile device. Different classification algorithms were searched for the most accurate diagnosis and Ensemble method which has a high success rate for thyroid disease was used in the system. Ensemble classification technique reached a success rate of 99.06% and 99.08% for the first and second data group, respectively. These success rates were calculated by using gold standard test and results were compared with the literature. Obtained test results showed that, the proposed mobile diagnosis system could be used for the diagnosis of the functional thyroid. At the same time, this system can be developed for different diseases.

Keywords

• Thyroid
• Mobile Diagnosis
• Ensemble Classifier
• SQL Server
• MATLAB

Mobile diagnosis of thyroid based on ensemble classifier

Öz

The thyroid gland plays a major role in many metabolic activities of the human body. Thyroid disease,
which is quite common in humans, affects people's quality of life significantly. Early diagnosis is very
important for taking precautions. The mobile diagnostic system can be the solution for early diagnosis
especially in rural areas or without going to health institution. This study has been proposed to enable
people with mobile devices to obtain quick information about the disease or to seek medical assistance in
any matter without going to the hospital. Functional thyroid diagnosis system is designed using mobile
device, Android based software application, Database (SQL) and Server (MATLAB based decision
algorithms). With the system, functional thyroid disease can be diagnosed using an android based mobile
device. Different classification algorithms were searched for the most accurate diagnosis and Ensemble
method which has a high success rate for thyroid disease was used in the system. Ensemble classification
technique reached a success rate of 99.06% and 99.08% for the first and second data group, respectively.
These success rates were calculated by using gold standard test and results were compared with the
literature. Obtained test results showed that, the proposed mobile diagnosis system could be used for the
diagnosis of the functional thyroid. At the same time, this system can be developed for different diseases.

Anahtar Kelimeler

• Thyroid
• Mobile Diagnosis
• Ensemble Classifier
• SQL Server
• MATLAB

References

1. Electronic Mobile Health https://www.healthparliament.eu/wpcontent/upload s/2017/09/Electronic_mobile-health.pdf/19.09.2019
2. J. John, & C. Raju, (2018), “Design and Comparative Analysis of Mobile Computing Software Framework,” 2018 Second International Conference on Inventive Communication and Computational Technologies (ICICCT). doi:10.1109/icicct.2018.8473350. 978-1-5386-1974-2/18/$31.00 ©2018 IEEE.
3. A. Uçar, & R. Özalp, (2017), “Efficient android electronic nose design for recognition and perception of fruit odors using Kernel Extreme Learning Machines,” Chemometrics and Intelligent Laboratory Systems, vol. 166, pp 69–80. doi:10.1016/j.chemolab.2017.05.013.
4. S. A. Tuncer and A. Alkan, "Segmentation of thyroid nodules with K-means algorithm on mobile devices," 2015 16th IEEE International Symposium on Computational Intelligence and Informatics (CINTI), Budapest, 2015, pp. 345-348.
5. S. A. Tuncer and A. Alkan, "Abdominal image segmentation on Android based mobile devices," 2014 22nd Signal Processing and Communications Applications Conference (SIU), Trabzon, 2014, pp. 806-809.
6. M. F. Amasyali, (2013), “A semi-random subspace method for classification ensembles,” 21st Signal Processing and Communications Applications Conference (SIU). doi:10.1109/siu.2013.6531301. 978-1-4673-5563- 6/13/$31.00 ©2013 IEEE.
7. A. Maniakas, L. Davies, & M. E. Zafereo, (2018), “Thyroid Disease Around the World,” Otolaryngologic Clinics of North America, vol 51(3), pp 631–642. doi:10.1016/j.otc.2018.01.014.
8. J. Longbottom & R. Macnab, (2014), “Thyroid disease and thyroid surgery,” Anaesthesia & Intensive Care Medicine, vol. 15(10), pp 458–464. doi:10.1016/j.mpaic.2014.07.006

9. H. Kaneko, (2018), “Automatic outlier sample detection based on regression analysis and repeated ensemble learning,” Chemometrics and Intelligent Laboratory Systems, vol. 177, pp 74–82.
10. M. Hosni, I. Abnane, A. Idri, J. M. C. de Gea, & J. L. F. Alemán, (2019), “Reviewing Ensemble Classification Methods in Breast Cancer”, Computer Methods and Programs in Biomedicine. doi:10.1016/j.cmpb.2019.05.019.
11. U. Agrawal, D. Soria, C. Wagner, J. Garibaldi, I. O. Ellis, J. M. S. Bartlett, A. R. Green, (2019), “Combining Clustering and Classification Ensembles: A Novel Pipeline to Identify Breast Cancer Profiles.” Artificial Intelligence in Medicine. doi:10.1016/j.artmed.2019.05.002.
12. Y. He, D. Chen, W. Zhao, (2006), “Ensemble classifier system based on ant colony algorithm and its application in chemical pattern classification, Chemometrics and Intelligent Laboratory Systems, vol. 80, pp. 39 – 49.
13. M. Czajkowski & M. Kretowski, (2019), “Decision Tree Underfitting in Mining of Gene Expression Data An Evolutionary Multi-Test Tree Approach,” Expert Systems with Applications. doi:10.1016/j.eswa.2019.07.019.
14. H. Sun, & X. Hu, (2017), “Attribute selection for decision tree learning with class constraint,” Chemometrics and Intelligent Laboratory Systems, 163, 16–23. doi:10.1016/j.chemolab.2017.02.004
15. N. Cerpa, M. Bardeen, C. A. Astudillo & J. Verner, (2016), “Evaluating different families of prediction methods for estimating software project outcomes,” Journal of Systems and Software, 112, 48–64. doi:10.1016/j.jss.2015.10.011.
16. H. Sun & X. Hu (2017), “Attribute selection for decision tree learning with class constraint.” Chemometrics and Intelligent Laboratory Systems, 163, 16–23. doi:10.1016/j.chemolab.2017.02.004.
17. Thyroid diseases diagnosis, treatment and follow-up guide, Turkey Endocrinology and Metabolism Society, ISBN No: ISBN: 978-605-4011-37-7, 2019.
18. https://www.statisticshowto.datasciencecentral.com/ gold-standard-test/Accessed 20/09/2019.
19. G. Serpen, H. Jiang, L. Allred, (1997), “Performance analysis of probabilistic potential function neural network classifier,” In Proceedings of artificial neural networks in engineering conference, St. Louis, MO, 7, pp. 471–476.
20. L. Ozyilmaz, T. Yildirim, (2002), “Diagnosis of thyroid disease using artificial neural network methods,” In Proceedings of ICONIP’02 nineth international conference on neural information processing, Orchid Country Club, Singapore, pp. 2033–2036.
21. L. Pasi,(2004), “Similarity classifier applied to medical data sets,” International conference on soft computing, Helsinki, Finland & Gulf of Finland & Tallinn, Estonia.
22. K. Polat, S. Sahan, S. Gunes, (2007), “A novel hybrid method based on artificial immune recognition system (AIRS) with fuzzy weighted pre-processing for thyroid disease diagnosis,” Expert Systems with Applications, 32(4), pp. 1141–1147.
23. A. Keles, A. Keles, (2008), “ESTDD: expert system for thyroid diseases diagnosis,” Expert Systems with Applications, 34(1), pp. 242–246.
24. P. Kukkurainen, P. Luukka, (2008), “Classification method using fuzzy level set subgrouping,” Expert Systems with Applications, 34, pp. 859–865.
25. F. Temurtas, (2009), “A comparative study on thyroid disease diagnosis using neural networks,” Expert Systems with Applications, 36(1) pp. 944–949.
26. H. Kodaz, S. Ozsen, A. Arslan, S. Gunes, (2009), “Medical application of information gain based artificial immune recognition system (AIRS): diagnosis of thyroid disease,” Expert Systems with Applications, 36, pp. 3086–3092.
27. E. Dogantekin, A. Dogantekin, D. Avci, (2010), “An automatic diagnosis system based on thyroid gland: ADSTG,” Expert Systems with Applications, 37, pp. 6368–6372.
28. E. Dogantekin, A. Dogantekin, D. Avci, (2011), “An expert system based on generalized discriminant analysis and wavelet support vector machine for diagnosis of thyroid diseases,” Expert Systems with Applications, 38(1), pp. 146–150.
29. H. L. Chen, B. Yang, G. Wang, J. Liu, Y. D. Chen, D. Y. Liu, (2011), “A three-stage expert system based on support vector machines for thyroid disease diagnosis,” J. Med. Syst., http://dx.doi.org/10.1007/s10916-011-9655-8.
30. D. Y. Liu, H. L. Chen, B. Yang, X. En Lv, L. N. Li (2011), “Design of an enhanced fuzzy k-nearest neighbor classifier based computer aided diagnostic system for thyroid disease,” Journal of Medical Systems, http://dx.doi.org/10.1007/s10916-011-9815-x.
31. L. N. Li, J. H. Ouyang, H. L. Chen, D. Y. Liu, (2012), “A computer aided diagnosis system for thyroid disease using extreme learning machine,” J. Med. Syst., 36, pp. 3327–3337, DOI 10.1007/s10916-012-9825- 3.
32. A. Dina, Sharaf-El-Deen, İ. F. Moawad, M. E. Khalifa, (2014), “A new hybrid case-based reasoning approach for medical diagnosis systems,” J. Med. Syst. 38(9), Doi 10.1007/s10916-014-0009-1.
33. Y. Kaya, (2014) “A Fast-Intelligent Diagnosis System for “Thyroid Diseases Based on Extreme Learning Machine,” Journal of Science and Technology A-Applied Sciences and Engineering, 15(1), pp. 41-49. https://dergipark.org.tr/en/download/articlefile/35611.
34. R. Solmaz, M. Günay, A. Alkan, (2013), “Uzman Sistemlerin Tiroit Teşhisinde Kullanılması,” Akademik Bilisim 2013 – XV. Akademik Bilisim Konferansı Bildirileri 23-25 Ocak 2013 – Akdeniz Üniversitesi, Antalya, Türkiye, pp. 864-867, 2013. https://ab.org.tr/ab13/bildiri/268.pdf.
35. R. Solmaz, A. Alkan, (2013), “Kan Testi Tabanlı Sınıflandırma Yöntemlerinin Tiroit Tanısında Kullanılması,” 6. Mühendislik ve Teknoloji Sempozyumu 25-26 Nisan 2013 I Çankaya Üniversitesi, Ankara, Türkiye, pp. 269-272. ISBN: 978-975-6734-155, https://zgrw.org/files/MTS6.pd
36. R. Solmaz, M. Günay, A. Alkan, (2014), “Fonksiyonel Tiroit Hastalığı Tanısında Naive Bayes Sınıflandırıcının Kullanılması,” Akademik Bilişim’14 - XVI. Akademik Bilişim Konferansı Bildirileri 5 - 7 Şubat 2014 Mersin Üniversitesi, Türkiye, pp. 891-897, 2014. https://ab.org.tr/ab14/kitap/solmaz_gunay_ab14.pdf.