Investigation of The Risk of Diabetes in Early Period using Machine Learning Algorithms

Abstract

Diabetes significantly affecting the quality of human life, the world and the incidence of a disease in Turkey is increasingly important. In particular, it causes damage to the nervous system, kidney, heart, eyes, limbs and blood vessels and can cause significant losses. For this reason, early diagnosis and follow-up is of great importance in order to prevent diabetes or to minimize the damage it will cause. Classification techniques obtained by machine learning algorithms have been accepted as important by researchers for the risk prediction model of the disease. In the study, a database created with information from 520 subjects was used to estimate the probability of developing diabetes. In the study, Multilayer Perceptron Artificial Neural Networks (MLPNN), Support Vector Machines (SVM), Decision Trees (DT), Ensemble Learning Algorithms (ELA), Linear Discriminant Analysis (LDA), k-NN Methods were used as machine learning methods. Among these methods, k-NN algorithm provided the highest accuracy and 99,81% accuracy was achieved with this algorithm. A diabetes early diagnosis kit was developed by including the algorithm providing the highest accuracy value into a computer user interface developed within the scope of the study

Keywords

• Diabetes risk
• Early stage
• Support Vector Machine
• Ensembles Learning
• Algorithm
• Decision Trees

Makine Öğrenmesi Algoritmaları Kullanarak Erken Dönemde Diyabet Hastalığı Riskinin Araştırılması

Abstract

Diyabet insanoğlunun yaşam kalitesini önemli derecede etkileyen, dünyada ve Türkiye’de görülme sıklığı giderek artan önemli bir hastalıktır. Özellikle sinir sistemi, böbrek, kalp, gözler, uzuvlar ve kan damarlarının tahribatına yol açmakta ve önemli kayıplara sebebiyet verebilmektedir. Bu sebeple diyabetin önlenebilmesi veya vereceği tahribatın en aza indirilebilmesi için erken tanısı ve takibi büyük önem kazanmaktadır. Makine öğrenme algoritmaları ile elde edilen sınıflandırma teknikleri, hastalığın risk tahmin modeli için araştırmacılar tarafından önemli olarak kabul görmüştür. Çalışmada, diyabete yakalanma olasılığını tahmin etmek için, 520 denekten alınan bilgiler ile oluşturulmuş olan bir veri tabanı kullanılmıştır. Çalışmada, makine öğrenmesi metotları olarak Çok Katmanlı Algılayıcı Yapay Sinir Ağları (ÇKAYSA), Destek Vektör Makinaları (DVM), Karar Ağaçları (KA), Topluluk Öğrenme Algoritmaları (TÖA), Doğrusal Ayrımcı Analizi (DAA), k-NN Metotları kullanılmıştır. Bu metotlar arasında en yüksek doğruluğu k-NN algoritması sağlamış ve bu algoritma ile %99,81 doğruluk elde edilmiştir. En yüksek doğruluk değeri sağlayan algoritmanın çalışma kapsamında geliştirilmiş olan bir bilgisayar kullanıcı arayüzü içerisine dâhil edilmesiyle bir diyabet erken tanı kiti geliştirilmiştir.

Keywords

• Diyabet riski
• Erken dönem
• Destek Vektör Makinesi
• Topluluk Öğrenme Algoritmaları
• Karar ağaçları

Thanks

Bu çalışma Burdur Mehmet Akif Ersoy Üniversitesi Bilimsel Araştırma Projeleri Koordinasyon Birimi tarafından desteklenmiştir.

References

1. Ahmed, T. M., 2016. Developing a predicted model for diabetes type 2 treatment plans by using data mining. Journal of Theoretical and Applied Information Technology, 90(2), 181.
2. Al Helal, M., Chowdhury, A. I., Islam, A., Ahmed, E., Mahmud, M. S., & Hossain, S., 2019. An optimization approach to improve classification performance in cancer and diabetes prediction. In 2019 International Conference on Electrical, Computer and Communication Engineering (ECCE), pp. 1-5, IEEE.
3. Bi, S., Ding, X., Yu, S., Guo, B., Mu, L., Wang, B., 2021. A machine learning model for quantifying the effect of lifestyle interventions for patients with type 2 diabetes mellitus. In Journal of Physics, Conference Series, Vol. 1732, No. 1, p. 012006, IOP Publishing.
4. Bishop, C. M., 2006. Pattern Recognition and Machine Learning Springer-Verlag New York. Inc. Secaucus, NJ, USA.
5. Cichosz, S. L., Johansen, M. D., Hejlesen, O., 2016. Toward big data analytics: review of predictive models in management of diabetes and its complications. Journal of diabetes science and technology, 10(1), 27-34.
6. Dua, D., Graff, C., 2019. UCI Machine Learning Repository [http://archive.ics.uci.edu/ml]. Irvine, CA: University of California, School of Information and Computer Science. Failure to detect type 2 diabetes early costing $700 million per year, Diabetes Australia, 8 July 2018. https://www.diabetesaustralia.com.au
7. Fan, S., Chen, B., Zhang, X., Hu, X., Bao, L., Yang, X., Liu, Z., Yu, Y., 2021. Machine Learning Algorithms in Classifying TCM Tongue Features in Diabetes Mellitus and Symptoms of Gastric Disease. European Journal of Integrative Medicine, 101288.
8. Friedman, J., Hastie, T., Tibshirani, R., 2000. Additive logistic regression: a statistical view of boosting. Annals of Statistics, 28 (2), 337–407.

9. Frimpong, E. A., Oluwasanmi, A., Baagyere, E. Y., Zhiguang, Q., 2021. A feedforward artificial neural network model for classification and detection of type 2 diabetes. In Journal of Physics: Conference Series, Vol. 1734, No. 1, p. 012026, IOP Publishing.
10. George, T., Rufus, E., Alex, Z.C., 2015. Simulation of microwave induced thermo-accoustical imaging technique for cancer detection. Journal of Engineering and Applied Sciences (ARPN), 10.
11. Goetz, T., 2010. The Decision Tree: Taking Control of Your Health in the New Era of Personalized Medicine, New York, NY, USA: Rodale.
12. Goldenberg, R., Punthakee, Z., 2013. Definition, classification and diagnosis of diabetes, prediabetes and metabolic syndrome. Canadian journal of diabetes, 37, S8-S11.
13. Harding, J. L., Pavkov, M. E., Magliano, D. J., Shaw, J. E., Gregg, E. W., 2019. Global trends in diabetes complications: a review of current evidence. Diabetologia, 62(1), 3-16.
14. Harris, M.I., Klein, R., Welborn, T.A., Knuiman, M. W., 1992. Onset of NIDDM occurs at least 4–7 yr before clinical diagnosis. Diabetes Care, 15(7), 815–819.
15. Hastie, T., Tibshirani, R., Friedman, J., 2009. The elements of statistical learning: data mining, inference, and prediction.
16. Hu, H.Y., Hwang, J.N., 2002. Handbook of Neural Network Signal Processing, New York, NY, USA: CRC Press.
17. Huang, S., Cai, N., Pacheco, P. P., Narrandes, S., Wang, Y., Xu, W., 2018. Applications of support vector machine (SVM) learning in cancer genomics. Cancer Genomics-Proteomics, 15(1), 41-51.
18. Islam, M. F., Ferdousi, R., Rahman, S., Bushra, H. Y., 2020. Likelihood prediction of diabetes at early stage using data mining techniques. In Computer Vision and Machine Intelligence in Medical Image Analysis pp. 113-125, Springer, Singapore.
19. Joshi, T. N., Chawan, P. P. M., 2018. Diabetes Prediction Using Machine Learning Techniques. International Journal of Engineering Research and Application (Ijera), vol. 8, no.1, pp. 9-13, 2018.
20. Jutel, A., 2011. Classification, disease, and diagnosis. Perspectives in biology and medicine, 54(2), 189-205.
21. Karthikeyani, V., Begum, I. P., 2013. Comparison a performance of data mining algorithms (CPDMA) in prediction of diabetes disease. International journal on computer science and engineering, 5(3), 205.
22. Kaur, H., Kumari, V., 2018. Predictive modelling and analytics for diabetes using a machine learning approach. Applied Computing and Informatics.
23. Kavakiotis, I., Tsave, O., Salifoglou, A., Maglaveras, N., Vlahavas, I., Chouvarda, I., 2017. Machine learning and data mining methods in diabetes research. Computational and structural biotechnology journal, 15, 104-116.
24. Kononenko, I., 2001. Machine learning for medical diagnosis: history, state of the art and perspective. Artificial Intelligence in Medicine, vol. 23, no. 1, pp. 89-109.
25. Mercaldo, F., Nardone, V., Santone, A., 2017. Diabetes Mellitus Affected Patients Classification and Diagnosis through Machine Learning Techniques. Procedia Computer Science, 112, 2519-2528.
26. Mohammed, M., Khan, M. B., Bashier, E. B. M., 2016. Machine learning: algorithms and applications. Crc Press.
27. Mujumdar, A., Vaidehi, V., 2019. Diabetes Prediction Using Machine Learning Algorithms. Procedia Computer Science, 165, 292–299.
28. Ogurtsova, K., da Rocha Fernandes, J. D., Huang Y., Linnenkamp, U., Guariguata, L., Cho, N. H., Cavan, D., Shaw, J. D., Makaroff, L. E., 2017. IDF Diabetes Atlas: global estimates for the prevalence of diabetes for 2015 and 2040. Diabetes research and clinical practice, 128, 40-50.
29. Özer, İ., 2020. Uzun Kısa Dönem Bellek Ağlarını Kullanarak Erken Aşama Diyabet Tahmini. Mühendislik Bilimleri ve Araştırmaları Dergisi, 2 (2) , 50-57.
30. Parashar, A., Burse, K., Rawat, K., 2014. A Comparative approach for Pima Indians diabetes diagnosis using lda-support vector machine and feed forward neural network. International Journal of Advanced Research in Computer Science and Software Engineering, 4(11), 378-383.
31. Parikh, R. B., Kakad, M., Bates, DW., 2016. Integrating predictive analytics into high-value care: the dawn of precision delivery. JAMA, 315, 651-652.
32. Rokach, L., Maimon, O., 2005. Decision trees. In Data mining and knowledge discovery handbook, pp. 165-192, Springer, Boston, MA.
33. Sapon, M. A., Ismail, K., Zainudin, S., 2011. Prediction of diabetes by using artificial neural network. In Proceedings of the 2011 International Conference on Circuits, System and Simulation, Singapore Vol. 2829.
34. Specht, D., 1991. A general regression neural network, IEEE Trans. Neural Netw. 2, 568-576.
35. Statistics About Diabetes: American Diabetes Association, 22 Mar 2018. https://www.diabetes. Org.
36. Thaiyalnayaki, K., 2021. Classification of Diabetes Using Deep Learning and SVM Techniques. International Journal of Current Research and Review, Vol, 13(01), 146.
37. The 6 Different Types of Diabetes: (5 Mar 2018). The diabetic journey. https:// thediabeticjourney.com/the-6-different-types-of-diabetes.
38. Tiwari, P., Singh, V., 2021. Diabetes disease prediction using significant attribute selection and classification approach. In Journal of Physics: Conference Series, Vol. 1714, No. 1, p. 012013.
39. Tran, B. X., Latkin, C. A., Giang, V. T., Huong, L. T. N., Son, N., Ming-Xuan, T., Zhi-Kai, L., Cyrus, S. H. H., Roger, C. M. H., 2019. The Current Research Landscape of the Application of
40. Artificial Intelligence in Managing Cerebrovascular and Heart Diseases: A Bibliometric and Content Analysis. International Journal of Environmental Research and Public Health, 16,2699.
41. Türk Endokrinoloji ve Metabolizma Derneği (TEMD), 2013. Diabetes mellitus ve komplikasyonlarının tanı, tedavi ve izlem kılavuzu (6.baskı). Ankara, BAYT Bilimsel Araştırmalar Basın Yayın, 2012, 15-42.
42. TC Sağlık Bakanlığı Temel Sağlık Hizmetleri Genel Müdürlüğü (TSHGM), 2011. Türkiye Diyabet Önleme ve Kontrol Programı Eylem Planı (2011- 2014). Ankara: Sağlık Bakanlığı Yayın No:816.
43. Vaibhaw, Jay Sarraf, P.K. Pattnaik, Chapter 2 - Brain–computer interfaces and their applications, Editor(s): Valentina Emilia Balas, Vijender Kumar Solanki, Raghvendra
44. Kumar, An Industrial IoT Approach for Pharmaceutical Industry Growth, Academic Press, 2020, Pages 31-54, ISBN 9780128213261.
45. Wang, C., Long, Y., Li, W., Dai, W., Xie, S., Liu, Y., Zhang, Y., Liu, M., Tian, Y., Li, Q., Duan, Y., 2020. Exploratory study on classification of lung cancer subtypes through a combined K-nearest neighbor classifier in breathomics. Scientific reports, 10(1), 1-12.
46. Zhong, G., Ling, X., Wang, L. N., 2019. From shallow feature learning to deep learning: Benefits from the width and depth of deep architectures. Wiley Interdisciplinary Reviews: Data Mining and Knowledge Discovery, 9(1), e1255.