Diyabet Tahmini İçin Geleneksel Yöntemlerin Analizi ve Değerlendirilmesi

Öz

Dünya çapında milyonlarca insanı etkileyen kronik bir hastalık olan diyabet, vücudun kan şekeri düzeylerini etkili bir şekilde yönetememesiyle karakterize edilir. Kontrol edilmezse veya uygun şekilde yönetilmezse, bu durum kalp hastalığı, felç, böbrek yetmezliği ve hatta körlük gibi ciddi sonuçlara yol açabilir. Genetik ve yaşam tarzı faktörlerinin karşılıklı etkileşimi nedeniyle, diyabet insidansı artmakta ve diyabet acil müdahale gerektiren önemli bir küresel sağlık sorunu olarak konumlanmaktadır. Dünya Sağlık Örgütü (WHO), diyabetin küresel prevalansının 1980'den bu yana neredeyse iki katına çıktığını ve yetişkin nüfusta %4,7'den %8,5'e yükseldiğini bildirmektedir. Bu artış, hastalığın erken teşhisine ve etkin yönetimine yönelik stratejilerin aciliyetini ve önemini vurgulamaktadır. Böyle bir halk sağlığı sorunu karşısında sağlık hizmetleri bu salgınla mücadele için teknolojik gelişmelerden yardım istemektedir. Sağlık hizmetlerinde en umut verici teknolojik sınırlar arasında, çok büyük miktarda veriyi analiz edebilen, kalıpları tanımlayabilen ve sonuçları tahmin edebilen yapay zekanın (AI) bir alt kümesi olan Makine Öğrenimi (ML) yer alıyor. Makine öğrenimi, hasta sağlığına ilişkin değerli içgörüler sağlayarak, tedavi kararlarını bildirerek ve hatta bir kişinin gelecekte hastalığa yakalanma riskini tahmin ederek diyabet yönetiminde devrim yaratma potansiyeline sahiptir. Bu teknoloji, doğru kullanılırsa diyabetle mücadelede oyunu değiştirebilir. Bu bağlamda, diyabet riskini tahmin etmek için geleneksel sınıflandırıcı yöntemlerin kullanılması uygulanabilir ve etkili bir yaklaşım gibi görünmektedir. Bu yöntemler gelişmeye devam ettikçe, bu kronik hastalığın erken teşhisi ve etkili tedavisinde önemli bir rol oynamakta ve diyabet risk tahmininin doğruluğunu ve kesinliğini artırma sözü vermektedir. Bu yazıda, diyabeti tahmin etmek için geleneksel sınıflandırıcı yöntemlerin nasıl kullanıldığını, bu teknolojinin hastalık teşhisindeki etkilerini ve gelişen bu alanın gelecekteki potansiyelini inceleyeceğiz.

Anahtar Kelimeler

• Diyabet
• Yapay zeka
• Sınıflandırıcılar
• Makine Öğrenmesi
• Tahmin.

Analysis and Evaluation of Conventional Methods for Diabetes Prediction

Abstract

Diabetes, a chronic disease that affects millions of people worldwide, is characterized by the body's inability to manage blood sugar levels effectively. If left unchecked or not managed properly, this condition can lead to serious consequences such as heart disease, stroke, kidney failure, and even blindness. Due to the interplay of genetic and lifestyle factors, the incidence of diabetes is increasing, positioning it as a significant global health problem requiring urgent attention. The World Health Organization (WHO) reports that the global prevalence of diabetes has nearly doubled since 1980, rising from 4.7% to 8.5% in the adult population. This increase highlights the urgency and importance of strategies aimed at early diagnosis and effective management of the disease. In the face of such a public health problem, health services seek help from technological developments to combat this epidemic. Among the most promising technological frontiers in healthcare is Machine Learning (ML), a subset of artificial intelligence (AI) that can analyze vast amounts of data, identify patterns and predict outcomes. Machine learning has the potential to revolutionize diabetes management by providing valuable insights into patient health, informing treatment decisions, and even predicting a person's risk of developing the disease in the future. This technology, if used properly, could change the game in the fight against diabetes. In this context, the use of traditional classifier methods to estimate diabetes risk seems to be a viable and efficient approach. As these methods continue to evolve, they play an important role in the early detection and effective treatment of this chronic disease, promising to increase the accuracy and precision of diabetes risk estimation. In this article, we will examine how traditional classifier methods are used to predict diabetes, the implications of this technology for disease diagnosis, and the future potential of this evolving field.

Keywords

• Diabetes
• Artificial Intelligence
• Classifiers
• Machine Learning
• Prediction

Kaynakça

1. IDF Diabetes Atlas, “Diabetes around the world in 2021”, Accessed 13.09.2023, https://diabetesatlas.org/.
2. Kalaycı, T. E. (2018). Kimlik hırsızı web sitelerinin sınıflandırılması için makine öğrenmesi yöntemlerinin karşılaştırılması. Pamukkale Üniversitesi Mühendislik Bilimleri Dergisi, 24(5), 870-878.
3. Chen, T., Guestrin, C. (2016). XGBoost: A Scalable Tree Boosting System. Proceedings of the 22nd acm sigkdd international conference on knowledge discovery and data mining (pp. 785–794). ACM. doi: 10.1145/2939672.2939785.
4. Prokhorenkova, L., Gusev, G., Vorobev, A., Dorogush, A. V., & Gulin, A. (2017). CatBoost: unbiased boosting with categorical features. arXiv preprint arXiv:1706.09516.
5. Karaıbrahımoglu, A. , Kara, Ü. , Kılıçoğlu, Ö. & Kara, Y. (2023). Prediction of absorption dose of radiation on Thorax CT imaging in geriatric patients with COVID-19 by classification algorithms . European Mechanical Science , 7 (2) , 89-98 . Retrieved from https://dergipark.org.tr/en/pub/ems/issue/76070/1262875.
6. Saritas, M.M., Yasar, A. (2019) Performance Analysis of ANN and Naive Bayes Classification Algorithm for Data Classification. International Journal of Intelligent Systems and Applications in Engineering 7(2), 88-91. (https://doi.org/10.18201// ijisae.2019252786).
7. Hsu, C.-W., Chang, C.-C., Lin, C.-J., 2010. A Practical Guide to Support Vector ClassificationDepartment of Computer Science, National Taiwan University, Taipei, Taiwan16.
8. Chandrashekhar, A.M., Raghuveer, K. (2014). Amalgamation of K-means Clustering Algorithm with Standard MLP and SVM Based Neural Networks to Implement Network Intrusion Detection System. In: Kumar Kundu, M., Mohapatra, D., Konar, A., Chakraborty, A. (eds) Advanced Computing, Networking and Informatics- Volume 2. Smart Innovation, Systems and Technologies, vol 28. Springer, Cham. https://doi.org/10.1007/978-3-319-07350-7_31

9. Chand, S., & Vishwakarma, V. P. (2022). Application of quadratic discriminant analysis algorithm for the classification of acute leukemia using microscopic image data. Adv. Appl. Math. Sci., 21, 2737-2750.
10. Hu, L.Y., Huang, M.W., Ke, S.W., Tsai, C.F., (2016), "The Distance Function Effect on kNearest Neighbor Classification for Medical Datasets", Springer Plus, 5(1), 1-9.
11. Friedman J., Greedy function approximation: A gradient boosting machine, Annals of Statistics, 29, 1189-1232, 2001.
12. Sai, M.J., Chettri, P., Panigrahi, R. et al. An Ensemble of Light Gradient Boosting Machine and Adaptive Boosting for Prediction of Type-2 Diabetes. Int J Comput Intell Syst 16, 14 (2023). https://doi.org/10.1007/s44196-023-00184-y
13. Al-Hameli, B., Alsewari, A., Basurra, S., Bhogal, J. & Ali, M. (2023). Diabetes disease prediction system using HNB classifier based on discretization method. Journal of Integrative Bioinformatics, 20(1), 20210037. https://doi.org/10.1515/jib-2021-0037.
14. Zou Q, Qu K, Luo Y, Yin D, Ju Y, Tang H. Predicting Diabetes Mellitus With Machine Learning Techniques. Front Genet. 2018 Nov 6;9:515. doi: 10.3389/fgene.2018.00515. PMID: 30459809; PMCID: PMC6232260.
15. Çalişir, D., & Doğantekin, E. (2011). An automatic diabetes diagnosis system based on LDA-Wavelet Support Vector Machine Classifier. Expert Systems with Applications, 38(7), 8311-8315.
16. Nirupama S, & Jenila Rani D. (2022). Analysis And Comparison Of Diabetic Prediction Using Medium KNN Classifier And Cosine KNN Classifier. Journal of Pharmaceutical Negative Results, 386–394. https://doi.org/10.47750/pnr.2022.13.S04.043.
17. Alex SA, Jhanjhi N, Humayun M, Ibrahim AO, Abulfaraj AW. Deep LSTM Model for Diabetes Prediction with Class Balancing by SMOTE. Electronics. 2022; 11(17):2737. https://doi.org/10.3390/electronics11172737
18. Nahzat, S. & Yağanoğlu, M. (2021). Diabetes Prediction Using Machine Learning Classification Algorithms. European Journal of Science and Technology, (24), 53-59.
19. Bulut, F. (2016). Determining Heart Attack Risk Ration Through AdaBoost/AdaBoost ile Kalp Krizi Risk Tespiti. Celal Bayar University Journal of Science, 12(3), 459-472.
20. M. K. Hasan, M. A. Alam, D. Das, E. Hossain and M. Hasan, "Diabetes Prediction Using Ensembling of Different Machine Learning Classifiers," in IEEE Access, vol. 8, pp. 76516-76531, 2020, doi: 10.1109/ACCESS.2020.2989857.
21. Gayathri, S., Gopi, V.P. & Palanisamy, P. Diabetic retinopathy classification based on multipath CNN and machine learning classifiers. Phys Eng Sci Med 44, 639–653 (2021). https://doi.org/10.1007/s13246-021-01012-3 Sharma, T., Shah, M. A comprehensive review of machine learning techniques on diabetes detection. Vis. Comput. Ind. Biomed. Art 4, 30 (2021). https://doi.org/10.1186/s42492-021-00097-7
22. T. Gupta, M. R. A T, R. C and R. Kumar M, "Diabetes Prediction using different Machine Learning Classifiers," 2023 2nd International Conference on Vision Towards Emerging Trends in Communication and Networking Technologies (ViTECoN), Vellore, India, 2023, pp. 1-5, doi: 10.1109/ViTECoN58111.2023.10157531.
23. Tasin, I., Nabil, T. U., Islam, S., & Khan, R. (2023). Diabetes prediction using machine learning and explainable AI techniques. Healthcare Technology Letters, 10(1-2), 1-10. https://doi.org/10.1049/htl2.12039
24. Puneeth N. Thotad, Geeta R. Bharamagoudar, Basavaraj S. Anami, Diabetes disease detection and classification on Indian demographic and health survey data using machine learning methods, Diabetes & Metabolic Syndrome: Clinical Research & Reviews, Volume 17, Issue 1, 2023, 102690, ISSN 1871-4021, https://doi.org/10.1016/j.dsx.2022.102690.
25. https://www.kaggle.com/datasets/mathchi/diabetes-data-set/code
26. El-Jerjawi, N.S., & Abu-Naser, S.S. (2018). Diabetes Prediction Using Artificial Neural Network.
27. D. Dutta, D. Paul and P. Ghosh, "Analysing Feature Importances for Diabetes Prediction using Machine Learning," 2018 IEEE 9th Annual Information Technology, Electronics and Mobile Communication Conference (IEMCON), Vancouver, BC, Canada, 2018, pp. 924-928, doi: 10.1109/IEMCON.2018.8614871.
28. Gökalp, O. (2021). Performance evaluation of Heuristic and Metaheuristic Algorithms for Independent and Static Task Scheduling in Cloud Computing. 2021 29th Signal Processing and Communications Applications Conference (SIU), 1-4.
29. Tanyıldız, H. & Batur Şahin, C. (2023). Transfer Learning for Detection of Casting Defects Model In Scope of Industrial 4.0 . Türk Doğa ve Fen Dergisi , 12 (3) , 45-51 . DOI: 10.46810/tdfd.1236584.
30. Şahin, C.B. (2023). Semantic-based vulnerability detection by functional connectivity of gated graph sequence neural networks. Soft Comput 27, 5703–5719 . https://doi.org/10.1007/s00500-022-07777-3.
31. C. B. Şahin, (2021).DCW-RNN: Improving Class Level Metrics for Software Vulnerability Detection Using Artificial Immune System with Clock-Work Recurrent Neural Network," 2021 International Conference on INnovations in Intelligent SysTems and Applications (INISTA), Kocaeli, Turkey, pp. 1-8, doi: 10.1109/INISTA52262.2021.9548609.