Diabetes Prediction Using Machine Learning Classification Algorithms

Abstract

Artificial intelligence’s use in health systems has evolved substantially in recent years. In medical diagnosis, machine learning (ML) has a wide variety of uses. Machine learning techniques are used to forecast or diagnose a variety of life-threatening illnesses, including cancer, diabetes, heart disease, thyroid disease, and so on. Chronic diabetes is one of the most common diseases worldwide and making the diagnosis process simpler and quicker would have a huge effect on the treatment process. The fundamental goal of this work is to prepare and carry out diabetes prediction using various machine learning techniques and Conduct output analysis of those techniques to find the best classifier with the highest accuracy. This study examines diabetes prediction by taking different diabetes disease-related attributes. We use the Pima Indian Diabetes Dataset and applied the Machine Learning classification methods like K-Nearest Neighbors (KNN), Random Forest (RF), Support Vector Machine (SVM), Artificial Neural Network (ANN), and Decision Tree (DT) for diabetes prediction. The models used in this analysis have various degrees of accuracy. This study shows a model that can correctly forecast diabetes. In comparison to other machine learning methods, the random forest has high accuracy in forecasting diabetes, according to the findings of this study.

Keywords

• Machine learning (ML)
• Classification
• Artificial Neural Network (ANN)
• Random Forest (RF)
• Decision Tree (DT)

Makine Öğrenimi Sınıflandırma Algoritmalarını Kullanarak Diyabet Tahmini

Abstract

Yapay zekanın sağlık sistemlerinde kullanımı son yıllarda önemli ölçüde gelişmiştir. Tıbbi teşhiste, makine öğreniminin (MÖ) çok çeşitli kullanımları vardır. Makine öğrenimi teknikleri, kanser, diyabet, kalp hastalığı, tiroid hastalığı v.b. dahil olmak üzere hayatı tehdit eden çeşitli hastalıkları tahmin etmek veya teşhis etmek için kullanılır. Kronik diyabet dünya çapında en yaygın hastalıklardan biridir ve teşhis sürecini daha basit ve daha hızlı hale getirmek tedavi süreci üzerinde çok büyük bir etkiye sahip olacaktır. Bu çalışmanın temel amacı, en yüksek doğrulukla en iyi sınıflandırıcıyı bulmak için çeşitli makine öğrenimi tekniklerini kullanarak diyabet tahminini yapmak ve bu tekniklerin çıktı analizini yapmaktır. Bu çalışma, diyabet hastalığıyla ilgili farklı özellikler alarak diyabet tahminini incelemektedir. Pima Indian Diyabet Veri Kümesini kullanıyoruz ve K-En Yakın Komşu (KNN), Rastgele Orman (RO), Destek Vektör Makinesi (DVM), Yapay Sinir Ağı (YSA) ve Karar Ağacı (KA) gibi Makine Öğrenimi sınıflandırma yöntemlerini diyabet tahmin etmek için uyguladık. Bu analizde kullanılan modeller çeşitli doğruluk derecelerine sahiptir. Bu çalışma, diyabeti doğru bir şekilde tahmin edebilen bir model göstermektedir. Bu çalışmanın bulgularına göre, diğer makine öğrenimi yöntemlerine kıyasla rastgele orman (RO), diyabet tahmininde yüksek doğruluğa sahiptir.

Keywords

• Makine öğrenimi (MÖ)
• Sınıflandırma
• Yapay Sinir Ağı (YSA)
• Rastgele Orman (RO)
• Karar Ağacı (KA)

References

1. Lonappan, A., Bindu, G., Thomas, V., Jacob, J., Rajasekaran, C., and Mathew, K. T. (2007). Diagnosis of diabetes mellitus using microwaves. J. Electromagnet. Wave. 21, 1393–1401. doi: 10.1163/156939307783239429
2. Kang, Hyun. (2013). The prevention and handling of the missing data. Korean journal of anesthesiology.
3. Iancu, I., Mota, M., and Iancu, E. (2008). “Method for the analysing of blood glucose dynamics in diabetes mellitus patients,” in Proceedings of the 2008 IEEE International Conference on Automation, Quality and Testing, Robotics, Cluj-Napoca. doi: 10.1109/AQTR.2008.4588883
4. Robertson, G., Lehmann, E. D., Sandham, W., and Hamilton, D. (2011). Blood glucose prediction using artificial neural networks trained with the AIDA diabetes simulator: a proof-of-concept pilot study. J. Electr. Comput. Eng.2011:681786. doi: 10.1155/2011/681786
5. Soni. M and Varma. S (2020), Diabetes Prediction using Machine Learning Techniques, International Journal of Engineering Research & Technology (IJERT)
6. Sarwar. M, Kamal. N, Hamid. W and Shah. A (2018), International Conference on Automation and Computing (ICAC)
7. Tejas N. Joshi, Prof. Pramila M. Chawan, Diabetes Prediction Using Machine Learning Techniques, January 2018, Int. Journal of Engineering Research and Application, Vol. 8, Issue 1, (Part -II), pp.-09-13
8. 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.

9. Al Helal, M., Chowdhury, A. I., Islam, A., Ahmed, E., Mahmud, M. S., & Hossain, S. (2019, February). 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.
10. Dataset, P. I. D. UCI Machine Learning Repository, diambil dari http://archive. ics. uci. edu/ml/datasets. Pima+ Indians+ Diabetes. Accessed (October,2020)
11. Fawagreh, K., Gaber, M. M., & Elyan, E. (2014). Random forests: from early developments to recent advancements. Systems Science & Control Engineering: An Open Access Journal, 2(1), 602-609.
12. Quinlan, J. R. (1986). Induction on decision tree. Mach. Learn.1, 81–106. doi: 10.1007/BF00116251
13. Jardel das C. Rodrigues a, Pedro P. Rebouças Filho a, Eugenio Peixoto Jr b, Arun Kumar N c, Victor Hugo C. de Albuquerque b, (2019), Classification of EEG signals to detect alcoholism using machine learning techniques, Pattern Recognition Letters
14. Sokolova M., Japkowicz N., Szpakowicz S., (2006), Beyond Accuracy, F-score and ROC: a Family of Discriminant Measures for Performance Evaluation, American Association for Artificial Intelligence (www.aaai.org).
15. Steven W., Narciso C., (2003) Encyclopedia of Physical Science and Technology (Third Edition).
16. Yağanoğlu, M., & Köse, C., (2018), Real-time detection of important sounds with a wearable vibration based device for hearing-impaired people. Electronics, 7(4), 50.