SavedAdd your journal

Journals / Turkish Journal of Science and Technology / 2026 / Volume: 21 Issue: 2

A New Approach in Diabetes Diagnosis: Performance Comparison using Machine Learning Algorithms

Diyabet Tanısında Yeni Bir Yaklaşım: Makine Öğrenmesi Algoritmaları Kullanılarak Performans Karşılaştırması

Cemal Aktürk(GAZIANTEP ISLAM SCIENCE AND TECHNOLOGY UNIVERSITY)0000-0003-3764-3862
Mustafa Turan Arslan(HATAY MUSTAFA KEMAL UNIVERSITY)0000-0001-5498-6571
Tarık Talan(Gaziantep İslam Bilim ve Teknoloji Üniversitesi)0000-0002-5371-4520
Pages
—
Publication Date
2026-09-30
🏛️Bibliographic metadata and full text access for this article are provided via DergiPark.
DergiPark Record ↗
✨

AI Summary & Key Takeaways

AI Insight
⚡ TL;DR(Too Long; Didn't Read)

This approach can facilitate early diagnosis and preventive measures for diabetes, especially in settings where access to laboratory testing is limited.

📌 3 Key Takeaways

🎯
Objective & Hypothesis:According to the International Diabetes Federation (IDF), approximately 589 million adults are expected to be living with diabetes in 2025.
📊
Key Findings & Data:Early and accurate diagnosis is crucial to prevent organ damage and improve patient outcomes.
💡
Conclusion & Impact:This approach can facilitate early diagnosis and preventive measures for diabetes, especially in settings where access to laboratory testing is limited.
🔬Design:Modeling & Simulation
📍Scope:2025 · 17,000 samples
⚙️Variables:classification · diagnosis of diabetes · machine learning algorithms

Abstract

According to the International Diabetes Federation (IDF), approximately 589 million adults are expected to be living with diabetes in 2025. This number continues to rise due to unhealthy eating habits and poor quality of life. Early and accurate diagnosis is crucial to prevent organ damage and improve patient outcomes. This study aims to develop a method for predicting diabetes without requiring individuals to visit healthcare facilities or undergo laboratory tests, using machine learning (ML) techniques to enable early intervention. A diabetes dataset containing 100,000 patient records was used. The dataset was reduced to 17,000 samples through undersampling. Ten different classification algorithms were applied to perform diabetes prediction. Initially, predictions were made using the full dataset, followed by a second phase where blood test data were excluded to assess the model's performance with fewer features. Among the ten algorithms tested, the BayesNet algorithm achieved the highest accuracy of 91% when using the full dataset. When blood-related features were removed, the BayesNet and Rotation Forest models still maintained a relatively high accuracy of 75.10%. The findings demonstrate that it is possible to predict diabetes with considerable accuracy even without blood test data. This approach can facilitate early diagnosis and preventive measures for diabetes, especially in settings where access to laboratory testing is limited.

Özet

Uluslararası Diyabet Federasyonu’na (IDF) göre, 2025 yılı itibarıyla yaklaşık 589 milyon yetişkinin diyabetle yaşayacağı öngörülmektedir. Bu sayı, sağlıksız beslenme alışkanlıkları ve düşük yaşam kalitesi nedeniyle artmaya devam etmektedir. Organ hasarını önlemek ve hasta sonuçlarını iyileştirmek için erken ve doğru tanı kritik öneme sahiptir. Bu çalışma, bireylerin sağlık kuruluşlarına başvurmalarına veya laboratuvar testleri yaptırmalarına gerek kalmadan, makine öğrenmesi teknikleri kullanarak diyabeti tahmin etmeyi ve böylece erken müdahale imkânı sağlamayı amaçlamaktadır. Çalışmada 100.000 hasta kaydını içeren bir diyabet veri seti kullanılmıştır. Veri seti, alt örnekleme yöntemiyle 17.000 örneğe indirgenmiştir. Diyabet tahmini gerçekleştirmek için on farklı sınıflandırma algoritması uygulanmıştır. İlk olarak, tüm veri seti kullanılarak tahminler yapılmış, ardından kan test verilerinin çıkarıldığı ikinci bir aşamada modelin daha az özellik ile performansı değerlendirilmiştir. Test edilen on algoritma arasında, BayesNet algoritması tüm veri seti kullanıldığında %91 ile en yüksek doğruluk oranını elde etmiştir. Kanla ilgili özellikler çıkarıldığında ise BayesNet ve Rotation Forest modelleri hâlâ %75,10 gibi nispeten yüksek bir doğruluk oranı sağlamıştır. Elde edilen bulgular, kan testi verileri olmadan da diyabetin kayda değer bir doğrulukla tahmin edilebileceğini göstermektedir. Bu yaklaşım, özellikle laboratuvar testlerine erişimin sınırlı olduğu ortamlarda diyabetin erken teşhisi ve önleyici tedbirlerin alınmasını kolaylaştırabilir.

🔖

Cite This Article

Aktürk, C., Arslan, M. T., Talan, T. (2026). A New Approach in Diabetes Diagnosis: Performance Comparison using Machine Learning Algorithms. Turkish Journal of Science and Technology, Volume: 21 Issue: 2. https://doi.org/10.55525/tjst.1888687

📄 Full Text PDF Viewer

📄

PDF görüntüleyici hazırlanıyor...

References (22)

  1. Yameny AA. Diabetes mellitus overview 2024. J Biosci Appl Res 2024; 10(3): 641-645.
  2. Anjana RM, et al. Prevalence of diabetes and prediabetes (impaired fasting glucose and/or impaired glucose tolerance) in urban and rural India: Phase I results of the Indian Council of Medical Research–INDIAB study. Diabetologia 2011; 54(12): 3022-3027.
  3. Mujumdar A, Vaidehi V. Diabetes prediction using machine learning algorithms. Procedia Comput Sci 2019; 165: 292-299.
  4. Maniruzzaman M, et al. Classification and prediction of diabetes disease using machine learning paradigm. Health Inf Sci Syst 2020; 8(1): 7.
  5. Sarwar MA, et al. Prediction of diabetes using machine learning algorithms in healthcare. In: 24th Int Conf Autom Comput; 2018; pp. 1-6.
  6. Rani KJ. Diabetes prediction using machine learning. Int J Sci Res Comput Sci Eng Inf Technol 2020; 6(4): 294-305.
  7. Hasan MK, et al. Diabetes prediction using ensembling of different machine learning classifiers. IEEE Access 2020; 8: 76516-76531.
  8. Febrian ME, et al. Diabetes prediction using supervised machine learning. Procedia Comput Sci 2023; 216: 21-30.
  9. Soni M, Varma S. Diabetes prediction using machine learning techniques. Int J Eng Res Technol 2020; 9(9): 921-925.
  10. Wee BF, et al. Diabetes detection based on machine learning and deep learning approaches. Multimed Tools Appl 2024; 83(8): 24153-24185.
  11. Khanam JJ, Foo SY. A comparison of machine learning algorithms for diabetes prediction. ICT Express 2021; 7(4): 432-439.
  12. Khaleel FA, Al-Bakry AM. Diagnosis of diabetes using machine learning algorithms. Mater Today Proc 2023; 80: 3200-3203.
  13. Mustafa M. Diabetes prediction dataset. Kaggle; 2023.
  14. Lundberg SM, Lee SI. A unified approach to interpreting model predictions. In: Adv Neural Inf Process Syst; 2017; Long Beach, CA, USA. pp. 1-10.
  15. Chawla NV, Bowyer KW, Hall LO, Kegelmeyer WP. SMOTE: Synthetic minority over-sampling technique. J Artif Intell Res 2002; 16: 321-357.
  16. Farnoosh R, Abnoosian K. A robust innovative pipeline-based machine learning framework for predicting COVID-19 in Mexican patients. Int J Syst Assur Eng Manag 2024; 15(7): 3466-3484.
  17. Abnoosian K, Farnoosh R, Behzadi MH. A pipeline-based framework for early prediction of diabetes. J Health Biomed Inform 2023; 10(2): 125-140.
  18. Abnoosian K, Farnoosh R, Behzadi MH. Prediction of diabetes disease using an ensemble of machine learning multi-classifier models. BMC Bioinformatics 2023; 24: 337.
  19. Güler H, Avcı D, Ulaş M, Omma T. In-depth analysis of machine learning models and explainable artificial intelligence methods in diabetes diagnosis. J Fac Eng Arch Gazi Univ 2025; 40(3): 1995-2011.
  20. Navarro-Cerdán JR, Pons-Suñer P, Arnal L, Arlandis J, Llobet R, Pérez-Cortés JC, et al. A machine learning approach for type 2 diabetes diagnosis and prognosis using tailored heterogeneous feature subsets. Med Biol Eng Comput 2025;63:2733–2752.
  21. Wei J, Yan Z, Mei M, Chen S, Geng W, Yu Z, et al. Machine learning-assisted BMOFs-derived 1D NiCo2O4 nanozyme photoelectrochemical detection of RBP4 for type 2 diabetes diagnosis. Chem Eng J 2025;524:169192.
  22. Enríquez-Ortega D, Chulde-Fernández B, Pozo-Coral P, Vaca A, Zhinin-Vera L, Almeida-Galárraga D, Ramírez-Cando L, et al. Enhancing diabetes diagnosis through machine learning: a comparative study. Appl Sci 2025;15(18):10087.