View in EDS PDF Full Text

Improvement of machine learning-based diabetes diagnosis via resampling techniques.

Saved in:
Bibliographic Details
Title: Improvement of machine learning-based diabetes diagnosis via resampling techniques.
Alternate Title: Makine öğrenmesi tabanlı diyabet teşhisinin yeniden örnekleme teknikleri ile iyileştirilmesi.
Authors: Yapıcı, İrem Şenyer1 senyerirem@beun.edu.tr, Arslan, Rukiye Uzun2 rukiye.uzun@beun.edu.tr, Engin, Mustafa Alptekin3 maengin@bayburt.edu.tr
Source: Pamukkale University Journal of Engineering Sciences. 2026, Vol. 32 Issue 2, p247-258. 12p.
Subjects: Diagnosis of diabetes, Resampling (Statistics), Data augmentation, Decision trees, Classification algorithms, Machine learning, Medical informatics
Abstract (English): The objective of this study is to enhance the accuracy of diabetes diagnosis through the utilisation of machine learning techniques and resampling methods. The imbalanced nature of diabetes datasets presents a significant challenge for traditional classification algorithms, which often struggle to accurately predict results. In order to enhance the efficacy of the model, a comparative analysis was conducted to assess the performance of a range of over-sampling and under-sampling techniques, including SMOTE, ADASYN, Borderline SMOTE, SVM SMOTE, Random Under Sampler, Near Miss, One Sided Selection, Neighbourhood Cleaning Rule, Edited Nearest Neighbours, Instance Hardness Threshold, AllKNN and Tomek Links. The aforementioned techniques were then applied to the Decision Tree, Random Forest, K-Nearest Neighbours, AdaBoost, Extra Tree Classifier, and machine learning classifiers, and their performance was evaluated using the accuracy, recall, precision, F-Score, and AUC-ROC performance metrics. The SVMSMOTE resampling technique was identified as the most successful method, achieving 99.06% accuracy when used in combination with the decision tree classifier. The findings demonstrate that the incorporation of resampling techniques markedly enhances diagnostic proficiency and yields more dependable forecasts. This research makes a significant contribution to the field of medical informatics, providing a robust framework for diabetes diagnosis and offering valuable insights into the application of machine learning in healthcare. [ABSTRACT FROM AUTHOR]
Abstract (Turkish): Bu çalışmanın amacı, makine öğrenimi teknikleri ve yeniden örnekleme yöntemlerini kullanarak diyabet teşhisinin doğruluğunu artırmaktır. Diyabet veri setlerinin dengesiz yapısı, sonuçları doğru bir şekilde tahmin etmekte zorlanan geleneksel sınıflandırma algoritmaları için önemli bir zorluk teşkil etmektedir. Modelin etkinliğini artırmak amacıyla, SMOTE, ADASYN, Borderline SMOTE, SVM SMOTE, Random Under Sampler, Near Miss, One Sided Selection, Neighbourhood Cleaning Rule, Edited Nearest Neighbours, Instance Hardness Threshold, AllKNN ve Tomek Links dahil olmak üzere bir dizi aşırı örnekleme ve düşük örnekleme tekniklerinin performansını değerlendirmek için karşılaştırmalı bir analiz yapılmıştır. Yukarıda bahsedilen teknikler daha sonra Karar Ağacı, Rastgele Orman, K-En Yakın Komşular, AdaBoost, Ekstra Ağaç Sınıflandırıcı ve makine öğrenimi sınıflandırıcılarına uygulanmış ve performansları doğruluk, geri çağırma, kesinlik, F-Skoru ve AUC-ROC performans ölçütleri kullanılarak değerlendirilmiştir. SVMSMOTE yeniden örnekleme tekniği, karar ağacı sınıflandırıcısı ile birlikte kullanıldığında %99,06 doğruluk elde ederek en başarılı yöntem olarak belirlenmiştir. Bulgular, yeniden örnekleme tekniklerinin dahil edilmesinin teşhis yeterliliğini önemli ölçüde artırdığını ve daha güvenilir tahminler sağladığını göstermektedir. Bu araştırma, diyabet teşhisi için sağlam bir çerçeve sağlayarak ve makine öğreniminin sağlık hizmetlerinde uygulanmasına ilişkin değerli bilgiler sunarak tıbbi bilişim alanına önemli bir katkıda bulunmaktadır. [ABSTRACT FROM AUTHOR]
Copyright of Pamukkale University Journal of Engineering Sciences is the property of Pamukkale University Journal of Engineering Sciences (PAJES) and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)
Database: Engineering Source
Description
Abstract:The objective of this study is to enhance the accuracy of diabetes diagnosis through the utilisation of machine learning techniques and resampling methods. The imbalanced nature of diabetes datasets presents a significant challenge for traditional classification algorithms, which often struggle to accurately predict results. In order to enhance the efficacy of the model, a comparative analysis was conducted to assess the performance of a range of over-sampling and under-sampling techniques, including SMOTE, ADASYN, Borderline SMOTE, SVM SMOTE, Random Under Sampler, Near Miss, One Sided Selection, Neighbourhood Cleaning Rule, Edited Nearest Neighbours, Instance Hardness Threshold, AllKNN and Tomek Links. The aforementioned techniques were then applied to the Decision Tree, Random Forest, K-Nearest Neighbours, AdaBoost, Extra Tree Classifier, and machine learning classifiers, and their performance was evaluated using the accuracy, recall, precision, F-Score, and AUC-ROC performance metrics. The SVMSMOTE resampling technique was identified as the most successful method, achieving 99.06% accuracy when used in combination with the decision tree classifier. The findings demonstrate that the incorporation of resampling techniques markedly enhances diagnostic proficiency and yields more dependable forecasts. This research makes a significant contribution to the field of medical informatics, providing a robust framework for diabetes diagnosis and offering valuable insights into the application of machine learning in healthcare. [ABSTRACT FROM AUTHOR]
ISSN:13007009
DOI:10.5505/pajes.2025.52882