Volume 25, Issue 5 (12-2025)
ijdld 2025, 25(5): 453-471 |
Back to browse issues page
Download citation:
BibTeX | RIS | EndNote | Medlars | ProCite | Reference Manager | RefWorks
Send citation to:
BibTeX | RIS | EndNote | Medlars | ProCite | Reference Manager | RefWorks
Send citation to:
Azgomi H, Asghari A. A Method for Diabetes Diagnosis Using Simulated Annealing and
K-Nearest Neighbor Algorithms. ijdld 2025; 25 (5) :453-471
URL: http://ijdld.tums.ac.ir/article-1-6431-en.html
URL: http://ijdld.tums.ac.ir/article-1-6431-en.html
1- Department of Computer Engineering, Ra.C., Islamic Azad University, Rasht, Iran , hossein.azgomi@gmail.com
2- Department of Computer Engineering, Shafagh Institute of Higher Education, Tonekabon, Iran
2- Department of Computer Engineering, Shafagh Institute of Higher Education, Tonekabon, Iran
Abstract: (527 Views)
Background: Diabetes is a chronic disease where the body cannot use or store glucose properly. Diabetes occurs when the pancreas is unable to produce insulin, or the body cannot use the insulin produced. Nowadays, diabetes is a common disease worldwide, and providing automated methods for its diagnosis is critically important.
Methods: This paper introduces a novel method for diagnosing diabetes using artificial intelligence (AI) algorithms. The proposed method is based on metaheuristic and classification algorithms. The simulated annealing (SA) metaheuristic algorithm was used for feature selection. Diabetes diagnosis was performed using the improved K-nearest neighbor (KNN) classification algorithm. In addition to the proposed method, the performance of two other methods, named MVMCNN and WKNN, was studied for diabetes diagnosis.
Results: The proposed method has been compared practically with the two other methods for diagnosing diabetes. The comparisons are based on the accuracy rate of disease diagnosis. In the experiments, the proposed method (SAKNN) demonstrated 95% accuracy, the MVMCNN method showed 93% accuracy, and the WKNN method demonstrated 90% accuracy. Thus, the proposed method outperformed the others. The proposed method also had acceptable performance in terms of time and several other criteria.
Conclusion: The proposed method for diagnosing diabetes, using metaheuristic and classification algorithms, provides higher accuracy compared to other methods. These results indicate that the proper use of AI techniques can offer effective solutions for the automatic diagnosis of diabetes and can be used as an auxiliary tool for doctors and researchers.
Methods: This paper introduces a novel method for diagnosing diabetes using artificial intelligence (AI) algorithms. The proposed method is based on metaheuristic and classification algorithms. The simulated annealing (SA) metaheuristic algorithm was used for feature selection. Diabetes diagnosis was performed using the improved K-nearest neighbor (KNN) classification algorithm. In addition to the proposed method, the performance of two other methods, named MVMCNN and WKNN, was studied for diabetes diagnosis.
Results: The proposed method has been compared practically with the two other methods for diagnosing diabetes. The comparisons are based on the accuracy rate of disease diagnosis. In the experiments, the proposed method (SAKNN) demonstrated 95% accuracy, the MVMCNN method showed 93% accuracy, and the WKNN method demonstrated 90% accuracy. Thus, the proposed method outperformed the others. The proposed method also had acceptable performance in terms of time and several other criteria.
Conclusion: The proposed method for diagnosing diabetes, using metaheuristic and classification algorithms, provides higher accuracy compared to other methods. These results indicate that the proper use of AI techniques can offer effective solutions for the automatic diagnosis of diabetes and can be used as an auxiliary tool for doctors and researchers.
Send email to the article author
| Rights and permissions | |
 |
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License. |
