Iranian Journal of

---

Background: Diabetes is a serious global health problem, and effective methods for its prediction and management are essential. Conventional diagnostic approaches typically rely on tests such as oral glucose tolerance test (OGTT), fasting plasma glucose (FPG) and glycated hemoglobin (HbA1c). Machine learning has the potential to enhance diagnostic accuracy; however, its performance and alignment with clinical guidelines require thorough evaluation.
Methods: This narrative review examines the effectiveness of machine learning in the early diagnosis of diabetes. Articles were selected based on predefined criteria and analyzed in terms of algorithm classification, output measures, involvement of clinical experts, and interpretability. Evaluation metrics such as accuracy, area under the curve (AUC), specificity and sensitivity were used to assess algorithmic performance. Relevant studies comparing prediabetes diagnosis using artificial intelligence and conventional methods were reviewed, and clinical guidelines from both domains were extracted and compared.
Results: Analysis of 41 articles showed that ANN, LR, and DNN were the most frequently used algorithms. Only 2% of the studies incorporated clinical rules and physician involvement, and 12% demonstrated model interpretability. While conventional methods rely on HbA1c and FPG tests, no clinical guidelines currently exist for AI-based diagnosis. Machine learning algorithms outperformed traditional methods, showing 29% higher sensitivity and 23% higher specificity.
Conclusion: Although artificial intelligence demonstrates superior performance in prediabetes diagnosis, limitations such as lack of interpretability and the absence of standardized clinical guidelines hinder its current clinical application. Addressing these challenges could enable AI to become a more efficient and reliable diagnostic tool.
 

---

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.