A Proposed Model for Diabetes Diagnosis Using a Hybrid Approach Based on an Improved Harris Hawks Algorithm and Machine Learning Methods

Fatemeh  Khani; Saeed Ayat; Mahdi  Esmaeili

Authors

Fatemeh Khani Ph.D. Student, Department of computer, kas.c., Islamic Azad university, kashan, iran Author https://orcid.org/0009-0005-8410-0408
Saeed Ayat Associate Professor, Department of Computer Engineering and Information Technology, Payame Noor University, Tehran, IRAN Corresponding author https://orcid.org/0000-0003-2998-6718
Mahdi Esmaeili Associate Professor, Department of computer, kas.c., Islamic Azad university, kashan, iran Author https://orcid.org/0000-0002-0124-8003

Keywords:

public policy, participatory governance, institutional capacity, public policy implementation, policy gap

Abstract

Early detection of diabetes represents a major challenge in healthcare systems, as a considerable proportion of patients are identified only at advanced stages, when opportunities for effective intervention have already diminished. Enhancing the accuracy of machine learning models depends critically on selecting optimal features—a process that becomes particularly important in high dimensional medical datasets. In the present study, an improved version of the Harris Hawks Optimization algorithm, referred to as Improved Harris Hawks Optimization (IHHO), was employed for feature selection. The proposed enhancements include the incorporation of chaotic maps for initialization, modification of the prey energy function, and the use of Lévy flight to strengthen the balance between exploration and exploitation. The performance of IHHO, in combination with eight widely used machine learning classifiers—RF, SVM, ANN, Logistic Regression, Linear Regression, KNN, Naive Bayes, and Decision Tree—was evaluated using the Pima Indians Diabetes dataset. The findings indicate that IHHO substantially outperforms both the Baseline methods and the standard HHO algorithm, achieving its best results in the IHHO+RF combination, with an Accuracy of 97.20 %, Precision of 94.51 %, Recall of 98.33 %, and an F1 Score of 96.38 %. Statistical analyses, including ANOVA, Post hoc tests, and the Friedman test, further confirm the significance of these differences. The results demonstrate that IHHO can serve as a robust framework for feature selection in medical diagnosis and can contribute to the development of reliable intelligent systems for diabetes screening.

References

[1] A. A. Yameny, "Diabetes Mellitus Overview 2024," Journal of Bioscience and Applied Research, vol. 10, no. 3, pp. 641-645, 2024.

[2] E. D. Parker et al., "Economic Costs of Diabetes in the United States in 2022," Diabetes Care, vol. 47, no. 1, pp. 26-43, 2024.

[3] U. K. Rangaswamy, C. Ratan, A. A. Anil, D. Rajesh, and A. Laxmi Krishnan, "Data Analysis in Diabetes and the Role of Technology in Diabetes Management," in Diabetes Mellitus: Academic Press, 2025, pp. 239-272.

[4] M. Nauman, A. S. Almadhor, M. Albekairi, A. R. Ansari, M. A. Fayyaz, and R. Nawaz, "The Role of Big Data Analytics in Revolutionizing Diabetes Management and Healthcare Decision-Making," IEEE Access, 2025.

[5] S. Padmalal, P. Arumugam, M. B. Anusha, K. D. Bamane, N. Yamsani, and K. Muppavaram, "Machine Learning for Early Detection of Chronic Diseases: A Case Study in Diabetes Prediction," in Machine Learning in Healthcare: Data-Driven Decisions, Predictive Modelling, Personalized Medicine, 2026, p. 171.

[6] P. Nayak, J. S. N. Jyothi, V. Harika, K. Swaraja, and A. S. Hanuman, "Diabetes Monitoring and Prediction Using Computational Intelligence Techniques: A Systematic Review," SN Computer Science, vol. 6, no. 3, p. 267, 2025.

[7] S. Verma, R. Rallan, T. Singh, and N. Kumar, "Unified Disease Prediction System Using Machine Learning Techniques," presented at the 2025 International Conference on Automation and Computation, 2025/03, 2025.

[8] D. Kalita, H. Sharma, and K. B. Mirza, "Deep Learning on Edge and Cloud for Intelligent Monitoring and Decision Making in Artificial Pancreas," Expert Systems with Applications, vol. 295, p. 128833, 2026.

[9] R. Rastogi and M. Bansal, "Diabetes Prediction Model Using Data Mining Techniques," Measurement: Sensors, vol. 25, p. 100605, 2023.

[10] P. N. Thotad, G. R. Bharamagoudar, and B. S. Anami, "Diabetes Disease Detection and Classification on Indian Demographic and Health Survey Data Using Machine Learning Methods," Diabetes & Metabolic Syndrome: Clinical Research & Reviews, vol. 17, no. 1, p. 102690, 2023.

[11] S. K. S. Modak and V. K. Jha, "Diabetes Prediction Model Using Machine Learning Techniques," Multimedia Tools and Applications, vol. 83, no. 13, pp. 38523-38549, 2024.

[12] M. S. Salih, R. K. Ibrahim, S. R. Zeebaree, D. Asaad, L. M. Zebari, and N. M. Abdulkareem, "Diabetic Prediction Based on Machine Learning Using PIMA Indian Dataset," Communications on Applied Nonlinear Analysis, vol. 31, no. 5s, pp. 138-156, 2024.

[13] M. R. Hossain, M. J. Hossain, M. M. Rahman, and M. M. Alam, "Machine Learning-Based Prediction and Insights of Diabetes Disease: Pima Indian and Frankfurt Datasets," Journal of Mechanics of Continua and Mathematical Sciences, vol. 20, no. 1, pp. 99-114, 2025.

[14] D. Alfredo, C. S. P. Fidel, and A. Gonzalo, "Stacking Ensemble Approach to Diagnosing the Disease of Diabetes," Informatics in Medicine Unlocked, vol. 44, p. 101427, 2024.

[15] Z. Zhang et al., "A Novel Evolutionary Ensemble Prediction Model Using Harmony Search and Stacking for Diabetes Diagnosis," Journal of King Saud University—Computer and Information Sciences, vol. 36, no. 1, p. 101873, 2024.

[16] M. Scholar, A. S. Singh, and K. K. Agrawal, "Optimizing Diabetes Prediction with Multi-Layer Perceptron: A Comprehensive Analysis on the Pima Indians Dataset," presented at the 2025 3rd International Conference on Communication, Security, and Artificial Intelligence, 2025/04, 2025.

[17] K. S. Farsana and A. Poulose, "Hybrid Convolutional Neural Networks for Pima Indians Diabetes Prediction," presented at the 2024 Fifteenth International Conference on Ubiquitous and Future Networks, 2024/07, 2024.

[18] H. Khan, N. Javaid, T. Bashir, Z. Ali, F. A. Khan, and D. Pamucar, "A Novel Deep Gated Network Model for Explainable Diabetes Mellitus Prediction at Early Stages," Knowledge-Based Systems, p. 114178, 2025.

[19] G. Dharmarathne, T. N. Jayasinghe, M. Bogahawaththa, D. P. P. Meddage, and U. Rathnayake, "A Novel Machine Learning Approach for Diagnosing Diabetes with a Self-Explainable Interface," Healthcare Analytics, vol. 5, p. 100301, 2024.

[20] I. Shaheen, N. Javaid, Z. Ali, I. Ahmed, F. A. Khan, and D. Pamucar, "A Trustworthy and Patient Privacy-Conscious Framework for Early Diabetes Prediction Using Deep Residual Networks and Proximity-Based Data," Biomedical Signal Processing and Control, vol. 112, p. 108361, 2026.

[21] B. Toleva, I. Atanasov, I. Ivanov, and V. Hooper, "An Effective Methodology for Diabetes Prediction in the Case of Class Imbalance," Bioengineering, vol. 12, no. 1, p. 35, 2025.

[22] O. Olabanjo, A. Wusu, O. Olabanjo, M. Asokere, O. Afisi, and B. Akinnuwesi, "A Novel Deep Learning Model for Early Diabetes Risk Prediction Using Attention-Enhanced Deep Belief Networks with Highly Imbalanced Data," International Journal of Information Technology, pp. 1-23, 2025.

[23] J. Wang and N. Awang, "A Novel Synthetic Minority Oversampling Technique for Multiclass Imbalance Problems," IEEE Access, 2025.

[24] I. Abousaber, "Enhanced Diabetes Prediction through Advanced Machine Learning and Imbalance Handling Techniques," presented at the 2025 4th International Conference on Computing and Information Technology, 2025/04, 2025.

[25] M. A. Uddin et al., "Machine Learning-Based Diabetes Detection Model for False Negative Reduction," Biomedical Materials & Devices, vol. 2, no. 1, pp. 427-443, 2024.

[26] N. Mumtazah, I. Waspada, K. D. Mutiara, and S. Adhy, "A Combination of Data Mining Methods for Disease Classification Using Patient-Perceived Symptoms from Medical Records," presented at the 2024 7th International Conference on Informatics and Computational Sciences, 2024/07, 2024.

[27] K. Natarajan, D. Baskaran, and S. Kamalanathan, "An Adaptive Ensemble Feature Selection Technique for Model-Agnostic Diabetes Prediction," Scientific Reports, vol. 15, no. 1, p. 6907, 2025.

[28] S. P. M. Kodete, S. H. Palli, J. Kola, S. P. Pasupuleti, G. Ravi, and M. H. Prasad, "A Hybrid Feature Selection and Logistic Regression Approach for High-Accuracy Early Diabetes Detection," presented at the 2025 5th International Conference on Soft Computing for Security Applications, 2025/08, 2025.

[29] M. Karuppasamy and K. Poorani, "Metaheuristic Feature Selection for Diabetes Prediction with PGS Approach," Procedia Computer Science, vol. 252, pp. 165-171, 2025.

[30] R. Kapila and S. Saleti, "Federated Learning-Based Disease Prediction: A Fusion Approach with Feature Selection and Extraction," Biomedical Signal Processing and Control, vol. 100, p. 106961, 2025.

[31] S. Shashaani and K. Vahdat, "Improved Feature Selection with Simulation Optimization," Optimization and Engineering, vol. 24, no. 2, pp. 1183-1223, 2023.

[32] A. Das, S. Mollick, H. Mondal, T. J. Bala, A. Nag, and A. Guho, "Meta-Heuristic Algorithms for High-Dimensional Feature Selection: A Systematic Review of Methodologies, Applications, and Emerging Challenges with Future Research Directions," in Feature Fusion for Next-Generation AI, 2026, pp. 51-61.

[33] R. K. Halder, M. N. Uddin, M. A. Uddin, S. Aryal, and A. Khraisat, "Enhancing K-Nearest Neighbor Algorithm: A Comprehensive Review and Performance Analysis of Modifications," Journal of Big Data, vol. 11, no. 1, p. 113, 2024.

[34] O. Peretz, M. Koren, and O. Koren, "Naive Bayes Classifier—An Ensemble Procedure for Recall and Precision Enrichment," Engineering Applications of Artificial Intelligence, vol. 136, p. 108972, 2024.

[35] S. K. S. Modak and V. K. Jha, "Machine and Deep Learning Techniques for the Prediction of Diabetics: A Review," Multimedia Tools and Applications, vol. 84, no. 18, pp. 19425-19549, 2025.

[36] K. Rajwar, K. Deep, and S. Das, "An Exhaustive Review of the Metaheuristic Algorithms for Search and Optimization: Taxonomy, Applications, and Open Challenges," Artificial Intelligence Review, vol. 56, no. 11, pp. 13187-13257, 2023.

[37] M. S. Shaikh et al., "Applications, Classifications, and Challenges: A Comprehensive Evaluation of Recently Developed Metaheuristics for Search and Analysis," Artificial Intelligence Review, vol. 58, no. 12, pp. 1-110, 2025.

[38] A. Singh, N. Prakash, and A. Jain, "Meta-Heuristic Optimization for the Multi-Classification of Chronic Disease: A Review with Machine Learning Perspectives," Wiley Interdisciplinary Reviews: Data Mining and Knowledge Discovery, vol. 15, no. 3, p. e70030, 2025.

[39] K. Veeranjaneyulu, M. Lakshmi, and S. Janakiraman, "Swarm Intelligent Metaheuristic Optimization Algorithms-Based Artificial Neural Network Models for Breast Cancer Diagnosis: Emerging Trends, Challenges and Future Research Directions," Archives of Computational Methods in Engineering, vol. 32, no. 1, pp. 381-398, 2025.

[40] M. Pluhacek, A. Kazikova, A. Viktorin, T. Kadavy, and R. Senkerik, "Chaos in Popular Metaheuristic Optimizers—A Bibliographic Analysis," in Recent Improvements in the Theory of Chaotic Attractors: CRC Press, 2025, pp. 106-121.

[41] D. T. Akl, M. M. Saafan, A. Y. Haikal, and E. M. El-Gendy, "IHHO: An Improved Harris Hawks Optimization Algorithm for Solving Engineering Problems," Neural Computing and Applications, vol. 36, no. 20, pp. 12185-12298, 2024.

[42] Y. X. Li, J. S. Wang, S. W. Zhang, S. H. Zhang, X. Y. Guan, and X. R. Ma, "Arithmetic Optimization Algorithm with Cosine Transform-Based Two-Dimensional Composite Chaotic Mapping," Soft Computing, pp. 1-41, 2025.

[43] Y. L. Qi, C. Xing, J. S. Wang, Y. W. Song, and X. Y. Guan, "Improved Goose Algorithm Based on Vertical and Horizontal Crossover Strategy and Random Walk to Solve Engineering Optimization Problems," Engineering Letters, vol. 33, no. 5, 2025.

[44] V. Awasthi et al., "ViT-HHO: Optimized Vision Transformer for Diabetic Retinopathy Detection Using Harris Hawk Optimization," MethodsX, vol. 13, p. 103018, 2024.

[45] Z. Zhang, K. A. Ahmed, M. R. Hasan, T. Gedeon, and M. Z. Hossain, "A Deep Learning Approach to Diabetes Diagnosis," presented at the Asian Conference on Intelligent Information and Database Systems, 2024/04, 2024.

[46] M. Zeinalnezhad and S. Shishehchi, "An Integrated Data Mining Algorithms and Metaheuristic Technique to Predict the Readmission Risk of Diabetic Patients," Healthcare Analytics, vol. 5, p. 100292, 2024.

[47] J. K. Shimpi, P. Shanmugam, and A. A. Stonier, "Analytical Model to Predict Diabetic Patients Using an Optimized Hybrid Classifier," Soft Computing, vol. 28, no. 3, pp. 1883-1892, 2024.

[48] J. Li, M. S. Othman, H. Chen, and L. M. Yusuf, "Optimizing IoT Intrusion Detection System: Feature Selection versus Feature Extraction in Machine Learning," Journal of Big Data, vol. 11, no. 1, p. 36, 2024.

[49] V. Ambikavathi, P. Arumugam, and P. Jose, "Diabetes Detection by Data Mining Methods," Wireless Personal Communications, vol. 133, no. 4, pp. 2087-2104, 2023.

[50] F. A. Jaber and J. W. James, "Early Prediction of Diabetic Using Data Mining," SN Computer Science, vol. 4, no. 2, p. 169, 2023.

[51] X. Li, J. Zhang, and F. Safara, "Improving the Accuracy of Diabetes Diagnosis Applications through a Hybrid Feature Selection Algorithm," Neural Processing Letters, vol. 55, no. 1, pp. 153-169, 2023.