Modifying Meta-Heuristic Algorithm to Identify the Most Important Features for Diagnosis of the Thalassemia Data in Baghdad
DOI:
https://doi.org/10.22401/anjs.29.3.3217Keywords:
Features subset selection, Meta-heuristic algorithms, hybrid machine learning model , Classification.Abstract
Machine learning feature selection is crucial for improving classification performance by breaking down high-dimensional data into manageable low-dimensional subsets. AI techniques have significantly improved the diagnosis of hematological illnesses, but little research has explored hybrid machine learning approaches that combine qualitative and quantitative data sources. This study introduces a hybrid feature selection method called ABC-PSO, which combines the strengths of artificial bee colony (ABC) and particle swarm optimization (PSO) algorithms. The method was tested against well-known meta-heuristic techniques like genetic algorithm (GA), PSO, ABC, and grey wolf optimizer (GWO) to improve classification accuracy in medical diagnosis. ABC-PSO uses both ABC's exploration potential and PSO's quick convergence to determine the most relevant subset of features. The ABC-PSO algorithm, which was tested on 300 Baghdadi thalassemia patients, demonstrated superior classification performance across various classifiers like support vector machine (SVM), random forest, and gradient boosting In terms of accuracy, AUC, and F1-score, it fared better than standalone methods, indicating its promise as a formidable feature selection method in the analysis of medical data. Using the random forest classifier, the algorithm achieved the greatest accuracy of 0.90 and an AUC of 0.95, outperforming other algorithms consistently across all assessment criteria. The algorithm's exceptional generalization ability and durability in diagnosing thalassemia are also emphasized.
References
[1] Barrera, J.; Cisternas, F.; Crawford, B.; Gómez, S. M.; Soto, R.; "Feature Selection Problem and Metaheuristics: A Systematic Literature Review about Its Formulation, Evaluation and Applications". Biomimetics, 9 (1): 9, 2024.
[2] Hoseini, S. M.; Ebtia, M.; Dehgardi, M.; "A Hybrid Feature Selection Technique Leveraging Principal Component Analysis And Support Vector Machines". J. Artif. Intell. Data Min., 13 (2): 159–173, 2025.
[3] Susanto, E. R.; Syarif, A.; Muludi, K.; Perdani, R. R. W.; Wantoro, A.; "Implementation of Fuzzy-based Model for Prediction of Thalassemia Diseases". J. Phys. Conf. Ser. 3rd Int. Conf. Appl. Sci. Math. Informatics Sept. 3-4, 2020, Bandar Lampung, Indones., 1751 (1): 012034, 2021.
[4] AL-hameedawi, A. K.; Al-Shawi, A. A.; "Identification of novel mutations in β-thalassemia patients in Maysan Governorate, Iraq". Mol. Biol. Rep., 50 (4): 3053–3062, 2023.
[5] Sallam, N. M.; Saleh, A. I.; Arafat, A. H.; Abdelsalam, M. M.; "An Efficient Strategy for Blood Diseases Detection Based on Grey Wolf Optimization as Feature Selection and Machine Learning Techniques". Appl. Sci., 12 (21): 10760, 2022.
[6] Sameer, F. O.; "Modified Multi-Criteria Decision Making Methods to Assess Classification Methods". Iraqi J. Sci., 64 (2): 893–906, 2023.
[7] Sameer, F. O.; "Comparison study on the performance of the multi classifiers with hybrid optimal features selection method for medical data diagnosis". Multimed. Tools Appl., 81 (13): 18073–18090, 2022.
[8] Narasimhan, G.; Victor, A.; "A hybrid approach with metaheuristic optimization and random forest in improving heart disease prediction". Sci. Rep., 15 :10971, 2025.
[9] Mehrabi, N.; Boroujeni, S. P. H.; Pashaei, E.; "An efficient high-dimensional gene selection approach based on the Binary Horse Herd Optimization Algorithm for biologicaldata classification". Iran J. Comput. Sci., 7 (2): 279–309, 2024.
[10] Lee, J.; Yoon, Y.; Kim, J.; Kim, Y. H.; "Metaheuristic-Based Feature Selection Methods for Diagnosing Sarcopenia with Machine Learning Algorithms". Biomimetics, 9 (3):179, 2024.
[11] Egejuru, N. C.; Olusanya, O. S.; Asinobi, O. A.; Adeyemi, J. O.; Adebayo, O. V.; Idowu, A. P.; "Using Data Mining Algorithms for Thalassemia Risk Prediction". Int. J. Biomed. Sci. Eng., 7 (2): 33, 2019.
[12] Elshaikh, R. H.; Amir, R.; Ahmeide, A.; Mohamedahmed, K. A.; Alfeel, A. H.; Higazi, H.; Hussein, S. E. O.; Babker, A. M. A.; "Evaluation of the Discrimination between Beta-Thalassemia Trait and Iron Deficiency Anemia Using Different Indexes". Int. J. Biomed., 12 (3): 375–379, 2022.
[13] Ayyıldız, H.; Tuncer, S. A.; "Determination of the effect of red blood cell parameters in the discrimination of iron deficiency anemia and beta thalassemia via Neighborhood Component Analysis Feature Selection-Based machine learning". Chemom. Intell. Lab. Syst., 196 (October): 103886., 2020.
[14] Jahangiri, M.; Rahim, F.; Saki, N.; Malehi, A. S.; "Application of Bayesian Decision Tree in Hematology Research: Differential Diagnosis of β -Thalassemia Trait from Iron Deficiency Anemia". Comput. Math. Methods Med., 2021 (1): 6401105, 2021.
[15] Mo, D.; Zheng, Q.; Xiao, B.; Li, L.; "Predicting thalassemia using deep neural network based on red blood cell indices". Clin. Chim. Acta, 543: 117329, 2023.
[16] Saleem, M.; Aslam, W.; Lali, M. I. U.; Rauf, H. T.; Nasr, E. A.; "Predicting Thalassemia Using Feature Selection Techniques: A Comparative Analysis". Diagnostics, 13 (22): 3441, 2023.
[17] Abdulridha, S. H.; Kadhim, D. J.; "Optimal Mobile Robot Navigation in Unknown Environments using Different Optimization Techniques". Al-Nahrain J. Eng. Sci. NJES, 28 (2): 164–173, 2025.
[18] Assi, J. H.; Sadiq, A. T.; "Modified artificial immune system as feature selection". Iraqi J. Sci., 59 (2): 733–738, 2018.
[19] Motair, H. M.; "Modified Firefly Algorithm using Iterated Descent Method to Solve Machine Scheduling Problems". Al-Nahrain J. Sci., 26 (4): 88–94, 2023.
[20] Samaah, F. N. U.; "A Timeless Guide to Evolutionary Problem Solving : A Review of David E . Goldberg ’ s Genetic Algorithms in Search , Optimization , and Machine Learning". J. Artif. Intell. Comput. Sci., 1: 16–21, 2025.
[21] Wang, D.; Tan, D.; Liu, L.; "Particle swarm optimization algorithm: an overview". Soft Comput., 22 (2): 387–408, 2018.
[22] Mirjalili, S.; Mirjalili, S. M.; Lewis, A.; "Grey Wolf Optimizer". Adv. Eng. Softw., 69: 46–61, 2014.
[23] Nozohour-leilabady, B.; Fazelabdolabadi, B.; "On the application of artificial bee colony (ABC) algorithm for optimization of well placements in fractured reservoirs; efficiency comparison with the particle swarm optimization (PSO) methodology". Petroleum, 2 (1): 79–89, 2016.
[24] Feng, X.; Xiao, Z.; Zhong, B.; Qiu, J.; Dong, Y.; "Dynamic ensemble classification for credit scoring using soft probability". Appl. Soft Comput. J., 65: 139–151, 2018.
[25] Salman, H. A.; Kalakech, A.; Steiti, A.; "Random Forest Algorithm Overview". Babylonian J. Mach. Learn., 2024: 69–79, 2024.
[26] Bowd, C.; Belghith, A.; Proudfoot, J. A.; Zangwill, L. M.; Goldbaum, M. H.; Hou, H.; Penteado, R. C.; Moghimi, S.; "Gradient Boosting Classifiers Combining Vessel Density and Tissue Thickness Measurements for Classifying Early to Moderate Glaucoma". Am J Ophthalmol, 217 (1): 131–139, 2021.
[27] Gad, A. G.; "Particle Swarm Optimization Algorithm and Its Applications: A Systematic Review". Arch. Comput. Methods Eng., 29 (5): 2531–2561, 2022.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Fadhaa O. Sameer
This work is licensed under a Creative Commons Attribution 4.0 International License.
.jpg)
