A New Approach for Thyroid Disease Detection Using Metaheuristic Algorithm-Machine Learning Technique

Year 2025, Volume: 25 Issue: 6, 1336 - 1347

Nurullah Öztürk

Abstract

Thyroid disease is a common health issue that can affect individuals of all ages and genders, often impairing the thyroid gland’s ability to produce adequate levels of hormones. Early diagnosis of thyroid disease is of great importance for controlling the progression and preventing potential complications. The aim of this study is to develop an innovative, machine learning-based method with high accuracy for the early diagnosis of thyroid disease. In this study, a novel hybrid method is proposed by integrating correlation-based feature selection, a softmax classifier, and the Artificial Bee Colony algorithm. The proposed method enhances diagnostic and classification performance by applying explainable feature extraction, multi-class classification via the softmax classifier, and hyperparameter optimization using the Artificial Bee Colony algorithm. Experimental evaluations were conducted using the “Thyroid Disease” dataset available in the UCI Machine Learning Repository. In addition, traditional classification algorithms such as K-Nearest Neighbors, Support Vector Machines, Artificial Neural Networks, and Naive Bayes were applied for comparative analysis. The results indicate that the proposed hybrid method outperforms other approaches, achieving the highest accuracy (96.11%), precision (82.38%), and F1-score (80.84%). Owing to its applicability in different clinical scenarios, the proposed hybrid method supports clinical decision making, especially in early diagnosis and treatment processes.

Keywords

Thyroid Disease Detection , Explainable Feature Extraction , Machine Learning , Meta-heuristic Algorithm , Clinical Decision System

Meta-sezgisel Algoritma Destekli Makine Öğrenmesi Yöntemiyle Tiroid Hastalığının Tespitinde Yeni Bir Yaklaşım

Abstract

Tiroid hastalığı, her yaş grubunda ve cinsiyette görülebilen, kişinin tiroid bezinin yeterli düzeyde hormon üretmesini engelleyen yaygın sağlık sorunları arasında yer almaktadır. Hastalığın erken dönemde teşhis edilmesi, ilerlemesinin kontrol altına alınması ve olası komplikasyonların önlenmesi açısından büyük önem taşımaktadır. Bu çalışmanın amacı, tiroid hastalığının erken evrede teşhisinde yüksek doğruluk sağlayan yenilikçi bir makine öğrenmesi tabanlı yöntem geliştirmektir. Bu çalışmada, korelasyon tabanlı özellik seçimi, softmax sınıflandırıcı ve Yapay Arı Kolonisi algoritması bir araya getirilerek yeni bir hibrit yöntem önerilmiştir. Önerilen yöntemde, açıklanabilir özellik çıkarımı uygulanmakta, çoklu sınıflandırma yapısına sahip softmax sınıflandırıcı ve Yapay Arı Kolonisi algoritması ile hiperparametre optimizasyonu kullanılarak tiroid hastalığının teşhisi ve sınıflandırma doğruluğu artırılmıştır. Deneysel çalışmalar, UCI makine öğrenme deposunda yer alan “Thyroid Disease” veri seti kullanılarak gerçekleştirilmiştir. Ayrıca, bu çalışmada K-En Yakın Komşu, Destek Vektör Makinası, Yapay Sinir Ağları ve Saf Bayes gibi klasik sınıflandırma algoritmaları da uygulanmıştır. Elde edilen sonuçlar, önerilen hibrit yöntemin uygulanan diğer yöntemlere kıyasla ortalama en iyi doğruluk (%96.11), duyarlılık (%82.38) ve F1-başarım (%80.84) değerlerine ulaştığını göstermektedir. Sunulan bu hibrit yöntem, farklı klinik senaryolarda uygulanabilirliği sayesinde özellikle erken tanı ve tedavi süreçlerinde klinik karar alma mekanizmalarına katkı sağlayabilecek niteliktedir.

Keywords

Tiroid Hastalığı Tespiti , Açıklanabilir Özellik Çıkarımı , Makine Öğrenmesi , Meta-sezgisel Algoritma , Klinik Karar Mekanizması

Ethical Statement

Yazarlar tüm etik standartlara uyduklarını beyan ederler.

References

• Akter, S., ve Mustafa, H. A. (2024). Analysis and interpretability of machine learning models to classify thyroid disease. Plos one, 19(5), e0300670. https://doi.org/10.1371/journal.pone.0300670
• Arslan, N. N., ve Ozdemir, D. (2024). Analysis of CNN models in classifying Alzheimer's stages: comparison and explainability examination of the proposed separable convolution-based neural network and transfer learning models. Signal, Image and Video Processing, 18(Suppl 1), 447-461. https://doi.org/10.1007/s11760-024-03166-5
• Beynon ME, Pinneri K. 2016. An overview of the thyroid gland and thyroid-related deaths for the forensic pathologist. Academic Forensic Pathology 6(2):217–236. https://doi.org/10.23907/2016.024
• Carrington, A. M., Manuel, D. G., Fieguth, P. W., Ramsay, T., Osmani, V., Wernly, B., Bennett, C., Hawken, S., Magwood, O., Sheikh, Y., Mclnnes, M., & Holzinger, A. (2022). Deep ROC analysis and AUC as balanced average accuracy, for improved classifier selection, audit and explanation. IEEE Transactions on Pattern Analysis and Machine Intelligence, 45(1), 329-341. https://doi.org/10.1109/TPAMI.2022.3145392
• Chaganti, R., Rustam, F., De La Torre Díez, I., Mazón, J. L. V., Rodríguez, C. L., & Ashraf, I. (2022). Thyroid disease prediction using selective features and machine learning techniques. Cancers, 14(16), 3914. https://doi.org/10.3390/cancers14163914
• D. Karaboga (2005). An idea based on honey bee swarm for numerical optimization, Technical report-tr06, Erciyes University, Engineering Faculty, 2005.
• D. Karaboga, B. Gorkemli, C. Ozturk, N. Karaboga (2014). A comprehensive survey: Artificial bee colony (ABC) algorithm and applications, Artificial Intelligence Review. 42, 21–57. https://doi.org/10.1007/s10462-0129328-0
• Dörterler, S. (2023). Kanser hastalığı teşhisinde ölüm oyunu optimizasyon algoritmasının etkisi. Mühendislik Alanında Uluslararası Araştırmalar, 8, 15. ISBN: 978-625-6382-17-6
• Dörterler, S., Dumlu, H., Özdemir, D., & Temurtaş, H. (2022). Hybridization of k-means and meta-heuristics algorithms for heart disease diagnosis. New Trends in Engineering and Applied Natural Sciences, 55. ISBN: 978-625-8109-42-9 Dörterler, S., Dumlu, H., Özdemir, D., & Temurtaş, H. (2024). Hybridization of meta-heuristic algorithms with k-means for clustering analysis: Case of medical datasets. Gazi Journal of Engineering Sciences, 10(1), 1-11. https://doi.org/10.30855/gmbd.0705N01
• Garcia de Lomana, M., Weber, A. G., Birk, B., Landsiedel, R., Achenbach, J., Schleifer, K. J., Mathea, M., & Kirchmair, J. (2020). In silico models to predict the perturbation of molecular initiating events related to thyroid hormone homeostasis. Chemical research in toxicology, 34(2), 396-411.
• https://doi.org/10.1021/acs.chemrestox.0c00304 Guler Ayyildiz, B., Karakis, R., Terzioglu, B., & Ozdemir, D. (2024). Comparison of deep learning methods for the radiographic detection of patients with different periodontitis stages. Dentomaxillofacial Radiology, 53(1), 32-42. https://doi.org/10.1093/dmfr/twad003
• Gupta, P., Rustam, F., Kanwal, K., Aljedaani, W., Alfarhood, S., Safran, M., & Ashraf, I. (2024). Detecting thyroid disease using optimized machine learning model based on differential evolution. International Journal of Computational Intelligence Systems, 17(1), 3. https://doi.org/10.1007/s44196-023-00388-2
• Hosseinzadeh, M., Ahmed, O. H., Ghafour, M. Y., Safara, F., Hama, H. K., Ali, S., Vo, B., & Chiang, H. S. (2021). A multiple multilayer perceptron neural network with an adaptive learning algorithm for thyroid disease diagnosis in the internet of medical things. The Journal of Supercomputing, 77, 3616-3637. https://doi.org/10.1007/s11227-020-03404-w
• Islam, S. S., Haque, M. S., Miah, M. S. U., Sarwar, T. B., & Nugraha, R. (2022). Application of machine learning algorithms to predict the thyroid disease risk: an experimental comparative study. PeerJ Computer Science, 8, e898. https://doi.org/10.7717/peerj-cs.898
• Khojaste-Sarakhsi, M., Haghighi, S. S., Ghomi, S. F., & Marchiori, E. (2022). Deep learning for Alzheimer's disease diagnosis: A survey. Artificial intelligence in medicine, 130, 102332. https://doi.org/10.1016/j.artmed.2022.102332
• Kumar, S. J. K., Parthasarathi, P., Masud, M., Al-Amri, J. F., & Abouhawwash, M. (2023). Butterfly Optimized Feature Selection with Fuzzy C-Means Classifier for Thyroid Prediction. Intelligent Automation & Soft Computing, 35(3). https://doi.org/10.32604/iasc.2023.030335
• Lee, K. S., & Park, H. (2022). Machine learning on thyroid disease: a review. Frontiers in Bioscience-Landmark, 27(3), 101. https://doi.org/10.31083/j.fbl2703101
• Nguyen QT, Lee EJ, Huang MG, Park YI, Khullar A, Plodkowski RA. 2015. Diagnosis and treatment of patients with thyroid cancer. American Health & Drug Benefits 8(1):30–40. PMID: 25964831; PMCID: PMC4415174.
• Özer, E. (2024). Thyroid Disease Diagnosis: A Study on the Efficacy of Feature Reduction and Biomarker Selection in Artificial Neural Network Models. International Journal of Multidisciplinary Studies and Innovative Technologies, 8(2), 59-62. https://doi.org/10.36287/ijmsit.8.2.2
• Parveen, H. S., Karthik, S., & MS, K. (2024). Neural harmony: revolutionizing thyroid nodule diagnosis with hybrid networks and genetic algorithms. Computer Methods in Biomechanics and Biomedical Engineering, 1-18. https://doi.org/10.1080/10255842.2024.2341969
• Pichardo G. 2021. Thyroid cancer: symptoms, causes, diagnosis, treatment, WebMD. Available at https://www.webmd.com/cancer/what-is-thyroid-cancer
• Quinlan, R. (1986). Thyroid Disease [Dataset]. UCI Machine Learning Repository. https://doi.org/10.24432/C5D010
• Riajuliislam, M., Rahim, K. Z., & Mahmud, A. (2021, February). Prediction of thyroid disease (hypothyroid) in early stage using feature selection and classification techniques. In 2021 International conference on information and communication technology for sustainable development (ICICT4SD) (pp. 60-64). IEEE. https://doi.org/10.1109/ICICT4SD50815.2021.9397052
• Sandhu, G., Singh, A., Lamba, P. S., Virmani, D., & Chaudhary, G. (2023). Modified Euclidean-Canberra blend distance metric for kNN classifier. Intelligent Decision Technologies, 17(2), 527-541. https://doi.org/10.3233/idt-220223
• Sarker, I. H. (2021). Deep cybersecurity: a comprehensive overview from neural network and deep learning perspective. SN Computer Science, 2(3), 154. https://doi.org/10.1007/s42979-021-00535-6
• Sarker, I. H. (2021). Machine learning: Algorithms, real-world applications and research directions. SN computer science, 2(3), 160. https://doi.org/10.1007/s42979-021-00592-x
• Sarkar P. (2023). Naive Bayes in Machine Learning [Examples, Models, Types], https://www.knowledgehut.com/blog/data-science/naive-bayes-in-machine-learning
• Sultana, A., & Islam, R. (2023). Machine learning framework with feature selection approaches for thyroid disease classification and associated risk factors identification. Journal of Electrical Systems and Information Technology, 10(1), 32. https://doi.org/10.1186/s43067-023-00101-5
• Taha, A., Saad, B., Taha-Mehlitz, S., Ochs, V., El-Awar, J., Mourad, M. M., Neuman, K., Glaser, C., Rosenberg, R., & Cattin, P. C. (2024). Analysis of artificial intelligence in thyroid diagnostics and surgery: a scoping review. The American Journal of Surgery, 229, 57-64. https://doi.org/10.1016/j.amjsurg.2023.11.019
• Taylor PN, Albrecht D, Scholz A, Gutierrez-Buey G, Lazarus JH, Dayan CM, Okosieme OE. 2018. Global epidemiology of hyperthyroidism and hypothyroidism. Nature Reviews Endocrinology 14(5):301–316. https://doi.org/10.1038/nrendo.2018.18
• Wani, J. A., Sharma, S., Muzamil, M., Ahmed, S., Sharma, S., & Singh, S. (2022). Machine learning and deep learning based computational techniques in automatic agricultural diseases detection: Methodologies, applications, and challenges. Archives of Computational methods in Engineering, 29(1), 641-677. https://doi.org/10.1007/s11831-021-09588-5