Development of an Intelligent Clinical Decision Support System for Early Detection of Thyroid Disorders Using Optimized Machine Learning Pipelines

Abraham Osemeke Agbonifo; Chidimma Grace Emmanuel; Nzubechi Augustine Oriaku; Onyedikachi Williams Onwuso; Uchechi Joyce Nneji; Benjamin Chiemeka Opara; Precious Mojolaoluwa Ojo; Richard Iherorochi Nneji

doi:10.56201/ijmepr.v10.no2.2026.pg96.123

Development of an Intelligent Clinical Decision Support System for Early Detection of Thyroid Disorders Using Optimized Machine Learning Pipelines

Abraham Osemeke Agbonifo, Chidimma Grace Emmanuel, Nzubechi Augustine Oriaku, Onyedikachi Williams Onwuso, Uchechi Joyce Nneji,, Benjamin Chiemeka Opara,, Precious Mojolaoluwa Ojo, Richard Iherorochi Nneji

Abstract

Thyroid disorders represent a significant endocrine imbalance that adversely affects the body's metabolic system. Critically, these physiological disorders often manifest as psychological symptoms, such as depression, anxiety, and cognitive decline leading to potential misdiagnosis in counseling and primary care settings. Traditional diagnosis is often labor-intensive, invasive, and costly. Machine learning (ML) offers a non-invasive pathway for early, cost-effective screening to support clinical decision-making. Method: Using the UCI thyroid illness dataset, we addressed missing data via mean imputation and constant placeholders to preserve clinical information. We optimized feature relevance using three distinct techniques: Hilbert-Schmidt Independence Criterion , Multi Spatially Uniform ReliefF (MultiSURF), and Minimum Redundancy- Maximum Relevance . These selected features were integrated with eight optimized classifiers, including SVM, Logistic Regression, KNN, Decision Tree, AdaBoost, Bagging, Stacking, and Voting models. Results: Experimental results demonstrate that applying robust feature selection significantly improved diagnostic performance. Among all combinations, mRMR combined with the Bagging classifier achieved optimal results, reaching an accuracy of 98.40%, precision of 97.85%, recall of 97.60%, F1-score of 97.31%, and an ROC-AUC of 99.57%. Conclusion: The results indicate that the proposed framework significantly enhances predictive stability and generalization. This intelligent system effectively predicts various thyroid conditions, including primary hypothyroidism and concurrent non-thyroidal illness offering counselors and clinicians a reliable auxiliary tool to identify physiological root causes of patient distress.

Keywords

Clinical Decision SupportThyroid DiseaseMachine LearningFeature SelectionmRMRHealth Informatics.

References

Anitha, M., R, K., E, R., & R, H. (2025, March). Smart thyroid: A deep learning-driven SVM model for thyroid diagnosis. In 2025 7th International Conference on Intelligent Sustainable Systems (pp. 1633–1639). IEEE. https://doi.org/10.1109/ICISS63372.2025.11076246 Kumari, P., Kaur, B., Rawat, A. K., & Rakhra, M. (2024, August). Role of machine learning in the prediction of thyroid disease. In 2024 International Conference on Electrical Electronics and Computing Technologies (pp. 1–5). IEEE. https://doi.org/10.1109/ICEECT61758.2024.10738959 Obaido, G., et al. (2024). An improved framework for detecting thyroid disease using filter-based feature selection and stacking ensemble. IEEE Access, 12, 89098–89112. https://doi.org/10.1109/ACCESS.2024.3418974 Prantik, M. Z. H., Abeda, M. M., & Alam, M. J. (2024, September). Hypothyroid disease prediction using machine learning & ensemble methods. In 2024 IEEE International Conference on Computing, Applications and Systems (pp. 1–6). IEEE. https://doi.org/10.1109/COMPAS60761.2024.10796084 Sakib, M. N., Sheakh, M. A., Tahosin, M. S., Sadik, M. R., Islam, M. A., & Akter, L. (2024, October). Accurate thyroid disease detection with ensemble learning models. In 2024 4th International Conference on Artificial Intelligence and Signal Processing (pp. 1– 6). IEEE. https://doi.org/10.1109/AISP61711.2024.10870726 Sanju, P., Ahmed, N. S. S., Ramachandran, P., Sajid, P. M., & Jayanthi, R. (2025). Enhancing thyroid disease prediction and comorbidity management through advanced machine learning frameworks. Clinical eHealth, 8, 7–16. https://doi.org/10.1016/j.ceh.2025.01.002 Sankar, S., Potti, A., Chandrika, G. N., & Ramasubbareddy, S. (2022). Thyroid disease prediction using XGBoost algorithms. Journal of Mobile Multimedia, 18(3), 917–933. https://doi.org/10.13052/jmm1550-4646.18322 Shelke, R. G., More, V. A., & Sayyad, J. (2025, August). Exploring artificial intelligence approach in internet of medical things for thyroid cancer detection. In 2025 International Conference on Applications of Machine Intelligence and Data Analytics (ICAMIDA) (pp. 1–6). IEEE. https://doi.org/10.1109/ICAMIDA64673.2025.11209522 Sujini, G. N., & Balakrishna, S. (2023, December). Machine learning based computer aided diagnosis models for thyroid nodule detection and classification: A comprehensive survey. In 2023 2nd International Conference on Automation, Computing and Renewable Systems (pp. 1283–1287). IEEE. https://doi.org/10.1109/ICACRS58579.2023.10404375 Sutradhar, A., et al. (2024). Advancing thyroid care: An accurate trustworthy diagnostics system with interpretable AI and hybrid machine learning techniques. Heliyon, 10(17), e36556. https://doi.org/10.1016/j.heliyon.2024.e36556 Uddin, K. M. M., Mamun, A. A., Chakrabarti, A., & Mostafiz, R. (2024). An ensemble machine learning-based approach to predict thyroid disease using hybrid feature selection. Biomedical Analysis, 1(3), 229–239. https://doi.org/10.1016/j.bioana.2024.08.001

Development of an Intelligent Clinical Decision Support System for Early Detection of Thyroid Disorders Using Optimized Machine Learning Pipelines

Abstract

Keywords

References

More Articles from INTERNATIONAL JOURNAL OF MEDICAL EVALUATION AND PHYSICAL REPORT