A Transparent AI-Driven Multiclass Decision Support System for Thyroid Risk Prediction Using Machine Learning and Deep Learning Approaches

Ouartani, Siouar; Taleb, Nora

doi:10.2478/fcds-2025-0019

Abstract

Early and accurate diagnosis of thyroid disorders is essential due to their prevalence and health impact. To enhance interpretability in clinical settings, we propose a comprehensive workflow for transparent thyroid disease prediction using a multiclass classification problem with five diagnostic categories. A dataset of 9172 samples with 31 features was used to train various machine and deep learning models. A dual-layered framework combining Feature Selection (ETC, MI, RFE) and Explainable AI (SHAP, LIME) improved performance and transparency. Gradient Boosting achieved the highest accuracy (0.97). SHAP explained global feature influence, while LIME clarified individual predictions. Our approach supports interpretable, reliable AI-based diagnostic tools for thyroid disorder classification.

References

Ahmad, W., Ahmad, A., Lu, C., A Novel Hybrid Decision Support System for Thyroid Disease Forecasting, Soft Computing, 22, 2018, 5377–5383.
Search in Google Scholar Back to article
Aldughayfiq, B., Ashfaq, F., Jhanjhi, N. Z., Humayun, M., Explainable AI for Retinoblastoma Diagnosis: Interpreting Deep Learning Models with LIME and SHAP, Diagnostics, 13, 2023, 1932, https://doi.org/10.3390/diagnostics13111932.
Search in Google Scholar Back to article
Allgaier, J., Mulansky, L., Draelos, R. L., Pryss, R., How Does the Model Make Predictions? A Systematic Literature Review on the Explainability Power of Machine Learning in Healthcare, Artificial Intelligence in Medicine, 143, 2023, 102616, https://doi.org/10.1016/j.artmed.2023.102616.
Search in Google Scholar Back to article
Amin, A., Hasan, K., Zein-Sabatto, S., Chimba, D., Ahmed, I., Islam, T., An Explainable AI Framework for Artificial Intelligence of Medical Things, Proc. IEEE Globecom Workshops (GC Wkshps), 2023, 2097–2102.
Search in Google Scholar Back to article
Chaganti, R., Rustam, F., De La Torre Díez, I., V. Mazon, J. L., Rodríguez, C. L., Ashraf, I., Thyroid Disease Prediction Using Selective Features and Machine Learning Techniques, Cancers, 14, 2022.
Search in Google Scholar Back to article
du Prel, J. B., Hommel, G., Röhrig, B., Blettner, M., Confidence Interval or P-Value? Part 4 of a Series on Evaluation of Scientific Publications, Deutsches Ärzteblatt International, 2009, https://doi.org/10.3238/arztebl.2009.0335.
Search in Google Scholar Back to article
Ghosh, S. K., Khandoker, A. H., Investigation on Explainable Machine Learning Models to Predict Chronic Kidney Diseases, Scientific Reports, 14, 2024, 3687.
Search in Google Scholar Back to article
Guler, H., Avcı, D., Ula¸s, M., Omma, T., Performance Comparison of Machine Learning Models Powered by SHAP and LIME Based Explainability Techniques on Diabetes Dataset, SSRN, 2024, https://ssrn.com/abstract=4713039.
Search in Google Scholar Back to article
Guidotti, R., Monreale, A., Giannotti, F., Pedreschi, D., Ruggieri, S., Turini, F., Factual and Counterfactual Explanations for Black Box Decision Making, IEEE Intelligent Systems, 34, 6, 2019, 14–23.
Search in Google Scholar Back to article
Hakkoum, H., Idri, A., Abnane, I., Assessing and Comparing Interpretability Techniques for Artificial Neural Networks in Breast Cancer Classification, Computer Methods in Biomechanics and Biomedical Engineering: Imaging and Visualization, 2021, https://doi.org/10.1080/21681163.2021.1901784.
Search in Google Scholar Back to article
Hu, Y., Sokolova, M., Explainable Multi-class Classification of the CAMH COVID-19 Mental Health Data, arXiv preprint, 2021, arXiv:2113.13430.
Search in Google Scholar Back to article
Junkang, A., Zhang, Y., Joe, I., Specific-Input LIME Explanations for Tabular Data Based on Deep Learning Models, Applied Sciences, 13, 15, 2023, 8782.
Search in Google Scholar Back to article
Kaggle, Thyroid Disease Dataset, https://www.kaggle.com/datasets/emmanuelfwerr/thyroid-diseasedata.
Search in Google Scholar Back to article
Mulwa, M. M., Mwangi, R. W., Mindila, A., GMM-LIME Explainable Machine Learning Model for Interpreting Sensor-Based Human Gait, Engineering Reports, 2024.
Search in Google Scholar Back to article
Ouartani, S., Taleb, N., Decision Support System for Thyroid Disease Prediction Using Decision Tree Algorithm and Ontology, Artificial Intelligence Theory and Applications (AITA), 2024.
Search in Google Scholar Back to article
Rahman, M., Ali, M., Mahim, M., Miah, S. M., Sipon, M., Enhancing Lung Abnormalities Detection and Classification Using a Deep CNN and GRU with Explainable AI, Machine Learning with Applications, 14, 2023, 100492, https://doi.org/10.1016/j.mlwa.2023.100492.
Search in Google Scholar Back to article
Rawte, V., Royl, B., V. L., Thyroid Disease Diagnosis using Ontology-based Expert System, International Journal of Engineering Research Technology (IJERT), 4, 6, 2015.
Search in Google Scholar Back to article
Settouti, N., Saidi, M., Preliminary Analysis of Explainable Machine Learning Methods for Multiple Myeloma Chemotherapy Treatment Recognition, Evolutionary Intelligence, 17, 2024, 513–533.
Search in Google Scholar Back to article
Shiuh, T. L., Khai, W. K., Xin, Y. C., Wai, C. Y., Prediction of Thyroid Disease Using Machine Learning Approaches and Featurewiz Selection, JTEC, 15, 3, 2023, 9–16.
Search in Google Scholar Back to article
Siddhartha, K., Abhishek, A., Gyanendra, S., Developing an Explainable Machine Learning-Based Thyroid Disease Prediction Model, International Journal of Business Analytics (IJBAN), 9, 3, 2022, 1–18.
Search in Google Scholar Back to article
Sun, Q., Akman, A., Schuller, B. W., Explainable Artificial Intelligence for Medical Applications: A Review, arXiv preprint, 2024, arXiv:2412.01829.
Search in Google Scholar Back to article
Tang, J., Alelyani, S., Liu, H., Feature Selection for Classification: A Review, in: C. C. Aggarwal (Ed.), Data Classification: Algorithms and Applications, Chapman and Hall/CRC, 2014, 37–64.
Search in Google Scholar Back to article
Zacharias, J., von Zahn, M., Chen, J., Designing a Feature Selection Method Based on Explainable Artificial Intelligence, Electronic Markets, 2022, https://doi.org/10.1007/s12525-022-00608-1.
Search in Google Scholar Back to article

A Transparent AI-Driven Multiclass Decision Support System for Thyroid Risk Prediction Using Machine Learning and Deep Learning Approaches

Abstract

Paradigm

My account