Predicting Hypothyroidism Risk using Machine Learning with Essential Feature Selection
Keywords:
ต้นไม้ตัดสินใจ การคัดเลือกคุณลักษณะ ภาวะพร่องไทรอยด์ การเรียนรู้ของเครื่อง แรนดอมฟอเรสต์Abstract
Hypothyroidism is a prevalent health condition with subtle early symptoms, leading to delayed diagnosis. This research develops a machine learning predictive model using secondary data of 3,772 patients from the UCI Machine Learning Repository. Challenges including class imbalance (24:1 ratio; 3,621 normal vs. 151 hypothyroid cases) and missing values were addressed using Median Imputation and SMOTE. We applied Random Forest-based Feature Importance for dimensionality reduction, systematically reducing features from 23 to 8 essential variables (TSH, FTI, T3, TT4, T4U, thyroid surgery history, thyroxine usage, and age) with a threshold of 0.01. Comparing SVM, Decision Tree Random Forest and MLP using Accuracy, Precision, Recall, and F1-Score, the Decision Tree optimized with GridSearchCV achieved the highest performance with 99.9% Accuracy, 99.9% Recall, and 99.6% F1-Score (decimal values: 0.993, 0.999, 0.996) on the Test Set, verified by 5-Fold Cross-Validation. The model offers high interpretability, making it suitable for clinical decision support.
Downloads
References
กรมการแพทย์ กระทรวงสาธารณสุข. (2564). แนวทางเวชปฏิบัติโรคต่อมไทรอยด์. กระทรวงสาธารณสุข ประเทศไทย.
Abiyev, R. H., & Ma'aitah, M. K. S. (2018). Deep convolutional neural networks for chest diseases detection. Journal of Healthcare Engineering, 2018, Article 4168538.
Biondi, A., & Cooper, D. S. (2008). The clinical significance of subclinical thyroid dysfunction. Endocrine Reviews, 29(1), 76–131.
Breiman, L. (2001). Random forests. Machine Learning, 45(1), 5–32.
Canaris, G. J., Manowitz, N. R., Mayor, G., & Ridgway, E. C. (2000). The Colorado thyroid disease prevalence study. Archives of Internal Medicine, 160(4), 526–534.
Chaganti, S., Rustam, F., DePaula, A. C. A., Daghrery, A., Mazin, I., & Ashraf, I. (2022). Thyroid disease prediction using selective features and machine learning techniques. Cancers, 14(16), 3914.
Chaker, L., Bianco, A. C., Jonklaas, J., & Peeters, R. P. (2017). Hypothyroidism. The Lancet, 390(10101), 1550–1562.
Chawla, N. V., Bowyer, K. W., Hall, L. O., & Kegelmeyer, W. P. (2002). SMOTE: Synthetic minority over-sampling technique. Journal of Artificial Intelligence Research, 16, 321–357.
Chen, M., Hao, Y., Hwang, K., Wang, L., & Wang, L. (2017). Disease prediction by machine learning over big data from healthcare communities. IEEE Access, 5, 8869–8879.
Cortes, C., & Vapnik, V. (1995). Support-vector networks. Machine Learning, 20(3), 273–297.
Ganie, S. M., & Malik, M. B. (2022). An ensemble machine learning approach for thyroid disease detection. International Journal of Applied Engineering Research, 17(4), 267–273.
Garber, J. R., Cobin, R. H., Gharib, H., Hennessey, J. V., Klein, I., Mechanick, J. I., & Woeber, K. A. (2012). Clinical practice guidelines for hypothyroidism in adults. Thyroid, 22(12), 1200–1235.
Guyon, I., & Elisseeff, A. (2003). An introduction to variable and feature selection. Journal of Machine Learning Research, 3, 1157–1182.
He, H., & Garcia, E. A. (2009). Learning from imbalanced data. IEEE Transactions on Knowledge and Data Engineering, 21(9), 1263–1284.
Jonklaas, J., et al. (2014). Guidelines for the treatment of hypothyroidism. Thyroid, 24(12), 1670–1751.Bidyapati. (n.d.). Hypothyroid disease dataset. Kaggle. https://www.kaggle.com/datasets/bidyapati/hypothyroid
Kaur, P., & Kumari, S. (2022). Diabetes prediction using SMOTE and k-nearest neighbor algorithm. International Journal of Advanced Computer Science and Applications, 13(5), 100–108.
Quinlan, J. R. (1986). Induction of decision trees. Machine Learning, 1(1), 81–106
Roberts, C. G. P., & Ladenson, P. W. (2004). Hypothyroidism. The Lancet, 363(9411), 793–803. Orgiazzi, J. (2012). Autoimmune thyroid disease. Endocrinology and Metabolism Clinics of North America, 41(2), 245–261.
Temurtas, H., Yumusak, N., & Temurtas, F. (2009). A comparative study on diabetes disease diagnosis using neural networks. Expert Systems with Applications, 36(4), 8610–8615.
Weetman, A. P. (2021). An update on the pathogenesis of Hashimoto's thyroiditis. Journal of Endocrinological Investigation, 44(5), 883–890.
World Health Organization. (2007). Assessment of iodine deficiency disorders and monitoring their elimination: A guide for programme managers (3rd ed.). World Health Organization.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2026 Journal of Innovations in Business Management and Accounting
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
ต้องใส่ข้อความลิขสิทธิ์
