Early Stage Prediction of Thyroid Disease Using Machine Learning
DOI:
https://doi.org/10.31305/rhimrj.2026.v13n10.004Keywords:
Thyroid, Support Vector Machines, Decision Tree, Xgboost, Logistic RegressionAbstract
Diagnosing thyroid disease is still difficult in medicine. This means doctors need computer methods to find the disease early and know what type it is. This study uses a set of 255 primary patient records. The dataset has information about various risk factors such as age, gender, pregnancy, family history and health symptoms. (P.B. Khanale & R.P. Ambilwade,2011). To make the computer models better the study looks at ways to clean the data, standardize the data, encoding and feature selection. The study shows how to use techniques to find classification of thyroid disease. Five computer models called Decision Tree, Logistic Regression, Random Forest, Support Vector Machines and Xgboost are tested. These models are trained using primary datasets and tested on external datasets. Support Vector Machines has provided highest accuracy, which is 88.89%.
References
[1] Abbad Ur Rehman, H., Lin, C.-Y., Mushtaq, Z., Su, S.-F.,” Performance analysis of machine learning algorithms for thyroid disease”, Arabian J. Sci. Eng. 46, 9437—9449, 2021
[2] Ali Keles a, Ayturk Keles, “ESTDD: Expert system for thyroid diseases diagnosis”, 2008 (a Department of Computer Education and Instructional Technology, Faculty of Kazım Karabekir Education, Ataturk University, Turkeyb Faculty of Engineering, Ataturk University, TR-25240 Erzurum, Turke Expert Systems with Applications 34 (2008) 242–246)
[3] Agrawal, P., Abutarboush, H.F., Ganesh, T., Mohamed, A.W., ”Metaheuristic algorithms on feature selection: a survey of one decade of research (2009-2019)”, 2021. IEEE Access 9, 26766—26791.
[4] Amjad Hussain, Syed Anwar Hussnain, Abeer Fatima, Shahan Yamin Siddiqui, Anwar Saeed, Yousaf Saeed, Aiesha Ahmed, Muhammad, “A Novel Approach for Thyroid Disease Identification Empowered with Fuzzy Logic “, IJCSNS International Journal of Computer Science and Network Security, VOL.20 No.1, January 2020
[5] Areej Mohammed, Munir Abu-Helalah, Abdulrahim Shamayleh,“An explainable non-invasive hybrid machine learning framework for accurate prediction of thyroid-stimulating hormone levels”
[6] Aversano, L., Bernardi, M.L., Cimitile, M., Maiellaro, A., Pecori, R., “A systematic review on artificial intelligence techniques for detecting thyroid diseases”,2023, PeerJ Comput. Sci. 9, e1394.
[7] Pushpa Choudhary, Sambit Satpathy, Arvind Dagur, Dhirendra Kumar Shukla,” Recent Trends in Intelligent Computing and Communication”,2025
[8] Chaker, L., Bianco, A. C., Jonklaas, J., & Peeters, R. P. “Hypothyroidism. The Lancet, 390(10101), 1550–1562”, (2017), https://doi.org/10.1016/S0140-6736(17)30703-1
[9] De Leo, S., Lee, S. Y., & Braverman, L. E.,” Hyperthyroidism. The Lancet, 388(10047), 906–918”,2016 ,https://doi.org/10.1016/S0140-6736(16)00278-6
[10] Dr. Dayanand Jamkhandikar, Neethi Priya,”THYROID DISEASE PREDICTION USING FEATURE SELECTION AND MACHINE LEARNING CLASSIFIERS” (The International journal of analytical and experimental modal analysis Volume XII, Issue VII, July/2020 ISSN NO:0886-9367)
[11] Hybrid Intelligent Systems”, ISSN (Print): 2328-3491, ISSN (Online): 2328-3580, ISSN (CD-ROM): 2328-3629)
[12] Jiaqi Guo Huazhong,”Regression on Seoul Bike Sharing Demand University of Science and Technology”, Wuhan, Hubei, 430074, China,2025
[13] K. Dharmarajan1, K. Balasree2, A.S. Arunachalam3, K. Abirmai ,“Thyroid Disease Classification Using Decision Tree and SVM “(Indian Journal of Public Health Research & Development, March 2020, Vol. 11, No. 0)
[14] Khalid Abdalsatar SALMAN,“THE EFFICIENCY OF CLASSIFICATION TECHNIQUES IN PREDICTING THYROID DISEASE”, 2021(Karabuk University Institute of Graduate Programs The Department of Computer Engineering Thesis Advisor: Assist. Prof. Dr. Emrullah SONUÇ June 2021)
[15] Osasere Oture, Muhammad Zahid Iqbal and Xining (Ning) Wang, “Enhanced Diagnosis of Thyroid Diseases Through Advanced Machine Learning Methodologies”, Sci 2025, 7, 66
[16] P.B. Khanale and R.P. Ambilwade,” A Fuzzy Inference System for Diagnosis of Hypothyroidism” ,2011(Journal of Artificial Intelligence 4(1):45-54 2011 ISSN 1954-5450/DOI:10.3923/jai.2011.45.54 2011 Asian Network of Scientific Information).
[17] Sambasivarao, K. V. (EDT); Bhima, Anasuya Sesha Roopa Devi (EDT), “Artificial Intelligence, Computational Intelligence and Inclusive Technologies”,2026
[18] SHAIK.RAZIA,” A NEURO COMPUTING FRAMEWORK FOR THYROID DISEASE DIAGNOSIS USING MACHINE LEARNING”, SEPTEMBER 2017
[19] S. Amrollahi Biyouki M.H. Fazel Zarandi I.B. Turksen, “Fuzzy Rule-based Expert System for Diagnosis of Thyroid Disease”,2015 (978-1-4799-6926-5/15/$31.00 ©2015 IEEE)
[20] Shaymaa R. Saleh, Zamen F. Jabr, “Wijdan R. Abdulhussein Thyroid Disease Diagnosis Using
[21] Tuqa Ahmed Elbillihy, Eman Abd Elhalim, Mohamed Ashour, Hala B. Nafea. “Prediction of Thyroid Disease Based on Machine Learning Prediction of Thyroid Disease Based on Machine Learning Algorithms”, February 2026(Mansoura Engineering Journal Volume 51 Issue 1 Article 14)
[22] Tanmay Kasbe, “DESIGN AND DEVELOPMENT OF FUZZY EXPERT SYSTEM FOR DISEASE “, Faculty of Computer Science and Application Ram Krishna Dharmarth Foundation University Bhopal 2018 A thesis submitted for the degree of Doctor of Philosophy In Computer Science and Application
[23] Unnikrishnan, A. G., Kalra, S., Sahay, R. K., Bantwal, G., John, M., & Tewari, N. ,”Prevalence of hypothyroidism in adults: An epidemiological study in eight cities of India.”, (2013). Indian Journal of Endocrinology and Metabolism, 17(4), 647–652. https://doi.org/10.4103/2230-8210.113755
[24] Yadav, D.C., Pal, S., “Prediction of thyroid disease using decision tree ensemble method”,2023 Hum-Intell. Syst. Integr. 2, 89—95.
