Application of machine learning algorithms to predict the thyroid disease risk: an experimental comparative study

Thyroid disease is the general concept for a medical problem that prevents one's thyroid from producing enough hormones. Thyroid disease can affect everyone-men, women, children, adolescents, and the elderly. Thyroid disorders are detected by blood tests, which are notoriously difficult to inte...

Full description

Bibliographic Details
Main Authors: Islam, Saima Sharleen, Haque, Md Samiul, Miah, M. Saef Ullah, Sarwar, Talha, Nugraha, Ramdhan
Format: Article
Language:English
Published: Peerj Inc. 2022
Subjects:
Online Access:https://umpir.ump.edu.my/id/eprint/45441/
_version_ 1848827419273723904
author Islam, Saima Sharleen
Haque, Md Samiul
Miah, M. Saef Ullah
Sarwar, Talha
Nugraha, Ramdhan
author_facet Islam, Saima Sharleen
Haque, Md Samiul
Miah, M. Saef Ullah
Sarwar, Talha
Nugraha, Ramdhan
author_sort Islam, Saima Sharleen
building UMP Institutional Repository
collection Online Access
description Thyroid disease is the general concept for a medical problem that prevents one's thyroid from producing enough hormones. Thyroid disease can affect everyone-men, women, children, adolescents, and the elderly. Thyroid disorders are detected by blood tests, which are notoriously difficult to interpret due to the enormous amount of data necessary to forecast results. For this reason, this study compares eleven machine learning algorithms to determine which one produces the best accuracy for predicting thyroid risk accurately. This study utilizes the Sick-euthyroid dataset, acquired from the University of California, Irvine's machine learning repository, for this purpose. Since the target variable classes in this dataset are mostly one, the accuracy score does not accurately indicate the prediction outcome. Thus, the evaluation metric contains accuracy and recall ratings. Additionally, the F1-score produces a single value that balances the precision and recall when an uneven distribution class exists. Finally, the F1-score is utilized to evaluate the performance of the employed machine learning algorithms as it is one of the most effective output measurements for unbalanced classification problems. The experiment shows that theANNClassifier with an F1-score of 0.957 outperforms the other nine algorithms in terms of accuracy.
first_indexed 2025-11-15T04:00:25Z
format Article
id ump-45441
institution Universiti Malaysia Pahang
institution_category Local University
language English
last_indexed 2025-11-15T04:00:25Z
publishDate 2022
publisher Peerj Inc.
recordtype eprints
repository_type Digital Repository
spelling ump-454412025-08-20T04:26:26Z https://umpir.ump.edu.my/id/eprint/45441/ Application of machine learning algorithms to predict the thyroid disease risk: an experimental comparative study Islam, Saima Sharleen Haque, Md Samiul Miah, M. Saef Ullah Sarwar, Talha Nugraha, Ramdhan QA75 Electronic computers. Computer science RC Internal medicine Thyroid disease is the general concept for a medical problem that prevents one's thyroid from producing enough hormones. Thyroid disease can affect everyone-men, women, children, adolescents, and the elderly. Thyroid disorders are detected by blood tests, which are notoriously difficult to interpret due to the enormous amount of data necessary to forecast results. For this reason, this study compares eleven machine learning algorithms to determine which one produces the best accuracy for predicting thyroid risk accurately. This study utilizes the Sick-euthyroid dataset, acquired from the University of California, Irvine's machine learning repository, for this purpose. Since the target variable classes in this dataset are mostly one, the accuracy score does not accurately indicate the prediction outcome. Thus, the evaluation metric contains accuracy and recall ratings. Additionally, the F1-score produces a single value that balances the precision and recall when an uneven distribution class exists. Finally, the F1-score is utilized to evaluate the performance of the employed machine learning algorithms as it is one of the most effective output measurements for unbalanced classification problems. The experiment shows that theANNClassifier with an F1-score of 0.957 outperforms the other nine algorithms in terms of accuracy. Peerj Inc. 2022-03 Article PeerReviewed pdf en cc_by_4 https://umpir.ump.edu.my/id/eprint/45441/1/Application%20of%20machine%20learning%20algorithms%20to%20predict%20the%20thyroid.pdf Islam, Saima Sharleen and Haque, Md Samiul and Miah, M. Saef Ullah and Sarwar, Talha and Nugraha, Ramdhan (2022) Application of machine learning algorithms to predict the thyroid disease risk: an experimental comparative study. PeerJ Computer Science, 8 (e898). pp. 1-35. ISSN 2376-5992. (Published) https://doi.org/10.7717/peerj-cs.898 https://doi.org/10.7717/peerj-cs.898 https://doi.org/10.7717/peerj-cs.898
spellingShingle QA75 Electronic computers. Computer science
RC Internal medicine
Islam, Saima Sharleen
Haque, Md Samiul
Miah, M. Saef Ullah
Sarwar, Talha
Nugraha, Ramdhan
Application of machine learning algorithms to predict the thyroid disease risk: an experimental comparative study
title Application of machine learning algorithms to predict the thyroid disease risk: an experimental comparative study
title_full Application of machine learning algorithms to predict the thyroid disease risk: an experimental comparative study
title_fullStr Application of machine learning algorithms to predict the thyroid disease risk: an experimental comparative study
title_full_unstemmed Application of machine learning algorithms to predict the thyroid disease risk: an experimental comparative study
title_short Application of machine learning algorithms to predict the thyroid disease risk: an experimental comparative study
title_sort application of machine learning algorithms to predict the thyroid disease risk: an experimental comparative study
topic QA75 Electronic computers. Computer science
RC Internal medicine
url https://umpir.ump.edu.my/id/eprint/45441/
https://umpir.ump.edu.my/id/eprint/45441/
https://umpir.ump.edu.my/id/eprint/45441/