TY - JOUR
T1 - Explainable artificial intelligence and machine learning algorithms for classification of thyroid disease
AU - Kumari, Priyanka
AU - Kaur, Baljinder
AU - Rakhra, Manik
AU - Deka, Aniruddha
AU - Byeon, Haewon
AU - Asenso, Evans
AU - Rawat, Anil Kumar
N1 - Publisher Copyright:
© The Author(s) 2024.
PY - 2024/7
Y1 - 2024/7
N2 - A common endocrine issue affecting millions globally is thyroid illness. For this ailment to be effectively treated and managed, an early and accurate diagnosis is essential. Machine learning algorithms have attracted a lot of attention recently in the healthcare industry and have the potential to improve thyroid disease diagnosis and categorization. The implementation of machine learning methods for the classification of thyroid disease is presented in this study. To create predictive models, the study makes use of a dataset that includes a variety of thyroid-related factors, including age, gender, and hormone levels. To evaluate the effectiveness of several machine learning techniques in classifying thyroid diseases, including random forest, support vector machines, XG-Boost, and ensemble classifier, they are implemented and compared. To ensure robust model performance, the methodology includes data preparation, feature selection, and model training, as well as strategies for hyperparameter adjustment and cross-validation. To assess the algorithms’ efficiency in differentiating between several thyroid illness classifications, such as hyperthyroidism, hypothyroidism, and the study measures the algorithms’ accuracy, precision, recall, F1-score, voting, and area under the ROC curve.
AB - A common endocrine issue affecting millions globally is thyroid illness. For this ailment to be effectively treated and managed, an early and accurate diagnosis is essential. Machine learning algorithms have attracted a lot of attention recently in the healthcare industry and have the potential to improve thyroid disease diagnosis and categorization. The implementation of machine learning methods for the classification of thyroid disease is presented in this study. To create predictive models, the study makes use of a dataset that includes a variety of thyroid-related factors, including age, gender, and hormone levels. To evaluate the effectiveness of several machine learning techniques in classifying thyroid diseases, including random forest, support vector machines, XG-Boost, and ensemble classifier, they are implemented and compared. To ensure robust model performance, the methodology includes data preparation, feature selection, and model training, as well as strategies for hyperparameter adjustment and cross-validation. To assess the algorithms’ efficiency in differentiating between several thyroid illness classifications, such as hyperthyroidism, hypothyroidism, and the study measures the algorithms’ accuracy, precision, recall, F1-score, voting, and area under the ROC curve.
KW - Data cleaning
KW - Ensemble classifier and their comparison
KW - Machine learning
KW - Prediction
KW - SVM
KW - Supervised learning algorithms
KW - Thyroid disease
UR - http://www.scopus.com/inward/record.url?scp=85197422208&partnerID=8YFLogxK
U2 - 10.1007/s42452-024-06068-w
DO - 10.1007/s42452-024-06068-w
M3 - Article
AN - SCOPUS:85197422208
SN - 2523-3971
VL - 6
JO - Discover Applied Sciences
JF - Discover Applied Sciences
IS - 7
M1 - 360
ER -