Advancing thyroid care: An accurate trustworthy diagnostics system with interpretable AI and hybrid machine learning techniques
Document Type
Article
Publication Date
9-1-2024
Abstract
The worldwide prevalence of thyroid disease is on the rise, representing a chronic condition that significantly impacts global mortality rates. Machine learning (ML) approaches have demonstrated potential superiority in mitigating the occurrence of this disease by facilitating early detection and treatment. However, there is a growing demand among stakeholders and patients for reliable and credible explanations of the generated predictions in sensitive medical domains. Hence, we propose an interpretable thyroid classification model to illustrate outcome explanations and investigate the contribution of predictive features by utilizing explainable AI. Two realtime thyroid datasets underwent various preprocessing approaches, addressing data imbalance issues using the Synthetic Minority Over-sampling Technique with Edited Nearest Neighbors (SMOTE-ENN). Subsequently, two hybrid classifiers, namely RDKVT and RDKST, were introduced to train the processed and selected features from Univariate and Information Gain feature selection techniques. Following the training phase, the Shapley Additive Explanation (SHAP) was applied to identify the influential characteristics and corresponding values contributing to the outcomes. The conducted experiments ultimately concluded that the presented RDKST classifier achieved the highest performance, demonstrating an accuracy of 98.98 % when trained on
Keywords
Thyroid disease, Machine learning, SMOTE-ENN, Ensemble methods, And explainable AI
Divisions
Computer
Publication Title
Heliyon
Volume
10
Issue
17
Publisher
Elsevier
Publisher Location
50 HAMPSHIRE ST, FLOOR 5, CAMBRIDGE, MA 02139 USA