Enhanced interpretable thyroid disease diagnosis by leveraging synthetic oversampling and machine learning models

Abstract Thyroid illness encompasses a range of disorders affecting the thyroid gland, leading to either hyperthyroidism or hypothyroidism, which can significantly impact metabolism and overall health. Hypothyroidism can cause a slowdown in bodily processes, leading to symptoms such as fatigue, weig...

Full description

Saved in:
Bibliographic Details
Main Authors: Ali Raza, Fatma Eid, Elisabeth Caro Montero, Irene Delgado Noya, Imran Ashraf
Format: Article
Language:English
Published: BMC 2024-11-01
Series:BMC Medical Informatics and Decision Making
Subjects:
Online Access:https://doi.org/10.1186/s12911-024-02780-0
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850216501199503360
author Ali Raza
Fatma Eid
Elisabeth Caro Montero
Irene Delgado Noya
Imran Ashraf
author_facet Ali Raza
Fatma Eid
Elisabeth Caro Montero
Irene Delgado Noya
Imran Ashraf
author_sort Ali Raza
collection DOAJ
description Abstract Thyroid illness encompasses a range of disorders affecting the thyroid gland, leading to either hyperthyroidism or hypothyroidism, which can significantly impact metabolism and overall health. Hypothyroidism can cause a slowdown in bodily processes, leading to symptoms such as fatigue, weight gain, depression, and cold sensitivity. Hyperthyroidism can lead to increased metabolism, causing symptoms like rapid weight loss, anxiety, irritability, and heart palpitations. Prompt diagnosis and appropriate treatment are crucial in managing thyroid disorders and improving patients’ quality of life. Thyroid illness affects millions worldwide and can significantly impact their quality of life if left untreated. This research aims to propose an effective artificial intelligence-based approach for the early diagnosis of thyroid illness. An open-access thyroid disease dataset based on 3,772 male and female patient observations is used for this research experiment. This study uses the nominal continuous synthetic minority oversampling technique (SMOTE-NC) for data balancing and a fine-tuned light gradient booster machine (LGBM) technique to diagnose thyroid illness and handle class imbalance problems. The proposed SNL (SMOTE-NC-LGBM) approach outperformed the state-of-the-art approach with high-accuracy performance scores of 0.96. We have also applied advanced machine learning and deep learning methods for comparison to evaluate performance. Hyperparameter optimizations are also conducted to enhance thyroid diagnosis performance. In addition, we have applied the explainable Artificial Intelligence (XAI) mechanism based on Shapley Additive exPlanations (SHAP) to enhance the transparency and interpretability of the proposed method by analyzing the decision-making processes. The proposed research revolutionizes the diagnosis of thyroid disorders efficiently and helps specialties overcome thyroid disorders early.
format Article
id doaj-art-c012b30a738f45bb95cde40be4f5552f
institution OA Journals
issn 1472-6947
language English
publishDate 2024-11-01
publisher BMC
record_format Article
series BMC Medical Informatics and Decision Making
spelling doaj-art-c012b30a738f45bb95cde40be4f5552f2025-08-20T02:08:16ZengBMCBMC Medical Informatics and Decision Making1472-69472024-11-0124111810.1186/s12911-024-02780-0Enhanced interpretable thyroid disease diagnosis by leveraging synthetic oversampling and machine learning modelsAli Raza0Fatma Eid1Elisabeth Caro Montero2Irene Delgado Noya3Imran Ashraf4Department of Software Engineering, University of LahoreDepartment of Applied Artificial Intelligence, School of Convergence, College of Computing and Informatics, Sungkyunkwan UniversityUniversidad Europea del AtlanticoUniversidad Europea del AtlanticoDepartment of Information and Communication Engineering, Yeungnam UniversityAbstract Thyroid illness encompasses a range of disorders affecting the thyroid gland, leading to either hyperthyroidism or hypothyroidism, which can significantly impact metabolism and overall health. Hypothyroidism can cause a slowdown in bodily processes, leading to symptoms such as fatigue, weight gain, depression, and cold sensitivity. Hyperthyroidism can lead to increased metabolism, causing symptoms like rapid weight loss, anxiety, irritability, and heart palpitations. Prompt diagnosis and appropriate treatment are crucial in managing thyroid disorders and improving patients’ quality of life. Thyroid illness affects millions worldwide and can significantly impact their quality of life if left untreated. This research aims to propose an effective artificial intelligence-based approach for the early diagnosis of thyroid illness. An open-access thyroid disease dataset based on 3,772 male and female patient observations is used for this research experiment. This study uses the nominal continuous synthetic minority oversampling technique (SMOTE-NC) for data balancing and a fine-tuned light gradient booster machine (LGBM) technique to diagnose thyroid illness and handle class imbalance problems. The proposed SNL (SMOTE-NC-LGBM) approach outperformed the state-of-the-art approach with high-accuracy performance scores of 0.96. We have also applied advanced machine learning and deep learning methods for comparison to evaluate performance. Hyperparameter optimizations are also conducted to enhance thyroid diagnosis performance. In addition, we have applied the explainable Artificial Intelligence (XAI) mechanism based on Shapley Additive exPlanations (SHAP) to enhance the transparency and interpretability of the proposed method by analyzing the decision-making processes. The proposed research revolutionizes the diagnosis of thyroid disorders efficiently and helps specialties overcome thyroid disorders early.https://doi.org/10.1186/s12911-024-02780-0Machine learningDeep learningThyroid disordersMedical diagnosisExplainable artificial intelligence
spellingShingle Ali Raza
Fatma Eid
Elisabeth Caro Montero
Irene Delgado Noya
Imran Ashraf
Enhanced interpretable thyroid disease diagnosis by leveraging synthetic oversampling and machine learning models
BMC Medical Informatics and Decision Making
Machine learning
Deep learning
Thyroid disorders
Medical diagnosis
Explainable artificial intelligence
title Enhanced interpretable thyroid disease diagnosis by leveraging synthetic oversampling and machine learning models
title_full Enhanced interpretable thyroid disease diagnosis by leveraging synthetic oversampling and machine learning models
title_fullStr Enhanced interpretable thyroid disease diagnosis by leveraging synthetic oversampling and machine learning models
title_full_unstemmed Enhanced interpretable thyroid disease diagnosis by leveraging synthetic oversampling and machine learning models
title_short Enhanced interpretable thyroid disease diagnosis by leveraging synthetic oversampling and machine learning models
title_sort enhanced interpretable thyroid disease diagnosis by leveraging synthetic oversampling and machine learning models
topic Machine learning
Deep learning
Thyroid disorders
Medical diagnosis
Explainable artificial intelligence
url https://doi.org/10.1186/s12911-024-02780-0
work_keys_str_mv AT aliraza enhancedinterpretablethyroiddiseasediagnosisbyleveragingsyntheticoversamplingandmachinelearningmodels
AT fatmaeid enhancedinterpretablethyroiddiseasediagnosisbyleveragingsyntheticoversamplingandmachinelearningmodels
AT elisabethcaromontero enhancedinterpretablethyroiddiseasediagnosisbyleveragingsyntheticoversamplingandmachinelearningmodels
AT irenedelgadonoya enhancedinterpretablethyroiddiseasediagnosisbyleveragingsyntheticoversamplingandmachinelearningmodels
AT imranashraf enhancedinterpretablethyroiddiseasediagnosisbyleveragingsyntheticoversamplingandmachinelearningmodels