Tehran University of Medical Sciences

Science Communicator Platform

Share By
Prediction of Thyroid Malignancy Risk Using Clinical and Ultrasonography Features and a Machine Learning Approach Publisher

Summary: Thyroid cancer risk? XGBoost model outperforms TI-RADS, ATA with 88% AUC, cuts unnecessary FNA—better diagnosis. #ThyroidCancer #MachineLearning

Hosseini Sarkhosh SM1 ; Shirzad N2, 3 ; Taghvaei M2 ; Tavangar SM4 ; Farhat S5 ; Ebrahiminik H6 ; Hemmatabadi M2
Authors

Source: European Radiology Published:2025


Abstract

Objective: This study aims to develop and validate a predictive model for thyroid nodule malignancy risks using clinical and ultrasonography features and a machine learning (ML) approach. Methods: This retrospective study is based on the clinical and ultrasound characteristics of 1035 thyroid nodules (845 benign and 190 malignant) to develop and validate the risk prediction model. Employing multiple logistic regression, key features were selected in developing the model. Eight ML algorithms were evaluated for predicting the risks of malignancy. Finally, the predictive ability of the best-performing algorithm was compared against American College of Radiology Thyroid Imaging Reporting and Data System (ACR TI-RADS) and American Thyroid Association (ATA) guidelines. Results: Based on AUC criteria (88.3, 95% CI: 81.2–94.2), sensitivity (84.2, 95% CI: 71.1–94.7), specificity (92.3, 95% CI: 88.2–95.9), positive predictive value, (71.4, 95% CI: 60.4–83.3) and negative predictive value (96.3, 95% CI: 93.5–98.8), the XGBoost algorithm exhibited superior performance over the other ML algorithms and ACR TI-RADS and ATA. These criteria were obtained for ACR TI-RADS at 54.2%, 63.2%, 48.5%, 21.1%, and 84.8%, while for ATA, they were 44.3%, 76.3%, 27.2%, 18.4%, and 81.6%. In addition, the unnecessary fine-needle aspiration (FNA) rate with ACR TI-RADS and ATA was 43% and 63%, respectively—significantly higher than the 7% obtained with XGBoost. Conclusions: This study demonstrated the capability of ML approaches in enhancing the accuracy of predicting thyroid malignancy risks as well as their potential benefits in optimizing healthcare resources by reducing unnecessary FNA rates. Using the proposed model through a web-based tool can facilitate clinical judgments in thyroid nodule management and personalized treatment. Key Points: Question Current risk assessment systems have limitations, with high unnecessary FNA rates compared to machine learning (ML) models. Findings The XGBoost algorithm was compared to other ML algorithms, ACR TI-RADS, and ATA and demonstrated superior performance. Clinical relevance This study demonstrated the capability of ML approaches in enhancing the accuracy of predicting thyroid malignancy. The proposed web-based tool to facilitate the prediction of thyroid nodule risk is available at https://aimedlab.ir/tnr. © The Author(s), under exclusive licence to European Society of Radiology 2025.
Related Docs
View other Related Docs
1. A Machine Learning-Based Sonomics for Prediction of Thyroid Nodule Malignancies, Endocrine (2023)
2. Eltirads Framework for Thyroid Nodule Classification Integrating Elastography, Tirads, and Radiomics With Interpretable Machine Learning, Scientific Reports (2025)
3. What Features Predict Poorer Outcomes in Micropapillary Thyroid Carcinoma? a Retrospective Cohort Study, Endocrine Practice (2025)
Experts (# of related papers)
View all Related Experts
Aydin Yaghobi Notash (2)
Hossein Arabalibeik (1)
Prediction of Thyroid Malignancy Risk Using Clinical and Ultrasonography Features and a Machine Learning Approach
Other Related Docs
4. Predicting Lymph Node Metastasis in Thyroid Cancer: Systematic Review and Meta-Analysis on the Ct/Mri-Based Radiomics and Deep Learning Models, Clinical Imaging (2025)
5. A Practical Score Model for Detecting Malignant Thyroid Nodules by Using Ultrasonographic Findings, Acta Medica Iranica (2018)
6. Applications of Machine-Learning Algorithms for Prediction of Benign and Malignant Breast Lesions Using Ultrasound Radiomics Signatures: A Multi-Center Study, Biocybernetics and Biomedical Engineering (2022)
7. Artificial Intelligence, Bi-Rads Evaluation and Morphometry: A Novel Combination to Diagnose Breast Cancer Using Ultrasonography, Results From Multi-Center Cohorts, European Journal of Radiology (2022)
8. Application of Neck Technetium Uptake of the Neck in Post-Operation Ptc Patients for Detection of Forthcoming Iodine Ablation Response to Therapy, Indian Journal of Surgery (2022)
9. A Comparison of Different Thyroid Imaging Reporting and Data Systems to Reduce Unnecessary Fnas and Missed Malignancies, Journal of Diagnostic Medical Sonography (2022)
10. Risk Predictions of Hospital-Acquired Pressure Injury in the Intensive Care Unit Based on a Machine Learning Algorithm, International Wound Journal (2023)
11. Ultrasound-Based Machine Learning Models for Predicting Response to Neoadjuvant Chemotherapy in Breast Cancer: A Meta-Analysis, Clinical Imaging (2025)
12. Endorectal Ultrasound Radiomics in Locally Advanced Rectal Cancer Patients: Despeckling and Radiotherapy Response Prediction Using Machine Learning, Abdominal Radiology (2022)
13. Machine Learning Models for Predicting Sudden Sensorineural Hearing Loss Outcome: A Systematic Review, Annals of Otology# Rhinology and Laryngology (2024)
14. Personalized Breast Cancer Prognosis Using a Model Based on Mri and Clinicopathological Variables, Journal of Imaging Informatics in Medicine (2025)
15. Evaluating Diagnostic Efficiency of Thyroid Imaging Reporting and Data Systems Proposed by the American College of Radiology in Surgically Resected Thyroid Nodules, Current Medical Imaging (2024)
16. Prediction of Lymphedema Occurrence in Patients With Breast Cancer Using the Optimized Combination of Ensemble Learning Algorithm and Feature Selection, BMC Medical Informatics and Decision Making (2022)
17. Burden Assessment of Thyroid Cancer in Iran From 1990 to 2010: Lessons Obtained From Global Burden of Disease Report 2010, Asian Pacific Journal of Cancer Prevention (2015)
18. Diagnostic Yield of Fine Needle Aspiration With Simultaneous Core Needle Biopsy for Thyroid Nodules, Journal of Pathology and Translational Medicine (2025)
19. Development of a Gastric Cancer Risk Calculator for Questionnaire-Based Surveillance of Iranian Dyspeptic Patients, BMC Gastroenterology (2024)
20. Machine Learning Approaches in the Prediction of Positive Axillary Lymph Nodes Post Neoadjuvant Chemotherapy Using Mri, Ct, or Ultrasound: A Systematic Review, European Journal of Radiology Open (2024)