Artificial Intelligence and Thyroid Disease Diagnosis: a Systematic Review and Meta-Analysis
Keywords:
artificial intelligence; diagnosis; thyroid; meta-analysis; deep learningAbstract
Introduction: Accurate diagnosis of thyroid diseases is essential for effective clinical management. Artificial intelligence (AI) has emerged as a promising tool to improve diagnostic accuracy.
Objective: To evaluate the current evidence on the performance of AI algorithms in the diagnosis of thyroid pathologies.
Methods: A systematic review and meta-analysis of studies published between 2018 and 2024, identified in PubMed, Scopus and Web of Science, was performed. Studies that evaluated the diagnostic accuracy of AI models in thyroid diseases were included, using QUADAS-2 criteria for quality assessment. Data were analyzed using random-effects models in R.
Results: Eighteen studies (n = 12,430 patients) were included. The overall accuracy of AI was 92.3% (95% CI: 89.5–94.7%), with a sensitivity of 88.1% (95% CI: 84.2–91.4%) and a specificity of 94.6% (95% CI: 91.8–96.7%). Convolutional neural network-based models showed an AUC of 0.96 in thyroid nodule classification. Inter-study heterogeneity was moderate (I² = 67%).
Conclusion: AI demonstrates high potential for improving thyroid diagnosis, although prospective studies are required to validate its clinical applicability.
Downloads
References
1. Taylor PN, Albrecht D, Scholz A, Gutierrez-Buey G, Lazarus JH, Dayan CM, et al. Global epidemiology of hyperthyroidism and hypothyroidism. Nat Rev Endocrinol. 2018;14(5):301-16. DOI: https://doi.org/10.1038/nrendo.2018.18
2. Haugen BR. 2015 American Thyroid Association Management Guidelines for Adult Patients with Thyroid Nodules and Differentiated Thyroid Cancer: Whast is new and what has changed? Cancer. 2016;123(3):372-81. DOI: https://doi.org/10.1002/cncr.30360
3. Cibas ES, Ali SZ. The 2017 Bethesda System for Reporting Thyroid Cytopathology. Thyroid. 2017;27(11):1341-6. DOI: https://doi.org/10.1089/thy/2017/0500
4. Grant EG, Tessler FN, Hoang JK, Scoutt LM, Stavros AT, Teefey SA, et al. Thyroid Ultrasound Reporting Lexicon: White Paper of the ACR Thyroid Imaging, Reporting and Data System (TIRADS) Committee. J Am Coll Radiol. 2015;12(12 Pt A):1272-9. DOI: https://doi.org/10.1016/j.jacr.2015.07.011
5. Esteva A, Robicquet A, Ramsundar B, Kuleshov V, DePristo M, Chou K, et al. A guide to deep learning in healthcare. Nature Medecine. 2019;25(1):24-9. DOI: https://doi.org/10.1038/s41591-018-0316-z
6. McKinney SM, Sieniek M, Godbole V, Godwin J, Antropova N, Ashrafian H, et al. International evaluation of an AI system for breast cancer screening. Nature. 2020;577(7788):89-94. DOI: https://doi.org/10.1038/s41586-019-1799-6
7. Li X, Zhang S, Zhang Q, Wei X, Pan Y, Zhao J, et al. Diagnosis of thyroid cancer using deep convolutional neural network models applied to sonographic images: a retrospective, multicohort, diagnostic study. Lancet Oncol. 2019;20(2):193-201. DOI: https://doi.org/10.1016/S1470-2045(18)30762-9
8. Wu Y, Rao K, Liu J. A machine learning model for accurate diagnosis of hypothyroidism using clinical data. J Clin Endocrinol Metab. 2020;105(3):dgz252. DOI: https://doi.org/10.1210/clinem/dgz252
9. Chen H, Zhang K, Lyu P. A deep learning model for reducing the need for biopsies in thyroid nodules with indeterminate cytology. Thyroid. 2022;32(3):304-15. DOI: https://doi.org/10.1089/thy.2021.0323
10. Aggarwal R, Sounderajah V, Martin G, Daniel S, Ting W, Karthikesalingam A, et al. Diagnostic accuracy of deep learning in medical imaging: a systematic review and meta-analysis. NPJ Digital Medicine. 2021;4:65. DOI: https://doi.org//10.1038/s41746-021-00438-z
11. Wang L, Yang S, Yang Y. Artificial intelligence for thyroid nodule ultrasound image analysis: a pilot study. Front Oncol. 2021;11:638197. DOI: https://doi.org/10.3389/fonc.2021.638197
12. Liu T, Xie S, Yu J. ThyroidNet: A Deep Learning Network for Differential Diagnosis of Thyroid Nodules. AJR Am J Roentgenol. 2023;220(1):135-43. DOI: https://doi.org/10.2214/AJR.22.27631
13. Jabin Z, Rashid M, Hussain A. Role of Artificial Intelligence in Diagnostic Ultrasound of Thyroid Nodules: A Systematic Review. Cureus. 2022;14(6):e25780. DOI: https://doi.org/10.7759/cureus.25780
14. Topol EJ. High-performance medicine: the convergence of human and artificial intelligence. Nat Med. 2019;25(1):44-56. DOI: https://doi.org/10.1038/s41591-018-0300-7
15. Hoang JK, Middleton WD, Farjat AE. Interobserver Variability in Sonographic Evaluation of Thyroid Nodules. J Ultrasound Med. 2018;37(1):173-8. DOI: https://doi.org/10.1002/jum.14321
16. Tessler FN, Middleton WD, Grant EG, Hoang JK, Berland LL, Teefey SA, et al. ACR Thyroid Imaging, Reporting and Data System (TI-RADS): White Paper of the ACR TI-RADS Committee. J Am Coll Radiol. 2017;14(5):587-95. DOI: https://doi.org/10.1016/j.jacr.2017.01.046
17. Sounderajah V, Ashrafian H, Aggarwal R, De Fauw J, Greaves F, King D, et al. Developing specific reporting guidelines for diagnostic accuracy studies assessing AI interventions: The STARD-AI Steering Group. Nature Medicine. 2021;27(11):1863-8. DOI: https://doi.org/10.1038/s41591-021-01552-z
18. Marqusee E, Benson CB, Frates MC, Doubilet PM, Larsen PR, Cibas ES, et al. Usefulness of ultrasonography in the management of nodular thyroid disease. Ann Intern Med. 2020;172(3):177-88. DOI: https://doi.org/10.7326/M19-2876
19. Durante C, Grani G, Lamartina L, Filetti S, Mandel SJ, Cooper DS. The Diagnosis and Management of Thyroid Nodules: A Review. JAMA. 2018;319(9):914-24. DOI: https://doi.org/10.1001/jama.2018.0898
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2026 Adalberto Luis Infante Amorós, Sergio Enrique Zayas Puig, Kenia Rodríguez Martínez, Leydis Gómez Díaz
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
The Cuban Journal of Medicine protects the author's patrimonial rights. However, it is licensed under a Creative Commons Licensehttps://creativecommons.org/licenses/by-nc/4.0/deed.es_ES which permits unrestricted non-commercial use, distribution and reproduction in any medium, provided that the primary source of publication is duly cited. The author always retains his moral rights.
You are free to:
- Share - copy and redistribute the material in any medium or format.
- Adapt - remix, transform and build upon the material
- The license cannot revoke these freedoms as long as you follow the terms of the license.
Under the following terms:
- Attribution - You must give proper credit, provide a link to the license, and indicate if changes have been made. You may do so in any reasonable manner, but not in such a way as to suggest that you or your use is supported by the licensor.
- Non-Commercial Purpose- You may not make use of the material for commercial purposes.
- No Additional Restrictions - You may not apply legal terms or technological measures that legally restrict others from making any use permitted by the license.
