Artificial intelligence as a tool for supporting the screening and diagnosis of thyroid disorders: current reality or future horizon
DOI:
https://doi.org/10.34119/bjhrv8n6-110Keywords:
Artificial Intelligence, Diagnosis, Thyroid Disorders, Machine Learning, Deep LearningAbstract
The use of Artificial Intelligence (AI) has emerged as a promising approach for the early detection of thyroid disorders. This study aimed to investigate the application of AI in the screening and diagnosis of these conditions. An exploratory and descriptive literature review with a qualitative approach was conducted. The PUBMED/MEDLINE and Embase databases were searched for articles published in the last five years. Original studies on AI applications in thyroid disease diagnosis were included, while opinion pieces and review articles were excluded. The search strategy incorporated terms such as “Artificial Intelligence,” “Machine Learning,” “Deep Learning,” “AI,” “Diagnosis,” and “Thyroid Diseases,” combined with Boolean operators “AND” and “OR,” yielding 14 eligible articles. AI demonstrated substantial potential to improve healthcare delivery. Machine learning models, particularly those based on deep learning, proved effective in classifying thyroid nodules and enhancing diagnostic accuracy. Studies reported that AI could outperform traditional methods in diagnostic precision, underscoring its utility in nodule screening and metastasis detection. Additionally, AI was effective in assessing Graves’ disease and identifying conditions such as hypokalemic paralysis, contributing to faster and more accurate diagnoses. In conclusion, the use of AI in diagnosing thyroid disorders represents a major advancement in endocrinology, with the potential to improve diagnostic precision and optimize clinical management. However, validation in larger and more diverse populations is required to consolidate its effectiveness and expand its clinical implementation.
References
ANTONELLI, L. et al. Graves' disease: Clinical manifestations, immune pathogenesis (cytokines and chemokines) and therapy. Best Practice & Research Clinical Endocrinology & Metabolism, v. 34, n. 1, p. 101388, 2020. doi: 10.1016/j.beem.2020.101388.
AVERSANO, L. et al. A systematic review on artificial intelligence techniques for detecting thyroid diseases. PeerJ Computer Science, v. 9, e1394, 2023. doi: 10.7717/peerj-cs.1394.
BINI, F. et al. Artificial intelligence in thyroid field - A comprehensive review. Cancers, v. 13, n. 19, p. 4740, 2021. doi: 10.3390/cancers13194740.
BOULD, H. et al. A investigação de disfunção tireoidiana é mais provável em pacientes com alta morbidade psicológica. Family Practice, v. 29, p. 163-167, 2012. doi: 10.1093/fampra/cmr059.
BUDA, M. et al. Management of thyroid nodules seen on US images: Deep learning may match performance of radiologists. Radiology, v. 292, n. 3, p. 695-701, 2019. doi: 10.1148/radiol.2019181343.
CHEN, X. et al. Artificial intelligence in the training of radiology residents: a multicenter randomized controlled trial. European Radiology, v. 34, n. 2, p. 1000-1012, 2024. doi: 10.1007/s13187-024-02502-0.
FREMOND, L. et al. Interpretable deep learning model to predict the molecular classification of endometrial cancer from haematoxylin and eosin-stained whole-slide images: a combined analysis of the PORTEC randomised trials and clinical cohorts. The Lancet Oncology, v. 24, n. 5, p. 600-612, 2023. doi: 10.1016/S2589-7500(22)00210-2.
GREEN, M. E.; BERNET, V.; CHEUNG, J. Thyroid dysfunction and sleep disorders. Frontiers in Endocrinology, v. 12, p. 725829, 2021. doi: 10.3389/fendo.2021.725829.
GRUSON, D. et al. Artificial intelligence and thyroid disease management: considerations for thyroid function tests. Biochemia Medica, v. 32, n. 2, p. 020601, 2022. doi: 10.11613/BM.2022.020601.
JACKSON, M. et al. Hypokalemic periodic paralysis precipitated by thyrotoxicosis and renal tubular acidosis. Case Reports in Endocrinology, e4529009, 2021. doi: 10.1155/2021/6662129.
LEE, J. H.; HA, E. J.; KIM, J. H. Application of deep learning to the diagnosis of cervical lymph node metastasis from thyroid cancer with CT. European Radiology, v. 29, n. 10, p. 5452-5457, 2019. doi: 10.1007/s00330-019-06488-3.
LI, X. et al. Integration of artificial intelligence with fine-needle aspiration cytology in thyroid nodules: a multicenter study. Frontiers in Endocrinology, v. 14, p. 115233, 2023. doi:10.3389/fendo.2023.115233.
LIN, C. et al. Artificial intelligence-assisted electrocardiography for early diagnosis of thyrotoxic periodic paralysis. Journal of the Endocrine Society, v. 5, n. 9, bvab120, 2021. doi: 10.1210/jendso/bvab120.
MINAMI, Y. et al. Diagnosis of depth of submucosal invasion in colorectal cancer with AI using deep learning. Cancers, v. 14, n. 21, p. 5361, 2022. doi: 10.3390/cancers14215361.
OH, D. et al. Artificial intelligence-based CT-free quantitative thyroid SPECT for thyrotoxicosis: study protocol of a multicentre, prospective, non-inferiority study. BMJ Open, v. 14, n. 10, e089552, 2024. doi: 10.1136/bmjopen-2023-089552.
SINHA, R. A.; YEN, P. M. Metabolic messengers: thyroid hormones. Nature Metabolism, v. 6, n. 4, p. 639-650, 2024. doi:10.1038/s41592-024-00455-0.
TAYLOR, P. N. et al. Global epidemiology of hyperthyroidism and hypothyroidism. Nature Reviews Endocrinology, v. 14, p. 301-316, 2018. doi: 10.1038/s41574-018-0006-8.
WANG, H. et al. Machine learning-based multiparametric MRI radiomics for predicting the aggressiveness of papillary thyroid carcinoma. European Journal of Radiology, v. 122, p. 108755, 2020. doi: 10.1016/j.ejrad.2020.108755.
WANG, J. et al. Deep learning models for thyroid nodules diagnosis of fine-needle aspiration biopsy: a retrospective, prospective, multicentre study in China (ThyroPower system). Cancer Medicine, v. 13, n. 2, p. 1221-1235, 2024. doi: 10.1002/cam4.1221.
XU, J. et al. The clinical value of artificial intelligence in assisting junior radiologists in thyroid ultrasound: a multicenter prospective study from real clinical practice. Ultrasound in Medicine & Biology, v. 50, n. 1, p. 45-55, 2024. doi: 10.1016/j.ultrasmedbio.2023.10.004.
ZHAO, H. N. et al. Contrast-enhanced ultrasound image sequences based on radiomics analysis for diagnosis of metastatic cervical lymph nodes from thyroid cancer. Gland surgery, v. 13, n. 8, p. 1437-1447, 2024a. doi: 10.21037/gs-24-98
ZHAO, L. et al. Diagnostic value of FNA, ultrasound elastography and CEUS in thyroid carcinoma. African Health Sciences, v. 24, n. 3, p. 188-193, 2024b. doi:10.4314/ahs.v24i3.21.
