USE OF ARTIFICIAL INTELLIGENCE IN THE DIAGNOSIS OF THYROID NODULES

Resumo

IntroductionThe use of Artificial Intelligence (AI) models in the diagnosis of thyroid nodules is growing, aiming to improve diagnostic accuracy and optimize clinical management. This study analyzes the effectiveness of AI in reducing the medical workload and enhancing the diagnosis of thyroid nodules (WANG et al., 2020; ZHANG et al., 2021; YANG et al., 2023).MethodsUltrasound data from thyroid nodules collected from various centers were used to develop and validate deep learning models (WANG et al., 2020). AI was integrated into clinical workflow to assist in decision-making, aiming to reduce diagnostic time and increase efficiency (ZHANG et al., 2021). Additionally, AI accuracy was compared with traditional clinical guidelines using the AI-SONICTM system (YANG et al., 2023);ResultsThe AI model developed by WANG et al. (2020) achieved accuracy similar to that of ultrasound specialists, aiding in the early diagnosis of malignancies. ZHANG et al. (2021) demonstrated that AI reduced interobserver variability and increased efficiency in nodule management. YANG et al, (2023) found that AI outperformed traditional guidelines in sensitivity and specificity for risk assessment.ConclusionAI shows promise in the diagnosis of thyroid nodules, improving accuracy and reducing the clinical workload, with the potential to become an essential tool in the management of these cases.References·         WANG, Jie et al. Deep learning-based artificial intelligence model to assist thyroid nodule diagnosis and management: a multicentre diagnostic study. The Lancet Digital Health, v. 2, n. 6, p. e250-e259, 2020.·         ZHANG, Y.; LI, X.; WANG, Y. Integration of Artificial Intelligence Decision Aids to Reduce Workload and Enhance Efficiency in Thyroid Nodule Management. Journal of Endocrinology and Metabolism, v. 14, n. 3, p. 187-195, 2021.·         YANG, L.; LIN, N.; WANG, M.; CHEN, G. Diagnostic efficiency of existing guidelines and the AI-SONIC™ artificial intelligence for ultrasound-based risk assessment of thyroid nodules. Frontiers in Endocrinology, 2023.