Abstract
<jats:p>Advancements in artificial intelligence (AI) havesignificantly influenced the development of diagnostic tools in medicine, including endocrinology.Thyroid nodules are a prevalent clinical occurrence, and their accurate evaluation about malignancy risk is essential for treatment decisions. Conventional diagnostic techniques, like ultrasonography and fine-needle aspiration biopsy (FNAB),although effective, are burdened with subjectivity and limited availability of specialists.This article discusses the contemporary applications of artificial intelligence, including machine learning and deep learning algorithms, in the detection, classification, and evaluation of thyroid nodules utilizing ultrasound pictures and clinical data. The text compares the performance of AI models with expert evaluations and examines the possible advantages of their application in clinical practice, including enhanced diagnostic accuracy, standardized assessments, and decreased time to diagnosis.Despite the promising research findings, additional efforts are required to validate models in extensive populations and to integrate AI systems with current clinical protocols. Artificial intelligence possesses the potential to support as a substantial aid in the diagnosis of thyroid disorders; nevertheless, its comprehensive implementation necessitates the evaluation of ethical, legal, and organizational factors. Aim of the study: The aim of this article is to assess the role of artificial intelligence in the diagnosis of thyroid nodules, with particular emphasis on the use of machine learning (ML) and deep learning (DL) algorithms in the analysis of ultrasound images, cancer risk classification, and clinical decision support. The article aims to compare the effectiveness of AI-based systems with radiological assessment performed by specialists and to discuss the potential benefits and limitations of implementing these technologies in endocrinology practice. Materials and methods: A review of the literature available in the PubMed and Google Scholar databases was performed, using the key words: “Artificial Intelligence”, “AI”, “Thyroid Nodules”, “Fine Needle Aspiration Biopsy”, “FNAB”, “TIRADS”.</jats:p>