GIÁ TRỊ CỦA BẢNG PHÂN LOẠI AI TIRADS 2019 TRONG ĐÁNH GIÁ NHÂN TUYẾN GIÁP

Abstract

Purpose: The value of the AI TIRADS 2019 classification table in evaluating thyroid nodules. Objects and methods of the research: The descriptive cross-sectional obvervational study was conducted on 200 patients who had thyroid nodules diagnosed by ultrasound and FNA method at Nghe An Oncology Hospital from March 2023 to the end of November 2023. Results: There are 40 nodules with malignant cells (accounting for 20%) and 160 nodules without malignant cells (accounting for 80%) out of a total of 200 thyroid nodules in 200 patients. The main component of malignant nodules is solid nodules with a ratio of 36/40 (accounting for 90%). The nuclei contain cystic and sponge-like components without malignant cells (100%). The features of thyroid nodules such as hypoechoic and irregular borders have high sensitivity and specificity (accounting for 88%; 62.5% and 74.4%; 81.9%, respectively) in diagnosing malignant nodules. Characteristics of thyroid nodules such as extremely hypoechoic and microcalcifications have a sensitivity and specificity in diagnosing malignant nodules of 15%, 100% and 45%, 98.6%, respectively. There is a statistically significant difference in malignant properties between the group of thyroid nodules with height>= width and height<width.. In malignant thyroid nodules diagnostic, the diagnostic productivity of the AI-TIRADS classification has an area under the curve (AUC) of 0.882, sensitivity of 87.5%, specificity of 76.3%, positive predictive value of 47.9%, negative predictive value of 96%, accuracy of 78.5%. Conclusion: The AI-TIRADS classification is simple, easy to apply and has good value for diagnosing malignant and benign thyroid nodules.