Real-world, Prospective, and Multicenter Validation of a microRNA-based Thyroid Molecular Classifier

Abstract

Background The diagnosis of cancer in thyroid nodules with indeterminate cytology (Bethesda III/IV) is challenging as fine-needle aspiration (FNA), the gold standard method, has limitations, and these cases usually require diagnostic surgery. As approximately 77% of these nodules are not malignant, a diagnostic test accurately identifying benign thyroid nodules can reduce surgery rates. We have previously reported the development and validation of a microRNA-based thyroid molecular classifier for precision endocrinology (mir-THYpe) with high sensitivity and specificity, which could be performed directly from readily available cytological smear slides without the need for a new dedicated FNA. We sought to evaluate whether the use of this test in real-world clinical routine can reduce the rates of surgeries for Bethesda III/IV thyroid nodules and analyze the test performance. Methods We designed a real-world, prospective, multicenter cohort study. Molecular tests were performed in a real-world clinical routine with samples (FNA smear slides) prepared at 128 cytopathology laboratories. Patients were followed-up from March 2018 until surgery or until March 2020 (for those patients not recommended for surgery). The final diagnosis of thyroid tissue samples was retrieved from postsurgical anatomopathological reports. Results After applying the exclusion criteria, 435 patients (440 nodules) classified as Bethesda III/IV were followed-up. The rate of avoided surgeries was 52.5% for all surgeries and 74.6% for potentially unnecessary surgeries. After the statistical treatment of non-resected test-negative samples, the test achieved 89.3% sensitivity (95% CI 82-94.3), 81.65% specificity (95% CI 76.6-86), 66.2% positive predictive value (95% CI 60.3-71.7), and 95% negative predictive value (95% CI 91.7-97) at 28.7% (95% CI 24.3-33.5) cancer prevalence. The test influenced 92.3% of clinical decisions. Conclusions The reported data demonstrate that the use of the microRNA-based classifier in the real-world can reduce the rate of thyroid surgery with robust performance and significantly influence clinical decision-making.