Retrospective Cohort Study of 1947 Thyroid Nodules: A Comparison of the 2017 American College of Radiology TI-RADS and the 2015 American Thyroid Association Classifications.

Abstract

OBJECTIVE. The objective of our study was to compare diagnostic accuracy and reliability of the 2017 American College of Radiology (ACR) Thyroid Imaging Reporting and Data System (TI-RADS) and 2015 American Thyroid Association (ATA) classifications for thyroid nodules. MATERIALS AND METHODS. This study was a retrospective cohort study of 1947 consecutive thyroid nodules sampled with fine-needle aspiration (FNA) from 2007 to 2016. Reviewers assigned TI-RADS scores to all nodules while blinded to clinical outcome and histologic diagnosis and compared TI-RADS scores with nodule-specific ATA scores from the same cohort. Five blinded radiologists independently assigned TI-RADS scores to a subset of 151 nodules (interrater agreement). The primary outcome was a comparison of the diagnostic accuracy of the TI-RADS and ATA classifications using ROC curve analysis. The reference standard was cytopathologic diagnosis according to the Bethesda system. Interrater agreement was determined using intraclass correlation (ICC) and kappa statistics. RESULTS. Of 1947 sampled thyroid nodules, 31.8% (n = 620) met TI-RADS criteria for FNA, 28.0% (n = 545) met TI-RADS criteria for follow-up, and 40.2% (n = 782) met TIRADS criteria to be ignored. Applying the 2015 ATA criteria resulted in recommendations of immediate FNA procedures for more nodules than applying the 2017 TI-RADS (ATA vs TIRADS: 62.3% [1213/1947] vs 31.8% [620/1947], p < 0.0001). Diagnostic accuracies (AUCs: TI-RADS score, 0.684 [95% CI, 0.644-0.724]; ATA, 0.686 [95% CI, 0.646-0.725]) and false-negative rates (TI-RADS, 2.2% [43/1947]; ATA, 2.4% [47/1947]) for the two classifications were similar (p = 0.75). Overall interrater agreement was fair for both (ICCs: TI-RADS, 0.437 [95% CI, 0.357-0.520]; ATA classification, 0.460 [95% CI, 0.391-0.533]). CONCLUSION. The 2017 ACR TI-RADS and 2015 ATA classifications have similar diagnostic accuracies and interrater agreement, but TI-RADS results in fewer nodules being recommended for immediate FNAs and more nodules being recommended for imaging surveillance.