A Thyroid Genetic Classifier Correctly Predicts Benign Nodules with Indeterminate Cytology: Two Independent, Multicenter, Prospective Validation Trials

Abstract

Background: Although most thyroid nodules with indeterminate cytology are benign, in most of the world, surgery remains as the most frequent diagnostic approach. We have previously reported a 10-gene thyroid genetic classifier, which accurately predicts benign thyroid nodules. The assay is a prototype diagnostic kit suitable for reference laboratory testing and could potentially avoid unnecessary diagnostic surgery in patients with indeterminate thyroid cytology. Methods: Classifier performance was tested in two independent, ethnically diverse, prospective multicenter trials (TGCT-1/Chile and TGCT-2/USA). A total of 4061 fine-needle aspirations were collected from 15 institutions, of which 897 (22%) were called indeterminate. The clinical site was blind to the classifier score and the clinical laboratory blind to the pathology report. A matched surgical pathology and valid classifier score was available for 270 samples. Results: Cohorts showed significant differences, including (i) clinical site patient source (academic, 43% and 97% for TGCT-1 and -2, respectively); (ii) ethnic diversity, with a greater proportion of the Hispanic population (40% vs. 3%) for TGCT-1 and a greater proportion of African American (11% vs. 0%) and Asian (10% vs. 1%) populations for TGCT-2; and (iii) tumor size (mean of 1.7 and 2.5 cm for TGCT-1 and -2, respectively). Overall, there were no differences in the histopathological profile between cohorts. Forty-one of 155 and 45 of 115 nodules were malignant (cancer prevalence of 26% and 39% for TGCT-1 and -2, respectively). The classifier predicted 37 of 41 and 41 of 45 malignant nodules, yielding a sensitivity of 90% [95% confidence interval; CI 77-97] and 91% [95% CI 79-98] for TGCT-1 and -2, respectively. One hundred one of 114 and 61 of 70 nodules were correctly predicted as benign, yielding a specificity of 89% [95% CI 82-94] and 87% [95% CI 77-94], respectively. The negative predictive values for TGCT-1 and TGCT-2 were 96% and 94%, respectively, whereas the positive predictive values were 74% and 82%, respectively. The overall accuracy for both cohorts was 89%. Conclusions: Clinical validation of the classifier demonstrates equivalent performance in two independent and ethnically diverse cohorts, accurately predicting benign thyroid nodules that can undergo surveillance as an alternative to diagnostic surgery.

Keywords: clinical validation; gene classifier; indeterminate thyroid cytology.

FIG. 1.

Exclusion process flowchart. Color images are available online.

FIG. 2.

Classifier dot plot and Bayes' theorem predicted values. The thyroid genetic classifier effectively classifies indeterminate, fine-needle aspiration biopsy samples. (A) Dot plot of classifier scores for nonsurgical (black circles) and surgical (red circles) gold standard diagnosis are shown. Cutoff score to classify samples as nonsurgical or surgical was 0.2. Blue lines indicate a 10% range of the cutoff score. (B) Bayes' theorem PPVs and NPVs are shown for TGCT-1 (blue) and TGCT-2 (red). The dark horizontal dashed line is set at 70% to represent the lower limit for the PPV, and the light horizontal dotted line is set at 94% to represent the lower limit for the NPV. NPV, negative predictive value; PPV, positive predictive value. Color images are available online.