A 10-Gene Classifier for Indeterminate Thyroid Nodules: Development and Multicenter Accuracy Study

Abstract

Background: In most of the world, diagnostic surgery remains the most frequent approach for indeterminate thyroid cytology. Although several molecular tests are available for testing in centralized commercial laboratories in the United States, there are no available kits for local laboratory testing. The aim of this study was to develop a prototype in vitro diagnostic (IVD) gene classifier for the further characterization of nodules with an indeterminate thyroid cytology.Methods: In a first stage, the expression of 18 genes was determined by quantitative polymerase chain reaction (qPCR) in a broad histopathological spectrum of 114 fresh-tissue biopsies. Expression data were used to train several classifiers by supervised machine learning approaches. Classifiers were tested in an independent set of 139 samples. In a second stage, the best classifier was chosen as a model to develop a multiplexed-qPCR IVD prototype assay, which was tested in a prospective multicenter cohort of fine-needle aspiration biopsies.Results: In tissue biopsies, the best classifier, using only 10 genes, reached an optimal and consistent performance in the ninefold cross-validated testing set (sensitivity 93% and specificity 81%). In the multicenter cohort of fine-needle aspiration biopsy samples, the 10-gene signature, built into a multiplexed-qPCR IVD prototype, showed an area under the curve of 0.97, a positive predictive value of 78%, and a negative predictive value of 98%. By Bayes' theorem, the IVD prototype is expected to achieve a positive predictive value of 64–82% and a negative predictive value of 97–99% in patients with a cancer prevalence range of 20–40%.Conclusions: A new multiplexed-qPCR IVD prototype is reported that accurately classifies thyroid nodules and may provide a future solution suitable for local reference laboratory testing.

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

“…This study reports the prospective clinical validation of a previously described thyroid genetic classifier (13). In two large, independent multicenter trials, we show that the classifier predicts benign thyroid nodules with an NPV of 95% and can identify true negative cases with an 88% specificity in the intended use population.…”

“…The classifier does not have specific biomarkers for Hürthle cell lesions or MTC given that the classifier was designed to predict benign rather than malignant histology. In fact, the algorithm identifies the interactions in the expression between inflammatory and epithelial genes composing the signature to generate a robust benign profile, avoiding the need to depend on a complex and heterogeneous malignant gene expression profile (13).…”

“…This significantly limits the access to molecular testing in the rest of the world where, in the absence of a diagnostic kit for local reference testing, surgery remains the most frequent choice for thyroid nodules with indeterminate cytology. We have recently reported the development of a 10-gene thyroid genetic classifier that accurately predicts benign thyroid nodules with an NPV of 96% and specificity of 87% and could potentially avoid more than 80% of unnecessary surgeries (13). The assay is built into a multiplexed quantitative polymerase chain reaction (qPCR) diagnostic kit format with a level of technical complexity that is suitable for reference laboratory testing (13).…”

“…We have recently reported the development of a 10-gene thyroid genetic classifier that accurately predicts benign thyroid nodules with an NPV of 96% and specificity of 87% and could potentially avoid more than 80% of unnecessary surgeries (13). The assay is built into a multiplexed quantitative polymerase chain reaction (qPCR) diagnostic kit format with a level of technical complexity that is suitable for reference laboratory testing (13). Clearance of a distributable kit by the Food and Drug Administration requires several stages of validation, including analytical and clinical studies to build an appropriate dossier for regulatory approval.…”

Development and validation of an individualized diagnostic signature in thyroid cancer

“…Year Area Platform Number of samples Total Tumor Nontumor Training set GSE27155 2011 USA GPL96 99 78 21 GSE33630 2012 Belgium GPL570 105 60 45 GSE35570 2015 Poland GPL570 116 65 51 GSE60542 2015 Belgium GPL570 63 33 30 GSE82208 2017 Poland GPL570 52 27 25 Test set GSE29265 2012 Belgium GPL570 49 29 20 GSE3467 2005 USA GPL570 18 for thyroid nodule malignancy [13,14]. As all nontumor samples in GSE82208 were obtained from thyroid nodules and diagnosed as follicular adenoma, this dataset was selected to reevaluate the two signatures using a logistics regression model.…”