Dataset Information

Classification of Benign and Malignant Thyroid Nodules Using a Combined Clinical Information and Gene Expression Signatures.

ABSTRACT: A key challenge in thyroid carcinoma is preoperatively diagnosing malignant thyroid nodules. A novel diagnostic test that measures the expression of a 3-gene signature (DPP4, SCG5 and CA12) has demonstrated promise in thyroid carcinoma assessment. However, more reliable prediction methods combining clinical features with genomic signatures with high accuracy, good stability and low cost are needed.25 clinical information were recorded in 771 patients. Feature selection and validation were conducted using random forest. Thyroid samples and clinical data were obtained from 142 patients at two different hospitals, and expression of the 3-gene signature was measured using quantitative PCR. The predictive abilities of three models (based on the selected clinical variables, the gene expression profile, and integrated gene expression and clinical information) were compared. Seven clinical characteristics were selected based on a training set (539 patients) and tested in three test sets, yielding predictive accuracies of 82.3% (n = 232), 81.4% (n = 70), and 81.9% (n = 72). The predictive sensitivity, specificity, and accuracy were 72.3%, 80.5% and 76.8% for the model based on the gene expression signature, 66.2%, 81.8% and 74.6% for the model based on the clinical data, and 83.1%, 84.4% and 83.8% for the combined model in a 10-fold cross-validation (n = 142).These findings reveal that the integrated model, which combines clinical data with the 3-gene signature, is superior to models based on gene expression or clinical data alone. The integrated model appears to be a reliable tool for the preoperative diagnosis of thyroid tumors.

SUBMITTER: Zheng B

PROVIDER: S-EPMC5077123 | biostudies-literature | 2016

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Classification of Benign and Malignant Thyroid Nodules Using a Combined Clinical Information and Gene Expression Signatures.

Zheng Bing B Liu Jun J Gu Jianlei J Du Jing J Wang Lin L Gu Shengli S Cheng Juan J Yang Jun J Lu Hui H

PloS one 20161024 10

<h4>Background</h4>A key challenge in thyroid carcinoma is preoperatively diagnosing malignant thyroid nodules. A novel diagnostic test that measures the expression of a 3-gene signature (DPP4, SCG5 and CA12) has demonstrated promise in thyroid carcinoma assessment. However, more reliable prediction methods combining clinical features with genomic signatures with high accuracy, good stability and low cost are needed.<h4>Methodology/principal findings</h4>25 clinical information were recorded in ...[more]

PMID: 27776138

Similar Datasets

Project description:The incidence of thyroid nodules has been increasing worldwide; however, there are currently no feasible and robust methods to differentiate malignant thyroid nodules from benign thyroid nodules. The present study aimed to establish a practical method to determine the malignancy of thyroid nodules. Reverse transcription‑quantitative PCR and western blot analyses were performed to compare the levels of long non‑coding RNA nuclear enriched abundant transcript 1 (NEAT1), microRNA (miR)‑9, miR‑124, PTEN and programmed cell death protein 6 (PDCD6) in the peripheral blood and thyroid tissue samples between patients with malignant and benign thyroid nodules. Additionally, a regulatory relationship between NEAT1, miR‑124, miR‑9, PTEN and PDCD6 was established in the present study. The diagnostic value of NEAT1, miR‑124 and miR‑9 was determined using a ROC analysis. The expression levels of NEAT1, PTEN and PDCD6 in peripheral blood and thyroid tissue samples collected from the benign group were higher compared with those in the malignant group, whereas the expression levels of miR‑124 and miR‑9 were lower in the benign group. In the peripheral blood, NEAT1 expression exhibited an area under the curve (AUC) value of 0.8546, whereas miR‑124 and miR‑9 expression had AUC values of 0.7657 and 0.7019, respectively. In the thyroid tissue, NEAT1, miR‑124, and miR‑9 had AUC values of 0.9304, 0.8221 and 0.7757, respectively. Additionally, miR‑9 and miR‑124 expression levels in BCPaP and SW579 cells was decreased after transfection with a NEAT1 expression vector compared with those in cells transfected with the control vector, whereas the expression of PTEN and PDCD6 was upregulated. By contrast, transfection with short hairpin RNA targeting NEAT1 notably increased the expression of miR‑9 and miR‑124 while downregulating the expression of PTEN and PDCD6 compared with that in the control cells. In conclusion, the results of the present study demonstrated that the dysregulation of NEAT1 expression may be used to differentiate benign and malignant thyroid nodules.

Dataset Information

Classification of Benign and Malignant Thyroid Nodules Using a Combined Clinical Information and Gene Expression Signatures.

Publications

Classification of Benign and Malignant Thyroid Nodules Using a Combined Clinical Information and Gene Expression Signatures.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets