A molecular computational model improves the preoperative diagnosis of thyroid nodules

Sara Tomei, Ivo Marchetti, Katia Zavaglia, Francesca Lessi, Alessandro Apollo, Paolo Aretini, Giancarlo Di Coscio, Generoso Bevilacqua, Chiara Mazzanti

Research output: Contribution to journalArticle

10 Citations (Scopus)

Abstract

Background: Thyroid nodules with indeterminate cytological features on fine needle aspiration (FNA) cytology have a 20% risk of thyroid cancer. The aim of the current study was to determine the diagnostic utility of an 8-gene assay to distinguish benign from malignant thyroid neoplasm.Methods: The mRNA expression level of 9 genes (KIT, SYNGR2, C21orf4, Hs.296031, DDI2, CDH1, LSM7, TC1, NATH) was analysed by quantitative PCR (q-PCR) in 93 FNA cytological samples. To evaluate the diagnostic utility of all the genes analysed, we assessed the area under the curve (AUC) for each gene individually and in combination. BRAF exon 15 status was determined by pyrosequencing. An 8-gene computational model (Neural Network Bayesian Classifier) was built and a multiple-variable analysis was then performed to assess the correlation between the markers.Results: The AUC for each significant marker ranged between 0.625 and 0.900, thus all the significant markers, alone and in combination, can be used to distinguish between malignant and benign FNA samples. The classifier made up of KIT, CDH1, LSM7, C21orf4, DDI2, TC1, Hs.296031 and BRAF had a predictive power of 88.8%. It proved to be useful for risk stratification of the most critical cytological group of the indeterminate lesions for which there is the greatest need of accurate diagnostic markers.Conclusion: The genetic classification obtained with this model is highly accurate at differentiating malignant from benign thyroid lesions and might be a useful adjunct in the preoperative management of patients with thyroid nodules.

Original languageEnglish
Article number396
JournalBMC Cancer
Volume12
DOIs
Publication statusPublished - 7 Sep 2012
Externally publishedYes

Fingerprint

Thyroid Nodule
Molecular Models
Fine Needle Biopsy
Genes
Thyroid Neoplasms
Area Under Curve
Neural Networks (Computer)
Cell Biology
Exons
Thyroid Gland
Polymerase Chain Reaction
Messenger RNA

Keywords

  • Area under the curve (AUC)
  • Computational model
  • Fine-needle aspiration (FNA)
  • Preoperative diagnosis
  • Thyroid

ASJC Scopus subject areas

  • Oncology
  • Cancer Research
  • Genetics

Cite this

Tomei, S., Marchetti, I., Zavaglia, K., Lessi, F., Apollo, A., Aretini, P., ... Mazzanti, C. (2012). A molecular computational model improves the preoperative diagnosis of thyroid nodules. BMC Cancer, 12, [396]. https://doi.org/10.1186/1471-2407-12-396

A molecular computational model improves the preoperative diagnosis of thyroid nodules. / Tomei, Sara; Marchetti, Ivo; Zavaglia, Katia; Lessi, Francesca; Apollo, Alessandro; Aretini, Paolo; Di Coscio, Giancarlo; Bevilacqua, Generoso; Mazzanti, Chiara.

In: BMC Cancer, Vol. 12, 396, 07.09.2012.

Research output: Contribution to journalArticle

Tomei, S, Marchetti, I, Zavaglia, K, Lessi, F, Apollo, A, Aretini, P, Di Coscio, G, Bevilacqua, G & Mazzanti, C 2012, 'A molecular computational model improves the preoperative diagnosis of thyroid nodules', BMC Cancer, vol. 12, 396. https://doi.org/10.1186/1471-2407-12-396
Tomei, Sara ; Marchetti, Ivo ; Zavaglia, Katia ; Lessi, Francesca ; Apollo, Alessandro ; Aretini, Paolo ; Di Coscio, Giancarlo ; Bevilacqua, Generoso ; Mazzanti, Chiara. / A molecular computational model improves the preoperative diagnosis of thyroid nodules. In: BMC Cancer. 2012 ; Vol. 12.
@article{88f6896d0179479595b9bc33e9a77e3a,
title = "A molecular computational model improves the preoperative diagnosis of thyroid nodules",
abstract = "Background: Thyroid nodules with indeterminate cytological features on fine needle aspiration (FNA) cytology have a 20{\%} risk of thyroid cancer. The aim of the current study was to determine the diagnostic utility of an 8-gene assay to distinguish benign from malignant thyroid neoplasm.Methods: The mRNA expression level of 9 genes (KIT, SYNGR2, C21orf4, Hs.296031, DDI2, CDH1, LSM7, TC1, NATH) was analysed by quantitative PCR (q-PCR) in 93 FNA cytological samples. To evaluate the diagnostic utility of all the genes analysed, we assessed the area under the curve (AUC) for each gene individually and in combination. BRAF exon 15 status was determined by pyrosequencing. An 8-gene computational model (Neural Network Bayesian Classifier) was built and a multiple-variable analysis was then performed to assess the correlation between the markers.Results: The AUC for each significant marker ranged between 0.625 and 0.900, thus all the significant markers, alone and in combination, can be used to distinguish between malignant and benign FNA samples. The classifier made up of KIT, CDH1, LSM7, C21orf4, DDI2, TC1, Hs.296031 and BRAF had a predictive power of 88.8{\%}. It proved to be useful for risk stratification of the most critical cytological group of the indeterminate lesions for which there is the greatest need of accurate diagnostic markers.Conclusion: The genetic classification obtained with this model is highly accurate at differentiating malignant from benign thyroid lesions and might be a useful adjunct in the preoperative management of patients with thyroid nodules.",
keywords = "Area under the curve (AUC), Computational model, Fine-needle aspiration (FNA), Preoperative diagnosis, Thyroid",
author = "Sara Tomei and Ivo Marchetti and Katia Zavaglia and Francesca Lessi and Alessandro Apollo and Paolo Aretini and {Di Coscio}, Giancarlo and Generoso Bevilacqua and Chiara Mazzanti",
year = "2012",
month = "9",
day = "7",
doi = "10.1186/1471-2407-12-396",
language = "English",
volume = "12",
journal = "BMC Cancer",
issn = "1471-2407",
publisher = "BioMed Central",

}

TY - JOUR

T1 - A molecular computational model improves the preoperative diagnosis of thyroid nodules

AU - Tomei, Sara

AU - Marchetti, Ivo

AU - Zavaglia, Katia

AU - Lessi, Francesca

AU - Apollo, Alessandro

AU - Aretini, Paolo

AU - Di Coscio, Giancarlo

AU - Bevilacqua, Generoso

AU - Mazzanti, Chiara

PY - 2012/9/7

Y1 - 2012/9/7

N2 - Background: Thyroid nodules with indeterminate cytological features on fine needle aspiration (FNA) cytology have a 20% risk of thyroid cancer. The aim of the current study was to determine the diagnostic utility of an 8-gene assay to distinguish benign from malignant thyroid neoplasm.Methods: The mRNA expression level of 9 genes (KIT, SYNGR2, C21orf4, Hs.296031, DDI2, CDH1, LSM7, TC1, NATH) was analysed by quantitative PCR (q-PCR) in 93 FNA cytological samples. To evaluate the diagnostic utility of all the genes analysed, we assessed the area under the curve (AUC) for each gene individually and in combination. BRAF exon 15 status was determined by pyrosequencing. An 8-gene computational model (Neural Network Bayesian Classifier) was built and a multiple-variable analysis was then performed to assess the correlation between the markers.Results: The AUC for each significant marker ranged between 0.625 and 0.900, thus all the significant markers, alone and in combination, can be used to distinguish between malignant and benign FNA samples. The classifier made up of KIT, CDH1, LSM7, C21orf4, DDI2, TC1, Hs.296031 and BRAF had a predictive power of 88.8%. It proved to be useful for risk stratification of the most critical cytological group of the indeterminate lesions for which there is the greatest need of accurate diagnostic markers.Conclusion: The genetic classification obtained with this model is highly accurate at differentiating malignant from benign thyroid lesions and might be a useful adjunct in the preoperative management of patients with thyroid nodules.

AB - Background: Thyroid nodules with indeterminate cytological features on fine needle aspiration (FNA) cytology have a 20% risk of thyroid cancer. The aim of the current study was to determine the diagnostic utility of an 8-gene assay to distinguish benign from malignant thyroid neoplasm.Methods: The mRNA expression level of 9 genes (KIT, SYNGR2, C21orf4, Hs.296031, DDI2, CDH1, LSM7, TC1, NATH) was analysed by quantitative PCR (q-PCR) in 93 FNA cytological samples. To evaluate the diagnostic utility of all the genes analysed, we assessed the area under the curve (AUC) for each gene individually and in combination. BRAF exon 15 status was determined by pyrosequencing. An 8-gene computational model (Neural Network Bayesian Classifier) was built and a multiple-variable analysis was then performed to assess the correlation between the markers.Results: The AUC for each significant marker ranged between 0.625 and 0.900, thus all the significant markers, alone and in combination, can be used to distinguish between malignant and benign FNA samples. The classifier made up of KIT, CDH1, LSM7, C21orf4, DDI2, TC1, Hs.296031 and BRAF had a predictive power of 88.8%. It proved to be useful for risk stratification of the most critical cytological group of the indeterminate lesions for which there is the greatest need of accurate diagnostic markers.Conclusion: The genetic classification obtained with this model is highly accurate at differentiating malignant from benign thyroid lesions and might be a useful adjunct in the preoperative management of patients with thyroid nodules.

KW - Area under the curve (AUC)

KW - Computational model

KW - Fine-needle aspiration (FNA)

KW - Preoperative diagnosis

KW - Thyroid

UR - http://www.scopus.com/inward/record.url?scp=84865816246&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84865816246&partnerID=8YFLogxK

U2 - 10.1186/1471-2407-12-396

DO - 10.1186/1471-2407-12-396

M3 - Article

VL - 12

JO - BMC Cancer

JF - BMC Cancer

SN - 1471-2407

M1 - 396

ER -