Dataset Information

Quantitative Biomarkers for Prediction of Epidermal Growth Factor Receptor Mutation in Non-Small Cell Lung Cancer.

ABSTRACT:

Objectives

To predict epidermal growth factor receptor (EGFR) mutation status using quantitative radiomic biomarkers and representative clinical variables.

Methods

The study included 180 patients diagnosed as of non-small cell lung cancer (NSCLC) with their pre-therapy computed tomography (CT) scans. Using a radiomic method, 485 features that reflect the heterogeneity and phenotype of tumors were extracted. Afterwards, these radiomic features were used for predicting epidermal growth factor receptor (EGFR) mutation status by a least absolute shrinkage and selection operator (LASSO) based on multivariable logistic regression. As a result, we found that radiomic features have prognostic ability in EGFR mutation status prediction. In addition, we used radiomic nomogram and calibration curve to test the performance of the model.

Results

Multivariate analysis revealed that the radiomic features had the potential to build a prediction model for EGFR mutation. The area under the receiver operating characteristic curve (AUC) for the training cohort was 0.8618, and the AUC for the validation cohort was 0.8725, which were superior to prediction model that used clinical variables alone.

Conclusion

Radiomic features are better predictors of EGFR mutation status than conventional semantic CT image features or clinical variables to help doctors to decide who need EGFR tyrosine kinase inhibitor (TKI) treatment.

SUBMITTER: Zhang L

PROVIDER: S-EPMC6002350 | biostudies-literature | 2018 Feb

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Quantitative Biomarkers for Prediction of Epidermal Growth Factor Receptor Mutation in Non-Small Cell Lung Cancer.

Zhang Liwen L Chen Bojiang B Liu Xia X Song Jiangdian J Fang Mengjie M Hu Chaoen C Dong Di D Li Weimin W Tian Jie J

Translational oncology 20171218 1

<h4>Objectives</h4>To predict epidermal growth factor receptor (EGFR) mutation status using quantitative radiomic biomarkers and representative clinical variables.<h4>Methods</h4>The study included 180 patients diagnosed as of non-small cell lung cancer (NSCLC) with their pre-therapy computed tomography (CT) scans. Using a radiomic method, 485 features that reflect the heterogeneity and phenotype of tumors were extracted. Afterwards, these radiomic features were used for predicting epidermal gro ...[more]

PMID: 29216508

Similar Datasets

Project description:BackgroundOsteoblastic bone reaction (OBR) refers to an increase in bone density at the site of bone metastasis or the appearance of new sclerotic bone lesions after anticancer treatment. OBR can be misunderstood as disease progression. In this study, we aimed to investigate the prevalence and details of OBR and its association with clinical outcomes in patients with epidermal growth factor receptor (EGFR)-mutant non-small cell lung cancer (NSCLC) treated with osimertinib.MethodsThis was a single-center, retrospective cohort study. We reviewed patients who were diagnosed with EGFR-mutant NSCLC with bone metastasis and received osimertinib as a first-line treatment between February 2018 and October 2022. The OBR was evaluated by comparing baseline computed tomography (CT) scans with the first CT scan after treatment initiation.ResultsA total of 45 patients were included in this study. Thirty-seven patients (82%) developed OBR. OBR developed in 94% (n = 16) of patients with sclerotic bone lesions (n = 17) at baseline. Similarly, OBR developed in lytic and mixed bone lesions in 76% and 82% of patients with lytic and mixed lesions, respectively. Progression-free survival (PFS) did not differ significantly between patients with (OBR group) and without OBR (non-OBR group) (median PFS, 24 months vs. 17 months; hazard ratio (HR), 0.62; 95% CI, 0.24-1.6; p = 0.31). In univariate analysis, the OBR group showed a trend toward longer skeletal-related events-free survival (SRE-FS) than the non-OBR group (median SRE-FS, 26 months vs. 12 months; HR, 0.53; 95% CI, 0.21-1.33; p = 0.16). Multivariate analysis showed OBR was a significant independent predictor of SRE-FS (HR, 0.35; 95% CI, 0.13-0.92; p = 0.034).ConclusionsOBR developed in most patients with NSCLC and bone metastasis who received osimertinib treatment. The increased incidence of OBR in patients with EGFR-mutant NSCLC with bone metastasis treated with osimertinib should not be confused with disease progression, and treatment decisions should be made carefully.

Project description:BackgroundThe level of tumor abnormal protein (TAP) level has a significant impact on tumor growth, recurrence, and metastasis. Previous studies have highlighted the influence of the mutations in exons 19 and 21 of the epidermal growth factor receptor (EGFR), particularly the sensitivity displayed by tumor cells to epidermal growth factor receptor-tyrosine kinase inhibitor (EGFR-TKI) therapy. Our study is centered on exploring the clinical relevance of TAP and EGFR mutations in patients with non-small cell lung cancer (NSCLC).Material and methodsIn this study, tissue samples were collected from a total of 176 patients diagnosed with non-small cell lung cancer (NSCLC). Real-time PCR technology was utilized to detect mutations within exons 19 and 21 of the epidermal growth factor receptor (EGFR) gene in these samples. This approach enables precise identification of EGFR mutations associated with NSCLC. Furthermore, the study investigated the impact of various tumor markers, including tumor abnormal protein (TAP) and carcinoembryonic antigen (CEA), on EGFR mutation status. Established assays were employed to evaluate TAP and CEA levels, aiming to ascertain their potential correlation with EGFR mutation in NSCLC patients.ResultsEGFR exhibited mutation rates of 23.86% and 12.50% in exons 19 and 21, respectively. EGFR mutations were more prevalent in younger women (< 60 years old) and in cases with pleural invasion, vessel invasion, CEA > 6.5 ng/mL, and TAP > 228 µm2 for both genders. Increased TAP levels independently predicted EGFR mutations (P = 0.001 for males; P = 0.000 for females). An area under the curve (AUC) of 0.833 indecated EGFR mutation prediction with sensitivity and specificity of 79.7% and 87.0%, respectively. For females, the sensitivity increased to 89.7% and specificity increased to 93.8%.ConclusionsTAP effectively predicts EGFR mutations in NSCLC patients with moderate accuracy, particularly benefiting diagnosis in females with high sensitivity and specificity. Integrating TAP assessment into EGFR mutation testing can significantly enhance diagnostic precision, especially in female NSCLC cases.

Dataset Information

Quantitative Biomarkers for Prediction of Epidermal Growth Factor Receptor Mutation in Non-Small Cell Lung Cancer.

Objectives

Methods

Results

Conclusion

Publications

Quantitative Biomarkers for Prediction of Epidermal Growth Factor Receptor Mutation in Non-Small Cell Lung Cancer.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets