Dataset Information

Machine Learning-Based CT Radiomics Analysis for Prognostic Prediction in Metastatic Non-Small Cell Lung Cancer Patients With EGFR-T790M Mutation Receiving Third-Generation EGFR-TKI Osimertinib Treatment

ABSTRACT:

Background and Purpose

As a third-generation EGFR tyrosine kinase inhibitor (TKI), osimertinib is approved for treating advanced non-small cell lung cancer (NSCLC) patients with EGFR-T790M mutation after progression on first- or second-generation EGFR-TKIs such as gefitinib, erlotinib and afatinib. We aim at exploring the feasibility and effectiveness of using radiomic features from chest CT scan to predict the prognosis of metastatic non-small cell lung cancer (NSCLC) patients with EGFR-T790M mutation receiving second-line osimertinib therapy.

Methods

Contrast-enhanced and unenhanced chest CT images before osimertinib treatment were collected from 201 and 273 metastatic NSCLC patients with EGFR-T790M mutation, respectively. Radiomic features were extracted from the volume of interest. LASSO regression was used to preliminarily evaluate the prognostic values of different radiomic features. We then performed machine learning-based analyses including random forest (RF), support vector machine (SVM), stepwise regression (SR) and LASSO regression with 5-fold cross-validation (CV) to establish the optimal radiomic model for predicting the progression-free survival (PFS) of osimertinib treatment. Finally, a combined clinical-radiomic model was developed and validated using the concordance index (C-index), decision-curve analysis (DCA) and calibration curve analysis.

Results

Disease progression occurred in 174/273 (63.7%) cases. CT morphological features had no ability in predicting patients’ prognosis in osimertinib treatment. Univariate COX regression followed by LASSO regression analyses identified 23 and 6 radiomic features from the contrast-enhanced and unenhanced CT with prognostic value, respectively. The 23 contrast-enhanced radiomic features were further used to construct radiomic models using different machine learning strategies. Radiomic model built by SR exhibited superior predictive accuracy than RF, SVR or LASSO model (mean C-index of the 5-fold CV: 0.660 vs. 0.560 vs. 0.598 vs. 0.590). Adding the SR radiomic model to the clinical model could remarkably strengthen the C-index of the latter from 0.672 to 0.755. DCA and calibration curve analyses also demonstrated good performance of the combined clinical-radiomic model.

Conclusions

Radiomic features extracted from the contrast-enhanced chest CT could be used to evaluate metastatic NSCLC patients’ prognosis in osimertinib treatment. Prognostic models combing both radiomic features and clinical factors had a great performance in predicting patients’ outcomes.

SUBMITTER: Tang X

PROVIDER: S-EPMC8511497 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Similar Datasets

Project description:BackgroundOsimertinib is an epidermal growth factor receptor tyrosine kinase inhibitor (EGFR-TKI) that is selective for both EGFR-TKI sensitizing and T790M resistance mutations in patients with non-small-cell lung cancer. The efficacy of osimertinib as compared with platinum-based therapy plus pemetrexed in such patients is unknown.MethodsIn this randomized, international, open-label, phase 3 trial, we assigned 419 patients with T790M-positive advanced non-small-cell lung cancer, who had disease progression after first-line EGFR-TKI therapy, in a 2:1 ratio to receive either oral osimertinib (at a dose of 80 mg once daily) or intravenous pemetrexed (500 mg per square meter of body-surface area) plus either carboplatin (target area under the curve, 5 [AUC5]) or cisplatin (75 mg per square meter) every 3 weeks for up to six cycles; maintenance pemetrexed was allowed. In all the patients, disease had progressed during receipt of first-line EGFR-TKI therapy. The primary end point was investigator-assessed progression-free survival.ResultsThe median duration of progression-free survival was significantly longer with osimertinib than with platinum therapy plus pemetrexed (10.1 months vs. 4.4 months; hazard ratio; 0.30; 95% confidence interval [CI], 0.23 to 0.41; P<0.001). The objective response rate was significantly better with osimertinib (71%; 95% CI, 65 to 76) than with platinum therapy plus pemetrexed (31%; 95% CI, 24 to 40) (odds ratio for objective response, 5.39; 95% CI, 3.47 to 8.48; P<0.001). Among 144 patients with metastases to the central nervous system (CNS), the median duration of progression-free survival was longer among patients receiving osimertinib than among those receiving platinum therapy plus pemetrexed (8.5 months vs. 4.2 months; hazard ratio, 0.32; 95% CI, 0.21 to 0.49). The proportion of patients with adverse events of grade 3 or higher was lower with osimertinib (23%) than with platinum therapy plus pemetrexed (47%).ConclusionsOsimertinib had significantly greater efficacy than platinum therapy plus pemetrexed in patients with T790M-positive advanced non-small-cell lung cancer (including those with CNS metastases) in whom disease had progressed during first-line EGFR-TKI therapy. (Funded by AstraZeneca; AURA3 ClinicalTrials.gov number, NCT02151981 .).

Project description:BackgroundClinical detection of EGFR-TKI resistance mechanism through tissue can be really challenging due to risks associated with the procedure. Thus, liquid biopsy, especially circulation tumor DNA (ctDNA) analysis, can be an adequate source for biomarker testing in targeted therapy. Our study was aimed at clinical validation of liquid biopsy next-generation sequencing (NGS) by comparison with tissue biopsy, and we also investigated clinical utility of ctDNA NGS on the prediction of TKI outcomes.MethodsUsing hybrid capture panel NGS, we compared the concordance, sensitivity, and specificity of ctDNA using 39 paired plasma and tissue biopsy, and investigated the association between ctDNA genomic alterations of 147 first-generation TKI-relapsed patients and their response to first- and third-generation TKIs.ResultsThe concordance for ctDNA and tissue biopsy was 84.62% among all patients, and even higher among late stage patients (88.24%). Among 147 EGFR-TKI-relapsed patients, T790M was the most common reason for resistance (40.13%). Compared with T790M-positive patients, patients only detected with sensitizing mutations (sensi-mutations) had lower mutant allele frequency (MAF) of sensi-mutations (P = 0.031). TP53 mutation showed negative impact on TKI treatments. In survival analysis of third-generation TKI, we found a positive correlation between ratio of T790M sensi-mutation and PFS (P = 0.018); also, higher MAFs of both sensi-mutation and T790M were observed in the PR group than the SD + PD group.ConclusionsBoth ratio of T790M sensi-mutations and MAFs of EGFR mutations were associated with third-generation TKI outcomes. Thus, incorporation of high-throughput NGS into clinical trials may be crucial to identifying the response to osimertinib, as it provides more comprehensive genomic information.Key pointsHigh concordance of ctDNA and tissue biopsy was observed. NGS of ctDNA from 147 TKI-relapsed patients showed that both high ratio of T790M sensitizing mutation (sensi-mutation) and high MAFs of mutations were all associated with better third generation TKI treatment outcomes. The quantification of both MAFs and T790M sensi-mutation ratio should be taken into consideration in some clinical situations, and incorporation of high-throughput NGS into clinical trials may be crucial to identifying the response to osimertinib, as it provides more comprehensive genomic information.