Predicting the prognosis of patients with lung adenocarcinoma treated with third-generation EGFR-TKI alone using nomograms based on CT radiomic and clinicopathological factors

Introduction

Lung cancer (LC) stands as the primary reason for cancer mortality worldwide, with advanced lung adenocarcinoma (LUAD) emerging as the prevailing histological subtype (1). The epidermal growth factor receptor (EGFR) signaling pathway is activated in some non-small cell lung cancer (NSCLC) cases and acts as a pivotal player in tumor cell progression and invasion (2). Clinical trials, such as the Iressa Pan-Asia Study (IPASS), have amply demonstrated that first-line use of generation I EGFR-tyrosine kinase inhibitors (EGFR-TKIs) among patients suffering through EGFR-sensitive mutations prominently postpones the progression-free survival (PFS) relative to conventional chemotherapy (3). It was discovered that the third-generation EGFR-TKI, osimertinib, significantly prolonged median PFS by 8.7 months (18.9 vs. 10.2 months) relative to the standard treatment arm of the first generation, and far exceeding results reported for the previous two generations (4). However, although the therapeutic effect of the third-generation EGFR-TKIs surpasses that of generation I and II EGFR-TKIs, the fact that not all patients will receive satisfactory clinical benefit from this class of drugs should not be overlooked. Therefore, the ability to accurately predict the effect of third-generation EGFR-TKI targeted therapies has become an important issue in current NSCLC treatment research.

Multiple investigations have examined the prognostic factors of third-generation EGFR-TKIs. As observed by Sheng et al., patients showing exon 19 deletions exhibited a more favorable prognosis following EGFR-TKI therapy relative to those showing exon 21 L858R mutations (5). As found by Phan et al., systemic inflammatory markers can also be applied to assess treatment efficacy among patients. However, we are unaware of studies examining the predictive factors with third-generation EGFR-TKI alone (6). Therefore, there exists a demand for a predictive model in view of clinicopathological factors, such as EGFR mutations, which can significantly recognize patients at higher risk of relapse, and enable earlier decision-making regarding combination therapies to decrease the hazard of relapse and ameliorate survival.

Radiomics serves as one quantitative analysis tool, changing medical images into extractable data via high-throughput mining of quantitative characteristics. This method shows a prospect for carcinoma diagnosis, predicting lymph node metastasis, and assessing prognosis (7-9). Previous research has utilized radiomics to forecast the prognosis of EGFR mutations following first- and second-line EGFR-TKI treatment (10-13). However, there remains a shortage of studies using radiomics to focus on the prognosis associated with receiving a third-generation EGFR-TKI as first-line therapy.

Therefore, this research comprehensively analyzed radiomic characteristics and clinicopathological factors to recognize the prediction factors influencing patients’ prognosis, and identify patients showing a high risk of relapse. This information could be used to instruct clinical therapy and ameliorate prognosis. We present this article in accordance with the TRIPOD reporting checklist (available at https://tlcr.amegroups.com/article/view/10.21037/tlcr-2025-763/rc).

Methods

Patient selection

Data were obtained for patients with LUAD who initiated first-line third-generation EGFR-TKI monotherapy between January 1, 2018 and December 31, 2022 at the Affiliated Cancer Hospital of Shandong First Medical University in Shandong, China. Inclusion criteria included: (I) patients with clinical stage IV adenocarcinoma; (II) pathologically confirmed EGFR 19del or EGFRex21 L858R mutations; (III) first-line therapy through a third-generation EGFR-TKI; and (IV) no systemic therapy other than the targeted therapy. Exclusion criteria included: (I) other treatments before targeted therapy; (II) death from non-cancer causes; (III) incomplete record of imaging data or clinicopathological data; (IV) loss to follow-up. In the 255 eligible patients, 169 were stochastically segregated to the training cohort and 76 to the validation cohort in a 7:3 proportion (Figure S1).

Our research received approvals from the Ethics Committee of Cancer Hospital Affiliated to Shandong First Medical University (No. SDTHEC202509014). The requirement for informed consent was waived due to the retrospective nature of this research. We have declared that patients’ information will be confidential. The study was conducted in accordance with the Declaration of Helsinki and its subsequent amendments.

Treatment

All patients experienced a multidisciplinary consultation to appraise the disease and select the treatment plan. The consensus from the consultations favored EGFR-TKI monotherapy as the recommended treatment. Among the enrolled patients, the EGFR-TKI drugs were all the third-generation EGFR-TKIs; the specific regimens included were: osimertinib (80 mg/dose, once/day, orally), almonertinib mesilate (110 mg/dose, once/day, orally), and furmonertinib (80 mg/dose, once/day, orally).

Study endpoints and follow-up

PFS and overall survival (OS) were the research endpoints. The duration between the initiation of EGFR-TKI therapy and the first reported recurrence, death because of carcinoma, or the final follow-up visit was designated as PFS. The duration between the initiation of EGFR-TKI therapy and the death because of carcinoma or the final follow-up visit was assigned as OS. As to the patient whose last case record in the case system was documented over 1 month prior to the cut-off time, telephone follow-up was applied to comprehensively collect their clinical information. The patient was asked about specific details on their disease development and survival. A database was established for statistical analysis. Follow-up terminated on January 15, 2024, showing a median OS of 35 months (range, 1–51 months) for enrolled patients.

Radiomics

Our study employed the newest computed tomography (CT) images before initiating the EGFR-TKI treatment. The total cancer target areas were described layer by layer by an author specializing in oncology through the medical image treatment and navigation software 3D Slicer (v 5.2.1). Then, the regions of interest were validated via a senior experienced clinician in chest CT analysis. To decrease the variation between images from discrepant patients, all data were Z-score standardized. Feature selection was carried out via a two-step process. For starters, features showing high stability and repeatability were filtered by computing the intra-class correlation coefficient (ICC) indicator, as well as by the criterion of ICC >0.9 to decrease bias or overfitting from excessive features. Features showing elevated repeatability were filtrated, deeply downscaled, and re-filtrated for pivotal characteristics by least absolute shrinkage and selection operator (LASSO) regression (14,15). At last, a radiomics score (Rad score) was figured out for each patient by weighting the LASSO-selected characteristics in accordance with their own coefficients (16).

Model construction and evaluation

In view of prior research on the prognosis of LUAD patients treated with EGFR-TKIs, we analyzed retrospective clinicopathological information such as EGFR-TKI treatment regimen, and hematology, as well as radiomics information. First, data from the training cohort were tested in a univariate Cox regression model to assess the prediction capacity of the clinicopathological and radiomics characteristics for PFS and OS. In univariate analyses, factors showing a significance level of P<0.05 were subsequently evaluated in multivariate analyses. After that, a nomogram was formulated via factors showing remarkable prediction value in multivariate Cox regression analyses. Ultimately, receiver operating characteristic (ROC) curves, calibration curves, and decision curve analysis (DCA) were utilized in both cohorts, respectively, to appraise the predictive ability of the nomogram for PFS and OS. Survival analyses on PFS and OS in both risk groups were executed in both cohorts to evaluate the prognosis of patients enduring discrepant hazards.

Statistical analyses

The independent samples t-test or rank sum test compared continuous variables, whereas the Chi-squared test or Fisher’s exact test assessed categorical variables. Through Cox proportional risk models, univariate and multivariate analyses identified independent prognostic variables for PFS and OS. Patient PFS and OS were evaluated through the Kaplan-Meier method, with a subsequent log-rank test for contrast. Significance was considered as P<0.05. All tests were implemented in a two-sided manner. R software (v 4.3.2) was applied to data analytics and graphing.

Results

Patient characteristics

In all, 255 patients were enrolled, including 86 (33.7%) males and 169 (66.3%) females. Approximately one-third (101; 39.6%) of the patients were <60 years old and 154 (60.4%) were ≥60 years old. The EGFR 19del mutation was found in 155 (60.8%) patients, while the remaining 100 (39.2%) carried the EGFRex21 L858R mutation. Deaths were reported for 63 (35.2%) among 179 patients in the training cohort, and for 31 (40.8%) among 76 patients in the validation cohort. As of the study cut-off date, disease progression had occurred in 93 (51.9%) and 45 (59.2%) patients in both cohorts, respectively (Table 1).

Analysis of prognosis in the training cohort

The univariate analysis on patients’ clinicopathological factors manifested that age (P=0.046), EGFR mutation type (P<0.001), brain metastasis (P<0.001), neutrophil-lymphocyte ratio (NLR) (P=0.009), and monocyte-lymphocyte ratio (MLR) (P=0.02) remarkably related to patients’ PFS (Table 2). Age (P=0.01), Karnofsky performance status (P=0.03), EGFR mutation type (P<0.001), brain metastasis (P<0.001), and MLR (P=0.003) were significantly related to patients’ OS (Table 3). After filtering with ICC indicator and LASSO regression, the 10 radiomics characteristics most pivotal to forecast PFS were chosen, with mean computed Rad scores of 0.83±1.59 and 1.80±1.43 (P<0.001) among patients with progression or not, respectively. The 12 radiomics characteristics most pivotal to forecast OS resulted in mean Rad scores of 0.41±1.41 and 1.78±1.48 (P<0.001) in deceased and surviving patients, respectively (Figure S2).

Clinicopathological factors and imaging characteristics as essential predictors in univariate analyses were contained in multivariable Cox hazard regression analyses. Four factors remained as independent prognosis factors for PFS: EGFRex21 L858R mutation [hazard ratio (HR): 2.01, 95% confidence interval (CI): 1.25–3.24, P=0.004], brain metastasis (HR: 2.66, 95% CI: 1.57–4.50, P<0.001), NLR ≥4.6 (HR: 1.68, 95% CI: 1.02–2.75, P=0.04), and Rad score (HR: 0.75, 95% CI: 0.65–0.87, P<0.001) (Table 2). Five independent prognostic factors were found for OS: age <60 years (HR: 0.58, 95% CI: 0.33–1.03, P=0.04), EGFRex21 L858R mutation (HR: 2.11, 95% CI: 1.15–3.85, P=0.01), brain metastasis (HR: 2.12, 95% CI: 1.11–4.06, P=0.02), MLR <0.3 (HR: 0.40, 95% CI: 0.36–1.02, P=0.047), and Rad score (HR: 0.60, 95% CI: 0.49–0.72, P<0.001) (Table 3).

Establishment and evaluation of the predictive nomogram

In light of the multivariable Cox regression analysis, the predictive model was regarded as a nomogram (Figure 1). The model’s ROC was used to appraise the model’s predictive effect (Figure 1). In the training cohort, the area under the curve (AUC) of the nomogram forecasting 6-, 12- and 24-month PFS was 0.810 (95% CI: 0.711–0.909), 0.862 (95% CI: 0.801–0.923), and 0.873 (95% CI: 0.806–0.940), respectively (Table S1). The AUCs predicting 1-, 2- and 3-year OS reached 0.886 (95% CI: 0.818–0.954), 0.881 (95% CI: 0.809–0.953), and 0.839 (95% CI: 0.712–0.966); all of them exceeded the AUC for single risk factors (Tables S1,S2). In the validation cohort, the AUCs of the nomogram forecasting 6-, 12- and 24-month PFS reached 0.885 (95% CI: 0.751–0.982), 0.858 (95% CI: 0.735–0.975), and 0.847 (95% CI: 0.734–0.962), and those forecasting 1-, 2- and 3-year OS reached 0.804 (95% CI: 0.575–0.936), 0.824 (95% CI: 0.719–0.929), and 0.806 (95% CI: 0.633–0.979). Again, all AUC values exceeded those for single risk factors. For these two cohorts, the calibration curves of both predictive models exhibited exceptional consistency between the predicted PFS and OS and the actual observations (Figures S3,S4). DCA showed a gratifying net benefit for both models in most threshold probabilities, illustrating a favorable clinical outcome from use of the model (Figures S5,S6).

Figure 1 Nomograms and ROC curves for predicted PFS and OS in the training and validation cohorts. Nomograms for predicting PFS (A) and OS (B). ROC curves for predicted PFS (C) and OS (D) in the training cohort and predicted PFS (E) and OS (F) in the validation cohort. AUC, area under the curve; EGFR, epidermal growth factor receptor; MLR, monocyte-lymphocyte ratio; NLR, neutrophil-lymphocyte ratio; OS, overall survival; PFS, progression-free survival; Rad score, radiomics score; ROC, receiver operating characteristic.

Prediction stratification model

Using the individual total scores computed through the nomograms forecasting PFS and OS, the patient population was divided into low-risk (n=200, total points ≤127.6; n=222, total points ≤126.4) and elevated-risk (n=55, total points >127.6; n=33, total point >126.4) groups. Subsequent Kaplan-Meier survival analysis on both risk groups exhibited exceptional differentiation, showing remarkable differences in 6-, 12-, and 24-month PFS (P<0.001), as well as in 1-, 2-, and 3-year OS (P<0.001) (Figure 2).

Figure 2 Kaplan-Meier survival analysis of PFS and OS for different risk subgroups in the total population. Kaplan-Meier survival analysis of PFS (A) for different risk subgroups in the total population. Kaplan-Meier survival analysis of OS (B) for different risk subgroups in the total population. CI, confidence interval; HR, hazard ratio; OS, overall survival; PFS, progression-free survival.

Discussion

EGFR-TKIs are one of the best options for patients suffering from advanced NSCLC harboring EGFR 19del or EGFRex21 L858R mutations (17). However, as with generation I and II EGFR-TKIs, patients will inevitably have resistance to third-generation treatments. Patients’ prognoses also vary widely (18). Therefore, our research developed and confirmed a clinical prediction model for patients with advanced LUAD, predicting patient-level PFS and OS based on CT images and clinicopathological factors measured prior to first-line EGFR-TKI monotherapy. Our model provided an effective prediction of patients with poor prognosis; information that can be used to formulate timely and individualized diagnosis and treatment strategies.

In our patient population, NLR ≥4.6, EGFRex21 L858R mutation, brain metastasis, and Rad score worked as independent risk factors for PFS. Patient age ≥60 years, EGFRex21 L858R mutation, brain metastasis, MLR ≥0.3, and Rad score served as independent risk factors predicting OS. The AUC of the nomogram in the training and validation cohorts highly exceeded the AUC of each factor alone, implying a nomogram’s elevated predictive value; Kaplan-Meier survival analysis also exhibited good differentiation.

Multiple research has investigated CT radiomics as a tool for predicting therapeutic efficacy and prognosis (9,19,20). Ravanelli et al. found that CT texture analysis served as one prognostic indicator among patients enduring metastatic LUAD and undergoing treatment with erlotinib or gefitinib, supporting our findings for the first-line with third-generation EGFR-TKI (21). Tang et al. also reported that radiomics characteristics obtained from contrast-enhanced chest CT scans could be applied to appraise the prognosis of patients suffering from advanced NSCLC treated with second-line osimertinib (22). This differs from our study, which focused on patients suffering from terminal NSCLC treated with the third-generation EGFR-TKI monotherapy in the first line.

As one of the most pervasive positions of metastasis in NSCLC, brain metastasis takes place in roughly 30–50% of NSCLC patients (23). Although third-generation EGFR-TKIs are believed to exert improved efficacy in treating brain metastases due to their purported ability to more effectively penetrate the blood-brain barrier, compared with the first- and second-generation EGFR-TKIs (24,25), heterogeneity in treatment response remains. In our study, as well as that by Tang et al., brain metastasis acted as an independent risk factor for PFS and OS (22).

Different types of EGFR mutations might differ in clinical and pathologic relationships and responses to EGFR-TKI (5,26). Prior research on patients receiving EGFR-TKI monotherapy have shown longer PFS among patients showing exon 19 deletions relative to patients showing the 21 L858R mutation (27-30). This is similar to our findings that the EGFRex21 L858R mutation is an independent risk factor for PFS and OS. Such a difference in survival between two groups may imply a discrepant prognosis, on account of the composition of the mutation itself, triggering a more invasive biological reaction (31).

Many studies have shown that systemic inflammatory markers help monitor the response and prognosis of NSCLC patients to chemotherapy, radiotherapy, or surgery (32-39). Indeed, NLR ≥4.6 became an independent risk factor for PFS, while MLR ≥0.3 acted as an independent risk factor for OS. Consistent with the discoveries of Chan and colleagues, patients with NLR >4.08 had a higher risk of recurrence (40). Bar-Ad et al. similarly found elevated NLR to be an underlying biomarker among patients showing weak lung cancer prognosis (41). Elevated NLR indicates a relative decrease in lymphocytes, and thus may reflect a weaker lymphocyte-mediated immune reaction to malignancy due to a decreased T-4 helper/T-8 suppressor proportion (42). Previous studies have manifested that a reduction in MLR prominently relates to a favorable effect of immunotherapy (43). However, we are unaware of studies assessing the predictive effect of MLR for third-generation EGFR-TKI monotherapy to treat patients enduring advanced NSCLC. Monocytes facilitate tumor development, are recruited to primary or metastatic tumors, and differentiate into tumor-related macrophages (44). These observations support our finding that a reduction in MLR is related to a better prognosis among our patients. However, in-depth prospective research should assess the significance of MLR in patient prognosis.

In our study, risk scores were calculated for each patient by a nomogram showing that if the risk was higher, namely, the score was higher, the progression probability would be greater and therefore the patient’s prognosis would be worse. Therefore, for patients identified as high-risk by the predictive models from this or other studies, we recommend combining additional treatments with EGFR-TKI to improve prognosis. The efficacy of this approach was demonstrated by FLAURA2 phase 3 trial. Results of that trial unveiled that the first-line osimertinib plus chemotherapy through pemetrexed and platinum agents related to a remarkably enhanced PFS relative to osimertinib monotherapy (HR: 0.62, 95% CI: 0.49–0.79; P<0.001) (45). As to low-risk patients, though we propose no recommendation for combining other treatments, they should be reviewed regularly, and changes in patients’ risk factors should be closely monitored.

There exist some restrictions in this research. Firstly, on account of the nature of our retrospective analysis, it is challenging to elude selection bias. Secondly, our study belongs to a single research center. Internal validation suggests that the present predictive model possesses a higher AUC in terms of PFS and OS. Findings will be more forceful with external validation. Moreover, this study does not account for intrinsic resistance arising from co-altered molecular mechanisms. Lastly, the sample size of our research is comparatively small. Thus, follow-up research should contain data from more research centers and larger sample sizes.

Conclusions

While first-line third-generation EGFR-TKI therapy for patients suffering from NSCLC is significantly more effective than previous treatments, there are still patients who do not respond well. This study found that NLR ≥4.6, EGFRex21 L858R mutation, brain metastasis, radiomics, age ≥60 years, and MLR ≥0.3 are independent predictive factors for patient prognosis. Our study formulated and corroborated a prediction nomogram according to clinicopathological factors and radiomics characteristics, a strong tool for forecasting the prognosis of patients enduring terminal LUAD receiving third-generation EGFR-TKI monotherapy.

Acknowledgments

We are grateful to each patient for allowing us to utilize their clinicopathological data.

Footnote

Reporting Checklist: The authors have achieved the TRIPOD reporting checklist. Available at https://tlcr.amegroups.com/article/view/10.21037/tlcr-2025-763/rc

Data Sharing Statement: Available at https://tlcr.amegroups.com/article/view/10.21037/tlcr-2025-763/dss

Peer Review File: Available at https://tlcr.amegroups.com/article/view/10.21037/tlcr-2025-763/prf

Funding: The work received support from the 2024 Shandong Medical Association Scientific Research Project (No. YXH2024QS053).

Conflicts of Interest: All authors have completed the ICMJE uniform disclosure form (available at https://tlcr.amegroups.com/article/view/10.21037/tlcr-2025-763/coif). The authors have no conflicts of interest to declare.

Ethical Statement: The authors are accountable for all aspects of the work in ensuring that questions related to the accuracy or integrity of any part of the work are appropriately investigated and resolved. This study was conducted in accordance with the Declaration of Helsinki and its subsequent amendments. The study was approved by the Ethics Committee of Cancer Hospital Affiliated to Shandong First Medical University (No. SDTHEC202509014). The requirement for informed consent was waived due to the retrospective nature of this research.

Open Access Statement: This is an Open Access article distributed in accordance with the Creative Commons Attribution-NonCommercial-NoDerivs 4.0 International License (CC BY-NC-ND 4.0), which permits the non-commercial replication and distribution of the article with the strict proviso that no changes or edits are made and the original work is properly cited (including links to both the formal publication through the relevant DOI and the license). See: https://creativecommons.org/licenses/by-nc-nd/4.0/.

References

1. Kuhn E, Morbini P, Cancellieri A, et al. Adenocarcinoma classification: patterns and prognosis. Pathologica 2018;110:5-11.
2. Tan AC, Tan DSW. Targeted Therapies for Lung Cancer Patients With Oncogenic Driver Molecular Alterations. J Clin Oncol 2022;40:611-25. [Crossref] [PubMed]
3. Grigoriu B, Berghmans T, Meert AP. Management of EGFR mutated nonsmall cell lung carcinoma patients. Eur Respir J 2015;45:1132-41. [Crossref] [PubMed]
4. Soria JC, Ohe Y, Vansteenkiste J, et al. Osimertinib in Untreated EGFR-Mutated Advanced Non-Small-Cell Lung Cancer. N Engl J Med 2018;378:113-25. [Crossref] [PubMed]
5. Sheng M, Wang F, Zhao Y, et al. Comparison of clinical outcomes of patients with non-small-cell lung cancer harbouring epidermal growth factor receptor exon 19 or exon 21 mutations after tyrosine kinase inhibitors treatment: a meta-analysis. Eur J Clin Pharmacol 2016;72:1-11. [Crossref] [PubMed]
6. Phan TT, Ho TT, Nguyen HT, et al. The prognostic impact of neutrophil to lymphocyte ratio in advanced non-small cell lung cancer patients treated with EGFR TKI. Int J Gen Med 2018;11:423-30. [Crossref] [PubMed]
7. Braman N, Prasanna P, Whitney J, et al. Association of Peritumoral Radiomics With Tumor Biology and Pathologic Response to Preoperative Targeted Therapy for HER2 (ERBB2)-Positive Breast Cancer. JAMA Netw Open 2019;2:e192561. [Crossref] [PubMed]
8. Coroller TP, Agrawal V, Huynh E, et al. Radiomic-Based Pathological Response Prediction from Primary Tumors and Lymph Nodes in NSCLC. J Thorac Oncol 2017;12:467-76. [Crossref] [PubMed]
9. Wang X, Zhao X, Li Q, et al. Can peritumoral radiomics increase the efficiency of the prediction for lymph node metastasis in clinical stage T1 lung adenocarcinoma on CT? Eur Radiol 2019;29:6049-58. [Crossref] [PubMed]
10. Jia TY, Xiong JF, Li XY, et al. Identifying EGFR mutations in lung adenocarcinoma by noninvasive imaging using radiomics features and random forest modeling. Eur Radiol 2019;29:4742-50. [Crossref] [PubMed]
11. Song J, Shi J, Dong D, et al. A New Approach to Predict Progression-free Survival in Stage IV EGFR-mutant NSCLC Patients with EGFR-TKI Therapy. Clin Cancer Res 2018;24:3583-92. [Crossref] [PubMed]
12. Yang X, Dong X, Wang J, et al. Computed Tomography-Based Radiomics Signature: A Potential Indicator of Epidermal Growth Factor Receptor Mutation in Pulmonary Adenocarcinoma Appearing as a Subsolid Nodule. Oncologist 2019;24:e1156-64. [Crossref] [PubMed]
13. Li H, Zhang R, Wang S, et al. CT-Based Radiomic Signature as a Prognostic Factor in Stage IV ALK-Positive Non-small-cell Lung Cancer Treated With TKI Crizotinib: A Proof-of-Concept Study. Front Oncol 2020;10:57. [Crossref] [PubMed]
14. Zhao W, Wu Y, Xu Y, et al. The Potential of Radiomics Nomogram in Non-invasively Prediction of Epidermal Growth Factor Receptor Mutation Status and Subtypes in Lung Adenocarcinoma. Front Oncol 2019;9:1485. [Crossref] [PubMed]
15. Zhao W, Xu Y, Yang Z, et al. Development and validation of a radiomics nomogram for identifying invasiveness of pulmonary adenocarcinomas appearing as subcentimeter ground-glass opacity nodules. Eur J Radiol 2019;112:161-8. [Crossref] [PubMed]
16. Liu Z, Zhang XY, Shi YJ, et al. Radiomics Analysis for Evaluation of Pathological Complete Response to Neoadjuvant Chemoradiotherapy in Locally Advanced Rectal Cancer. Clin Cancer Res 2017;23:7253-62. [Crossref] [PubMed]
17. Yang JC, Mok T, Han B, et al. A Review of Regimens Combining Pemetrexed With an Epidermal Growth Factor Receptor Tyrosine Kinase Inhibitor in the Treatment of Advanced Nonsquamous Non-Small-Cell Lung Cancer. Clin Lung Cancer 2018;19:27-34. [Crossref] [PubMed]
18. Fu K, Xie F, Wang F, et al. Therapeutic strategies for EGFR-mutated non-small cell lung cancer patients with osimertinib resistance. J Hematol Oncol 2022;15:173. [Crossref] [PubMed]
19. Perez-Johnston R, Araujo-Filho JA, Connolly JG, et al. CT-based Radiogenomic Analysis of Clinical Stage I Lung Adenocarcinoma with Histopathologic Features and Oncologic Outcomes. Radiology 2022;303:664-72. [Crossref] [PubMed]
20. Nam JG, Park S, Park CM, et al. Histopathologic Basis for a Chest CT Deep Learning Survival Prediction Model in Patients with Lung Adenocarcinoma. Radiology 2022;305:441-51. [Crossref] [PubMed]
21. Ravanelli M, Agazzi GM, Ganeshan B, et al. CT texture analysis as predictive factor in metastatic lung adenocarcinoma treated with tyrosine kinase inhibitors (TKIs). Eur J Radiol 2018;109:130-5. [Crossref] [PubMed]
22. Tang X, Li Y, Yan WF, et al. 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. Front Oncol 2021;11:719919. [Crossref] [PubMed]
23. Lombardi G, Di Stefano AL, Farina P, et al. Systemic treatments for brain metastases from breast cancer, non-small cell lung cancer, melanoma and renal cell carcinoma: an overview of the literature. Cancer Treat Rev 2014;40:951-9. [Crossref] [PubMed]
24. Leonetti A, Facchinetti F, Tiseo M. Upfront osimertinib in EGFR-mutated non-small cell lung cancer: is brain still a sanctuary? Ann Transl Med 2018;6:S110. [Crossref] [PubMed]
25. Reungwetwattana T, Nakagawa K, Cho BC, et al. CNS Response to Osimertinib Versus Standard Epidermal Growth Factor Receptor Tyrosine Kinase Inhibitors in Patients With Untreated EGFR-Mutated Advanced Non-Small-Cell Lung Cancer. J Clin Oncol 2018; Epub ahead of print. [Crossref]
26. Ichihara S, Toyooka S, Fujiwara Y, et al. The impact of epidermal growth factor receptor gene status on gefitinib-treated Japanese patients with non-small-cell lung cancer. Int J Cancer 2007;120:1239-47. [Crossref] [PubMed]
27. Goto K, Nishio M, Yamamoto N, et al. A prospective, phase II, open-label study (JO22903) of first-line erlotinib in Japanese patients with epidermal growth factor receptor (EGFR) mutation-positive advanced non-small-cell lung cancer (NSCLC). Lung Cancer 2013;82:109-14. [Crossref] [PubMed]
28. Jackman DM, Yeap BY, Sequist LV, et al. Exon 19 deletion mutations of epidermal growth factor receptor are associated with prolonged survival in non-small cell lung cancer patients treated with gefitinib or erlotinib. Clin Cancer Res 2006;12:3908-14. [Crossref] [PubMed]
29. Sequist LV, Yang JC, Yamamoto N, et al. Phase III study of afatinib or cisplatin plus pemetrexed in patients with metastatic lung adenocarcinoma with EGFR mutations. J Clin Oncol 2013;31:3327-34. [Crossref] [PubMed]
30. Wu YL, Zhou C, Hu CP, et al. Afatinib versus cisplatin plus gemcitabine for first-line treatment of Asian patients with advanced non-small-cell lung cancer harbouring EGFR mutations (LUX-Lung 6): an open-label, randomised phase 3 trial. Lancet Oncol 2014;15:213-22. [Crossref] [PubMed]
31. Shigematsu H, Gazdar AF. Somatic mutations of epidermal growth factor receptor signaling pathway in lung cancers. Int J Cancer 2006;118:257-62. [Crossref] [PubMed]
32. Kemal Y, Yucel I, Ekiz K, et al. Elevated serum neutrophil to lymphocyte and platelet to lymphocyte ratios could be useful in lung cancer diagnosis. Asian Pac J Cancer Prev 2014;15:2651-4. [Crossref] [PubMed]
33. Botta C, Barbieri V, Ciliberto D, et al. Systemic inflammatory status at baseline predicts bevacizumab benefit in advanced non-small cell lung cancer patients. Cancer Biol Ther 2013;14:469-75. [Crossref] [PubMed]
34. Kos FT, Hocazade C, Kos M, et al. Assessment of Prognostic Value of "Neutrophil to Lymphocyte Ratio" and "Prognostic Nutritional Index" as a Sytemic Inflammatory Marker in Non-small Cell Lung Cancer. Asian Pac J Cancer Prev 2015;16:3997-4002. [Crossref] [PubMed]
35. Wu G, Yao Y, Bai C, et al. Combination of platelet to lymphocyte ratio and neutrophil to lymphocyte ratio is a useful prognostic factor in advanced non-small cell lung cancer patients. Thorac Cancer 2015;6:275-87. [Crossref] [PubMed]
36. Yao Y, Yuan D, Liu H, et al. Pretreatment neutrophil to lymphocyte ratio is associated with response to therapy and prognosis of advanced non-small cell lung cancer patients treated with first-line platinum-based chemotherapy. Cancer Immunol Immunother 2013;62:471-9. [Crossref] [PubMed]
37. Lee Y, Kim SH, Han JY, et al. Early neutrophil-to-lymphocyte ratio reduction as a surrogate marker of prognosis in never smokers with advanced lung adenocarcinoma receiving gefitinib or standard chemotherapy as first-line therapy. J Cancer Res Clin Oncol 2012;138:2009-16. [Crossref] [PubMed]
38. Zhang H, Zhang L, Zhu K, et al. Prognostic Significance of Combination of Preoperative Platelet Count and Neutrophil-Lymphocyte Ratio (COP-NLR) in Patients with Non-Small Cell Lung Cancer: Based on a Large Cohort Study. PLoS One 2015;10:e0126496. [Crossref] [PubMed]
39. Lin GN, Peng JW, Xiao JJ, et al. Prognostic impact of circulating monocytes and lymphocyte-to-monocyte ratio on previously untreated metastatic non-small cell lung cancer patients receiving platinum-based doublet. Med Oncol 2014;31:70. [Crossref] [PubMed]
40. Chan A, Bentzen S, Rout A, et al. Predicting if Lung Cancer Will Relapse-The Role of Neutrophil/Lymphocyte Ratio. Hematol Oncol Stem Cell Ther 2023;16:158-61. [Crossref] [PubMed]
41. Bar-Ad V, Palmer J, Li L, et al. Neutrophil to lymphocyte ratio associated with prognosis of lung cancer. Clin Transl Oncol 2017;19:711-7. [Crossref] [PubMed]
42. Hung HY, Chen JS, Yeh CY, et al. Effect of preoperative neutrophil-lymphocyte ratio on the surgical outcomes of stage II colon cancer patients who do not receive adjuvant chemotherapy. Int J Colorectal Dis 2011;26:1059-65.
43. Zheng L, Xiong A, Wang S, et al. Decreased monocyte-to-lymphocyte ratio was associated with satisfied outcomes of first-line PD-1 inhibitors plus chemotherapy in stage IIIB-IV non-small cell lung cancer. Front Immunol 2023;14:1094378. [Crossref] [PubMed]
44. Cassetta L, Fragkogianni S, Sims AH, et al. Human Tumor-Associated Macrophage and Monocyte Transcriptional Landscapes Reveal Cancer-Specific Reprogramming, Biomarkers, and Therapeutic Targets. Cancer Cell 2019;35:588-602.e10. [Crossref] [PubMed]
45. Planchard D, Jänne PA, Cheng Y, et al. Osimertinib with or without Chemotherapy in EGFR-Mutated Advanced NSCLC. N Engl J Med 2023;389:1935-48. [Crossref] [PubMed]