Search

ObjectiveThis study aimed to explore the relationship between smoking status and the interval to brain metastasis in patients with non-small cell lung cancer (NSCLC) and its impact on survival time after brain metastasis.MethodsData were collected from patients with NSCLC with brain metastases who were treated at our centre between January 2005 and December 2017. Clinical indices such as clinicopathological features and smoking status were recorded, and patients were followed up until 1 September 2022. Based on our inclusion and exclusion criteria, 461 patients were analysed and matched using 1:1 propensity score matching. Three balanced groups were formed: non-smoking (n = 113), smoking cessation (n = 113), and smoking (n = 113). The interval to brain metastasis and overall survival were compared between the groups.ResultsThere was a statistically significant difference in the interval to brain metastasis between the non-smoking and smoking cessation groups (p = 0.001), as well as between the non-smoking and smoking groups (p < 0.001). However, the difference between the smoking cessation and smoking groups was not statistically significant (p = 0.106). Multivariate and univariate analyses identified smoking status, clinical stage, lung cancer surgery, chemotherapy, and chest radiotherapy as independent predictors of the interval to brain metastasis. Additionally, the multivariate analysis showed that smoking status, driver gene mutations, and chest radiotherapy independently influenced survival after brain metastasis.ConclusionSmoking status in patients with NSCLC affects the interval to brain metastasis and survival after brain metastasis.

BackgroundDefinitive concurrent chemoradiotherapy (CCRT) followed by maintenance therapy with immune checkpoint inhibitors offers the best chance of cure for patients with stage III non-small cell lung cancer (NSCLC). A significant challenge in this regimen is the occurrence of acute severe lymphopenia (ASL), which can compromise treatment efficacy. Currently, there are no effective strategies for preventing and treating ASL. Shenglin decoction (SLD), a traditional Chinese herbal medicine formulation, has demonstrated preliminary efficacy in mitigating ASL. However, robust evidence from clinical trials and a clear understanding of its mechanism of action are still needed. This study aims to comprehensively assess the efficacy, safety, and underlying mechanisms of SLD in the prevention of ASL.MethodsThis prospective, dual-center, open-label, randomized controlled trial will enroll 140 stage III NSCLC patients. Participants will be randomly allocated in a 1:1 ratio to a control group or an experimental group. Both groups will undergo definitive CCRT. Alongside the commencement of CCRT, the experimental group will receive an additional oral SLD intervention for a duration of three months. The primary outcome is the incidence rate of ASL, defined as the proportion of patients who experience at least one instance of a total lymphocyte count falling below 0.5 × 10^9 cells/L within 3 months of initiating CCRT treatment. Additionally, 16S rRNA gene sequencing analysis of fecal samples to assess gut microbiota, as well as metabolomic analysis of fecal/blood samples, will be conducted to explore potential mechanisms.DiscussionThis study protocol aims to rigorously evaluate the efficacy and safety of SLD, as well as elucidate its mechanism of action in preventing ASL. Successful outcomes could establish SLD as an evidence-based intervention for ASL prevention in NSCLC patients undergoing CCRT.Trial RegistrationThe trial was registered at the Chinese Clinical Trials Registry (ChiCTR2300071788, https://www.chictr.org.cn/).

ObjectiveMajor pathological response (MPR) helps evaluate the prognosis of patients with lung squamous cell carcinoma (LUSC). However, the clinical factors that affect the achievement of MPR after neoadjuvant chemoimmunotherapy (NCIO) in patients with LUSC remain unclear. This study aimed to explore the clinical factors affecting the MPR after NCIO in patients with potentially resectable LUSC.MethodsThis retrospective study included patients with stage IIB-IIIC LUSC who underwent surgical resection after receiving NCIO at a center between March 2020 and November 2022. In addition to the postoperative pathological remission rate, sex, age, body mass index (BMI), smoking history, TNM stage, hematological and imaging test results, and other indicators were examined before NCIO. According to the pathological response rate of the surgically removed tumor tissue, the patients were split into MPR and non-MPR groups.ResultsIn total, 91 LUSC patients who met the study’s eligibility criteria were enrolled: 32 (35%) patients in the non-MPR group and 59 (65%) in the MPR group, which included 43 cases of pathological complete remission (pCR). Pre-treatment lymphocyte level (LY) (odds ratio [OR] =5.997), tumor burden (OR=0.958), N classification (OR=15.915), radiographic response (OR=11.590), pulmonary atelectasis (OR=5.413), and PD-L1 expression (OR=1.028) were independently associated with MPR (all P < 0.05). Based on these six independent predictors, we developed a nomogram model of prediction having an area under the curve (AUC) of 0.914 that is simple to apply clinically to predict the MPR. The MPR group showed greater disease-free survival (DFS) than the non-MPR group, according to the survival analysis (P < 0.001).ConclusionThe MPR rate of NCIO for potentially resectable LUSC was 65%. LY, tumor burden, N classification, radiographic response, pulmonary atelectasis, and PD-L1 expression in patients with LUSC before NCIO were the independent and ideal predictors of MPR. The developed nomogram demonstrated a good degree of accuracy and resilience in predicting the MPR following NCIO, indicating that it is a useful tool for assuring customized therapy for patients with possibly resectable LUSC.

BackgroundThe treatment of local–regional recurrent breast cancer (BC) after external beam radiotherapy is challenging. We aim to evaluate the effectiveness and safety of computed tomography (CT)–guided percutaneous iodine-125 brachytherapy for local recurrent BC.MethodsWe retrospectively analyzed 15 patients with local recurrent BC treated with CT-guided interstitial implantation of iodine-125 seeds. Regular contrast-enhanced CT was conducted to evaluate the tumor response. Follow-up survival, quality of life, and adverse events were analyzed.ResultsAmong the 15 patients, five were elderly patients (older than 80 years) and six were complicated with chronic underlying diseases. The median number of 125I seeds implantation was 33 (range: 20–130) with median dose 90 (D90, the minimum dose covering 90% of the target volume) of 108 Gy (range: 60–120 Gy). There was no significant difference in D90, V100 (the volume of the target receiving 100% of the prescription dose), and V150 (the volume of the target receiving 150% of the prescription dose) before and after operation (p > 0.05). The median follow-up was 14 months (range: 6–18 months). Six months after operation, the ORR was 66.7% (10/15) and the LCR was 93.3% (14/15). The 6- and 12-month survival rates were 100 and 41.6%, respectively, and the median survival time was 12.5 months. PS score decreased from 1.53 ± 0.81 to 0.53 ± 0.49. The pain score decreased from 2.87 ± 1.67 before operation to 1.07 ± 1.18 after operation, and the differences were statistically significant (p< 0.05). No severe complications occurred.ConclusionsCT-guided iodine-125 brachytherapy provided a safe and effective choice for recurrent BC with significant local therapeutic effects and minor complications, especially for elderly patients with chronic underlying disease and those who were not eligible for surgical resection and had failed to benefit from systemic therapy.

Squamous cell lung carcinoma (LUSC) originates from squamous cells and has a high rate of metastasis and recurrence. The lack of effective genetic targets and specific therapies has resulted in a poor prognosis for patients with LUSC. Gastrointestinal metastasis of LUSC is a rare occurrence in clinical practice. Patients with gastrointestinal metastasis usually have worse overall survival and the process of diagnosis is more complicated than those with metastasis elsewhere. What’s more, there are no helpful guidelines for treating patients with a clinically confirmed diagnosis of gastrointestinal metastasis, which means the treatment method is limited. Here, we review the clinical features, diagnosis, and treatment of LUSC patients with gastrointestinal metastasis and report a rare case of LUSC accompanied by gastrointestinal metastasis. The patient was admitted to the hospital with coughing and hemoptysis. A tumor was found in his lung, and lesions were initially controlled with standard treatment. The patient’s tumor re-occurred again shortly for which treatment was lacking. Without effective treatment methods, the disease was difficult to control. Our learnings from the case demonstrate that LUSC metastasizes to secondary lymphoid organs of the gastrointestinal tract, usually with a poor prognosis.

BackgroundThis retrospective study compared positron emission tomography (PET)/computed tomography (CT) and CT in the treatment of extracranial oligometastatic non-small-cell lung cancer (NSCLC) and explored the impact of thorax radiotherapy (TRT) on patient survival.MethodsWe reviewed the medical records of Chinese patients with stage IV extracranial oligometastatic NSCLC who underwent PET/CT or CT at two centers. Propensity score matching (PSM) was used to control differences in patient characteristics between the maintenance chemotherapy alone and TRT plus maintenance chemotherapy groups.ResultsWe analyzed 192 eligible patients. The median survival time was better in patients who received PET/CT than in those who only received CT (n = 192, 16 months vs. 6 months, p

BackgroundGastroenteropancreatic neuroendocrine carcinomas (GEP-NECs) are a rare, highly malignant subset of gastroenteropancreatic neuroendocrine neoplasms (GEP-NENs). However, how to predict the prognosis of GEP-NECs by clinical features is still under study. This study aims to establish and validate a nomogram model of overall survival (OS) in patients with GEP-NECs for predicting their prognosis.MethodsWe selected patients diagnosed with GEP-NECs from the Surveillance, Epidemiology, and End Results (SEER) database and two Chinese hospitals. After randomization, we divided the data in the SEER database into the train cohort and the test cohort at a ratio of 7:3 and used the Chinese cohort as the validation cohort. The Cox univariate and multivariate analyses were performed to incorporate statistically significant variables into the nomogram model. We then established a nomogram and validated it by concordance index (C-index), calibration curve, receiver operating characteristic (ROC) curve, the area under the curve (AUC), and the decision curve analysis (DCA) curve.ResultsWe calculated the nomogram C-index as 0.797 with a 95% confidence interval (95% CI) of 0.783–0.815 in the train cohort, 0.816 (95% CI: 0.794–0.833) in the test cohort and 0.801 (95% CI: 0.784–0.827) in the validation cohort. Then, we plotted the calibration curves and ROC curves, and AUCs were obtained to verify the specificity and sensitivity of the model, with 1-, 3- and 5-year AUCs of 0.776, 0.768, and 0.770, respectively, in the train cohort; 0.794, 0.808, and 0.799 in the test cohort; 0.922, 0.925, and 0.947 in the validation cohort. The calibration curve and DCA curves also indicated that this nomogram model had good clinical benefits.ConclusionsWe established the OS nomogram model of GEP-NEC patients, including variables of age, race, sex, tumor site, tumor grade, and TNM stage. This model has good fitting, high sensitivity and specificity, and good clinical benefits.

AimA programmed death 1 (PD-1) inhibitor coupled with radiotherapy and antiangiogenic therapy is a potential therapeutic strategy for advanced hepatocellular carcinoma (HCC). We aimed to determine if circulating tumor cells (CTCs) positive for programmed death-ligand 1 (PD-L1) could be employed as a predictive biomarker in HCC patients receiving triple therapy.MethodsIn this study, HCC patients received a PD-1 inhibitor in combination with intensity-modulated radiotherapy (IMRT) and antiangiogenic therapy. Following IMRT, the PD-1 inhibitor was administrated once every 3 weeks, while the antiangiogenic drug was given once a day. Treatment was continued until the disease progressed. Two mL of peripheral blood was collected at baseline, 1 month, and 3 months after treatment for CTC enrichment using the CytoSorter® system with a CytoSorter™ CTC PD-L1 Kit (Watson Biotech., China).ResultA total of 47 HCC patients receiving the triple therapy were enrolled in this study. Patients with < 2 PD-L1+ CTCs at baseline had a higher objective response rate (ORR) and longer overall survival (OS) than those with ≥ 2 PD-L1+ CTCs (56.5% vs. 16.7%, p = 0.007; not reach vs. 10.8 months, p = 0.001, respectively). The count of PD-L1+ CTCs was found to be an independent predictive biomarker of OS. Furthermore, the objective response was more likely to be achieved in patients with a dynamic decrease in PD-L1+ CTC counts at 1 month after treatment.ConclusionsOur study demonstrated that PD-L1+ CTCs could be a predictive biomarker for HCC patients receiving PD-1 inhibitors in combination with IMRT and antiangiogenic therapy.

BackgroudSkin cutaneous melanoma (SKCM) is an extremely metastatic form of skin cancer. However, there are few valuable molecular biomarkers, and accurate diagnosis is still a challenge. Hypercoagulable state encourages the infiltration and development of tumor cells and is significantly associated with poor prognosis in cancer patients. However, the use of a coagulation-related gene (CRG) signature for prognosis in SKCM, on the other hand, has yet to be determined.MethodWe used data from The Cancer Genome Atlas (TCGA) and Genotype Tissue Expression (GTEx) databases to identify differentially expressed CRGs, then designed a prognostic model by using the LASSO algorithm, univariate and multivariate Cox regression analysis, and constructed a nomogram which was evaluated by calibration curves. Moreover, the Gene Expression Omnibus (GEO), GSE54467 was used as an independent validation. The correlation between risk score and clinicopathological characteristics, tumor microenvironment (TME), and immunotherapy was further analyzed.ResultsTo develop a prognostic model, seven CRGs in SKCM patients related to overall survival (OS) were selected: ANG, C1QA, CFB, DUSP6, KLKB1, MMP7, and RABIF. According to the Kaplan-Meier survival analysis, an increased OS was observed in the low-risk group than in the high-risk group (P

Malignant peritoneal mesothelioma (MPM) is a sporadic and fatal disease of the peritoneal lining. Its diagnosis has been known to be challenging, time-consuming, and money-consuming. In this paper, we report an MPM case of a 58-year-old man with severe abdominal distension. After he had received all kinds of auxiliary examination, including computed tomography scans of the chest and whole abdomen, examinations of peripheral and pleural fluid, positron emission tomography, and twice fine-needle peritoneal biopsies, his disease still could not be confirmed. Eventually, the patient was diagnosed with MPM through laparoscopic biopsy and IHC. From this case, we concluded that clinicians can gradually discover and diagnose the disease through 1) high platelet and CA125 levels and CT imaging results, 2) cytologic examinations of ascites and pleural fluid, 3) peritoneal biopsies (fine-needle biopsy, laparoscopy biopsy), and 4) histopathological examinations and immunohistochemistry findings. The diagnostic process involving this patient can be an example to demonstrate the effectiveness of various auxiliary examination methods in MPM diagnosis.

IntroductionPancreatic neuroendocrine neoplasms (PNENs) are rare pancreatic tumors originating from pancreatic neuroendocrine cells. There is no consensus on the treatment for PNENs with unresectable liver metastases. Transcatheter arterial chemoembolization (TACE) is the preferred treatment for unresectable primary liver cancer. But the efficacy of TACE and anticoagulation in PNENs with unresectable liver metastases and portal vein thrombosis has never been reported.Methods and ResultsWe present the case of a 50-year-old male patient with hepatitis C who was found to have a single liver mass during a regular physical examination in 2016. The liver mass was surgically removed. Postoperative pathology suggested a neuroendocrine tumor of the liver, and it was suggested to look for the primary tumor. The patient was followed up until 2020, and the primary pancreatic tumor was found, along with multiple liver metastases and portal vein thrombosis. After transcatheter arterial embolization, anticoagulation, and endocrine therapy, the patient’s tumor load was relieved, and the portal vein was recanalized.ConclusionThe article reports the disease course in a case of a functional pancreatic neuroendocrine tumor with liver metastasis and portal vein thrombosis and reviews previous literature. To our knowledge, we reported for the first time the efficacy of TACE and anticoagulation in PNENs with unresectable liver metastases and portal vein thrombosis.

Exploring the biological function of periostin (POSTN) in prostate cancer (PCa) bone metastasis is of importance. It was observed that the expression of POSTN was high in PCa, especially highest in PCa metastasized to bone. In this study, we found that inhibiting POSTN in PCa cells could significantly alleviate PCa bone metastasis in vivo, suggesting POSTN is a promising therapeutic target. Since, due to the secreted expression of POSTN in osteoblasts and PCa, we hypothesized the positive feedback loop between osteoblasts and PCa mediated by POSTN in PCa bone metastasis. The in vitro experiments demonstrated that osteoblast-derived POSTN promoted PCa cell proliferation and invasion and PCa cell-derived POSTN promotes proliferation of osteoblasts. Furthermore, we found that POSTN regulated PCa and osteoblast function through integrin receptors. Finally, 18F-Alfatide II was used as the molecule probe of integrin αvβ3 in PET-CT, revealing high intake in metastatic lesions. Our findings together indicate that targeting POSTN in PCa cells as well as in the osteoblastic may be an effective treatment for PCa bone metastasis.

BackgroundCX3CL1 is a chemokine that may play important roles in cancer immune regulation. Its mechanism in bladder cancer (BCa) is poorly understood. The objective of the current study was to evaluate the association between CX3CL1 and BCa and the related biological mechanisms.MethodsA total of 277 patients with BCa were enrolled in the present study. The association between CX3CL1 expression and disease outcome was evaluated. In vitro and in vivo experiments were performed using the TCCSUP cell line to investigate the function of CX3CL1 in BCa.ResultsCompared with low expression, high expression of CX3CL1 was significantly associated with poorer progression-free survival (hazard ratio [HR]=2.03, 95% confidence interval [95% CI]: 1.26-3.27, P=0.006), cancer-specific survival (HR=2.16, 95% CI: 1.59-2.93, P

BackgroundLiver dysfunction and chronic inflammation influence the prognosis of many tumors and surgical outcomes. This study was performed to determine whether the Fibrosis-4 (FIB-4) index, originally defined as a noninvasive fibrosis marker, can predict the prognosis of patients with gastric cancer undergoing radical gastric cancer surgery.MethodsWe have retrospectively analyzed 594 consecutive patients with gastric cancer who underwent gastrectomy in our database. The FIB-4 index was calculated using laboratory data and age before gastrectomy. The clinical utility of FIB-4 was evaluated by X-tile. Patients were divided into two groups (high and low FIB-4 index groups), and their overall survival (OS) was investigated. Cox regression analysis was used to identify the independent parameters associated with prognosis. Finally, we developed a prognostic prediction model by using R statistical software.ResultsA total of 556 patients, including 422 men and 134 women, were enrolled. Of these, 61 (11.0%) and 495 (89.0%) patients had low and FIB-4 indexes, respectively. In addition to the indicators of FIB-4, preoperative age, tumor site, surgical procedure, TNM stage, and postoperative complications were found to be independent predictors of prognosis (P < 0.05). Among patients, the FIB-4 index group had significantly shorter OS (log-rank P = 0.01) than the low FIB-4 index group. This association was also confirmed in the multivariate analysis (hazard ratio, 4.65; 95% confidence interval, 1.07-4.29; P = 0.031).ConclusionsPreoperative FIB-4 index can predict long-term outcomes of gastric cancer patients who had undergone gastrectomy.

PurposeThe purpose of this study was to investigate the prognostic value of pre-treatment CT radiomics and clinical factors for the overall survival (OS) of advanced (IIIB–IV) lung adenocarcinoma patients.MethodsThis study involved 165 patients with advanced lung adenocarcinoma. The Lasso–Cox regression model was used for feature selection and radiomics signature building. Then a clinical model was built based on clinical factors; a combined model in the form of nomogram was constructed with both clinical factors and the radiomics signature. Harrell’s concordance index (C-Index) and Receiver operating characteristic (ROC) curves at cut-off time points of 1-, 2-, and 3- year were used to estimate and compare the predictive ability of all three models. Finally, the discriminatory ability and calibration of the nomogram were analyzed.ResultsThirteen significant features were selected to build the radiomics signature whose C-indexes were 0.746 (95% CI, 0.699 to 0.792) in the training cohort and 0.677 (95% CI, 0.597 to 0.766) in the validation cohort. The C-indexes of combined model achieved 0.799 (95% CI, 0.757 to 0.84) in the training cohort and 0.733 (95% CI, 0.656 to 0.81) in the validation cohort, which outperformed the clinical model and radiomics signature. Moreover, the areas under the curve (AUCs) of the radiomic signature for 2-year prediction was superior to that of the clinical model. The combined model had the best AUCs for 2- and 3-year predictions.ConclusionsRadiomic signatures and clinical factors have prognostic value for OS in advanced (IIIB–IV) lung adenocarcinoma patients. The optimal model should be selected according to different cut-off time points in clinical application.

Background: Postoperative hemorrhage (POH) is a severe complication following vestibular schwannoma surgery that may require surgical treatment. The purpose of our study is to identify risk factors associated with POH and reoperation following the resection of vestibular schwannoma.Methods: We retrospectively recruited 452 vestibular schwannoma patients treated with retrosigmoid approach. The primary outcome was POH, and the secondary outcome was reoperation for POH. Clinical and radiographic data were compared by performing univariate analysis and logistic regression analysis.Results: Among the 452 patients, 37 patients (8.2%) presented with POH and14 patients (3.1%) required reoperation within a 30-day hospitalization period. The univariate analysis showed that peritumoral edema, tumor diameter >30 mm, severe postoperative hypertension, and length of hospital stay were associated with POH and reoperation for POH. Logistic regression analysis showed that peritumoral edema [odds ratio (OR) 4.042, 95% confident interval (CI) 1.830–8.926, P = 0.001] and tumor diameter >30 mm (OR 3.192, 95% CI 1.421–7.168, P = 0.005) were independent predictive factors for POH. Peritumoral edema (OR 7.071, 95% CI 2.342–21.356, P = 0.001) was an independent predictive factor for reoperation by using logistic regression analysis. Further analysis revealed that larger tumor and incomplete tumor resection were both associated with a higher incidence of peritumoral edema.Conclusion: Peritumoral edema and tumor size are independent risk factors for POH following vestibular schwannoma surgery. And larger hematoma occurs more commonly in tumors with peritumoral edema which may require reoperation. Tumor size and extent of tumor resection are associated with peritumoral edema. Close attention should be paid to high-risk patients especially for those who presented with severe postoperative hypertension.

PurposeTo establish and validate a radiomics model to estimate the malignancy of mediastinal lymph nodes (LNs) based on contrast-enhanced CT imaging.MethodIn total, 201 pathologically confirmed mediastinal LNs from 129 patients were enrolled and assigned to training and test sets. Radiomics features were extracted from the region of interest (ROI) delineated on venous-phase CT imaging of LN. Feature selection was performed with least absolute shrinkage and selection operator (LASSO) binary logistic regression. Multivariate logistic regression was performed with the backward stepwise elimination. A model was fitted to associate mediastinal LN malignancy with selected features. The performance of the model was assessed and compared to that of five other machine learning algorithms (support vector machine, naive Bayes, random forest, decision tree, K-nearest neighbor) using receiver operating characteristic (ROC) curves. Calibration curves and Hosmer-Lemeshow tests were used to assess the calibration degree. Decision curve analysis (DCA) was used to assess the clinical usefulness of the logistic regression model in both the training and test sets. Stratified analysis was performed for different scanners and slice thicknesses.ResultAmong the six machine learning methods, the logistic regression model with the eight strongest features showed a significant association with mediastinal LN status and the satisfactory diagnostic performance for distinguishing malignant LNs from benign LNs. The accuracy, sensitivity, specificity and area under the ROC curve (AUC) were 0.850/0.803, 0.821/0.806, 0.893/0.800, and 0.922/0.850 in the training/test sets, respectively. The Hosmer-Lemeshow test showed that the P value was > 0.05, indicating good calibration, and the calibration curves showed good agreement between the classifications and actual observations. DCA showed that the model would obtain more benefit when the threshold probability was between 30% and 90% in the test set. Stratified analysis showed that the performance was not affected by different scanners or slice thicknesses. There was no significant difference (DeLong test, P > 0.05) between any two subgroups, which showed the generalization of the radiomics score across different factors.ConclusionThe model we built could help assist the preoperative estimation of mediastinal LN malignancy based on contrast-enhanced CT imaging, with stability for different scanners and slice thicknesses.

We report a case of successful neoadjuvant four-drug combination therapy to avoid total pneumonectomy. A 33-year-old male patient was diagnosed with locally advanced non-squamous NSCLC harboring EGFR mutation in the left lower lobe. The patient experienced significant clinical downstaging after two cycles of neoadjuvant therapy, including icotinib, carboplatin, pemetrexed, and bevacizumab. He underwent a successful lobectomy avoiding pneumonectomy. The patient showed no recurrence in the follow-up of a chest computed tomographic scan, which is 17 months after surgery. The promising results of this neoadjuvant combination therapy provided a novel therapeutic option for patients with locally advanced EGFR-mutated NSCLC facing total pneumonectomy.

Purpose: To develop and validate a radiomic signature to identify EGFR mutations in patients with advanced lung adenocarcinoma.Methods: This study involved 201 patients with advanced lung adenocarcinoma (140 in the training cohort and 61 in the validation cohort). A total of 396 features were extracted from manual segmentation based on enhanced and non-enhance CT imaging after image preprocessing. The Lasso algorithm was used for feature selection, 6 machine learning methods were used to construct radiomics models. Receiver operating characteristic (ROC) curve analysis was applied to evaluate the performance of the radiomic signature between different data and methods. A nomogram was developed using clinical factors and the radiomics signature, then it was analyzed based on its discriminatory ability and calibration. Decision curve analysis (DCA) was implemented to evaluate the clinical utility.Results: Ten features for contrast data and eleven features for non-contrast data were selected through LASSO algorithm. The performance of the radiomics signature for contrast images was better than that for non-contrast images in all of the 6 different machine learning methods. Finally, the best radiomics signature was built with logistic regression method based on enhanced CT imaging with an area under the curve (AUC) of 0.851 (95% CI, 0.750 to 0.951) in the validation cohort. A nomogram was developed using the radiomics signature and sex with a C-index of 0.908 (95%CI, 0.862 to 0.954) in the training cohort and 0.835 (95% CI, 0.825 to 0.845) in the validation cohort. It showed good discrimination and calibration (Hosmer-Lemeshow test, P = 0.621 for the training cohort and P = 0.605 for the validation cohort).Conclusion: Radiomics signature can help to distinguish between EGFR positive and wild type advanced lung adenocarcinomas.