scholarly journals An Artificial Intelligence Model for Predicting 1-Year Survival of Bone Metastases in Non-Small-Cell Lung Cancer Patients Based on XGBoost Algorithm

2020 ◽  
Vol 2020 ◽  
pp. 1-13
Author(s):  
Zhangheng Huang ◽  
Chuan Hu ◽  
Changxing Chi ◽  
Zhe Jiang ◽  
Yuexin Tong ◽  
...  
Keyword(s):  
Artificial Intelligence ◽  
Lung Cancer ◽  
Survival Rate ◽  
Small Cell Lung Cancer ◽  
Bone Metastases ◽  
Cell Lung Cancer ◽  
Predictive Models ◽  
Small Cell ◽  
Small Cell Lung ◽  
Nsclc Patients

Non-small-cell lung cancer (NSCLC) patients often develop bone metastases (BM), and the overall survival for these patients is usually perishing. However, a model with high accuracy for predicting the survival of NSCLC with BM is still lacking. Here, we aimed to establish a model based on artificial intelligence for predicting the 1-year survival rate of NSCLC with BM by using extreme gradient boosting (XGBoost), a large-scale machine learning algorithm. We selected NSCLC patients with BM between 2010 and 2015 from the Surveillance, Epidemiology, and End Results database. In total, 5973 cases were enrolled and divided into the training (n=4183) and validation (n=1790) sets. XGBoost, random forest, support vector machine, and logistic algorithms were used to generate predictive models. Receiver operating characteristic curves were used to evaluate and compare the predictive performance of each model. The parameters including tumor size, age, race, sex, primary site, histological subtype, grade, laterality, T stage, N stage, surgery, radiotherapy, chemotherapy, distant metastases to other sites (lung, brain, and liver), and marital status were selected to construct all predictive models. The XGBoost model had a better performance in both training and validation sets as compared with other models in terms of accuracy. Our data suggested that the XGBoost model is the most precise and personalized tool for predicting the 1-year survival rate for NSCLC patients with BM. This model can help the clinicians to design more rational and effective therapeutic strategies.

The effect of pain on survival in non-small cell lung cancer (NSCLC) patients with bone metastases receiving chemotherapy

2008 ◽  
Vol 26 (15_suppl) ◽  
pp. 20666-20666
Author(s):  
K. Yoh ◽  
K. Kubota ◽  
H. Ohmatsu ◽  
K. Goto ◽  
S. Niho ◽  
...  
Keyword(s):  
Lung Cancer ◽  
Small Cell Lung Cancer ◽  
Bone Metastases ◽  
Cell Lung Cancer ◽  
Small Cell ◽  
Small Cell Lung ◽  
Nsclc Patients

Clinical impact of targetable gene alterations on therapeutic outcomes in stage II/III locally advanced non-small cell lung cancer patients.

2020 ◽  
Vol 38 (15_suppl) ◽  
pp. 9038-9038
Author(s):  
Yoshitaka Zenke ◽  
Shingo Matsumoto ◽  
Terufumi Kato ◽  
Shingo Miyamoto ◽  
Takuma Imakita ◽  
...  
Keyword(s):  
Lung Cancer ◽  
Survival Rate ◽  
Small Cell Lung Cancer ◽  
Cell Lung Cancer ◽  
Small Cell ◽  
Stage Ii ◽  
Small Cell Lung ◽  
Free Survival ◽  
Nsclc Patients ◽  
Gene Alterations

9038 Background: The clinical significance of genetic alterations in stage II/III non-small cell lung cancer (NSCLC) patients has not yet been clarified. We have prospectively analyzed NSCLC patients for cancer-related gene alterations and have followed up clinical course of the patients, establishing a large-scale clinico-genomic database in our nationwide genome screening project (LC-SCRUM-Japan). Methods: Submitted tumor samples were subjected to a targeted next-generation sequencing (NGS) system, Oncomine™ Comprehensive Assay. Therapeutic and prognostic data were collected and updated every year. Results: Since March 2015 to May 2019, 5166 non-squamous NSCLC patients from 263 institutions had been enrolled in the LC-SCRUM-Japan, and 754 of them were diagnosed as stage II/III. The median age of the 754 patients was 67 years (range, 21-92), and 503 (67%) were male, 595 (79%) smokers and 631 (84%) stage III. Of 640 available samples, 258 (40%) had targetable gene alterations, comprising 106 KRAS mut, 42 EGFR mut, 29 BRAF mut, 20 MET ex14skip/amp, 16 ALK fus, 12 ROS1 fus, 11 ERBB2 ex20ins, 8 RET fus, 7 EGFR ex20ins, 5 AKT1 mut, 1 NRG1 fus, 1 FGFR2/3 fus. In patients who received surgery (n = 159), 3-year disease-free survival rate was worse in patients with targetable gene alterations than in those without (40% vs 58% months; p = 0.03). In patients who received cytotoxic chemo-radiotherapy (n = 148), the response rate was similar in patients with targetable gene alterations and those without (70% vs. 77%); however, 3-year progression-free survival rate tended to be shorter in patients with targetable gene alterations than in those without (19% vs 35%; p = 0.08). Conclusions: In stage II/III NSCLC, the total frequency of targetable gene alterations was similar to that previously evaluated in our stage IV cohort (45%), and the current standard therapies showed early progression in the targetable gene-altered patients. A novel effective multimodality treatment in combination with targeted therapies is needed for this population.

RB1 mutation had influenced on bone metastases in advanced treatment-naïve lung cancer.

2020 ◽  
Vol 38 (15_suppl) ◽  
pp. e21668-e21668
Author(s):  
Chengzhi Zhou ◽  
Ying Xu ◽  
Xinqing Lin ◽  
Fei Wang ◽  
Huojin Deng ◽  
...  
Keyword(s):  
Lung Cancer ◽  
Small Cell Lung Cancer ◽  
Bone Metastases ◽  
Cell Lung Cancer ◽  
Suppressor Gene ◽  
Small Cell ◽  
Small Cell Lung ◽  
Treatment Naïve ◽  
Cancer Types ◽  
Nsclc Patients

e21668 Background: RB1 is one of the most vital cancer suppressor genes in various cancer types. RB1 mutation always occurs in treatment-naïve small cell lung cancer (SCLC) patients or in resistance to EGFR TKI therapy of non-small cell lung cancer (NSCLC) patients. However, we observed a group of clinical NSCLC patients, and found that RB1 mutations also occurred in treatment-naïve patients. Methods: RB1 is one of the most vital cancer suppressor genes in various cancer types. RB1 mutation always occurs in treatment-naïve small cell lung cancer (SCLC) patients or in resistance to EGFR TKI therapy of non-small cell lung cancer (NSCLC) patients. However, we observed a group of clinical NSCLC patients, and found that RB1 mutations also occurred in treatment-naïve patients. Results: Nonsense and frame-shift mutations were the major pathogenic mutations found in RB1 gene, which predicted RB1 protein-deficient in these mutational patients. Furthermore, we found these RB1 mutation patients had TP53 mutations at the same time. Patients with RB1 mutation had a higher smoking prevalence than patients who had wildtype RB1 genes (P < 0.0001). Gene testing showed RB1 mutations patients also developed EGFR driver mutations, while the mutation frequency was significantly lower than RB1 wildtype patients ( P = 0.0368). Eight RB1 mutated patients diagnosed with actionable EGFR mutations, including exon 19 del, L858R, L861Q, G719S and S768I, while no patients diagnosed with EGFR exon 20 insertion. 10 (62.5%, 10/16) patients in RB1 mutated group, and 25(32.1%, 25/78) patients with RB1 wildtype had bone metastases. The proportion of bone metastases in patients with RB1 mutation was significantly increased than others ( P = 0.0216). Conclusions: This study demonstrates that the function of tumor suppressor gene RB1 in advanced stage of NSCLC. From the results, we considered RB1 mutation had influence on bone metastases. Although loss-of-function mutations in tumor suppressor gene (TSG) RB1 always had no targets therapeutic drugs, it also suggested that some other clinically treatment can be performed as soon as possible.

scholarly journals Predictive Radiomic Models for the Chemotherapy Response in Non-Small-Cell Lung Cancer based on Computerized-Tomography Images

2021 ◽  
Vol 11 ◽  
Author(s):  
Runsheng Chang ◽  
Shouliang Qi ◽  
Yong Yue ◽  
Xiaoye Zhang ◽  
Jiangdian Song ◽  
...  
Keyword(s):  
Lung Cancer ◽  
Small Cell Lung Cancer ◽  
Cell Lung Cancer ◽  
Predictive Models ◽  
Ct Images ◽  
Small Cell ◽  
Chemotherapy Response ◽  
Small Cell Lung ◽  
Independent Test ◽  
Nsclc Patients

The heterogeneity and complexity of non-small cell lung cancer (NSCLC) tumors mean that NSCLC patients at the same stage can have different chemotherapy prognoses. Accurate predictive models could recognize NSCLC patients likely to respond to chemotherapy so that they can be given personalized and effective treatment. We propose to identify predictive imaging biomarkers from pre-treatment CT images and construct a radiomic model that can predict the chemotherapy response in NSCLC. This single-center cohort study included 280 NSCLC patients who received first-line chemotherapy treatment. Non-contrast CT images were taken before and after the chemotherapy, and clinical information were collected. Based on the Response Evaluation Criteria in Solid Tumors and clinical criteria, the responses were classified into two categories: response (n = 145) and progression (n = 135), then all data were divided into two cohorts: training cohort (224 patients) and independent test cohort (56 patients). In total, 1629 features characterizing the tumor phenotype were extracted from a cube containing the tumor lesion cropped from the pre-chemotherapy CT images. After dimensionality reduction, predictive models of the chemotherapy response of NSCLC with different feature selection methods and different machine-learning classifiers (support vector machine, random forest, and logistic regression) were constructed. For the independent test cohort, the predictive model based on a random-forest classifier with 20 radiomic features achieved the best performance, with an accuracy of 85.7% and an area under the receiver operating characteristic curve of 0.941 (95% confidence interval, 0.898–0.982). Of the 20 selected features, four were first-order statistics of image intensity and the others were texture features. For nine features, there were significant differences between the response and progression groups (p &lt; 0.001). In the response group, three features, indicating heterogeneity, were overrepresented and one feature indicating homogeneity was underrepresented. The proposed radiomic model with pre-chemotherapy CT features can predict the chemotherapy response of patients with non-small cell lung cancer. This radiomic model can help to stratify patients with NSCLC, thereby offering the prospect of better treatment.

scholarly journals Nomogram Predicting the Prognosis of Patients with Surgically Resected Stage IA Non-Small Cell Lung Cancer

2021 ◽  
Author(s):  
Quan-Xing Liu ◽  
Zi-Qi Huang ◽  
Dong Zhou ◽  
Hong Zheng ◽  
Ji-Gang Dai
Keyword(s):  
Lung Cancer ◽  
Survival Rate ◽  
Small Cell Lung Cancer ◽  
Cell Lung Cancer ◽  
Small Cell ◽  
Small Cell Lung ◽  
Significant Difference ◽  
Stage Ia ◽  
Resected Stage ◽  
Nsclc Patients

Abstract Background: The AJCC 8th stage system was limited in accuracy for predicting prognosis of stage IA non-small cell lung cancer (NSCLC) patients. This study aimed to establish and validate two nomograms that predict overall survival (OS) and lung cancer specific survival (LCSS) in surgically resected stage IA NSCLC patients. Methods: Postoperative patients with stage IA NSCLC in SEER database between 2004 and 2015 were examined. Survival and clinical information according to the inclusion and exclusion criteria was collected. All patients were randomly divided into the training cohort and validation cohort with a ratio of 7:3. Independent prognosis factors were evaluated using univariate and multivariate Cox regression analyses, and predictive nomogram was established based on these factors. Nomogram performance was measured using the C-index, calibration plots, and decision curve analysis (DCA). Patients were grouped by quartiles of nomogram scores and survival curves were plotted by Kaplan-Meier analysis.Results: In total, 33533 patients were included in the study. The nomogram of OS and LCSS contained 12 and 10 prognostic factors respectively. The C-index of nomogram showed a relative good performance which was significantly superior than AJCC 8th stage both in training set and validating set (P＜0.001). The calibration curve results showed that the actual survival rate was consistent with the predicted survival rate. Nomogram scores related risk stratification revealed statistically significant difference which have better discrimination than AJCC 8th stage.Conclusions: The two established nomograms can accurately predict OS and LCSS in surgical resected patients with stage IA NSCLC.

scholarly journals Biomarkers and Gene Signatures to Predict Durable Response to Pembrolizumab in Non-Small Cell Lung Cancer

Cancers ◽  
2021 ◽  
Vol 13 (15) ◽  
pp. 3828
Author(s):  
Anello Marcello Poma ◽  
Rossella Bruno ◽  
Iacopo Pietrini ◽  
Greta Alì ◽  
Giulia Pasquini ◽  
...  
Keyword(s):  
Lung Cancer ◽  
T Cells ◽  
Small Cell Lung Cancer ◽  
Cell Lung Cancer ◽  
Immune Cell ◽  
Small Cell ◽  
Small Cell Lung ◽  
First Line ◽  
Durable Response ◽  
Nsclc Patients

Pembrolizumab has been approved as first-line treatment for advanced Non-small cell lung cancer (NSCLC) patients with tumors expressing PD-L1 and in the absence of other targetable alterations. However, not all patients that meet these criteria have a durable benefit. In this monocentric study, we aimed at refining the selection of patients based on the expression of immune genes. Forty-six consecutive advanced NSCLC patients treated with pembrolizumab in first-line setting were enrolled. The expression levels of 770 genes involved in the regulation of the immune system was analysed by the nanoString system. PD-L1 expression was evaluated by immunohistochemistry. Patients with durable clinical benefit had a greater infiltration of cytotoxic cells, exhausted CD8, B-cells, CD45, T-cells, CD8 T-cells and NK cells. Immune cell scores such as CD8 T-cell and NK cell were good predictors of durable response with an AUC of 0.82. Among the immune cell markers, XCL1/2 showed the better performance in predicting durable benefit to pembrolizumab, with an AUC of 0.85. Additionally, CD8A, CD8B and EOMES showed a high specificity (>0.86) in identifying patients with a good response to treatment. In the same series, PD-L1 expression levels had an AUC of 0.61. The characterization of tumor microenvironment, even with the use of single markers, can improve patients’ selection for pembrolizumab treatment.

Sign in / Sign up

Export Citation Format

Share Document