scholarly journals Risk Score Generated from CT-Based Radiomics Signatures for Overall Survival Prediction in Non-Small Cell Lung Cancer

Cancers ◽  
2021 ◽  
Vol 13 (14) ◽  
pp. 3616
Author(s):  
Viet-Huan Le ◽  
Quang-Hien Kha ◽  
Truong Nguyen Khanh Hung ◽  
Nguyen Quoc Khanh Le

This study aimed to create a risk score generated from CT-based radiomics signatures that could be used to predict overall survival in patients with non-small cell lung cancer (NSCLC). We retrospectively enrolled three sets of NSCLC patients (including 336, 84, and 157 patients for training, testing, and validation set, respectively). A total of 851 radiomics features for each patient from CT images were extracted for further analyses. The most important features (strongly linked with overall survival) were chosen by pairwise correlation analysis, Least Absolute Shrinkage and Selection Operator (LASSO) regression model, and univariate Cox proportional hazard regression. Multivariate Cox proportional hazard model survival analysis was used to create risk scores for each patient, and Kaplan–Meier was used to separate patients into two groups: high-risk and low-risk, respectively. ROC curve assessed the prediction ability of the risk score model for overall survival compared to clinical parameters. The risk score, which developed from ten radiomics signatures model, was found to be independent of age, gender, and stage for predicting overall survival in NSCLC patients (HR, 2.99; 95% CI, 2.27–3.93; p < 0.001) and overall survival prediction ability was 0.696 (95% CI, 0.635–0.758), 0.705 (95% CI, 0.649–0.762), 0.657 (95% CI, 0.589–0.726) (AUC) for 1, 3, and 5 years, respectively, in the training set. The risk score is more likely to have a better accuracy in predicting survival at 1, 3, and 5 years than clinical parameters, such as age 0.57 (95% CI, 0.499–0.64), 0.552 (95% CI, 0.489–0.616), 0.621 (95% CI, 0.544–0.689) (AUC); gender 0.554, 0.546, 0.566 (AUC); stage 0.527, 0.501, 0.459 (AUC), respectively, in 1, 3 and 5 years in the training set. In the training set, the Kaplan–Meier curve revealed that NSCLC patients in the high-risk group had a lower overall survival time than the low-risk group (p < 0.001). We also had similar results that were statistically significant in the testing and validation set. In conclusion, risk scores developed from ten radiomics signatures models have great potential to predict overall survival in NSCLC patients compared to the clinical parameters. This model was able to stratify NSCLC patients into high-risk and low-risk groups regarding the overall survival prediction.

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Nan Ma ◽  
Lu Si ◽  
Meiling Yang ◽  
Meihua Li ◽  
Zhiyi He

AbstractThere is an urgent need to identify novel biomarkers that predict the prognosis of patients with NSCLC. In this study,we aim to find out mRNA signature closely related to the prognosis of NSCLC by new algorithm of bioinformatics. Identification of highly expressed mRNA in stage I/II patients with NSCLC was performed with the “Limma” package of R software. Survival analysis of patients with different mRNA expression levels was subsequently calculated by Cox regression analysis, and a multi-RNA signature was obtained by using the training set. Kaplan–Meier estimator, log-rank test and receiver operating characteristic (ROC) curves were used to analyse the predictive ability of the multi-RNA signature. RT-PCR used to verify the expression of the multi-RNA signature, and Westernblot used to verify the expression of proteins related to the multi-RNA signature. We identified fifteen survival-related mRNAs in the training set and classified the patients as high risk or low risk. NSCLC patients with low risk scores had longer disease-free survival than patients with high risk scores. The fifteen-mRNA signature was an independent prognostic factor, as shown by the ROC curve. ROC curve also showed that the combined model of the fifteen-mRNA signature and tumour stage had higher precision than stage alone. The expression of fifteen mRNAs and related proteins were higher in stage II NSCLC than in stage I NSCLC. Multi-gene expression profiles provide a moderate prognostic tool for NSCLC patients with stage I/II disease.


2021 ◽  
Vol 14 (1) ◽  
Author(s):  
Qian Yan ◽  
Wenjiang Zheng ◽  
Boqing Wang ◽  
Baoqian Ye ◽  
Huiyan Luo ◽  
...  

Abstract Background Hepatocellular carcinoma (HCC) is a disease with a high incidence and a poor prognosis. Growing amounts of evidence have shown that the immune system plays a critical role in the biological processes of HCC such as progression, recurrence, and metastasis, and some have discussed using it as a weapon against a variety of cancers. However, the impact of immune-related genes (IRGs) on the prognosis of HCC remains unclear. Methods Based on The Cancer Gene Atlas (TCGA) and Immunology Database and Analysis Portal (ImmPort) datasets, we integrated the ribonucleic acid (RNA) sequencing profiles of 424 HCC patients with IRGs to calculate immune-related differentially expressed genes (DEGs). Survival analysis was used to establish a prognostic model of survival- and immune-related DEGs. Based on genomic and clinicopathological data, we constructed a nomogram to predict the prognosis of HCC patients. Gene set enrichment analysis further clarified the signalling pathways of the high-risk and low-risk groups constructed based on the IRGs in HCC. Next, we evaluated the correlation between the risk score and the infiltration of immune cells, and finally, we validated the prognostic performance of this model in the GSE14520 dataset. Results A total of 100 immune-related DEGs were significantly associated with the clinical outcomes of patients with HCC. We performed univariate and multivariate least absolute shrinkage and selection operator (Lasso) regression analyses on these genes to construct a prognostic model of seven IRGs (Fatty Acid Binding Protein 6 (FABP6), Microtubule-Associated Protein Tau (MAPT), Baculoviral IAP Repeat Containing 5 (BIRC5), Plexin-A1 (PLXNA1), Secreted Phosphoprotein 1 (SPP1), Stanniocalcin 2 (STC2) and Chondroitin Sulfate Proteoglycan 5 (CSPG5)), which showed better prognostic performance than the tumour/node/metastasis (TNM) staging system. Moreover, we constructed a regulatory network related to transcription factors (TFs) that further unravelled the regulatory mechanisms of these genes. According to the median value of the risk score, the entire TCGA cohort was divided into high-risk and low-risk groups, and the low-risk group had a better overall survival (OS) rate. To predict the OS rate of HCC, we established a gene- and clinical factor-related nomogram. The receiver operating characteristic (ROC) curve, concordance index (C-index) and calibration curve showed that this model had moderate accuracy. The correlation analysis between the risk score and the infiltration of six common types of immune cells showed that the model could reflect the state of the immune microenvironment in HCC tumours. Conclusion Our IRG prognostic model was shown to have value in the monitoring, treatment, and prognostic assessment of HCC patients and could be used as a survival prediction tool in the near future.


2020 ◽  
Author(s):  
Jianfeng Zheng ◽  
Jinyi Tong ◽  
Benben Cao ◽  
Xia Zhang ◽  
Zheng Niu

Abstract Background: Cervical cancer (CC) is a common gynecological malignancy for which prognostic and therapeutic biomarkers are urgently needed. The signature based on immune‐related lncRNAs(IRLs) of CC has never been reported. This study aimed to establish an IRL signature for patients with CC.Methods: The RNA-seq dataset was obtained from the TCGA, GEO, and GTEx database. The immune scores(IS)based on single-sample gene set enrichment analysis (ssGSEA) were calculated to identify the IRLs, which were then analyzed using univariate Cox regression analysis to identify significant prognostic IRLs. A risk score model was established to divide patients into low-risk and high-risk groups based on the median risk score of these IRLs. This was then validated by splitting TCGA dataset(n=304) into a training-set(n=152) and a valid-set(n=152). The fraction of 22 immune cell subpopulations was evaluated in each sample to identify the differences between low-risk and high-risk groups. Additionally, a ceRNA network associated with the IRLs was constructed.Results: A cohort of 326 CC and 21 normal tissue samples with corresponding clinical information was included in this study. Twenty-eight IRLs were collected according to the Pearson’s correlation analysis between immune score and lncRNA expression (P < 0.01). Four IRLs (BZRAP1-AS1, EMX2OS, ZNF667-AS1, and CTC-429P9.1) with the most significant prognostic values (P < 0.05) were identified which demonstrated an ability to stratify patients into low-risk and high-risk groups by developing a risk score model. It was observed that patients in the low‐risk group showed longer overall survival (OS) than those in the high‐risk group in the training-set, valid-set, and total-set. The area under the curve (AUC) of the receiver operating characteristic curve (ROC curve) for the four IRLs signature in predicting the one-, two-, and three-year survival rates were larger than 0.65. In addition, the low-risk and high-risk groups displayed different immune statuses in GSEA. These IRLs were also significantly correlated with immune cell infiltration. Conclusions: Our results showed that the IRL signature had a prognostic value for CC. Meanwhile, the specific mechanisms of the four-IRLs in the development of CC were ascertained preliminarily.


Author(s):  
Shuang Liu ◽  
Ruonan Shao ◽  
Xiaoyun Bu ◽  
Yujie Xu ◽  
Ming Shi

Hepatocellular carcinoma (HCC) is the second most lethal malignant tumor worldwide, with an increasing incidence and mortality. Due to general resistance to antitumor drugs, only limited therapies are currently available for advanced HCC patients, leading to a poor prognosis with a 5-year survival rate less than 20%. Pyroptosis is a type of inflammation-related programmed cell death and may become a new potential target for cancer therapy. However, the function and prognostic value of pyroptosis-related genes (PRGs) in HCC remain unknown. Here, we identified a total of 58 PRGs reported before and conducted a six-PRG signature via the LASSO regression method in the GEO training cohort, and model efficacy was further validated in an external dataset. The HCC patients can be classified into two subgroups based on the median risk score. High-risk patients have significantly shorter overall survival (OS) than low-risk patients in both training and validation cohorts. Multivariable analysis indicated that the risk score was an independent prognostic factor for OS of HCC patients. Functional enrichment analysis and immune infiltration evaluation suggested that immune status was more activated in the low-risk group. In summary, PRGs can be a prediction factor for prognosis of HCC patients and targeting pyroptosis is a potential therapeutic alternative in HCC.


2020 ◽  
Vol 10 ◽  
Author(s):  
Youchao Xiao ◽  
Gang Cui ◽  
Xingguang Ren ◽  
Jiaqi Hao ◽  
Yu Zhang ◽  
...  

The overall survival of patients with lower grade glioma (LGG) varies greatly, but the current histopathological classification has limitations in predicting patients’ prognosis. Therefore, this study aims to find potential therapeutic target genes and establish a gene signature for predicting the prognosis of LGG. CD44 is a marker of tumor stem cells and has prognostic value in various tumors, but its role in LGG is unclear. By analyzing three glioma datasets from Gene Expression Omnibus (GEO) database, CD44 was upregulated in LGG. We screened 10 CD44-related genes via protein–protein interaction (PPI) network; function enrichment analysis demonstrated that these genes were associated with biological processes and signaling pathways of the tumor; survival analysis showed that four genes (CD44, HYAL2, SPP1, MMP2) were associated with the overall survival (OS) and disease-free survival (DFS)of LGG; a novel four-gene signature was constructed. The prediction model showed good predictive value over 2-, 5-, 8-, and 10-year survival probability in both the development and validation sets. The risk score effectively divided patients into high- and low- risk groups with a distinct outcome. Multivariate analysis confirmed that the risk score and status of IDH were independent prognostic predictors of LGG. Among three LGG subgroups based on the presence of molecular parameters, IDH-mutant gliomas have a favorable OS, especially if combined with 1p/19q codeletion, which further confirmed the distinct biological pattern between three LGG subgroups, and the gene signature is able to divide LGG patients with the same IDH status into high- and low- risk groups. The high-risk group possessed a higher expression of immune checkpoints and was related to the activation of immunosuppressive pathways. Finally, this study provided a convenient tool for predicting patient survival. In summary, the four prognostic genes may be therapeutic targets and prognostic predictors for LGG; this four-gene signature has good prognostic prediction ability and can effectively distinguish high- and low-risk patients. High-risk patients are associated with higher immune checkpoint expression and activation of the immunosuppressive pathway, providing help for screening immunotherapy-sensitive patients.


2007 ◽  
Vol 25 (18_suppl) ◽  
pp. 16031-16031
Author(s):  
L. Mas Lopez ◽  
M. Olivera ◽  
L. Casanova ◽  
C. Santos ◽  
S. Neciosup ◽  
...  

16031 Background: To evaluate the clinical behavior and results of treatment of gestational trophoblastic disease at INEN between 1980 to 2005. Methods: This is a retrospective analysis of patients with gestational trophoblastic disease, clinical characteristics, results of treatment, toxicity, objective response and survival from January 1980 to December 2005. Descriptive statistics and Kaplan-Meier for survival analysis were performed. Results: Since Jan 1980 to Dec 2005. 595 patients were admitted at INEN; Hydatidiform mole 254 (42.7%) choriocarcinoma 201 (33.8%) invasive mole 41(6.8%). FIGO scoring System, high risk (score >6): 247 (41.5%), low risk (score 1–6): 348 (58.5%). Age ranged from 14 to 54 years, with 255 (44%) cases between 20 to 29 years. The sities of metastasis: lung 67.3%, vaginal 17.9%, brain 8.7%, liver 5.1%. The patients with low risks received treatment with Metotrexate 0.4mg/kg x day x 5 days po, reach disease control with a mean course of 6 (1 - 14), complete remission in 66.1% cases and 97% the overall survival rate to 20 years. Patients with high risk received treatment with: MAC 77 patients, MEC 19 patients, EMACO 48 patients and BEP 14 patients and achieved complete remission in 32.5%, 36.8%, 50% and 25% respectively. On the high risk group we detected two groups according to score > 12 and < 12, with diferent probability of survival at 20 years, for the group with score <12, 80% and the group with score >12, 48%. 98 patients were identified with score >12, and the age of these patients ranged from 15 to 51 years, with a mean age of 36.5 years. The blood B- HCG titers of these patients ranged from 198 to 6710,500. Liver and brain metastasis in 26 cases, number metastasis mayor 8 in 78 cases. Conclusions: Gestational trofhoblastic disease is highly curable. Patients of low risk achieved a 97% overall survival rate to 20 years. There are differences in the overall survival rate between patients of high risk with a score < 12 (80%) and score >12 (48%). This group presented with brain and liver metastasis, and it is important to define the best treatment for this group of patients No significant financial relationships to disclose.


Author(s):  
JinQun Jiang ◽  
HongYan Xu ◽  
PingShen Zhao ◽  
Hai Lu

Cervical cancer is a common malignancy in women and has a poor prognosis.More and more studies have shown that autophagy disorder is closely related to the occurrence of tumors. However, the prognostic role of autophagy gene in cervical cancer is still unclear. In this study, we constructed the risk signatures of autophagy related genes to predict the prognosis of cervical cancer. The expression profiles and clinical information of autophagy gene sets were downloaded from the TCGA and GES52903 queues as training sets and validation sets. The cervical normal tissue expression profile data from UCSC XENA website is GTEx data as a supplement to TCGA normal cervical tissue. Univariate COX regression analysis of 17 different autophagy genes with the Consensus approach tumor samples from the TCGA is divided into six subtypes, and the clinical traits in the six subtypes have different distribution, with further then absolute shrinkage and selection operator (LASSO) and multiariable COX regression method finally got seven autophagy genetic risk model is constructed, in the training set, the survival rate of high risk group is lower than the low risk group (p &lt; 0.0001), the validation set,The AUC area of the receiver operating characteristic (ROC) curve, the training set is 0.894, and the verification set is 0.736. We find that the high and low risk score is closely related to the TMN stage (All P is less than 0.05).The nomogram shows that the risk score combined with other indicators such as age, G,T,M, and N better predicts 1-year, 2-year, 3-year survival, and the DCA curve shows that the risk model combined with other indicators produces better clinical efficacy.Then immune cells in 28 in the enrichment score, there were statistically significant differences, high and low risk most GSEA enrichment analysis, the main enrichment in G2 / M checkpoint high-risk score, Genes defining epithelial and mesenchymal transition, raised in response to the low oxygen levels (hypoxia) gene, gene is important to the mitotic spindle assembly, these are closely related with the occurrence of tumor . In conclusion, our constructed autophagy risk signature may be a prognostic tool for cervical cancer.


2021 ◽  
Vol 104 (1) ◽  
pp. 003685042110065
Author(s):  
Jing Wan ◽  
Peigen Chen ◽  
Yu Zhang ◽  
Jie Ding ◽  
Yuebo Yang ◽  
...  

Endometrial carcinoma (EC) is the fourth most common cancer in women. Some long non-coding RNAs (lncRNAs) are regarded as potential prognostic biomarkers or targets for treatment of many types of cancers. We aim to screen prognostic-related lncRNAs and build a possible lncRNA signature which can effectively predict the survival of patients with EC. We obtained lncRNA expression profiling from the TCGA database. The patients were classified into training set and verification set. By performing Univariate Cox regression model, Robust likelihood-based survival analysis, and Cox proportional hazards model, we developed a risk score with the Cox co-efficient of individual lncRNAs in the training set. The optimum cut-off point was selected by ROC analysis. Patients were effectively divided into high-risk group and low-risk group according to the risk score. The OS of the low-risk patients was significantly prolonged compared with that of the high-risk group. At last, we validated this 11-lncRNA signature in the verification set and the complete set. We identified an 11-lncRNA expression signature with high stability and feasibility, which can predict the survival of patients with EC. These findings provide new potential biomarkers to improve the accuracy of prognosis prediction of EC.


2021 ◽  
Vol 12 ◽  
Author(s):  
Junwan Lu ◽  
Changrui Qian ◽  
Yongan Ji ◽  
Qiyu Bao ◽  
Bin Lu

Bromodomain (BRD) proteins exhibit a variety of activities, such as histone modification, transcription factor recruitment, chromatin remodeling, and mediator or enhancer complex assembly, that affect transcription initiation and elongation. These proteins also participate in epigenetic regulation. Although specific epigenetic regulation plays an important role in the occurrence and development of cancer, the characteristics of the BRD family in renal clear cell carcinoma (KIRC) have not been determined. In this study, we investigated the expression of BRD family genes in KIRC at the transcriptome level and examined the relationship of the expression of these genes with patient overall survival. mRNA levels of tumor tissues and adjacent tissues were extracted from The Cancer Genome Atlas (TCGA) database. Seven BRD genes (KAT2A, KAT2B, SP140, BRD9, BRPF3, SMARCA2, and EP300) were searched by using LASSO Cox regression and the model with prognostic risk integration. The patients were divided into two groups: high risk and low risk. The combined analysis of these seven BRD genes showed a significant association with the high-risk groups and lower overall survival (OS). This analysis demonstrated that total survival could be predicted well in the low-risk group according to the time-dependent receiver operating characteristic (ROC) curve. The prognosis was determined to be consistent with that obtained using an independent dataset from TCGA. The relevant biological functions were identified using Gene Set Enrichment Analysis (GSEA). In summary, this study provides an optimized survival prediction model and promising data resources for further research investigating the role of the expression of BRD genes in KIRC.


Blood ◽  
2018 ◽  
Vol 132 (Supplement 1) ◽  
pp. 4747-4747
Author(s):  
Daniel A. Ermann ◽  
Victoria Vardell Noble ◽  
Avyakta Kallam ◽  
James O. Armitage

Abstract Background: Diffuse large B-cell lymphoma (DLBCL) is the most common subtype of non-Hodgkin lymphoma, and is characterized as a heterogenous disease associated with varying outcomes. The International Prognostic Index (IPI) has been the standard for baseline prognostic assessment in these patients. In this study we aimed to determine the impact of treatment facility (academic versus non-academic centers) on overall survival outcomes in DLBCL patients stratified by IPI score risk groups, with a focus on high risk disease as this is associated with poorer outcomes. Methods: The 2018 National Cancer Database (NCDB) was utilized for patients diagnosed with DLBCL between 2004-2015. Patients were then stratified based on IPI risk score from low to high risk. Four risk groups were formed: low (0-1), low-intermediate (2), high-intermediate (3), and high (4-5). Overall survival was calculated using Kaplan-Meyer analysis with bivariate cox proportional hazard ratios to compare survival by facility type (academic or community centers) within these risk groups. Results: A total of 160,137 patients were identified. Of these cases 31.8% were classified as low risk, 21.9% were low-intermediate risk, 22.2% were high-intermediate risk, and 24% were high risk. 59.3% of patients were treated at a community center and 40.7% were treated at academic centers. Treatment at academic centers was associated with a significantly improved overall survival (OS) for each risk category. Median survival (in months) for high risk IPI score DLBCL was 47.9 months in community and 61.1 months in academic centers (p<.0001). Median survival for high-intermediate risk score was 48.3 months in community and 87.3 months in academic centers (p<.0001). Median survival for low-intermediate score was 90.3 months in community and 122.8 months in academic centers (p<.0001). Median survival for low risk score was 132 months in community and 148 months in academic centers (p<.0001). Hazard ratios for academic center versus community center for high risk, high-intermediate, low-intermediate and low risk are 0.768, 0.71, 0.848 and 0.818 respectively (p<.0001). Conclusions: Facility type is significantly associated with improved survival outcomes across all IPI based risk groups for DLBCL. This benefit is especially significant in higher risk disease where positive outcomes are less common, suggesting treatment at academic centers may be particularly beneficial in these patients. Some of the possible reasons for this difference may include provider experience, increased access to resources, and opportunity for clinical trials. Further investigations into the factors contributing to such disparities should be done to help standardize care and improve outcomes. Disclosures No relevant conflicts of interest to declare.


Sign in / Sign up

Export Citation Format

Share Document