EPCO-25. MULTI-OMICS DISEASE STRATIFICATION IN PATIENTS WITH IDH-WILDTYPE GLIOBLASTOMA: SYNERGISTIC VALUE OF CLINICAL MEASURES, CONVENTIONAL AND DEEP RADIOMICS, AND GENOMICS FOR PREDICTION OF OVERALL SURVIVAL

2021 ◽  
Vol 23 (Supplement_6) ◽  
pp. vi7-vi7
Author(s):  
Anahita Fathi Kazerooni ◽  
Sanjay Saxena ◽  
Danni Tu ◽  
Erik Toorens ◽  
Vishnu Bashyam ◽  
...  
Keyword(s):  
Overall Survival ◽  
Multiple Scales ◽  
Cox Proportional Hazards ◽  
Diagnostic Methods ◽  
Added Value ◽  
Recursive Feature Elimination ◽  
Survival Prediction ◽  
Omics Data ◽  
Replication Cohort ◽  
Disease Stratification

Abstract PURPOSE Multi-omics data integration captures tumor characteristics at multiple scales [i.e., microscopic (genomics and epigenetics), macroscopic (radiomics), clinical manifestation], provides a more comprehensive assessment of patient’s risk, and facilitates personalized therapies. In this work, we investigated the synergistic value of such multiple data sources for risk stratification and prediction of overall survival in IDH-wildtype glioblastoma tumors. METHODS Quantitative conventional and deep radiomics were extracted from pre-operative multi-parametric structural MRI (T1, T1Gd, T2, T2-FLAIR) of 501 patients with newly diagnosed glioblastoma. 389/501 and 112/501 patients formed our discovery and replication cohorts, respectively. Conventional radiomics were extracted from CaPTk, and deep radiomics from a pre-trained VGG-19 model. Multivariate SVM classification was performed on the discovery cohort to stratify patients in high, medium, and low-risk groups, using recursive feature elimination and 5-fold cross-validation. This model was independently tested on the replication cohort, and a radiomic-based survival prediction index (SPIradiomics) was calculated for each patient. Multi-stage integration of omics data, i.e., clinical (age, gender, extent of resection (EOR)), SPIradiomics, epigenetics (MGMT promoter methylation), and genomics (27 clinically relevant gene mutations via next-generation sequencing (NGS)), was performed using multivariate Cox proportional hazards (Cox-PH) model for stratification of the risk in the replication cohort. RESULTS Cox-PH modeling resulted in a concordance index (c-index) of 0.65 (95% CI:0.6–0.7) for clinical data, 0.67 (95% CI:0.62–0.72) for clinical and epigenetics, 0.70 (95% CI:0.65–0.75) for clinical and radiomics, 0.72 (95% CI:0.68–0.77) for clinical, epigenetics, and radiomics, and 0.75 (95% CI:0.71 – 0.78) for the multi-omics combination of all data; highlighting the added value of each layer of information in prediction of the patient’s risk. CONCLUSION Our results reinforce the synergistic value of integrated diagnostic methods for improving risk assessment of patients with glioblastoma that may pave the path towards a more personalized treatment planning.

The role of ALBI and IGF-CTP score in refining prognostication of HCC.

2020 ◽  
Vol 38 (15_suppl) ◽  
pp. e16659-e16659
Author(s):  
Sunyoung S. Lee ◽  
Yehia I. Mohamed ◽  
Aliya Qayyum ◽  
Manal Hassan ◽  
Lianchun Xiao ◽  
...  
Keyword(s):  
Overall Survival ◽  
Proportional Hazards ◽  
Cox Proportional Hazards ◽  
Survival Prediction ◽  
Score System ◽  
Risk Of Death ◽  
U Statistics ◽  
Cox Proportional Hazards Models ◽  
Ctp Score

e16659 Background: Child-Turcotte-Pugh (CTP) score is widely used in the assessment of prognosis of HCC and CTP-A is the standard criterion for active therapy and clinical trials entry. Recently, ALBI and insulin-like growth factor-1 (IGF)-CTP scores have been reported to improve survival prediction over CTP score. However, comparative studies to compare both scores and to integrate IGF into Albi score are lacking. Methods: After institutional board approval, data and samples were prospectively collected. 299 HCC patients who had data to generate both IGF-CPG and Albi index were used. The ALBI index, and IGF score were calculated, Cox proportional hazards models were fitted to evaluation the association between overall survival (OS) and CTP, IGF-CTP, Albi and IGF, albumin, bilirubin. Harrell’s Concordance index (C-index) was calculated to evaluate the ability of the three score system to predict overall survival. And the U-statistics was used to compare the performance of prediction of OS between the score system. Results: OS association with CTP, IGF-CTP and Albi was performed (Table). IGF-CTP B was associated with a higher risk of death than A (HR = 1.6087, 95% CI: 1.2039, 2.1497, p = 0.0013), ALBI grade 2 was also associated with a higher risk of death than 1 (HR = 2.2817, 95% CI: 1.7255, 3.0172, p < 0.0001). IGF-1(analyzed as categorical variable) was independently associated with OS after adjusting for the effects of ALBI grade. Which showed IGF-1 ≤26 was significantly associated with poor OS, P = 0.001. Conclusions: Although ALBI grade and IGF-CTP score in this analysis had similar prognostic values in most cases, their benefits might be heterogenous in some specific conditions. We looked into corporation of IGF-1 into ALBI grade, IGF score with cutoff ≤26 which clearly refined OS prediction and better OS stratification of ALBI-grade.

scholarly journals Integrated Analysis of lncRNA-Associated ceRNA Network Identifies Two lncRNA Signatures as a Prognostic Biomarker in Gastric Cancer

2021 ◽  
Vol 2021 ◽  
pp. 1-16
Author(s):  
Shuyan Zhang ◽  
Shanshan Li ◽  
Jian-Lin Guo ◽  
Ningyi Li ◽  
Cai-Ning Zhang ◽  
...  
Keyword(s):  
Gastric Cancer ◽  
Overall Survival ◽  
Proportional Hazards ◽  
Cox Regression ◽  
Cox Proportional Hazards ◽  
Integrated Analysis ◽  
Survival Prediction ◽  
Survival Prognosis ◽  
Cox Regression Analysis ◽  
Cerna Network

Background. Gastric cancer (GC) is a malignant tumour that originates in the gastric mucosal epithelium and is associated with high mortality rates worldwide. Long noncoding RNAs (lncRNAs) have been identified to play an important role in the development of various tumours, including GC. Yet, lncRNA biomarkers in a competing endogenous RNA network (ceRNA network) that are used to predict survival prognosis remain lacking. The aim of this study was to construct a ceRNA network and identify the lncRNA signature as prognostic factors for survival prediction. Methods. The lncRNAs with overall survival significance were used to construct the ceRNA network. Function enrichment, protein-protein interaction, and cluster analysis were performed for dysregulated mRNAs. Multivariate Cox proportional hazards regression was performed to screen the potential prognostic lncRNAs. RT-qPCR was used to measure the relative expression levels of lncRNAs in cell lines. CCK8 assay was used to assess the proliferation of GC cells transfected with sh-lncRNAs. Results. Differentially expressed genes were identified including 585 lncRNAs, 144 miRNAs, and 2794 mRNAs. The ceRNA network was constructed using 35 DElncRNAs associated with overall survival of GC patients. Functional analysis revealed that these dysregulated mRNAs were enriched in cancer-related pathways, including TGF-beta, Rap 1, calcium, and the cGMP-PKG signalling pathway. A multivariate Cox regression analysis and cumulative risk score suggested that two of those lncRNAs (LINC01644 and LINC01697) had significant prognostic value. Furthermore, the results indicate that LINC01644 and LINC01697 were upregulated in GC cells. Knockdown of LINC01644 or LINC01697 suppressed the proliferation of GC cells. Conclusions. The authors identified 2-lncRNA signature in ceRNA regulatory network as prognostic biomarkers for the prediction of GC patient survival and revealed that silencing LINC01644 or LINC01697 inhibited the proliferation of GC cells.

scholarly journals SOURCE: Prediction Models for Overall Survival in Patients With Metastatic and Potentially Curable Esophageal and Gastric Cancer

2021 ◽  
Vol 19 (4) ◽  
pp. 403-410
Author(s):  
Héctor G. van den Boorn ◽  
Ameen Abu-Hanna ◽  
Nadia Haj Mohammad ◽  
Maarten C.C.M. Hulshof ◽  
Suzanne S. Gisbertz ◽  
...  
Keyword(s):  
Gastric Cancer ◽  
Overall Survival ◽  
Proportional Hazards ◽  
Prediction Models ◽  
Metastatic Cancer ◽  
Cox Proportional Hazards ◽  
Future Research ◽  
Survival Prediction ◽  
Netherlands Cancer Registry ◽  
Treatment Type

Background: Personalized prediction of treatment outcomes can aid patients with cancer when deciding on treatment options. Existing prediction models for esophageal and gastric cancer, however, have mostly been developed for survival prediction after surgery (ie, when treatment has already been completed). Furthermore, prediction models for patients with metastatic cancer are scarce. The aim of this study was to develop prediction models of overall survival at diagnosis for patients with potentially curable and metastatic esophageal and gastric cancer (the SOURCE study). Methods: Data from 13,080 patients with esophageal or gastric cancer diagnosed in 2015 through 2018 were retrieved from the prospective Netherlands Cancer Registry. Four Cox proportional hazards regression models were created for patients with potentially curable and metastatic esophageal or gastric cancer. Predictors, including treatment type, were selected using the Akaike information criterion. The models were validated with temporal cross-validation on their C-index and calibration. Results: The validated model’s C-index was 0.78 for potentially curable gastric cancer and 0.80 for potentially curable esophageal cancer. For the metastatic models, the c-indices were 0.72 and 0.73 for esophageal and gastric cancer, respectively. The 95% confidence interval of the calibration intercepts and slopes contain the values 0 and 1, respectively. Conclusions: The SOURCE prediction models show fair to good c-indices and an overall good calibration. The models are the first in esophageal and gastric cancer to predict survival at diagnosis for a variety of treatments. Future research is needed to demonstrate their value for shared decision-making in clinical practice.

scholarly journals Deep learning based feature-level integration of multi-omics data for breast cancer patients survival analysis

2020 ◽  
Vol 20 (1) ◽  
Author(s):  
Li Tong ◽  
Jonathan Mitchel ◽  
Kevin Chatlin ◽  
May D. Wang
Keyword(s):  
Breast Cancer ◽  
Dna Methylation ◽  
Overall Survival ◽  
Mirna Expression ◽  
Survival Prediction ◽  
Omics Data ◽  
Breast Cancer Patients ◽  
Omics Integration ◽  
Personalized Diagnosis ◽  
Overall Survival Prediction

Abstract Background Breast cancer is the most prevalent and among the most deadly cancers in females. Patients with breast cancer have highly variable survival lengths, indicating a need to identify prognostic biomarkers for personalized diagnosis and treatment. With the development of new technologies such as next-generation sequencing, multi-omics information are becoming available for a more thorough evaluation of a patient’s condition. In this study, we aim to improve breast cancer overall survival prediction by integrating multi-omics data (e.g., gene expression, DNA methylation, miRNA expression, and copy number variations (CNVs)). Methods Motivated by multi-view learning, we propose a novel strategy to integrate multi-omics data for breast cancer survival prediction by applying complementary and consensus principles. The complementary principle assumes each -omics data contains modality-unique information. To preserve such information, we develop a concatenation autoencoder (ConcatAE) that concatenates the hidden features learned from each modality for integration. The consensus principle assumes that the disagreements among modalities upper bound the model errors. To get rid of the noises or discrepancies among modalities, we develop a cross-modality autoencoder (CrossAE) to maximize the agreement among modalities to achieve a modality-invariant representation. We first validate the effectiveness of our proposed models on the MNIST simulated data. We then apply these models to the TCCA breast cancer multi-omics data for overall survival prediction. Results For breast cancer overall survival prediction, the integration of DNA methylation and miRNA expression achieves the best overall performance of 0.641 ± 0.031 with ConcatAE, and 0.63 ± 0.081 with CrossAE. Both strategies outperform baseline single-modality models using only DNA methylation (0.583 ± 0.058) or miRNA expression (0.616 ± 0.057). Conclusions In conclusion, we achieve improved overall survival prediction performance by utilizing either the complementary or consensus information among multi-omics data. The proposed ConcatAE and CrossAE models can inspire future deep representation-based multi-omics integration techniques. We believe these novel multi-omics integration models can benefit the personalized diagnosis and treatment of breast cancer patients.

scholarly journals A five metastasis-related long noncoding RNA risk signature for osteosarcoma survival prediction

2021 ◽  
Vol 14 (1) ◽  
Author(s):  
SiYuan Yu ◽  
FengLing Shao ◽  
HuiJun Liu ◽  
QingQing Liu
Keyword(s):  
Overall Survival ◽  
Noncoding Rna ◽  
Risk Group ◽  
Characteristic Curve ◽  
Bone Tumour ◽  
Cox Proportional Hazards ◽  
Functional Enrichment ◽  
Survival Prediction ◽  
Survival Difference ◽  
Potential Biomarker

Abstract Background Osteosarcoma is a highly malignant and common bone tumour with an aggressive disease course and a poor prognosis. Previous studies have demonstrated the relationship between long noncoding RNAs (lncRNAs) and tumorigenesis, metastasis, and progression. Methods We utilized a large cohort from the Therapeutically Applicable Research to Generate Effective Treatments (TARGET) database osteosarcoma project to identify potential lncRNAs related to the overall survival of patients with osteosarcoma by using univariate and multivariate Cox proportional hazards regression analyses. Kaplan–Meier curves were generated to evaluate the overall survival difference between patients in the high-risk group and the low-risk group. A time-dependent receiver operating characteristic curve (ROC) was employed, and the area under the curve (AUC) of ROC was measured to assess the sensitivity and specificity of the multi-lncRNA signature. Results Five lncRNAs (RP11-128N14.5, RP11-231|13.2, RP5-894D12.4, LAMA5-AS1, RP11-346L1.2) were identified, and a five-lncRNA signature was constructed. The AUC for predicting 5-year survival was 0.745, which suggested good performance of the five-lncRNA signature. In addition, functional enrichment analysis of the five-lncRNA-correlated protein-coding genes (PCGs) was performed to show the biological function of the five lncRNAs. Additionally, PPI network suggested RTP1 is a potential biomarker that regulates the prognosis of osteosarcoma. Conclusions We developed a five-lncRNA signature as a potential prognostic indicator for osteosarcoma.

scholarly journals Added Value of Cognition in the Prediction of Survival in Low and High Grade Glioma

2021 ◽  
Vol 12 ◽  
Author(s):  
Emma van Kessel ◽  
Ewoud Schuit ◽  
Irene M. C. Huenges Wajer ◽  
Carla Ruis ◽  
Filip Y. F. L. De Vos ◽  
...  
Keyword(s):  
Prognostic Value ◽  
Proportional Hazards ◽  
Cox Proportional Hazards ◽  
Added Value ◽  
Cognitive Domain ◽  
Survival Prediction ◽  
High Grade ◽  
Who Grade ◽  
Discriminative Performance ◽  
Cognitive Domains

Background: Diffuse gliomas, which are at WHO grade II-IV, are progressive primary brain tumors with great variability in prognosis. Our aim was to investigate whether pre-operative cognitive functioning is of added value in survival prediction in these patients.Methods: In a retrospective cohort study of patients undergoing awake craniotomy between 2010 and 2019 we performed pre-operative neuropsychological assessments in five cognitive domains. Their added prognostic value on top of known prognostic factors was assessed in two patient groups [low- (LGG) and high-grade gliomas (HGG]). We compared Cox proportional hazards regression models with and without the cognitive domain by means of loglikelihood ratios tests (LRT), discriminative performance measures (by AUC), and risk classification [by Integrated Discrimination Index (IDI)].Results: We included 109 LGG and 145 HGG patients with a median survival time of 1,490 and 511 days, respectively. The domain memory had a significant added prognostic value in HGG as indicated by an LRT (p-value = 0.018). The cumulative AUC for HGG with memory included was.78 (SD = 0.017) and without cognition 0.77 (SD = 0.018), IDI was 0.043 (0.000–0.102). In LGG none of the cognitive domains added prognostic value.Conclusions: Our findings indicated that memory deficits, which were revealed with the neuropsychological examination, were of additional prognostic value in HGG to other well-known predictors of survival.

scholarly journals Multi-Omic Prediction of Overall Survival in Patients With Glioblastoma: Additive and Synergistic Value of Clinical Measures, Radiomics, and Genomics

2021 ◽  
Author(s):  
Anahita Fathi Kazerooni ◽  
Sanjay Saxena ◽  
Erik Toorens ◽  
Danni Tu ◽  
Vishnu Bashyam ◽  
...  
Keyword(s):  
Overall Survival ◽  
Deep Learning ◽  
High Risk ◽  
Low Risk ◽  
Survival Prediction ◽  
Mgmt Methylation ◽  
Replication Cohort ◽  
Treatment Naïve ◽  
Integrated Diagnostics ◽  
Clinical Measures

Abstract Background. Multi-omic data, i.e., clinical measures, radiomic, and genetic data, capture multi-faceted tumor characteristics, contributing to a comprehensive patient risk assessment. Here, we investigate the additive value and independent reproducibility of integrated diagnostics in prediction of overall survival (OS) in newly diagnosed, treatment-naïve, IDH-wildtype GBM patients, by combining conventional and deep learning methods.Methods. Conventional radiomics and deep learning features were extracted from pre-operative multi-parametric MRI of 516 GBM patients. SVM classifiers were trained on the discovery cohort (n=404) to categorize patient groups of high-risk (OS<6 months) vs all, and low-risk (OS≥18 months) vs all. The trained patient stratification model was independently tested in the replication cohort (n=112) and a patient-wise survival prediction index (SPIradiomics) was produced. Multivariate Cox-PH models were generated for the replication cohort, first based on clinical measures solely, and then by layering on radiomics and molecular information.Results. Evaluation of the high-risk and low-risk classifiers in the discovery/replication cohorts revealed AUCs of 0.78 (95%CI:0.70–0.85)/0.75 (95%CI:0.64–0.79) and 0.75 (95%CI: 0.65–0.84)/0.63 (95%CI: 0.52–0.71), respectively. Cox-PH modeling showed a concordance index of 0.65 (95%CI:0.6–0.7) for clinical data, 0.70 (95%CI:0.65–0.75) for clinical and radiomics, 0.72 (95%CI:0.68–0.77) for clinical, MGMT methylation, and radiomics, and 0.75 (95%CI:0.72–0.79) for the combination of all omics, i.e., clinical, MGMT methylation, radiomics, and genomics.Conclusions. This study signifies the value of integrated diagnostics for improved prediction of OS in GBM. Our multi-omic survival prediction tool is easily scalable and can be used for more effective clinical trial stratification.

scholarly journals Predicting Overall Survival Time in Glioblastoma Patients Using Gradient Boosting Machines Algorithm and Recursive Feature Elimination Technique

Cancers ◽  
2021 ◽  
Vol 13 (19) ◽  
pp. 4976
Author(s):  
Golestan Karami ◽  
Marco Giuseppe Orlando ◽  
Andrea Delli Pizzi ◽  
Massimo Caulo ◽  
Cosimo Del Gratta
Keyword(s):  
Overall Survival ◽  
Survival Time ◽  
Cox Regression ◽  
Feature Selection Method ◽  
Rate Of Change ◽  
Supervised Machine Learning ◽  
Recursive Feature Elimination ◽  
Gradient Boosting ◽  
Survival Prediction ◽  
Classifier Performance

Despite advances in tumor treatment, the inconsistent response is a major challenge among glioblastoma multiform (GBM) that lead to different survival time. Our aim was to integrate multimodal MRI with non-supervised and supervised machine learning methods to predict GBM patients’ survival time. To this end, we identified different compartments of the tumor and extracted their features. Next, we applied Random Forest-Recursive Feature Elimination (RF-RFE) to identify the most relevant features to feed into a GBoost machine. This study included 29 GBM patients with known survival time. RF-RFE GBoost model was evaluated to assess the survival prediction performance using optimal features. Furthermore, overall survival (OS) was analyzed using univariate and multivariate Cox regression analyses, to evaluate the effect of ROIs and their features on survival. The results showed that a RF-RFE Gboost machine was able to predict survival time with 75% accuracy. The results also revealed that the rCBV in the low perfusion area was significantly different between groups and had the greatest effect size in terms of the rate of change of the response variable (survival time). In conclusion, not only integration of multi-modality MRI but also feature selection method can enhance the classifier performance.

scholarly journals Survival rates and prognostic factors in right- and left-sided colon cancer stage I–IV: an unselected retrospective single-center trial

2021 ◽  
Author(s):  
Claudius E. Degro ◽  
Richard Strozynski ◽  
Florian N. Loch ◽  
Christian Schineis ◽  
Fiona Speichinger ◽  
...  
Keyword(s):  
Colon Cancer ◽  
Overall Survival ◽  
Blood Level ◽  
Proportional Hazards ◽  
Survival Rates ◽  
Cox Proportional Hazards ◽  
Stage I ◽  
Cancer Stage ◽  
Single Center ◽  
Significant Difference

Abstract Purpose Colorectal cancer revealed over the last decades a remarkable shift with an increasing proportion of a right- compared to a left-sided tumor location. In the current study, we aimed to disclose clinicopathological differences between right- and left-sided colon cancer (rCC and lCC) with respect to mortality and outcome predictors. Methods In total, 417 patients with colon cancer stage I–IV were analyzed in the present retrospective single-center study. Survival rates were assessed using the Kaplan–Meier method and uni/multivariate analyses were performed with a Cox proportional hazards regression model. Results Our study showed no significant difference of the overall survival between rCC and lCC stage I–IV (p = 0.354). Multivariate analysis revealed in the rCC cohort the worst outcome for ASA (American Society of Anesthesiologists) score IV patients (hazard ratio [HR]: 16.0; CI 95%: 2.1–123.5), CEA (carcinoembryonic antigen) blood level > 100 µg/l (HR: 3.3; CI 95%: 1.2–9.0), increased lymph node ratio of 0.6–1.0 (HR: 5.3; CI 95%: 1.7–16.1), and grade 4 tumors (G4) (HR: 120.6; CI 95%: 6.7–2179.6) whereas in the lCC population, ASA score IV (HR: 8.9; CI 95%: 0.9–91.9), CEA blood level 20.1–100 µg/l (HR: 5.4; CI 95%: 2.4–12.4), conversion to laparotomy (HR: 14.1; CI 95%: 4.0–49.0), and severe surgical complications (Clavien-Dindo III–IV) (HR: 2.9; CI 95%: 1.5–5.5) were identified as predictors of a diminished overall survival. Conclusion Laterality disclosed no significant effect on the overall prognosis of colon cancer patients. However, group differences and distinct survival predictors could be identified in rCC and lCC patients.

Sign in / Sign up

Export Citation Format

Share Document