scholarly journals Investigate the relevance of major signaling pathways in cancer survival using a biologically meaningful deep learning model

2020 ◽  
Author(s):  
Jiarui Feng ◽  
Heming Zhang ◽  
Fuhai Li

AbstractSurvival analysis and prediction are important in cancer studies. In addition to the Cox proportional hazards model, recently deep learning models have been proposed to integrate the multi-omics data for survival prediction. Cancer signaling pathways are important and interpretable concepts that define the signaling cascades regulating cancer development and drug resistance. Thus, it is interesting and important to investigate the relevance to patients’ survival of individual signaling pathways. In this exploratory study, we propose to investigate the relevance and difference of a small set of core cancer signaling pathways in the survival analysis of cancer patients. Specifically, we built a biologically meaningful and simplified deep neural network, DeepSigSurvNet, for survival prediction. In the model, the gene expression and copy number data of 1648 genes from 46 major signaling pathways are used. We applied the model on 4 types of cancer and investigated the relevance and difference of the 46 signaling pathways among the 4 types of cancer. Interestingly, the interpretable analysis identified the distinct patterns of these signaling pathways, which are helpful to understand the relevance of the signaling pathways in terms of their association with cancer survival time. These highly relevant signaling pathways can be novel targets, combined with other essential signaling pathways inhibitors, for drug and drug combination prediction to improve cancer patients’ survival time.

2021 ◽  
Vol 22 (1) ◽  
Author(s):  
Jiarui Feng ◽  
Heming Zhang ◽  
Fuhai Li

Abstract Background Survival analysis is an important part of cancer studies. In addition to the existing Cox proportional hazards model, deep learning models have recently been proposed in survival prediction, which directly integrates multi-omics data of a large number of genes using the fully connected dense deep neural network layers, which are hard to interpret. On the other hand, cancer signaling pathways are important and interpretable concepts that define the signaling cascades regulating cancer development and drug resistance. Thus, it is important to investigate potential associations between patient survival and individual signaling pathways, which can help domain experts to understand deep learning models making specific predictions. Results In this exploratory study, we proposed to investigate the relevance and influence of a set of core cancer signaling pathways in the survival analysis of cancer patients. Specifically, we built a simplified and partially biologically meaningful deep neural network, DeepSigSurvNet, for survival prediction. In the model, the gene expression and copy number data of 1967 genes from 46 major signaling pathways were integrated in the model. We applied the model to four types of cancer and investigated the influence of the 46 signaling pathways in the cancers. Interestingly, the interpretable analysis identified the distinct patterns of these signaling pathways, which are helpful in understanding the relevance of signaling pathways in terms of their application to the prediction of cancer patients’ survival time. These highly relevant signaling pathways, when combined with other essential signaling pathways inhibitors, can be novel targets for drug and drug combination prediction to improve cancer patients’ survival time. Conclusion The proposed DeepSigSurvNet model can facilitate the understanding of the implications of signaling pathways on cancer patients’ survival by integrating multi-omics data and clinical factors.


2020 ◽  
Vol 23 (3) ◽  
pp. 655-664
Author(s):  
Vu-Thanh Nguyen ◽  
Thi Diem-Chinh Ho

Introduction: This paper studies risk factors which can have effects on the survival time of lung cancer patients during the treatment. Methods: The Cox proportional-hazards model has been applied for investigating the association between the survival time of patients and the predictors such as age, gender, the weight of patients, meal, the ECOG, and Karnofsky scores. Results: In the study, we find that the ECOG score, the Karnofsky score evaluated by doctors and the gender are the top three factors that significantly affect the hazard rate. Also, we utilize the estimated model to predict survival probability for the patients. Conclusion: In this article, we intentionally present a complete and detailed guide on how to perform a R-based package in survival analysis step by step as well as how to interpret all output results.  


Risks ◽  
2021 ◽  
Vol 9 (6) ◽  
pp. 103
Author(s):  
Morne Joubert ◽  
Tanja Verster ◽  
Helgard Raubenheimer ◽  
Willem D. Schutte

Survival analysis is one of the techniques that could be used to predict loss given default (LGD) for regulatory capital (Basel) purposes. When using survival analysis to model LGD, a proposed methodology is the default weighted survival analysis (DWSA) method. This paper is aimed at adapting the DWSA method (used to model Basel LGD) to estimate the LGD for International Financial Reporting Standard (IFRS) 9 impairment requirements. The DWSA methodology allows for over recoveries, default weighting and negative cashflows. For IFRS 9, this methodology should be adapted, as the estimated LGD is a function of in the expected credit losses (ECL). Our proposed IFRS 9 LGD methodology makes use of survival analysis to estimate the LGD. The Cox proportional hazards model allows for a baseline survival curve to be adjusted to produce survival curves for different segments of the portfolio. The forward-looking LGD values are adjusted for different macro-economic scenarios and the ECL is calculated for each scenario. These ECL values are probability weighted to produce a final ECL estimate. We illustrate our proposed IFRS 9 LGD methodology and ECL estimation on a dataset from a retail portfolio of a South African bank.


Risks ◽  
2021 ◽  
Vol 9 (7) ◽  
pp. 121
Author(s):  
Beata Bieszk-Stolorz ◽  
Krzysztof Dmytrów

The aim of our research was to compare the intensity of decline and then increase in the value of basic stock indices during the SARS-CoV-2 coronavirus pandemic in 2020. The survival analysis methods used to assess the risk of decline and chance of rise of the indices were: Kaplan–Meier estimator, logit model, and the Cox proportional hazards model. We observed the highest intensity of decline in the European stock exchanges, followed by the American and Asian plus Australian ones (after the fourth and eighth week since the peak). The highest risk of decline was in America, then in Europe, followed by Asia and Australia. The lowest risk was in Africa. The intensity of increase was the highest in the fourth and eleventh week since the minimal value had been reached. The highest odds of increase were in the American stock exchanges, followed by the European and Asian (including Australia and Oceania), and the lowest in the African ones. The odds and intensity of increase in the stock exchange indices varied from continent to continent. The increase was faster than the initial decline.


2019 ◽  
Vol 8 (2) ◽  
pp. 218
Author(s):  
Po-Hung Lin ◽  
Shun-Ku Lin ◽  
Ren-Jun Hsu ◽  
See-Tong Pang ◽  
Cheng-Keng Chuang ◽  
...  

Depression is associated with higher mortality in prostate cancer. However, whether traditional Chinese medicine (TCM) for depression improves outcomes in patients with prostate cancer is unclear. This retrospective cohort study evaluated the association between TCM for depression and mortality in patients with prostate cancer. During the period 1998–2012, a total of 248 prostate cancer patients in Taiwan with depression were enrolled and divided into three groups: TCM for depression (n = 81, 32.7%), TCM for other purposes (n = 53, 21.3%), and no TCM (n = 114, 46.0%). During a median follow-up of 6.2 years, 12 (14.8%), 13 (24.5%), and 36 (31.6%) deaths occurred in the TCM for depression, TCM for other purposes, and no TCM groups, respectively. After adjusting age at diagnosis, urbanization, insured amount, comorbidity disease, and prostate cancer type, TCM for depression was associated with a significantly lower risk of overall mortality based on a multivariate-adjusted Cox proportional-hazards model (hazard ratio 0.42, 95% confidence interval: 0.21–0.85, p = 0.02) and Kaplan–Meier survival curve (log-rank test, p = 0.0055) compared to no TCM. In conclusion, TCM for depression may have a positive association with the survival of prostate cancer patients with depression.


Blood ◽  
2009 ◽  
Vol 114 (22) ◽  
pp. 2789-2789 ◽  
Author(s):  
Kiran Naqvi ◽  
Guillermo Garcia-Manero ◽  
Sagar Sardesai ◽  
Jeong Oh ◽  
Sherry Pierce ◽  
...  

Abstract Abstract 2789 Poster Board II-765 Background: Cancer patients often experience comorbidities that may affect their therapeutic options, prognosis, and outcome (1). Limited studies have evaluated the characteristics and impact of comorbidities in myelodysplastic syndromes (MDS). The aim of this study was to determine the effect of comorbidities on the survival of patients with MDS. Methods: We reviewed the medical records of 500 consecutive MDS patients who presented to MD Anderson Cancer Center from January 2002 to June 2004. The Adult Comorbidity Evaluation-27 (ACE-27), a validated 27-item comorbidity index for cancer patients (2), was used to assess the severity of comorbid conditions. For each patient, we obtained demographic data and specific staging information based on the International Prognostic Scoring System (IPSS). We also collected information on stem cell transplantation (SCT), mortality and survival. Kaplan-Meier methods and log-rank tests were used to assess survival. Multivariate analysis was performed using the Cox Proportional Hazards Model. Results: Of the 500 patients included in this study, 327 (65.4%) were male, and 436 (87.9%) were white; median age at presentation was 66.6 years (17.7, 93.5); mean duration of follow-up was 23.5 months (0, 88). A total of 49% of patients had IPSS intermediate-1 or lower risk. The ACE-27 comorbidity scores were as follows: none, 106 patients (21.2%); mild, 213 (42.6%); moderate, 108 (21.6%); and severe, 73 (14.6%). Three hundred and eighty one (76.2%) patients died, and 44 (8.8%) patients underwent SCT. Overall median survival using the Kaplan-Meier method was 17.6 months. Median survival according to ACE-27 scores was: 27.9 months for no comorbidity, 18.9 months for mild comorbidity, 15.2 months for moderate comorbidity, and 9.7 months for severe comorbidity. This trend reached statistical significance (p < 0.0001). The median survival by IPSS ranged from 40.9 months for patients in the low risk group versus 8.1 months for those in the high risk category (p < 0.0001). The hazards ratio obtained from the multivariate Cox Proportional Hazards Model was 1.5 and 2.0 for moderate and severe comorbidity scores when adjusted for age and IPSS (p < 0.0001). A linear trend was also observed between the severity of comorbidity and having received SCT (p = 0.001). Of the 44 patients who had SCT, 21 (47.7%) died. The median survival of patients who did not undergo stem cell transplantation ranged from 22.7 months for patients with no comorbidity to 9.3 months for patients with severe comorbidity (p = 0.0002). Conclusion: Comorbidities had a significant impact on the survival of patients with myelodysplastic syndrome. Patients with higher ACE-27 comorbidity scores had a shorter survival than those with no comorbidity, independent of their age and the IPSS risk group. Also patients with comorbid conditions received SCT less often than those without comorbidity. A comprehensive assessment of comorbidity is therefore needed to determine the prognosis in patients with MDS. References: (1) Extermann M. Measurement and impact of comorbidity in older cancer patients. Crit Rev Oncol Hematol. 2000;35:181-200. (1) Piccirillo JF, Tierney RM, Costas I, et al. Prognostic importance of comorbidity in a hospital-based cancer registry. JAMA. 2004;291:2441-47. Disclosures: No relevant conflicts of interest to declare.


Sign in / Sign up

Export Citation Format

Share Document