scholarly journals High-Dimensional Cox Regression Analysis in Genetic Studies with Censored Survival Outcomes

2012 ◽  
Vol 2012 ◽  
pp. 1-14 ◽  
Author(s):  
Jinfeng Xu
Keyword(s):  
Relative Risk ◽  
Variable Selection ◽  
Cox Regression ◽  
Cox Model ◽  
Partial Likelihood ◽  
Likelihood Method ◽  
Dimensional Case ◽  
High Dimensional ◽  
Cox Regression Analysis ◽  
Penalization Methods

With the advancement of high-throughput technologies, nowadays high-dimensional genomic and proteomic data are easy to obtain and have become ever increasingly important in unveiling the complex etiology of many diseases. While relating a large number of factors to a survival outcome through the Cox relative risk model, various techniques have been proposed in the literature. We review some recently developed methods for such analysis. For high-dimensional variable selection in the Cox model with parametric relative risk, we consider the univariate shrinkage method (US) using the lasso penalty and the penalized partial likelihood method using the folded penalties (PPL). The penalization methods are not restricted to the finite-dimensional case. For the high-dimensional (p→∞,p≪n) or ultrahigh-dimensional case (n→∞,n≪p), both the sure independence screening (SIS) method and the extended Bayesian information criterion (EBIC) can be further incorporated into the penalization methods for variable selection. We also consider the penalization method for the Cox model with semiparametric relative risk, and the modified partial least squares method for the Cox model. The comparison of different methods is discussed and numerical examples are provided for the illustration. Finally, areas of further research are presented.

Variable selection for high-dimensional quadratic Cox model with application to Alzheimer’s disease

2020 ◽  
Vol 0 (0) ◽  
Author(s):  
Cong Li ◽  
Jianguo Sun
Keyword(s):  
Alzheimer’S Disease ◽  
Alzheimer's Disease ◽  
Variable Selection ◽  
Linear Models ◽  
Cox Model ◽  
Partial Likelihood ◽  
High Dimensional ◽  
Stat Assoc ◽  
Selection For ◽  
Disease Study

AbstractThis paper discusses variable or covariate selection for high-dimensional quadratic Cox model. Although many variable selection methods have been developed for standard Cox model or high-dimensional standard Cox model, most of them cannot be directly applied since they cannot take into account the important and existing hierarchical model structure. For the problem, we present a penalized log partial likelihood-based approach and in particular, generalize the regularization algorithm under marginality principle (RAMP) proposed in Hao et al. (J Am Stat Assoc 2018;113:615–25) under the context of linear models. An extensive simulation study is conducted and suggests that the presented method works well in practical situations. It is then applied to an Alzheimer’s Disease study that motivated this investigation.

Incorporating biological networks into high-dimensional Bayesian survival analysis using an ICM/M algorithm

2021 ◽  
Author(s):  
Vitara Pungpapong
Keyword(s):  
Variable Selection ◽  
Proportional Hazards Model ◽  
Cox Regression ◽  
Predictive Accuracy ◽  
Cox Model ◽  
Cox Proportional Hazards Model ◽  
Adaptive Lasso ◽  
Genomic Research ◽  
High Dimensional ◽  
Cox Models

The Cox proportional hazards model has been widely used in cancer genomic research that aims to identify genes from high-dimensional gene expression space associated with the survival time of patients. With the increase in expertly curated biological pathways, it is challenging to incorporate such complex networks in fitting a high-dimensional Cox model. This paper considers a Bayesian framework that employs the Ising prior to capturing relations among genes represented by graphs. A spike-and-slab prior is also assigned to each of the coefficients for the purpose of variable selection. The iterated conditional modes/medians (ICM/M) algorithm is proposed for the implementation for Cox models. The ICM/M estimates hyperparameters using conditional modes and obtains coefficients through conditional medians. This procedure produces some coefficients that are exactly zero, making the model more interpretable. Comparisons of the ICM/M and other regularized Cox models were carried out with both simulated and real data. Compared to lasso, adaptive lasso, elastic net, and DegreeCox, the ICM/M yielded more parsimonious models with consistent variable selection. The ICM/M model also provided a smaller number of false positives than the other methods and showed promising results in terms of predictive accuracy. In terms of computing times among the network-aware methods, the ICM/M algorithm is substantially faster than DegreeCox even when incorporating a large complex network. The implementation of the ICM/M algorithm for Cox regression model is provided in R package icmm, available on the Comprehensive R Archive Network (CRAN).

scholarly journals Analysis of Scoring Sequences in Matches of the Portuguese Premier League

2018 ◽  
Vol 64 (1) ◽  
pp. 255-263
Author(s):  
José M. Pratas ◽  
Anna Volossovitch ◽  
Ana I. Carita
Keyword(s):  
Regression Analysis ◽  
Cox Regression ◽  
Cox Model ◽  
Positive Association ◽  
Descriptive Statistics ◽  
Chi Square ◽  
Cox Regression Analysis ◽  
Premier League ◽  
Chi Square Test

AbstractThe aim of this study was to examine the sequences of the first two goals scored in soccer matches in accordance with a range of different match contexts. Data from 1506 matches played in the Portuguese Premier League during six consecutive competitive seasons (2009-10 to 2014-2015) were analysed using descriptive statistics and the chi-square test in order to verify the association between variables and a Cox regression analysis was used to predict the time the second goal was scored in function of the time of the first goal scored in the match and the scoreline. The results revealed a higher frequency of the second goals being scored in the second half of a match (58%) and in the last 5 min periods of each half. A positive association was found for home teams and score-doubling goals (58%), as well as for away teams and score-equalizing goals (56%). For home and away teams the score-doubling goal of a match was strongly and positively associated with a win outcome for home (93%) and away teams (92%), while the score-equalizing goals were associated with a draw (home and away teams: 44%) and loss outcome (home: 33% and away teams: 32%). Finally, the Cox model showed that if the first goal was scored in the second half of the match, the probability of the second goal being scored was three times higher compared to the first half.

scholarly journals Associated Factories and Time to Occurrence of Tuberculosis Among Children on HIV/AIDS Care in Assosa and Pawe General Hospitals North West Ethiopia: A Retrospective Cohort Study 2020

2020 ◽  
Author(s):  
Fassikaw kebede Bizuneh ◽  
Tadese Tollosa Daba ◽  
Belayneh Mengist Mitike ◽  
Tamrat sheawno Fikretsion ◽  
Belete Negese Negese
Keyword(s):  
Cohort Study ◽  
Retrospective Cohort Study ◽  
Retrospective Cohort ◽  
Cox Regression ◽  
Cox Model ◽  
Incidence Density ◽  
Human Immune Deficiency Virus ◽  
Cox Regression Analysis ◽  
Hiv Aids

Abstract Background: Tuberculosis (TB) incidence in peadtrics and children living with human immune-deficiency virus (HIV) is an emerging global concern. Although, the incidence of TB among adult HIV patients is exhaustively studied in Ethiopia, but among children on HIV/AIDS care is overlooked. Knowledge of the time when TB develops during successive follow up could be helpful for time relevant intervention strategies.Methods: health institution based retrospective cohort study conducted among 421 children on HIV/AIDS from 2009-2018. Time to develop TB was defined as time from enrollment for ART care until development of TB among children on ART. Proportional hazard assumption was checked for each variable and no variable was found with Schoenfeld test <0.05. Variables with P-value <0.25 at bivariate Cox regression analysis were entered into multivariable Cox model. Multivariable Cox regression model with 95%CI and AHR was used to identify significant predictor variables to develop TB at P< 0.05.Result: Totally 421 children were followed for a total of 662.5 Person Years of observation (PYO). The maximum and minimum follow up time on ART was 0.37 and 4.49 years, respectively. The median age of the children on ART at enrollment was 8 years (IQR=2-15). The Overall incidence density of tuberculosis in HIV infected children was 9.6/ 100 PYOs 95%CI (8.06-10.3). Tuberculosis occurrence among HIV infected children was significantly associated within TB history of contact AHR=3.7, 95%CI (2.89-7.2), not started on cotrimoxazole(CPT) AHR=2.4: 95%CI (1.84-4.74), incomplete vaccination AHR=2.4, 95%CI (1.32-4.5), sever stunting AHR =2.99:95%CI (1.2-7.81), having hemoglobin (Hgb) ≤10 mg/dl AHR = 4.02, 95%CI (2.01-8.1).Conclusion: More than 80% of TB incidences occurred during two years of follow up after ART started. So intensified screening of CPT& therapeutic feeding is highly recommended for all children.

scholarly journals PENAKSIRAN PARAMETER ANALISIS REGRESI COX DAN ANALISIS SURVIVAL BAYESIAN

2019 ◽  
Vol 1 (2) ◽  
pp. 16-26
Author(s):  
Rina Wijayanti
Keyword(s):  
Parameter Estimation ◽  
Statistical Approach ◽  
Cox Regression ◽  
Partial Likelihood ◽  
Parameter Estimates ◽  
Cox Regression Analysis ◽  
New Information ◽  
Classical Statistics ◽  
Model Complex ◽  
Close Form

In the theory of estimation, there are two approaches, namely the classical statistical approach and global statistical approach (Bayesian). Classical statistics are statistics in which the procedure is the decision based only on the data samples taken from the population. While Bayesian statistics in making decisions based on new information from the observed data (sample) and prior knowledge. At this writing Cox Regression Analysis will be taken as an example of parameter estimation by the classical statistical approach Survival Analysis and Bayesian statistical approach as an example of global (Bayesian). Survival Bayesial parameter estimation using MCMC algorithms for model complex / complicated and difficult to resolve while the Cox regression models using the method of partial likelihood. Results of the parameter estimates do not close form that needs to be done by the method of Newton-Raphson iteration.

scholarly journals Comprehensive Characterization of Alternative mRNA Splicing Events in Glioblastoma: Implications for Prognosis, Molecular Subtypes, and Immune Microenvironment Remodeling

2021 ◽  
Vol 10 ◽  
Author(s):  
Liang Zhao ◽  
Jiayue Zhang ◽  
Zhiyuan Liu ◽  
Yu Wang ◽  
Shurui Xuan ◽  
...  
Keyword(s):  
Risk Score ◽  
Immune Cell ◽  
Cox Regression ◽  
Malignant Tumors ◽  
Cox Model ◽  
Molecular Classification ◽  
The Cancer Genome Atlas ◽  
Consensus Clustering ◽  
Cox Regression Analysis ◽  
Alternative Mrna Splicing

Alternative splicing (AS) of pre-mRNA has been widely reported to be associated with the progression of malignant tumors. However, a systematic investigation into the prognostic value of AS events in glioblastoma (GBM) is urgently required. The gene expression profile and matched AS events data of GBM patients were obtained from The Cancer Genome Atlas Project (TCGA) and TCGA SpliceSeq database, respectively. 775 AS events were identified as prognostic factors using univariate Cox regression analysis. The least absolute shrinkage and selection operator (LASSO) cox model was performed to narrow down candidate AS events, and a risk score model based on several AS events were developed subsequently. The risk score-based signature was proved as an efficient predictor of overall survival and was closely related to the tumor purity and immunosuppression in GBM. Combined similarity network fusion and consensus clustering (SNF-CC) analysis revealed two distinct GBM subtypes based on the prognostic AS events, and the associations between this novel molecular classification and clinicopathological factors, immune cell infiltration, as well as immunogenic features were further explored. We also constructed a regulatory network to depict the potential mechanisms that how prognostic splicing factors (SFs) regulate splicing patterns in GBM. Finally, a nomogram incorporating AS events signature and other clinical-relevant covariates was built for clinical application. This comprehensive analysis highlights the potential implications for predicting prognosis and clinical management in GBM.

scholarly journals Prediction of Overall Survival Rate in Patients With Hepatocellular Carcinoma Using an Integrated Model Based on Autophagy Gene Marker

2021 ◽  
Vol 12 ◽  
Author(s):  
Shuaiqun Wang ◽  
Dalu Yang ◽  
Wei Kong
Keyword(s):  
Hepatocellular Carcinoma ◽  
Overall Survival ◽  
Survival Rate ◽  
Clinical Data ◽  
Cox Regression ◽  
Cox Model ◽  
Pathway Enrichment Analysis ◽  
Gene Marker ◽  
Overall Survival Rate ◽  
Cox Regression Analysis

The autophagy cell, which can inhibit the formation of tumor in the early stage and can promote the development of tumor in the late stage, plays an important role in the development of tumor. Therefore, it has potential significance to explore the influence of autophagy-related genes (AAGs) on the prognosis of hepatocellular carcinoma (HCC). The differentially expressed AAGs are selected from HCC gene expression profile data and clinical data downloaded from the TCGA database, and human autophagy database (HADB). The role of AAGs in HCC is elucidated by GO functional annotation and KEGG pathway enrichment analysis. Combining with clinical data, we selected age, gender, grade, stage, T state, M state, and N state as Cox model indexes to construct the multivariate Cox model and survival curve of Kaplan Meier (KM) was drawn to estimate patients’ survival between high- and low-risk groups. Through an ROC curve drawn by univariate and multivariate Cox regression analysis, we found that seven genes with high expression levels, including HSP90AB1, SQSTM1, RHEB, HDAC1, ATIC, HSPB8, and BIRC5 were associated with poor prognosis of HCC patients. Then the ICGC database is used to verify the reliability and robustness of the model. Therefore, the prognosis model of HCC constructed by autophagy genes might effectively predict the overall survival rate and help to find the best personalized targeted therapy of patients with HCC, which can provide better prognosis for patients.

scholarly journals Asymmetric leaflet tethering is associated with worse outcomes after edge-to-edge mitral valve repair for secondary mitral regurgitation

2021 ◽  
Vol 42 (Supplement_1) ◽  
Author(s):  
L Stolz ◽  
M Orban ◽  
D Braun ◽  
P Doldi ◽  
M Orban ◽  
...  
Keyword(s):  
Mitral Valve ◽  
Mitral Regurgitation ◽  
Mitral Valve Repair ◽  
Cox Regression ◽  
Cox Model ◽  
Operating Characteristics ◽  
Valve Repair ◽  
Cox Regression Analysis ◽  
Secondary Mitral Regurgitation ◽  
The Impact

Abstract Background The impact of mitral valve (MV) tethering patterns on outcomes of patients undergoing transcatheter edge-to-edge mitral valve repair (TEER) for severe secondary mitral regurgitation (SMR) is unknown. Purpose The purpose of this study was to evaluate the impact of asymmetric postero-anterior and medio-lateral MV leaflet tethering on procedural and survival outcomes after TEER for SMR. Methods Symmetry of postero-anterior leaflet tethering was defined as the ratio of the posterior to anterior MV leaflet angle (PLA/ALA) in the central MV segment 2. The ratio of the tenting area between MV segments 3 and 1 (S3/S1 ratio) was defined as medio-lateral tethering symmetry. We used receiver operating characteristics and a proportional Cox model to identify cut-off values of asymmetric postero-anterior and medio-lateral tethering for prediction of two-year survival after TEER. Results 178 patients receiving TEER for SMR were included. Asymmetric postero-anterior tethering was observed in 67 patients (37.6%, PLA/ALA ratio cut-off &gt;1.54). Medio-lateral tethering was asymmetric in 49 patients (27.5%, S3/S1 ratio cut-off &gt;1.49). MR was reduced to MR ≤2+ in 91.6% of patients, while postprocedural MR remained higher in the presence of asymmetric postero-anterior tethering (p=0.01). After adjustment for potential clinical and echocardiographic confounders, multivariable Cox regression analysis confirmed asymmetric postero-anterior tethering (HR=2.77, CI=1.43–5.38, p&lt;0.01) and asymmetric medio-lateral tethering (HR=2.90, CI=1.54–5.45, p&lt;0.01) as independent predictors for two-year survival. Conclusions Asymmetric postero-anterior and medio-lateral MV leaflet tethering patterns independently increase two-year all-cause mortality in patients undergoing TEER for SMR. Detailed echocardiographic patient selection might improve outcomes after TEER. FUNDunding Acknowledgement Type of funding sources: None. Postero-anterior tethering Medio-lateral tethering

scholarly journals Malnutrition Affects Cholesterol Paradox in Coronary Artery Disease: a 41,229 Chinese Cohort Study

2021 ◽  
Author(s):  
Bo Wang ◽  
Jin Liu ◽  
Shiqun Chen ◽  
Ming Ying ◽  
Guanzhong Chen ◽  
...  
Keyword(s):  
Cox Regression ◽  
Cox Model ◽  
Cox Regression Analysis ◽  
Coronary Syndrome ◽  
Kaplan Meier ◽  
All Cause Mortality ◽  
Chinese Cohort ◽  
Artery Disease

Abstract Background: Several studies found that baseline low LDL-C concentration was associated with poor prognosis in patients with acute coronary syndrome (ACS), which was called “cholesterol paradox”. Low LDL-C concentration may reflect underlying malnutrition, which was strongly associated with increased mortality. We objected to investigate the cholesterol paradox in patients with CAD and the effects of malnutrition.Method: A total of 41,229 CAD patients admitted to Guangdong Provincial People's Hospital in China were included in this study from January 2007 to December 2018, and divided into two groups (LDL-C < 1.8 mmol/L, n=4,863; LDL-C ≥ 1.8 mmol/L, n = 36,366). We used Kaplan-Meier method and Cox regression analyses to assess the association between LDL-C levels and long-term all-cause mortality and the effect of malnutrition. Result: In this real-world cohort (mean age 62.94 years; 74.94% male), there were 5257 incidents of all-cause death during a median follow-up of 5.20 years [Inter-quartile range (IQR): 3.05-7.78 years]. Kaplan–Meier analysis showed that low LDL-C levels were associated with worse prognosis. After adjusting for baseline confounders (e.g., age, sex and comorbidities, etc.), multivariate Cox regression analysis revealed that low LDL-C level (<1.8mmol/L) was not significantly associated with all-cause mortality (adjusted HR, 1.04; 95% CI, 0.96-1.24). After adjustment of nutritional status, risk of all-cause mortality of patients with low LDL-C level decreased (adjusted HR, 0.90; 95% CI, 0.83-0.98). In the final multivariate Cox model, low LDL-C level was related to better prognosis (adjusted HR, 0.91; 95% CI, 0.84-0.99).Conclusion: Our results demonstrate that the cholesterol paradox persisted in CAD patients, but disappeared after accounting for the effects of malnutrition.

Sign in / Sign up

Export Citation Format

Share Document