Robust prediction of the cumulative incidence function under non-proportional subdistribution hazards

2016 ◽  
Vol 44 (2) ◽  
pp. 127-141 ◽  
Author(s):  
Qing Liu ◽  
Gong Tang ◽  
Joseph P. Costantino ◽  
Chung-Chou H. Chang
Keyword(s):  
Cumulative Incidence ◽  
Cumulative Incidence Function ◽  
Incidence Function ◽  
Proportional Subdistribution Hazards ◽  
Robust Prediction

Dynamic prediction of competing risk events using landmark sub-distribution hazard model with multiple longitudinal biomarkers

2020 ◽  
Vol 29 (11) ◽  
pp. 3179-3191
Author(s):  
Cai Wu ◽  
Liang Li ◽  
Ruosha Li
Keyword(s):  
Kidney Disease ◽  
Cumulative Incidence ◽  
Disease Risk ◽  
Predictor Variable ◽  
Cumulative Incidence Function ◽  
Competing Risk ◽  
Model Parameters ◽  
Dynamic Prediction ◽  
Risk Of Death ◽  
Incidence Function

The cause-specific cumulative incidence function quantifies the subject-specific disease risk with competing risk outcome. With longitudinally collected biomarker data, it is of interest to dynamically update the predicted cumulative incidence function by incorporating the most recent biomarker as well as the cumulating longitudinal history. Motivated by a longitudinal cohort study of chronic kidney disease, we propose a framework for dynamic prediction of end stage renal disease using multivariate longitudinal biomarkers, accounting for the competing risk of death. The proposed framework extends the local estimation-based landmark survival modeling to competing risks data, and implies that a distinct sub-distribution hazard regression model is defined at each biomarker measurement time. The model parameters, prediction horizon, longitudinal history and at-risk population are allowed to vary over the landmark time. When the measurement times of biomarkers are irregularly spaced, the predictor variable may not be observed at the time of prediction. Local polynomial is used to estimate the model parameters without explicitly imputing the predictor or modeling its longitudinal trajectory. The proposed model leads to simple interpretation of the regression coefficients and closed-form calculation of the predicted cumulative incidence function. The estimation and prediction can be implemented through standard statistical software with tractable computation. We conducted simulations to evaluate the performance of the estimation procedure and predictive accuracy. The methodology is illustrated with data from the African American Study of Kidney Disease and Hypertension.

Regression modeling of the cumulative incidence function with missing causes of failure using pseudo-values

2013 ◽  
Vol 32 (18) ◽  
pp. 3206-3223 ◽  
Author(s):  
Margarita Moreno-Betancur ◽  
Aurélien Latouche
Keyword(s):  
Cumulative Incidence ◽  
Cumulative Incidence Function ◽  
Regression Modeling ◽  
Incidence Function ◽  
Pseudo Values ◽  
Causes Of Failure

scholarly journals Parametric regression on cumulative incidence function

Biostatistics ◽  
2006 ◽  
Vol 8 (2) ◽  
pp. 184-196 ◽  
Author(s):  
J.-H. Jeong ◽  
J. P. Fine
Keyword(s):  
Cumulative Incidence ◽  
Cumulative Incidence Function ◽  
Parametric Regression ◽  
Incidence Function

scholarly journals Prognostic factors in Asian and white American patients with cervical cancer, considering competing risks

2019 ◽  
Vol 26 (3) ◽  
Author(s):  
Y. Hou ◽  
S. Guo ◽  
J. Lyu ◽  
Z. Lu ◽  
Z. Yang ◽  
...  
Keyword(s):  
Cervical Cancer ◽  
Prognostic Factors ◽  
Competing Risks ◽  
Asian American ◽  
Cumulative Incidence ◽  
Figo Stage ◽  
Cumulative Incidence Function ◽  
White American ◽  
Node Metastasis ◽  
Incidence Function

Background Cervical cancer is the 2nd most common malignant tumour in women worldwide. Previous research studies have given little attention to its prognostic factors in the rapidly growing Asian American population. In the present study, we explored prognostic factors in Asian and white American patients with cervical cancer, considering competing risks.Methods The study included 58,780 patients with cervical cancer, of whom 54,827 were white and 3953 were Asian American, and for all of whom complete clinical information was available in the U.S. Surveillance, Epidemiology, and End Results database. Death from cervical cancer was considered to be the event of interest, and deaths from other causes were defined as competing risks. The cumulative incidence function and the Fine–Gray method were applied for univariate and multivariate analysis respectively.Results We found that, for all patients (white and Asian American combined), the cumulative incidence function was associated with several factors, such as age at diagnosis, figo (Fédération internationale de Gynécologie et d’Obstétrique) stage, registry area, and lymph node metastasis. Similar results were found when considering white patients only. However, for Asian American patients, registry area was not associated with the cumulative incidence function, but the other factors (for example, figo stage) remained statistically significant. Similarly, in multivariate analyses, we found that age at diagnosis, figo stage, lymph node metastasis, tumour histology, treatment method, and race were all associated with prognosis.Conclusions Survival status differs for white and Asian American patients with cervical cancer. Our results could guide the treatment of, and facilitate prognostic judgments about, white and Asian American patients with cervical cancer.

scholarly journals Regression Analysis of Masked Competing Risks Data under Cumulative Incidence Function Framework

2020 ◽  
Vol 49 (3) ◽  
pp. 25-29
Author(s):  
Yosra Yousif ◽  
Faiz Ahmed Mohamed Elfaki ◽  
Meftah Hrairi
Keyword(s):  
Competing Risks ◽  
Cumulative Incidence ◽  
Model Simulation ◽  
Cumulative Incidence Function ◽  
Subdistribution Hazard ◽  
Incidence Function ◽  
Proposed Model ◽  
Competing Risks Data ◽  
Cause Of Failure ◽  
Proportional Subdistribution Hazard

In the studies that involve competing risks, somehow, masking issues might arise. That is, the cause of failure for some subjects is only known as a subset of possible causes. In this study, a Bayesian analysis is developed to assess the effect of risks factor on the Cumulative Incidence Function (CIF) by adopting the proportional subdistribution hazard model. Simulation is conducted to evaluate the performance of the proposed model and it shows that the model is feasible for the possible applications.

Sign in / Sign up

Export Citation Format

Share Document