Individual patient data meta-analysis of survival data using Poisson regression models
<p>Abstract</p> <p>Background</p> <p>An Individual Patient Data (IPD) meta-analysis is often considered the gold-standard for synthesising survival data from clinical trials. An IPD meta-analysis can be achieved by either a two-stage or a one-stage approach, depending o...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
BMC
2012-03-01
|
| Series: | BMC Medical Research Methodology |
| Online Access: | http://www.biomedcentral.com/1471-2288/12/34 |
| _version_ | 1819027578884718592 |
|---|---|
| author | Crowther Michael J Riley Richard D Staessen Jan A Wang Jiguang Gueyffier Francois Lambert Paul C |
| author_facet | Crowther Michael J Riley Richard D Staessen Jan A Wang Jiguang Gueyffier Francois Lambert Paul C |
| author_sort | Crowther Michael J |
| collection | DOAJ |
| description | <p>Abstract</p> <p>Background</p> <p>An Individual Patient Data (IPD) meta-analysis is often considered the gold-standard for synthesising survival data from clinical trials. An IPD meta-analysis can be achieved by either a two-stage or a one-stage approach, depending on whether the trials are analysed separately or simultaneously. A range of one-stage hierarchical Cox models have been previously proposed, but these are known to be computationally intensive and are not currently available in all standard statistical software. We describe an alternative approach using Poisson based Generalised Linear Models (GLMs).</p> <p>Methods</p> <p>We illustrate, through application and simulation, the Poisson approach both classically and in a Bayesian framework, in two-stage and one-stage approaches. We outline the benefits of our one-stage approach through extension to modelling treatment-covariate interactions and non-proportional hazards. Ten trials of hypertension treatment, with all-cause death the outcome of interest, are used to apply and assess the approach.</p> <p>Results</p> <p>We show that the Poisson approach obtains almost identical estimates to the Cox model, is additionally computationally efficient and directly estimates the baseline hazard. Some downward bias is observed in classical estimates of the heterogeneity in the treatment effect, with improved performance from the Bayesian approach.</p> <p>Conclusion</p> <p>Our approach provides a highly flexible and computationally efficient framework, available in all standard statistical software, to the investigation of not only heterogeneity, but the presence of non-proportional hazards and treatment effect modifiers.</p> |
| first_indexed | 2024-12-21T05:44:42Z |
| format | Article |
| id | doaj.art-37c8bb5ee0fb4fccaab1391345e55db2 |
| institution | Directory Open Access Journal |
| issn | 1471-2288 |
| language | English |
| last_indexed | 2024-12-21T05:44:42Z |
| publishDate | 2012-03-01 |
| publisher | BMC |
| record_format | Article |
| series | BMC Medical Research Methodology |
| spelling | doaj.art-37c8bb5ee0fb4fccaab1391345e55db22022-12-21T19:14:09ZengBMCBMC Medical Research Methodology1471-22882012-03-011213410.1186/1471-2288-12-34Individual patient data meta-analysis of survival data using Poisson regression modelsCrowther Michael JRiley Richard DStaessen Jan AWang JiguangGueyffier FrancoisLambert Paul C<p>Abstract</p> <p>Background</p> <p>An Individual Patient Data (IPD) meta-analysis is often considered the gold-standard for synthesising survival data from clinical trials. An IPD meta-analysis can be achieved by either a two-stage or a one-stage approach, depending on whether the trials are analysed separately or simultaneously. A range of one-stage hierarchical Cox models have been previously proposed, but these are known to be computationally intensive and are not currently available in all standard statistical software. We describe an alternative approach using Poisson based Generalised Linear Models (GLMs).</p> <p>Methods</p> <p>We illustrate, through application and simulation, the Poisson approach both classically and in a Bayesian framework, in two-stage and one-stage approaches. We outline the benefits of our one-stage approach through extension to modelling treatment-covariate interactions and non-proportional hazards. Ten trials of hypertension treatment, with all-cause death the outcome of interest, are used to apply and assess the approach.</p> <p>Results</p> <p>We show that the Poisson approach obtains almost identical estimates to the Cox model, is additionally computationally efficient and directly estimates the baseline hazard. Some downward bias is observed in classical estimates of the heterogeneity in the treatment effect, with improved performance from the Bayesian approach.</p> <p>Conclusion</p> <p>Our approach provides a highly flexible and computationally efficient framework, available in all standard statistical software, to the investigation of not only heterogeneity, but the presence of non-proportional hazards and treatment effect modifiers.</p>http://www.biomedcentral.com/1471-2288/12/34 |
| spellingShingle | Crowther Michael J Riley Richard D Staessen Jan A Wang Jiguang Gueyffier Francois Lambert Paul C Individual patient data meta-analysis of survival data using Poisson regression models BMC Medical Research Methodology |
| title | Individual patient data meta-analysis of survival data using Poisson regression models |
| title_full | Individual patient data meta-analysis of survival data using Poisson regression models |
| title_fullStr | Individual patient data meta-analysis of survival data using Poisson regression models |
| title_full_unstemmed | Individual patient data meta-analysis of survival data using Poisson regression models |
| title_short | Individual patient data meta-analysis of survival data using Poisson regression models |
| title_sort | individual patient data meta analysis of survival data using poisson regression models |
| url | http://www.biomedcentral.com/1471-2288/12/34 |
| work_keys_str_mv | AT crowthermichaelj individualpatientdatametaanalysisofsurvivaldatausingpoissonregressionmodels AT rileyrichardd individualpatientdatametaanalysisofsurvivaldatausingpoissonregressionmodels AT staessenjana individualpatientdatametaanalysisofsurvivaldatausingpoissonregressionmodels AT wangjiguang individualpatientdatametaanalysisofsurvivaldatausingpoissonregressionmodels AT gueyffierfrancois individualpatientdatametaanalysisofsurvivaldatausingpoissonregressionmodels AT lambertpaulc individualpatientdatametaanalysisofsurvivaldatausingpoissonregressionmodels |