A sequential Cox approach for estimating the causal effect of treatment in the presence of time-dependent confounding applied to data from the Swiss HIV Cohort Study.
When estimating the effect of treatment on HIV using data from observational studies, standard methods may produce biased estimates due to the presence of time-dependent confounders. Such confounding can be present when a covariate, affected by past exposure, is both a predictor of the future exposu...
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Journal article |
| Language: | English |
| Published: |
2010
|
| _version_ | 1826290802727321600 |
|---|---|
| author | Gran, J Røysland, K Wolbers, M Didelez, V Sterne, J Ledergerber, B Furrer, H von Wyl, V Aalen, O |
| author_facet | Gran, J Røysland, K Wolbers, M Didelez, V Sterne, J Ledergerber, B Furrer, H von Wyl, V Aalen, O |
| author_sort | Gran, J |
| collection | OXFORD |
| description | When estimating the effect of treatment on HIV using data from observational studies, standard methods may produce biased estimates due to the presence of time-dependent confounders. Such confounding can be present when a covariate, affected by past exposure, is both a predictor of the future exposure and the outcome. One example is the CD4 cell count, being a marker for disease progression for HIV patients, but also a marker for treatment initiation and influenced by treatment. Fitting a marginal structural model (MSM) using inverse probability weights is one way to give appropriate adjustment for this type of confounding. In this paper we study a simple and intuitive approach to estimate similar treatment effects, using observational data to mimic several randomized controlled trials. Each 'trial' is constructed based on individuals starting treatment in a certain time interval. An overall effect estimate for all such trials is found using composite likelihood inference. The method offers an alternative to the use of inverse probability of treatment weights, which is unstable in certain situations. The estimated parameter is not identical to the one of an MSM, it is conditioned on covariate values at the start of each mimicked trial. This allows the study of questions that are not that easily addressed fitting an MSM. The analysis can be performed as a stratified weighted Cox analysis on the joint data set of all the constructed trials, where each trial is one stratum. The model is applied to data from the Swiss HIV cohort study. |
| first_indexed | 2024-03-07T02:49:46Z |
| format | Journal article |
| id | oxford-uuid:ad4578bd-2555-450d-b9f0-c9c2c0cc36af |
| institution | University of Oxford |
| language | English |
| last_indexed | 2024-03-07T02:49:46Z |
| publishDate | 2010 |
| record_format | dspace |
| spelling | oxford-uuid:ad4578bd-2555-450d-b9f0-c9c2c0cc36af2022-03-27T03:34:34ZA sequential Cox approach for estimating the causal effect of treatment in the presence of time-dependent confounding applied to data from the Swiss HIV Cohort Study.Journal articlehttp://purl.org/coar/resource_type/c_dcae04bcuuid:ad4578bd-2555-450d-b9f0-c9c2c0cc36afEnglishSymplectic Elements at Oxford2010Gran, JRøysland, KWolbers, MDidelez, VSterne, JLedergerber, BFurrer, Hvon Wyl, VAalen, OWhen estimating the effect of treatment on HIV using data from observational studies, standard methods may produce biased estimates due to the presence of time-dependent confounders. Such confounding can be present when a covariate, affected by past exposure, is both a predictor of the future exposure and the outcome. One example is the CD4 cell count, being a marker for disease progression for HIV patients, but also a marker for treatment initiation and influenced by treatment. Fitting a marginal structural model (MSM) using inverse probability weights is one way to give appropriate adjustment for this type of confounding. In this paper we study a simple and intuitive approach to estimate similar treatment effects, using observational data to mimic several randomized controlled trials. Each 'trial' is constructed based on individuals starting treatment in a certain time interval. An overall effect estimate for all such trials is found using composite likelihood inference. The method offers an alternative to the use of inverse probability of treatment weights, which is unstable in certain situations. The estimated parameter is not identical to the one of an MSM, it is conditioned on covariate values at the start of each mimicked trial. This allows the study of questions that are not that easily addressed fitting an MSM. The analysis can be performed as a stratified weighted Cox analysis on the joint data set of all the constructed trials, where each trial is one stratum. The model is applied to data from the Swiss HIV cohort study. |
| spellingShingle | Gran, J Røysland, K Wolbers, M Didelez, V Sterne, J Ledergerber, B Furrer, H von Wyl, V Aalen, O A sequential Cox approach for estimating the causal effect of treatment in the presence of time-dependent confounding applied to data from the Swiss HIV Cohort Study. |
| title | A sequential Cox approach for estimating the causal effect of treatment in the presence of time-dependent confounding applied to data from the Swiss HIV Cohort Study. |
| title_full | A sequential Cox approach for estimating the causal effect of treatment in the presence of time-dependent confounding applied to data from the Swiss HIV Cohort Study. |
| title_fullStr | A sequential Cox approach for estimating the causal effect of treatment in the presence of time-dependent confounding applied to data from the Swiss HIV Cohort Study. |
| title_full_unstemmed | A sequential Cox approach for estimating the causal effect of treatment in the presence of time-dependent confounding applied to data from the Swiss HIV Cohort Study. |
| title_short | A sequential Cox approach for estimating the causal effect of treatment in the presence of time-dependent confounding applied to data from the Swiss HIV Cohort Study. |
| title_sort | sequential cox approach for estimating the causal effect of treatment in the presence of time dependent confounding applied to data from the swiss hiv cohort study |
| work_keys_str_mv | AT granj asequentialcoxapproachforestimatingthecausaleffectoftreatmentinthepresenceoftimedependentconfoundingappliedtodatafromtheswisshivcohortstudy AT røyslandk asequentialcoxapproachforestimatingthecausaleffectoftreatmentinthepresenceoftimedependentconfoundingappliedtodatafromtheswisshivcohortstudy AT wolbersm asequentialcoxapproachforestimatingthecausaleffectoftreatmentinthepresenceoftimedependentconfoundingappliedtodatafromtheswisshivcohortstudy AT didelezv asequentialcoxapproachforestimatingthecausaleffectoftreatmentinthepresenceoftimedependentconfoundingappliedtodatafromtheswisshivcohortstudy AT sternej asequentialcoxapproachforestimatingthecausaleffectoftreatmentinthepresenceoftimedependentconfoundingappliedtodatafromtheswisshivcohortstudy AT ledergerberb asequentialcoxapproachforestimatingthecausaleffectoftreatmentinthepresenceoftimedependentconfoundingappliedtodatafromtheswisshivcohortstudy AT furrerh asequentialcoxapproachforestimatingthecausaleffectoftreatmentinthepresenceoftimedependentconfoundingappliedtodatafromtheswisshivcohortstudy AT vonwylv asequentialcoxapproachforestimatingthecausaleffectoftreatmentinthepresenceoftimedependentconfoundingappliedtodatafromtheswisshivcohortstudy AT aaleno asequentialcoxapproachforestimatingthecausaleffectoftreatmentinthepresenceoftimedependentconfoundingappliedtodatafromtheswisshivcohortstudy AT granj sequentialcoxapproachforestimatingthecausaleffectoftreatmentinthepresenceoftimedependentconfoundingappliedtodatafromtheswisshivcohortstudy AT røyslandk sequentialcoxapproachforestimatingthecausaleffectoftreatmentinthepresenceoftimedependentconfoundingappliedtodatafromtheswisshivcohortstudy AT wolbersm sequentialcoxapproachforestimatingthecausaleffectoftreatmentinthepresenceoftimedependentconfoundingappliedtodatafromtheswisshivcohortstudy AT didelezv sequentialcoxapproachforestimatingthecausaleffectoftreatmentinthepresenceoftimedependentconfoundingappliedtodatafromtheswisshivcohortstudy AT sternej sequentialcoxapproachforestimatingthecausaleffectoftreatmentinthepresenceoftimedependentconfoundingappliedtodatafromtheswisshivcohortstudy AT ledergerberb sequentialcoxapproachforestimatingthecausaleffectoftreatmentinthepresenceoftimedependentconfoundingappliedtodatafromtheswisshivcohortstudy AT furrerh sequentialcoxapproachforestimatingthecausaleffectoftreatmentinthepresenceoftimedependentconfoundingappliedtodatafromtheswisshivcohortstudy AT vonwylv sequentialcoxapproachforestimatingthecausaleffectoftreatmentinthepresenceoftimedependentconfoundingappliedtodatafromtheswisshivcohortstudy AT aaleno sequentialcoxapproachforestimatingthecausaleffectoftreatmentinthepresenceoftimedependentconfoundingappliedtodatafromtheswisshivcohortstudy |