Tags

Type your tag names separated by a space and hit enter

On the use of propensity scores in case of rare exposure.
BMC Med Res Methodol. 2016 Mar 31; 16:38.BM

Abstract

BACKGROUND

Observational post-marketing assessment studies often involve evaluating the effect of a rare treatment on a time-to-event outcome, through the estimation of a marginal hazard ratio. Propensity score (PS) methods are the most used methods to estimate marginal effect of an exposure in observational studies. However there is paucity of data concerning their performance in a context of low prevalence of exposure.

METHODS

We conducted an extensive series of Monte Carlo simulations to examine the performance of the two preferred PS methods, known as PS-matching and PS-weighting to estimate marginal hazard ratios, through various scenarios.

RESULTS

We found that both PS-weighting and PS-matching could be biased when estimating the marginal effect of rare exposure. The less biased results were obtained with estimators of average treatment effect in the treated population (ATT), in comparison with estimators of average treatment effect in the overall population (ATE). Among ATT estimators, PS-weighting using ATT weights outperformed PS-matching. These results are illustrated using a real observational study.

CONCLUSIONS

When clinical objectives are focused on the treated population, applied researchers are encouraged to estimate ATT with PS-weighting for studying the relative effect of a rare treatment on time-to-event outcomes.

Authors+Show Affiliations

APHP, Hôpital Louis Mourier, Département d'Epidémiologie et Recherche Clinique, 178 Rue des Renouillers, Colombes, 92700, France. david.hajage@aphp.fr. APHP, Hôpital Bichat, Centre de Pharmacoépidémiologie (Cephepi), 46 Rue Henri Huchard, Paris, F-75018, France. david.hajage@aphp.fr. Univ Paris Diderot, Sorbonne Paris Cité, UMR 1123 ECEVE, Paris, F-75018, France. david.hajage@aphp.fr. INSERM, UMR 1123 ECEVE, Paris, F-75018, France. david.hajage@aphp.fr. INSERM, CIE-1425, Paris, F-75018, France. david.hajage@aphp.fr.APHP, Hôpital Bichat, Département d'Epidémiologie et Recherche Clinique, 46 Rue Henri Huchard, Paris, F-75018, France. APHP, Hôpital Bichat, Centre de Pharmacoépidémiologie (Cephepi), 46 Rue Henri Huchard, Paris, F-75018, France. Univ Paris Diderot, Sorbonne Paris Cité, UMR 1123 ECEVE, Paris, F-75018, France. INSERM, UMR 1123 ECEVE, Paris, F-75018, France. INSERM, CIE-1425, Paris, F-75018, France.FACT, DHU FIRE, Univ Paris-Diderot, Sorbonne Paris-Cité, Paris, F-75018, France. LVTS, INSERM U-1148, Hôpital Bichat, HUPNVS, AP-HP, Paris, F-75018, France. NHLI, Imperial College, Royal Brompton Hospital, London, UK.Brigham and Women's Hospital Heart & Vascular Center and Harvard Medical School, Boston, Massachusetts, USA.APHP, Hôpital Bichat, Département d'Epidémiologie et Recherche Clinique, 46 Rue Henri Huchard, Paris, F-75018, France. APHP, Hôpital Bichat, Centre de Pharmacoépidémiologie (Cephepi), 46 Rue Henri Huchard, Paris, F-75018, France. Univ Paris Diderot, Sorbonne Paris Cité, UMR 1123 ECEVE, Paris, F-75018, France. INSERM, UMR 1123 ECEVE, Paris, F-75018, France. INSERM, CIE-1425, Paris, F-75018, France.

Pub Type(s)

Journal Article
Research Support, Non-U.S. Gov't

Language

eng

PubMed ID

27036963

Citation

Hajage, David, et al. "On the Use of Propensity Scores in Case of Rare Exposure." BMC Medical Research Methodology, vol. 16, 2016, p. 38.
Hajage D, Tubach F, Steg PG, et al. On the use of propensity scores in case of rare exposure. BMC Med Res Methodol. 2016;16:38.
Hajage, D., Tubach, F., Steg, P. G., Bhatt, D. L., & De Rycke, Y. (2016). On the use of propensity scores in case of rare exposure. BMC Medical Research Methodology, 16, 38. https://doi.org/10.1186/s12874-016-0135-1
Hajage D, et al. On the Use of Propensity Scores in Case of Rare Exposure. BMC Med Res Methodol. 2016 Mar 31;16:38. PubMed PMID: 27036963.
* Article titles in AMA citation format should be in sentence-case
TY - JOUR T1 - On the use of propensity scores in case of rare exposure. AU - Hajage,David, AU - Tubach,Florence, AU - Steg,Philippe Gabriel, AU - Bhatt,Deepak L, AU - De Rycke,Yann, Y1 - 2016/03/31/ PY - 2015/05/28/received PY - 2016/03/15/accepted PY - 2016/4/3/entrez PY - 2016/4/3/pubmed PY - 2016/10/8/medline KW - Hazard ratio KW - Monte Carlo simulations KW - Observational studies KW - Pharmacoepidemiology KW - Propensity scores KW - Rare exposure SP - 38 EP - 38 JF - BMC medical research methodology JO - BMC Med Res Methodol VL - 16 N2 - BACKGROUND: Observational post-marketing assessment studies often involve evaluating the effect of a rare treatment on a time-to-event outcome, through the estimation of a marginal hazard ratio. Propensity score (PS) methods are the most used methods to estimate marginal effect of an exposure in observational studies. However there is paucity of data concerning their performance in a context of low prevalence of exposure. METHODS: We conducted an extensive series of Monte Carlo simulations to examine the performance of the two preferred PS methods, known as PS-matching and PS-weighting to estimate marginal hazard ratios, through various scenarios. RESULTS: We found that both PS-weighting and PS-matching could be biased when estimating the marginal effect of rare exposure. The less biased results were obtained with estimators of average treatment effect in the treated population (ATT), in comparison with estimators of average treatment effect in the overall population (ATE). Among ATT estimators, PS-weighting using ATT weights outperformed PS-matching. These results are illustrated using a real observational study. CONCLUSIONS: When clinical objectives are focused on the treated population, applied researchers are encouraged to estimate ATT with PS-weighting for studying the relative effect of a rare treatment on time-to-event outcomes. SN - 1471-2288 UR - https://www.unboundmedicine.com/medline/citation/27036963/On_the_use_of_propensity_scores_in_case_of_rare_exposure_ L2 - https://bmcmedresmethodol.biomedcentral.com/articles/10.1186/s12874-016-0135-1 DB - PRIME DP - Unbound Medicine ER -