Cargando…

On the aggregation of published prognostic scores for causal inference in observational studies

As real world evidence on drug efficacy involves nonrandomized studies, statistical methods adjusting for confounding are needed. In this context, prognostic score (PGS) analysis has recently been proposed as a method for causal inference. It aims to restore balance across the different treatment gr...

Descripción completa

Detalles Bibliográficos
Autores principales: Nguyen, Tri‐Long, Collins, Gary S., Pellegrini, Fabio, Moons, Karel G.M., Debray, Thomas P.A.
Formato: Online Artículo Texto
Lenguaje:English
Publicado: John Wiley & Sons, Inc. 2020
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7187258/
https://www.ncbi.nlm.nih.gov/pubmed/32022311
http://dx.doi.org/10.1002/sim.8489
_version_ 1783527137376993280
author Nguyen, Tri‐Long
Collins, Gary S.
Pellegrini, Fabio
Moons, Karel G.M.
Debray, Thomas P.A.
author_facet Nguyen, Tri‐Long
Collins, Gary S.
Pellegrini, Fabio
Moons, Karel G.M.
Debray, Thomas P.A.
author_sort Nguyen, Tri‐Long
collection PubMed
description As real world evidence on drug efficacy involves nonrandomized studies, statistical methods adjusting for confounding are needed. In this context, prognostic score (PGS) analysis has recently been proposed as a method for causal inference. It aims to restore balance across the different treatment groups by identifying subjects with a similar prognosis for a given reference exposure (“control”). This requires the development of a multivariable prognostic model in the control arm of the study sample, which is then extrapolated to the different treatment arms. Unfortunately, large cohorts for developing prognostic models are not always available. Prognostic models are therefore subject to a dilemma between overfitting and parsimony; the latter being prone to a violation of the assumption of no unmeasured confounders when important covariates are ignored. Although it is possible to limit overfitting by using penalization strategies, an alternative approach is to adopt evidence synthesis. Aggregating previously published prognostic models may improve the generalizability of PGS, while taking account of a large set of covariates—even when limited individual participant data are available. In this article, we extend a method for prediction model aggregation to PGS analysis in nonrandomized studies. We conduct extensive simulations to assess the validity of model aggregation, compared with other methods of PGS analysis for estimating marginal treatment effects. We show that aggregating existing PGS into a “meta‐score” is robust to misspecification, even when elementary scores wrongfully omit confounders or focus on different outcomes. We illustrate our methods in a setting of treatments for asthma.
format Online
Article
Text
id pubmed-7187258
institution National Center for Biotechnology Information
language English
publishDate 2020
publisher John Wiley & Sons, Inc.
record_format MEDLINE/PubMed
spelling pubmed-71872582020-04-28 On the aggregation of published prognostic scores for causal inference in observational studies Nguyen, Tri‐Long Collins, Gary S. Pellegrini, Fabio Moons, Karel G.M. Debray, Thomas P.A. Stat Med Research Articles As real world evidence on drug efficacy involves nonrandomized studies, statistical methods adjusting for confounding are needed. In this context, prognostic score (PGS) analysis has recently been proposed as a method for causal inference. It aims to restore balance across the different treatment groups by identifying subjects with a similar prognosis for a given reference exposure (“control”). This requires the development of a multivariable prognostic model in the control arm of the study sample, which is then extrapolated to the different treatment arms. Unfortunately, large cohorts for developing prognostic models are not always available. Prognostic models are therefore subject to a dilemma between overfitting and parsimony; the latter being prone to a violation of the assumption of no unmeasured confounders when important covariates are ignored. Although it is possible to limit overfitting by using penalization strategies, an alternative approach is to adopt evidence synthesis. Aggregating previously published prognostic models may improve the generalizability of PGS, while taking account of a large set of covariates—even when limited individual participant data are available. In this article, we extend a method for prediction model aggregation to PGS analysis in nonrandomized studies. We conduct extensive simulations to assess the validity of model aggregation, compared with other methods of PGS analysis for estimating marginal treatment effects. We show that aggregating existing PGS into a “meta‐score” is robust to misspecification, even when elementary scores wrongfully omit confounders or focus on different outcomes. We illustrate our methods in a setting of treatments for asthma. John Wiley & Sons, Inc. 2020-02-05 2020-05-15 /pmc/articles/PMC7187258/ /pubmed/32022311 http://dx.doi.org/10.1002/sim.8489 Text en © 2020 The Authors. Statistics in Medicine published by John Wiley & Sons, Ltd. This is an open access article under the terms of the http://creativecommons.org/licenses/by-nc/4.0/ License, which permits use, distribution and reproduction in any medium, provided the original work is properly cited and is not used for commercial purposes.
spellingShingle Research Articles
Nguyen, Tri‐Long
Collins, Gary S.
Pellegrini, Fabio
Moons, Karel G.M.
Debray, Thomas P.A.
On the aggregation of published prognostic scores for causal inference in observational studies
title On the aggregation of published prognostic scores for causal inference in observational studies
title_full On the aggregation of published prognostic scores for causal inference in observational studies
title_fullStr On the aggregation of published prognostic scores for causal inference in observational studies
title_full_unstemmed On the aggregation of published prognostic scores for causal inference in observational studies
title_short On the aggregation of published prognostic scores for causal inference in observational studies
title_sort on the aggregation of published prognostic scores for causal inference in observational studies
topic Research Articles
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7187258/
https://www.ncbi.nlm.nih.gov/pubmed/32022311
http://dx.doi.org/10.1002/sim.8489
work_keys_str_mv AT nguyentrilong ontheaggregationofpublishedprognosticscoresforcausalinferenceinobservationalstudies
AT collinsgarys ontheaggregationofpublishedprognosticscoresforcausalinferenceinobservationalstudies
AT pellegrinifabio ontheaggregationofpublishedprognosticscoresforcausalinferenceinobservationalstudies
AT moonskarelgm ontheaggregationofpublishedprognosticscoresforcausalinferenceinobservationalstudies
AT debraythomaspa ontheaggregationofpublishedprognosticscoresforcausalinferenceinobservationalstudies