Incorporating published univariable associations in diagnostic and prognostic modeling
Background: Diagnostic and prognostic literature is overwhelmed with studies reporting univariable predictor-outcome associations. Currently, methods to incorporate such information in the construction of a prediction model are underdeveloped and unfamiliar to many researchers. Methods. This article...
Published in: | BMC Medical Research Methodology |
---|---|
Main Authors: | , , , , , |
Format: | Article in Journal/Newspaper |
Language: | English |
Published: |
2012
|
Subjects: | |
Online Access: | http://repub.eur.nl/pub/56802 https://doi.org/10.1186/1471-2288-12-121 |
id |
ftunivrotterdam:oai:repub.eur.nl:56802 |
---|---|
record_format |
openpolar |
spelling |
ftunivrotterdam:oai:repub.eur.nl:56802 2023-07-16T03:58:47+02:00 Incorporating published univariable associations in diagnostic and prognostic modeling Debray, T.P.A. (Thomas) Koffijberg, H. (Hendrik) Lu, D. (Difei) Vergouwe, Y. (Yvonne) Steyerberg, E.W. (Ewout) Moons, K.G.M. (Karel) 2012-08-14 application/pdf http://repub.eur.nl/pub/56802 https://doi.org/10.1186/1471-2288-12-121 en eng http://repub.eur.nl/pub/56802 doi:10.1186/1471-2288-12-121 urn:hdl:1765/56802 info:eu-repo/semantics/openAccess B M C Medical Research Methodology vol. 12 info:eu-repo/semantics/article 2012 ftunivrotterdam https://doi.org/10.1186/1471-2288-12-121 2023-06-26T22:38:13Z Background: Diagnostic and prognostic literature is overwhelmed with studies reporting univariable predictor-outcome associations. Currently, methods to incorporate such information in the construction of a prediction model are underdeveloped and unfamiliar to many researchers. Methods. This article aims to improve upon an adaptation method originally proposed by Greenland (1987) and Steyerberg (2000) to incorporate previously published univariable associations in the construction of a novel prediction model. The proposed method improves upon the variance estimation component by reconfiguring the adaptation process in established theory and making it more robust. Different variants of the proposed method were tested in a simulation study, where performance was measured by comparing estimated associations with their predefined values according to the Mean Squared Error and coverage of the 90% confidence intervals. Results: Results demonstrate that performance of estimated multivariable associations considerably improves for small datasets where external evidence is included. Although the error of estimated associations decreases with increasing amount of individual participant data, it does not disappear completely, even in very large datasets. Conclusions: The proposed method to aggregate previously published univariable associations with individual participant data in the construction of a novel prediction models outperforms established approaches and is especially worthwhile when relatively limited individual participant data are available. Article in Journal/Newspaper Greenland RePub - Publications from Erasmus University, Rotterdam Greenland BMC Medical Research Methodology 12 1 |
institution |
Open Polar |
collection |
RePub - Publications from Erasmus University, Rotterdam |
op_collection_id |
ftunivrotterdam |
language |
English |
description |
Background: Diagnostic and prognostic literature is overwhelmed with studies reporting univariable predictor-outcome associations. Currently, methods to incorporate such information in the construction of a prediction model are underdeveloped and unfamiliar to many researchers. Methods. This article aims to improve upon an adaptation method originally proposed by Greenland (1987) and Steyerberg (2000) to incorporate previously published univariable associations in the construction of a novel prediction model. The proposed method improves upon the variance estimation component by reconfiguring the adaptation process in established theory and making it more robust. Different variants of the proposed method were tested in a simulation study, where performance was measured by comparing estimated associations with their predefined values according to the Mean Squared Error and coverage of the 90% confidence intervals. Results: Results demonstrate that performance of estimated multivariable associations considerably improves for small datasets where external evidence is included. Although the error of estimated associations decreases with increasing amount of individual participant data, it does not disappear completely, even in very large datasets. Conclusions: The proposed method to aggregate previously published univariable associations with individual participant data in the construction of a novel prediction models outperforms established approaches and is especially worthwhile when relatively limited individual participant data are available. |
format |
Article in Journal/Newspaper |
author |
Debray, T.P.A. (Thomas) Koffijberg, H. (Hendrik) Lu, D. (Difei) Vergouwe, Y. (Yvonne) Steyerberg, E.W. (Ewout) Moons, K.G.M. (Karel) |
spellingShingle |
Debray, T.P.A. (Thomas) Koffijberg, H. (Hendrik) Lu, D. (Difei) Vergouwe, Y. (Yvonne) Steyerberg, E.W. (Ewout) Moons, K.G.M. (Karel) Incorporating published univariable associations in diagnostic and prognostic modeling |
author_facet |
Debray, T.P.A. (Thomas) Koffijberg, H. (Hendrik) Lu, D. (Difei) Vergouwe, Y. (Yvonne) Steyerberg, E.W. (Ewout) Moons, K.G.M. (Karel) |
author_sort |
Debray, T.P.A. (Thomas) |
title |
Incorporating published univariable associations in diagnostic and prognostic modeling |
title_short |
Incorporating published univariable associations in diagnostic and prognostic modeling |
title_full |
Incorporating published univariable associations in diagnostic and prognostic modeling |
title_fullStr |
Incorporating published univariable associations in diagnostic and prognostic modeling |
title_full_unstemmed |
Incorporating published univariable associations in diagnostic and prognostic modeling |
title_sort |
incorporating published univariable associations in diagnostic and prognostic modeling |
publishDate |
2012 |
url |
http://repub.eur.nl/pub/56802 https://doi.org/10.1186/1471-2288-12-121 |
geographic |
Greenland |
geographic_facet |
Greenland |
genre |
Greenland |
genre_facet |
Greenland |
op_source |
B M C Medical Research Methodology vol. 12 |
op_relation |
http://repub.eur.nl/pub/56802 doi:10.1186/1471-2288-12-121 urn:hdl:1765/56802 |
op_rights |
info:eu-repo/semantics/openAccess |
op_doi |
https://doi.org/10.1186/1471-2288-12-121 |
container_title |
BMC Medical Research Methodology |
container_volume |
12 |
container_issue |
1 |
_version_ |
1771546081613578240 |