Evidence synthesis in harm assessment of medicines using the example of rosiglitazone and myocardial infarction

Charlotte Rietbergen; Gudrun Stefansdottir; Hubert G. Leufkens; Mirjam J. Knol; Marie L. De Bruin; Irene Klugkist

doi:10.3389/fmed.2017.00228

Evidence synthesis in harm assessment of medicines using the example of rosiglitazone and myocardial infarction

Charlotte Rietbergen^*, Gudrun Stefansdottir, Hubert G. Leufkens, Mirjam J. Knol, Marie L. De Bruin, Irene Klugkist

^*Corresponding author for this work

Abstract

The current system of harm assessment of medicines has been criticized for relying on intuitive expert judgment. There is a call for more quantitative approaches and transparency in decision-making. Illustrated with the case of cardiovascular safety concerns for rosiglitazone, we aimed to explore a structured procedure for the collection, quality assessment, and statistical modeling of safety data from observational and randomized studies. We distinguished five stages in the synthesis process. In Stage I, the general research question, population and outcome, and general inclusion and exclusion criteria are defined and a systematic search is performed. Stage II focusses on the identification of sub-questions examined in the included studies and the classification of the studies into the different categories of sub-questions. In Stage III, the quality of the identified studies is assessed. Coding and data extraction are performed in Stage IV. Finally, meta-analyses on the study results per sub-question are performed in Stage V. A Pubmed search identified 30 randomized and 14 observational studies meeting our search criteria. From these studies, we identified 4 higher level sub-questions and 4 lower level sub-questions. We were able to categorize 29 individual treatment comparisons into one or more of the sub-question categories, and selected study duration as an important covariate. We extracted covariate, outcome, and sample size information at the treatment arm level of the studies. We extracted absolute numbers of myocardial infarctions from the randomized study, and adjusted risk estimates with 95% confidence intervals from the observational studies. Overall, few events were observed in the randomized studies that were frequently of relatively short duration. The large observational studies provided more information since these were often of longer duration. A Bayesian random effects meta-analysis on these data showed no significant increase in risk of rosiglitazone for any of the sub-questions. The proposed procedure can be of additional value for drug safety assessment because it provides a stepwise approach that guides the decision-making in increasing process transparency. The procedure allows for the inclusion of results from both randomized an observational studies, which is especially relevant for this type of research.

Original language	English
Article number	228
Journal	Frontiers in Medicine
Volume	4
Issue number	FEB
ISSN	2296-858X
DOIs	https://doi.org/10.3389/fmed.2017.00228
Publication status	Published - 1 Jan 2017

Keywords

Bayesian inference
Benefit vs. risk
Evidence synthesis
Informative priors
Safety

Access to Document

10.3389/fmed.2017.00228

pdfFinal published version, 616 KBLicence: CC BY

Cite this

@article{99c4fcd5791f4564bb020c0e6d2d6f1e,

title = "Evidence synthesis in harm assessment of medicines using the example of rosiglitazone and myocardial infarction",

abstract = "The current system of harm assessment of medicines has been criticized for relying on intuitive expert judgment. There is a call for more quantitative approaches and transparency in decision-making. Illustrated with the case of cardiovascular safety concerns for rosiglitazone, we aimed to explore a structured procedure for the collection, quality assessment, and statistical modeling of safety data from observational and randomized studies. We distinguished five stages in the synthesis process. In Stage I, the general research question, population and outcome, and general inclusion and exclusion criteria are defined and a systematic search is performed. Stage II focusses on the identification of sub-questions examined in the included studies and the classification of the studies into the different categories of sub-questions. In Stage III, the quality of the identified studies is assessed. Coding and data extraction are performed in Stage IV. Finally, meta-analyses on the study results per sub-question are performed in Stage V. A Pubmed search identified 30 randomized and 14 observational studies meeting our search criteria. From these studies, we identified 4 higher level sub-questions and 4 lower level sub-questions. We were able to categorize 29 individual treatment comparisons into one or more of the sub-question categories, and selected study duration as an important covariate. We extracted covariate, outcome, and sample size information at the treatment arm level of the studies. We extracted absolute numbers of myocardial infarctions from the randomized study, and adjusted risk estimates with 95% confidence intervals from the observational studies. Overall, few events were observed in the randomized studies that were frequently of relatively short duration. The large observational studies provided more information since these were often of longer duration. A Bayesian random effects meta-analysis on these data showed no significant increase in risk of rosiglitazone for any of the sub-questions. The proposed procedure can be of additional value for drug safety assessment because it provides a stepwise approach that guides the decision-making in increasing process transparency. The procedure allows for the inclusion of results from both randomized an observational studies, which is especially relevant for this type of research.",

keywords = "Bayesian inference, Benefit vs. risk, Evidence synthesis, Informative priors, Safety",

author = "Charlotte Rietbergen and Gudrun Stefansdottir and Leufkens, {Hubert G.} and Knol, {Mirjam J.} and {De Bruin}, {Marie L.} and Irene Klugkist",

year = "2017",

month = jan,

day = "1",

doi = "10.3389/fmed.2017.00228",

language = "English",

volume = "4",

journal = "Frontiers in Medicine",

issn = "2296-858X",

publisher = "Frontiers Media S.A.",

number = "FEB",

}

TY - JOUR

T1 - Evidence synthesis in harm assessment of medicines using the example of rosiglitazone and myocardial infarction

AU - Rietbergen, Charlotte

AU - Stefansdottir, Gudrun

AU - Leufkens, Hubert G.

AU - Knol, Mirjam J.

AU - De Bruin, Marie L.

AU - Klugkist, Irene

PY - 2017/1/1

Y1 - 2017/1/1

N2 - The current system of harm assessment of medicines has been criticized for relying on intuitive expert judgment. There is a call for more quantitative approaches and transparency in decision-making. Illustrated with the case of cardiovascular safety concerns for rosiglitazone, we aimed to explore a structured procedure for the collection, quality assessment, and statistical modeling of safety data from observational and randomized studies. We distinguished five stages in the synthesis process. In Stage I, the general research question, population and outcome, and general inclusion and exclusion criteria are defined and a systematic search is performed. Stage II focusses on the identification of sub-questions examined in the included studies and the classification of the studies into the different categories of sub-questions. In Stage III, the quality of the identified studies is assessed. Coding and data extraction are performed in Stage IV. Finally, meta-analyses on the study results per sub-question are performed in Stage V. A Pubmed search identified 30 randomized and 14 observational studies meeting our search criteria. From these studies, we identified 4 higher level sub-questions and 4 lower level sub-questions. We were able to categorize 29 individual treatment comparisons into one or more of the sub-question categories, and selected study duration as an important covariate. We extracted covariate, outcome, and sample size information at the treatment arm level of the studies. We extracted absolute numbers of myocardial infarctions from the randomized study, and adjusted risk estimates with 95% confidence intervals from the observational studies. Overall, few events were observed in the randomized studies that were frequently of relatively short duration. The large observational studies provided more information since these were often of longer duration. A Bayesian random effects meta-analysis on these data showed no significant increase in risk of rosiglitazone for any of the sub-questions. The proposed procedure can be of additional value for drug safety assessment because it provides a stepwise approach that guides the decision-making in increasing process transparency. The procedure allows for the inclusion of results from both randomized an observational studies, which is especially relevant for this type of research.

AB - The current system of harm assessment of medicines has been criticized for relying on intuitive expert judgment. There is a call for more quantitative approaches and transparency in decision-making. Illustrated with the case of cardiovascular safety concerns for rosiglitazone, we aimed to explore a structured procedure for the collection, quality assessment, and statistical modeling of safety data from observational and randomized studies. We distinguished five stages in the synthesis process. In Stage I, the general research question, population and outcome, and general inclusion and exclusion criteria are defined and a systematic search is performed. Stage II focusses on the identification of sub-questions examined in the included studies and the classification of the studies into the different categories of sub-questions. In Stage III, the quality of the identified studies is assessed. Coding and data extraction are performed in Stage IV. Finally, meta-analyses on the study results per sub-question are performed in Stage V. A Pubmed search identified 30 randomized and 14 observational studies meeting our search criteria. From these studies, we identified 4 higher level sub-questions and 4 lower level sub-questions. We were able to categorize 29 individual treatment comparisons into one or more of the sub-question categories, and selected study duration as an important covariate. We extracted covariate, outcome, and sample size information at the treatment arm level of the studies. We extracted absolute numbers of myocardial infarctions from the randomized study, and adjusted risk estimates with 95% confidence intervals from the observational studies. Overall, few events were observed in the randomized studies that were frequently of relatively short duration. The large observational studies provided more information since these were often of longer duration. A Bayesian random effects meta-analysis on these data showed no significant increase in risk of rosiglitazone for any of the sub-questions. The proposed procedure can be of additional value for drug safety assessment because it provides a stepwise approach that guides the decision-making in increasing process transparency. The procedure allows for the inclusion of results from both randomized an observational studies, which is especially relevant for this type of research.

KW - Bayesian inference

KW - Benefit vs. risk

KW - Evidence synthesis

KW - Informative priors

KW - Safety

UR - http://www.scopus.com/inward/record.url?scp=85062799122&partnerID=8YFLogxK

U2 - 10.3389/fmed.2017.00228

DO - 10.3389/fmed.2017.00228

M3 - Journal article

AN - SCOPUS:85062799122

SN - 2296-858X

VL - 4

JO - Frontiers in Medicine

JF - Frontiers in Medicine

IS - FEB

M1 - 228

ER -

Evidence synthesis in harm assessment of medicines using the example of rosiglitazone and myocardial infarction

Abstract

Keywords

Access to Document

Other files and links

Fingerprint

Cite this