Quantitative bias analysis in practice: review of software for regression with unmeasured confounding
Abstract Background Failure to appropriately account for unmeasured confounding may lead to erroneous conclusions. Quantitative bias analysis (QBA) can be used to quantify the potential impact of unmeasured confounding or how much unmeasured confounding would be needed to change a study’s conclusion...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
BMC
2023-05-01
|
| Series: | BMC Medical Research Methodology |
| Subjects: | |
| Online Access: | https://doi.org/10.1186/s12874-023-01906-8 |
| _version_ | 1797832042504781824 |
|---|---|
| author | Emily Kawabata Kate Tilling Rolf H. H. Groenwold Rachael A. Hughes |
| author_facet | Emily Kawabata Kate Tilling Rolf H. H. Groenwold Rachael A. Hughes |
| author_sort | Emily Kawabata |
| collection | DOAJ |
| description | Abstract Background Failure to appropriately account for unmeasured confounding may lead to erroneous conclusions. Quantitative bias analysis (QBA) can be used to quantify the potential impact of unmeasured confounding or how much unmeasured confounding would be needed to change a study’s conclusions. Currently, QBA methods are not routinely implemented, partly due to a lack of knowledge about accessible software. Also, comparisons of QBA methods have focused on analyses with a binary outcome. Methods We conducted a systematic review of the latest developments in QBA software published between 2011 and 2021. Our inclusion criteria were software that did not require adaption (i.e., code changes) before application, was still available in 2022, and accompanied by documentation. Key properties of each software tool were identified. We provide a detailed description of programs applicable for a linear regression analysis, illustrate their application using two data examples and provide code to assist researchers in future use of these programs. Results Our review identified 21 programs with $$62\%$$ 62 % created post 2016. All are implementations of a deterministic QBA with $$81\%$$ 81 % available in the free software R. There are programs applicable when the analysis of interest is a regression of binary, continuous or survival outcomes, and for matched and mediation analyses. We identified five programs implementing differing QBAs for a continuous outcome: treatSens, causalsens, sensemakr, EValue, and konfound. When applied to one of our illustrative examples, causalsens incorrectly indicated sensitivity to unmeasured confounding whereas the other four programs indicated robustness. sensemakr performs the most detailed QBA and includes a benchmarking feature for multiple unmeasured confounders. Conclusions Software is now available to implement a QBA for a range of different analyses. However, the diversity of methods, even for the same analysis of interest, presents challenges to their widespread uptake. Provision of detailed QBA guidelines would be highly beneficial. |
| first_indexed | 2024-04-09T14:01:23Z |
| format | Article |
| id | doaj.art-adf6a617ec334600b2816d17187f9523 |
| institution | Directory Open Access Journal |
| issn | 1471-2288 |
| language | English |
| last_indexed | 2024-04-09T14:01:23Z |
| publishDate | 2023-05-01 |
| publisher | BMC |
| record_format | Article |
| series | BMC Medical Research Methodology |
| spelling | doaj.art-adf6a617ec334600b2816d17187f95232023-05-07T11:16:41ZengBMCBMC Medical Research Methodology1471-22882023-05-0123111310.1186/s12874-023-01906-8Quantitative bias analysis in practice: review of software for regression with unmeasured confoundingEmily Kawabata0Kate Tilling1Rolf H. H. Groenwold2Rachael A. Hughes3MRC Integrative Epidemiology Unit, University of BristolMRC Integrative Epidemiology Unit, University of BristolDepartment of Clinical Epidemiology, Leiden University Medical CenterMRC Integrative Epidemiology Unit, University of BristolAbstract Background Failure to appropriately account for unmeasured confounding may lead to erroneous conclusions. Quantitative bias analysis (QBA) can be used to quantify the potential impact of unmeasured confounding or how much unmeasured confounding would be needed to change a study’s conclusions. Currently, QBA methods are not routinely implemented, partly due to a lack of knowledge about accessible software. Also, comparisons of QBA methods have focused on analyses with a binary outcome. Methods We conducted a systematic review of the latest developments in QBA software published between 2011 and 2021. Our inclusion criteria were software that did not require adaption (i.e., code changes) before application, was still available in 2022, and accompanied by documentation. Key properties of each software tool were identified. We provide a detailed description of programs applicable for a linear regression analysis, illustrate their application using two data examples and provide code to assist researchers in future use of these programs. Results Our review identified 21 programs with $$62\%$$ 62 % created post 2016. All are implementations of a deterministic QBA with $$81\%$$ 81 % available in the free software R. There are programs applicable when the analysis of interest is a regression of binary, continuous or survival outcomes, and for matched and mediation analyses. We identified five programs implementing differing QBAs for a continuous outcome: treatSens, causalsens, sensemakr, EValue, and konfound. When applied to one of our illustrative examples, causalsens incorrectly indicated sensitivity to unmeasured confounding whereas the other four programs indicated robustness. sensemakr performs the most detailed QBA and includes a benchmarking feature for multiple unmeasured confounders. Conclusions Software is now available to implement a QBA for a range of different analyses. However, the diversity of methods, even for the same analysis of interest, presents challenges to their widespread uptake. Provision of detailed QBA guidelines would be highly beneficial.https://doi.org/10.1186/s12874-023-01906-8Causal inferenceQuantitative bias analysisSensitivity analysisSoftware reviewUnmeasured confounding |
| spellingShingle | Emily Kawabata Kate Tilling Rolf H. H. Groenwold Rachael A. Hughes Quantitative bias analysis in practice: review of software for regression with unmeasured confounding BMC Medical Research Methodology Causal inference Quantitative bias analysis Sensitivity analysis Software review Unmeasured confounding |
| title | Quantitative bias analysis in practice: review of software for regression with unmeasured confounding |
| title_full | Quantitative bias analysis in practice: review of software for regression with unmeasured confounding |
| title_fullStr | Quantitative bias analysis in practice: review of software for regression with unmeasured confounding |
| title_full_unstemmed | Quantitative bias analysis in practice: review of software for regression with unmeasured confounding |
| title_short | Quantitative bias analysis in practice: review of software for regression with unmeasured confounding |
| title_sort | quantitative bias analysis in practice review of software for regression with unmeasured confounding |
| topic | Causal inference Quantitative bias analysis Sensitivity analysis Software review Unmeasured confounding |
| url | https://doi.org/10.1186/s12874-023-01906-8 |
| work_keys_str_mv | AT emilykawabata quantitativebiasanalysisinpracticereviewofsoftwareforregressionwithunmeasuredconfounding AT katetilling quantitativebiasanalysisinpracticereviewofsoftwareforregressionwithunmeasuredconfounding AT rolfhhgroenwold quantitativebiasanalysisinpracticereviewofsoftwareforregressionwithunmeasuredconfounding AT rachaelahughes quantitativebiasanalysisinpracticereviewofsoftwareforregressionwithunmeasuredconfounding |