Identifying compliant participants through data matching improved estimation of intervention efficacy: randomized trials with opt-in/opt-out

View/ Open
Author(s)
Ng, Shu Kay
Byrnes, Joshua
Scuffham, Paul
Year published
2019
Metadata
Show full item recordAbstract
OBECTIVE: We propose a data-matching approach to estimate intervention efficacy for randomised controlled trials (RCTs) when there is non-compliance to the allocated treatment with induced selection bias. STUDY DESIGN: and Settings: We considered a large RCT to compare healthcare costs and hospital length-of-stay 12 months post randomisation. Participants allocated to the intervention group were eligible to receive health-coaching and disease-management services. An opt-out approach was adopted for recruitment. Control-group participants received usual care but were allowed to opt-in to receive the intervention. Using ...
View more >OBECTIVE: We propose a data-matching approach to estimate intervention efficacy for randomised controlled trials (RCTs) when there is non-compliance to the allocated treatment with induced selection bias. STUDY DESIGN: and Settings: We considered a large RCT to compare healthcare costs and hospital length-of-stay 12 months post randomisation. Participants allocated to the intervention group were eligible to receive health-coaching and disease-management services. An opt-out approach was adopted for recruitment. Control-group participants received usual care but were allowed to opt-in to receive the intervention. Using "nearest-neighbour"-matched data, we identified compliant participants in both arms to estimate intervention efficacy. Results were compared with intention-to-treat (ITT), instrumental-variable (IV)-adjusted ITT, per-protocol (PP), and as-treated (AT) analyses. RESULTS: The ITT estimated an intervention effect of a 1.5% reduction in cost, but 56.7% of intervention-group participants did not receive health-coaching. The PP and AT found an increase in cost of 9.4% and 17.1%, respectively. The matching method estimated a 12.3% reduction in cost. After adjustment for baseline covariates, the intervention group had lower same-day admission cost (13.6%; 95% CI: 7.3%-20.0%; p<0.001) and shorter hospital stay (11.2%; 95% CI: 2.6%-19.9%; p=0.021). CONCLUSION: Opt-in/opt-out strategies in RCTs misled intervention comparisons and the matching approach improved estimation of intervention efficacy.
View less >
View more >OBECTIVE: We propose a data-matching approach to estimate intervention efficacy for randomised controlled trials (RCTs) when there is non-compliance to the allocated treatment with induced selection bias. STUDY DESIGN: and Settings: We considered a large RCT to compare healthcare costs and hospital length-of-stay 12 months post randomisation. Participants allocated to the intervention group were eligible to receive health-coaching and disease-management services. An opt-out approach was adopted for recruitment. Control-group participants received usual care but were allowed to opt-in to receive the intervention. Using "nearest-neighbour"-matched data, we identified compliant participants in both arms to estimate intervention efficacy. Results were compared with intention-to-treat (ITT), instrumental-variable (IV)-adjusted ITT, per-protocol (PP), and as-treated (AT) analyses. RESULTS: The ITT estimated an intervention effect of a 1.5% reduction in cost, but 56.7% of intervention-group participants did not receive health-coaching. The PP and AT found an increase in cost of 9.4% and 17.1%, respectively. The matching method estimated a 12.3% reduction in cost. After adjustment for baseline covariates, the intervention group had lower same-day admission cost (13.6%; 95% CI: 7.3%-20.0%; p<0.001) and shorter hospital stay (11.2%; 95% CI: 2.6%-19.9%; p=0.021). CONCLUSION: Opt-in/opt-out strategies in RCTs misled intervention comparisons and the matching approach improved estimation of intervention efficacy.
View less >
Journal Title
Journal of Clinical Epidemiology
Volume
115
Copyright Statement
© 2019 Elsevier. Licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International Licence (http://creativecommons.org/licenses/by-nc-nd/4.0/) which permits unrestricted, non-commercial use, distribution and reproduction in any medium, providing that the work is properly cited.
Subject
Medical and Health Sciences
Mathematical Sciences
Non-compliance
health coaching
nearest-neighbour matching
randomised controlled trial
selection bias