Likelihood Ratio Meta-Analysis

Colin Dormuth

Likelihood Ratio Meta-Analysis

Colin Dormuth

This live webinar has already taken place. Scroll down to view the video recording.

—–

Dr. Colin Dormuth discussed the Likelihood Ratio Meta-Analysis (LRMA) method, an approach used to pool data from separate studies to quantitatively assess where the total evidence points. A log-likelihood ratio function is used to measure the association in each study and the functions are summed to determine a total effect estimate, and ‘intrinsic’ confidence interval (CI). The intrinsic CI is more readily interpretable and there is no need to account for previous statistical significance in an updated analysis. Also, results can be presented in a familiar forest plot format. Dr Dormuth demonstrated LRMA using an example of the influence of a concomitant conventional synthetic disease-modifying antirheumatic drug (csDMARD) on adherence to biologic DMARDs (bDMARD) in rheumatoid arthritis.

—–

TITLE: Likelihood Ratio Meta-Analysis

WHEN: Wednesday, November 29th, 2023 at 12:00 noon PST [convert to your local time]

WHERE: This is a free online webinar.

SPEAKER: Dr. Colin Dormuth, Sc.D., Associate Professor, Department of Anesthesiology, Pharmacology & Therapeutics, Faculty of Medicine, University of British Columbia, and Co-Managing Director of the Therapeutics Initiative


About the topic: A likelihood ratio–based approach is used in a meta-analysis to pool data from separate studies to quantitatively assess where the total evidence points. A log-likelihood ratio function is used for the measure of association in each study. Those functions are summed to obtain a combined function from which a total effect estimate, and ‘intrinsic’ confidence interval (CI), can be retrieved. Results can be presented in a familiar forest plot format.

Dr. Dormuth demonstrated the Likelihood Ratio Meta-Analysis (LRMA) method using an example of the influence of a concomitant conventional synthetic disease-modifying antirheumatic drug (csDMARD) on adherence to biologic DMARDs (bDMARD) in rheumatoid arthritis. The example includes population-based cohort studies of adult patients with rheumatoid arthritis between January 2007 and March 2014 in five Canadian provinces, and the US IBM MarketScan database. The outcome of discontinuation of bDMARD therapy was compared between patients who were concomitant versus non-concomitant users of csDMARDs. The study population comprised 20,221 new users of bDMARDs: those using adalimumab (7609), etanercept (9809), abatacept (1024) or infliximab (1779). Overall, concomitant use of csDMARD therapy was not statistically significantly associated with reduced discontinuation of bDMARD treatment in a random effects LRMA in these patients (hazard ratio=0.90, 95% intrinsic CI=0.79-1.02). The association was statistically significant when using usual random effects meta-analysis (95% CI=0.81-0.99). In the hypothetical scenario where the IBM MarketScan data were added after the original analysis, the 95% intrinsic CI remained unchanged at 0.79-1.02, but the 95% CI became uninterpretable.

The conclusion is that LRMA yields the same point estimate as a usual meta-analysis but with a 95% intrinsic CI that is wider than the traditional 95% CI and the intrinsic CI is more readily interpretable. Further, with LRMA, there is no need to account for previous statistical significance in an updated analysis.


About the speaker: Dr. Colin Dormuth is an Associate Professor in the Department of Anesthesiology, Pharmacology & Therapeutics, Faculty of Medicine, University of British Columbia. He is also Co-Managing Director of the Therapeutics Initiative. Dr. Dormuth has extensive experience using administrative health care databases to evaluate pharmaceutical policy changes and physician prescribing behaviour. He has been a member of the Therapeutics Initiative since 1995. His research focuses on drug safety and effectiveness, as well as the design and evaluation of reimbursement policies for prescription drugs. He has training in economic theory, applied econometrics, epidemiology, health services outcome research and biostatistics. Dr. Dormuth holds a Sc.D. and S.M. in epidemiology from Harvard University, an M.A. in economics from the University of Victoria, and a B.A. in economics from the University of Manitoba.


About the TI Methods Speaker Series: The TI Methods Speaker Series are offered free of charge and everyone is welcome. The event is usually held at noon on the last Wednesday of each month via Zoom videoconference. The presentations are recorded and the video recordings are posted online. Click here to view a list of talks offered in 2023.

No Comments

Post A Comment