Summary:
The two studies find similar RR (risk reduction as
RR=riskivermectinriskcontrol)
Bryant found RR = 0.38 [CI 95%: (0.19, 0.73)]
Roman found RR = 0.37 [CI 95%: (0.12, 1.13)]
Roman et al should conclude there’s not enough evidence because they can’t rule out RR >= 1 at 95% confidence.
Instead they conclude:
In comparison to SOC or placebo, IVM did not reduce all-cause mortality, length of
stay or viral clearance in RCTs in COVID-19 patients with mostly mild disease. IVM
did not have effect on AEs or SAEs. IVM is not a viable option to treat COVID-19
patients.
Bryant and Roman use similar methods, the difference in the confidence interval is because they picked different studies.
Bryant has different estimates for mild vs severe vs all cases. 0.38 is for all-cases to allow comparison with Roman batched all-cases together and has no breakdowns.
This third Bayesian (meta-?)meta-analysis concludes:
This Bayesian meta-analysis has shown that the posterior probability for the hypothesis of a
causal link between, Covid-19 severity ivermectin and mortality is over 99%. From the
Bayesian meta-analysis estimates the mean probability of death of patients with severe Covid19 to be 11.7% (CI 12.6 – 34.75%) for those given ivermectin compared to 22.9% (CI 1.83 –
27.62%) for those not given ivermectin. For the severe Covid-19 cases the probability of the
7
risk ratio being less than one is 90.7% while for mild/moderate cases this probability it is
84.1%.
In our view this Bayesian analysis, based on the statistical study data, provides sufficient
confidence that ivermectin is an effective treatment for Covid-19 and this belief supports the
conclusions of (Bryant et al., 2021) over those of (Roman et al., 2021).
The paper has also highlighted the advantages of using Bayesian methods over classical
statistical methods for meta-analysis, which is especially persuasive in providing a transparent
marginal probability distribution for both risk ratio 𝑅𝑅 and risk difference, 𝑅𝐷. Furthermore, we
show that using 𝑅𝐷 avoids the estimation and computational issues encountered using 𝑅𝑅 ,
thus making full and more efficient use of all evidence.
Update:
A recent preprint compares Roman et al and Bryant et al: Bayesian Meta Analysis of Ivermectin Effectiveness in Treating Covid-19 Disease
Summary:
The two studies find similar
RR
(risk reduction as RR=riskivermectinriskcontrol)Bryant found
RR = 0.38 [CI 95%: (0.19, 0.73)]
Roman found
RR = 0.37 [CI 95%: (0.12, 1.13)]
Roman et al should conclude there’s not enough evidence because they can’t rule out RR >= 1 at 95% confidence. Instead they conclude:
Bryant and Roman use similar methods, the difference in the confidence interval is because they picked different studies.
Bryant has different estimates for mild vs severe vs all cases. 0.38 is for all-cases to allow comparison with Roman batched all-cases together and has no breakdowns.
This third Bayesian (meta-?)meta-analysis concludes: