Skip to main content
Indian Journal of Critical Care Medicine : Peer-reviewed, Official Publication of Indian Society of Critical Care Medicine logoLink to Indian Journal of Critical Care Medicine : Peer-reviewed, Official Publication of Indian Society of Critical Care Medicine
. 2014 Jan;18(1):51. doi: 10.4103/0972-5229.125445

Authors’ reply

Bhuvana Krishna 1,✉, Sriram Sampath 1, John L Moran 1
PMCID: PMC3912675  PMID: 24550620

Sir,

The points mentioned in the letter[1] are well taken. Random effects analyses are preferable and the risk ratios have indeed been calculated using a random effect estimator for binary outcomes as mentioned in the methods section.

We had carried out sensitivity analyses excluding earlier studies with poorer quality scores and the results did decrease the heterogeneity and revealed the beneficial effects of prophylactic non-invasive positive pressure ventilation more clearly. There were three studies with lower study quality. We have not shown these sensitivity analyses separately as they did not change the overall message. Rather than cherry picking to show a robust result we have arranged the forest plot chronologically and it can be seen that the more recent studies with higher quality are in the same direction as the pooled relative risk despite the weightage of the earlier study.

Chronic obstructive pulmonary disease and congestive heart failure are clinically important covariates and we have explored the effects of these with meta-regression; rather than show multiple sensitivity analyses.

Reference


Articles from Indian Journal of Critical Care Medicine : Peer-reviewed, Official Publication of Indian Society of Critical Care Medicine are provided here courtesy of Indian Society of Critical Care Medicine

RESOURCES