Search results

Approach 3 is what they've done with Vortioxetine trial and it is possible to combine this with approach 1 for point estimates that are higher than the MID. So that would be ok. The thing that doesn't fit is that they themselves claim: "When the point estimate exceeded the MID, we rated...

Yes. GRADE calls it 'little or no effect'. It's a bit beside the point but is described in this paper: Rating certainty when the target threshold is the null and the point estimate is close to the null | BMJ Evidence-Based Medicine If the point estimate is lower than the MID, GRADE finds it...

Rating (im)precision is different from null-hypothesis testing though so wouldn't phrase it like that.

Here's my understanding of the GRADE approach: In study B the point estimate (0.8) is lower than the MID (1) so GRADE recommends rating the evidence of there being NO effect. In that case you cannot chose the null and have to compare to the MID. The confidence interval (0.5-1.1) includes values...

This also doesn't seem correct. The sample size in this CBT trial (114, or 57 per group) is so far of from what GRADE recommends as sufficient for good precision (800 or 400 per group) as a rule of thumb for continuous outcomes. So something has gone wrong here and I it's how they used the CIS...

Thanks for checking. I think Figure 5b. forms an illustrative example. The text says: Zeraatkar says: "we rated certainty of an important effect". That means that they should rate down for imprecision of the confidence intervals cross the MID. Zeraatkar, however, says that they didn't so...

I'm mostly interested in this issue of imprecision which I wrote a blog post on. The authors reply to this point by writing: Perhaps others can check but this seems like a contradiction to me. If you're rating the certainty of an important effect then this means not just any effect that is...

There is a new reply by first author Dena Zeraatkar to previous rapid responses but unfortunately it does not address most of the points raised. https://www.bmj.com/content/387/bmj-2024-081318/rr-12

I think this sentence shows how they view this issue: EDIT: So they think that the biomedical model is causing patients to exaggerate their symptoms. I suspect that might also be the reason why Busse got involved in ME/CFS research and criticised the NICE guidance quite aggressively.

I don't understand because burnout is defined as being work-related. The WHO states: https://www.who.int/news/item/28-05-2019-burn-out-an-occupational-phenomenon-international-classification-of-diseases So this mainly shows that the authors of this study did not understand the concept of...

Yes that seems about 10-20 times too large.

The point was so clear that it seems that Larun et al. are intentionally misrepresenting it.

It states: So: we the reviewers determined that our review is well-conducted?

I also don't get that if the main problem is that the drug is really expensive, then why would you include 86 participants on the drug, and nobody on a placebo (which costs virtually nothing).

The paper states: But as someone pointed out to me on Twitter, table 1 shows that 'no change in symptoms' (n = 17) was more common than 'financially unable' (n = 10). So lack of perceived benefit seems to be the primary, not a secondary reason for dropout?

I also think Carson has never done any research on ME/CFS, yet he has been able to comment as an SMC expert on multiple ME/CFS studies. For example: expert reaction to cytokines for Chronic Fatigue Syndrome | Science Media Centre expert reaction to study linking higher levels of antibodies...

I also don't get this. The only statement I see is: "Evidence that there is a large number of replicated and diverse blood biomarkers that differentiate between ME/CFS cases and controls should now dispel any lingering perception that ME/CFSis caused by deconditioning and exercise intolerance...

Because they controlled the FDR at 0.05, the expected proportions of false positives among the 116 significant features is approximately 6 (not 150).

This method controls the false discovery rate (FDR) at 0.05, which is mentioned multiple times in the paper and graphs. It means that among the significant findings, the expected proportion of false positives (the false discoveries) is only 5%. It's not that complicated and standard in large...

The commentary by Prof Kevin McConway (Emeritus Professor of Applied Statistics) seems quite sensible.