Responses

Download PDFPDF

Non-inferiority trials in cardiology: what clinicians need to know
Compose Response

Plain text

  • No HTML tags allowed.
  • Web page addresses and e-mail addresses turn into links automatically.
  • Lines and paragraphs break automatically.
Author Information
First or given name, e.g. 'Peter'.
Your last, or family, name, e.g. 'MacMoody'.
Your email address, e.g. higgs-boson@gmail.com
Your role and/or occupation, e.g. 'Orthopedic Surgeon'.
Your organization or institution (if applicable), e.g. 'Royal Free Hospital'.
Statement of Competing Interests

PLEASE NOTE:

  • Responses are moderated before posting and publication is at the absolute discretion of BMJ, however they are not peer-reviewed
  • Once published, you will not have the right to remove or edit your response. Removal or editing of responses is at BMJ's absolute discretion
  • If patients could recognise themselves, or anyone else could recognise a patient from your description, please obtain the patient's written consent to publication and send them to the editorial office before submitting your response [Patient consent forms]
  • By submitting this response you are agreeing to our full [Response terms and requirements]

Vertical Tabs

Other responses

Jump to comment:

  • Published on:
    Response to letter to the editor
    • Dominic Y Leung, Cardiologist Liverpool Hospital, University of New South Wales

    We thank Dr Althouse for his letter and the interests in our article and for taking time to send us his comments. We appreciate it very much.

    In Figure 1, in scenario C, we incorporated the findings of “equivalence” in cases of equivalence trials. We stated in the article under the section of “Equivalence trials versus non-inferiority trials” that, in equivalence trials, the significance level is set as a two-sided p value of 0.05. We agree that, in non-inferiority trials, a one-sided p value of 0.025 is usually set as the significant level, although in some non-inferiority trials in cardiology, a significance level of one-sided p value of 0.05 was used. This is also mentioned under the same section. We have considered using a separate figure in the submission. However, we decided to submit a single figure as the separate figure incorporating only equivalence trials may be too simple and not the focus of the discussion.

    In scenario E, the lower limit of the confidence intervals is below 1 and the upper limit of the confidence interval is above the non-inferior margin. Therefore, the null hypothesis that the new treatment is inferior to standard treatment cannot be rejected and the alternative hypothesis that the new treatment is non-inferior to standard treatment cannot be accepted. We agree that the interpretation is more correctly stated as “New treatment not non-inferior to standard treatment”. Alternatively, as Dr Althouse suggested “New treatment...

    Show More
    Conflict of Interest:
    None declared.
  • Published on:
    Correction on Figure 1

    I submit this comment on the recent publication by Leung et al entitled “Non-inferiority trials in cardiology: what clinicians need to know” (1) which I believe has a slight error that merits correction.

    On Figure 1 in the original publication, the label says that Result E shows “New treatment inferior” but that is not a correct interpretation. The text in the footnote (“the upper bound of the 95% CI exceeds the predetermined non-inferior margin. Therefore, the new treatment is inferior to standard treatment”) is also incorrect. The data shown in Result E are not sufficient to declare a non-inferiority hypothesis met (the upper limit of the CI for relative risk is above the non-inferiority margin) but nor are they sufficient to declare the new treatment inferior (the lower limit of the CI for relative risk is below the null value). Therefore, the correct label for Result E is “New treatment neither inferior nor non-inferior.” The new treatment would only be declared inferior to the standard treatment in cases F and G (where the lower limit of the 95% CI for relative risk is above the null).

    REFERENCE

    1. Leung JT, Barnes SL, Lo ST, Leung DY. Non-inferiority trials in cardiology: what clinicians need to know. Heart 2019 [epub ahead of print]

    Conflict of Interest:
    None declared.