Endgames Statistical Question

How to read a Kaplan-Meier survival plot

BMJ 2014; 349 doi: https://doi.org/10.1136/bmj.g5608 (Published 12 September 2014) Cite this as: BMJ 2014;349:g5608
  1. Philip Sedgwick, reader in medical statistics and medical education1
  1. 1Institute for Medical and Biomedical Education, St George’s, University of London, London, UK
  1. p.sedgwick{at}sgul.ac.uk

Researchers investigated the effectiveness of larval therapy for the treatment of sloughy or necrotic leg ulcers. A three armed randomised controlled trial study design was used. The intervention consisted of loose larvae or bagged larvae. The control treatment was the standard debridement technique of hydrogel. Participants had at least one venous or mixed venous and arterial ulcer, with at least 25% coverage of slough or necrotic tissue. The outcome measures included time to healing of the largest eligible ulcer and time to debridement (defined as a cosmetically clean wound) after the ulcer healed. The maximum length of follow-up was 12 months.1

In total, 267 participants were recruited and randomised to loose larvae (n=94), bagged larvae (n=86), or hydrogel (n=87). Healing rates did not differ between the loose and the bagged larvae arms, so the results were presented for larvae overall (loose and bagged larvae arms combined). Time to healing was not significantly different between the larvae groups (combined) and hydrogel treatment groups (hazard ratio for healing using larvae v hydrogel 1.13, 95% confidence interval 0.76 to 1.68; P=0.54). Larval therapy significantly reduced the time to debridement compared with hydrogel (hazard ratio 2.31, 1.65 to 3.2; P<0.001; figure). It was concluded that larval therapy did not improve the rate of healing of sloughy or necrotic leg ulcers compared with hydrogel but did significantly reduce the time to debridement.

Kaplan-Meier plot of time to debridement of ulcer using larval therapy (loose and bagged combined) compared with hydrogel. The median survival time for each treatment group is the length of time corresponding to the probability of 0.5

Which of the following statements, if any, are true?

  • a) If a patient did not experience debridement during follow-up, their observation would be “censored”

  • b) Participants were excluded from the analyses if they did …

View Full Text

Sign in

Log in through your institution

Free trial

Register for a free trial to thebmj.com to receive unlimited access to all content on thebmj.com for 14 days.
Sign up for a free trial