PulseExploreJournal ClubDebatesTrendingResearchersJournals
Instagram
HomeExploreJournal ClubTrending
Synapse
⌘+K
Synapse
April 30, 2014American Journal of Respiratory and Critical Care Medicine203 citations

Outcomes and Statistical Power in Adult Critical Care Randomized Trials

View Full Paper
MHMichael O. HarhayJWJason WagnerSRSarah J. Ratcliffe

Key Points

  • To examine critical methodological challenges concerning statistical power, effect size assumptions, and outcome selection in adult intensive care randomized trials.
  • Assessed adult critical care randomized controlled trials regarding statistical power calculations and mortality endpoint designs.
  • Evaluated methodological practices including patient accrual, baseline event rate estimation, and standardization of clinical outcome assessments.
  • Adult ICU trials frequently yield negative findings because they are powered to detect unrealistically large treatment effects on mortality.
  • Trials commonly demonstrate flawed baseline event rate predictions, inadequate patient enrollment, and unjustified power calculation parameters.

Abstract

ICU-based RCTs are commonly negative and powered to identify what appear to be unrealistic treatment effects, particularly when using mortality as the primary outcome. Additional concerns include a lack of standardized methods for assessing common outcomes, unclear justifications for statistical power calculations, insufficient patient accrual, and incorrect predictions of baseline event rates.

Ask AI
Helpful
Bookmark
Share
View Full Paper

Cite This Study

Harhay et al. (2014) studied this question.

synapsesocial.com/papers/69531e2e1dfba461e51d4bb8https://doi.org/10.1164/rccm.201401-0056cp
Ask AI
Helpful
Bookmark
Share
View Full Paper