The ACCEPT-AI study is a multicenter trial designed to evaluate Qure.ai’s qER software for identifying and prioritizing critical findings in non-contrast head CT (NCCT) scans in emergency departments (EDs). Conducted over 13 months across four diverse sites, the study will include all adult ED patients referred for NCCT. Using a stepped-wedge design, the trial consists of three phases: pre-implementation (baseline data collection), implementation (staff training and AI threshold adjustments), and post-implementation (integrating AI notifications in the radiology system for radiologist validation). The study aims to assess AI’s impact on workflow efficiency, diagnostic accuracy, and patient care amid radiology workforce shortages. Ethical approval was granted by the East Midlands Research Ethics Committee (REC 23/EM/0108) in May 2023, and findings will be disseminated through peer-reviewed publications and scientific conferences (ClinicalTrials.gov: NCT06027411).
Published 30 Apr 2024
Assessing the effectiveness of artificial intelligence (AI) in prioritising CT head interpretation: study protocol for a stepped-wedge cluster randomised trial (ACCEPT-AI)
Author: Kavitha Vimalesvaran,
Dennis Robert,
Shamie Kumar,
Ayan Kumar,
Mariapola Narbone,
Rahul Dharmadhikari,
Mark Harrison,
Sarim Ather,
Alex Novak,
Mariusz Grzeda,
Jane Gooch,
Nicholas Woznitza,
Mark Hall,
Haris Shuaib,
David J Lowe
