Tuesday, December 3 | 8:00 a.m.-8:10 a.m. | T1-SSCH05-1 | E451A
In this presentation, researchers from the U.K. will discuss the impact of AI triage on chest x-rays for the purpose of accelerating lung cancer diagnosis.
The LungIMPACT study is a large, randomized control trial underway across five geographically diverse distinct hospital sites in England. The study incorporates AI prioritization of abnormal chest x-rays for clinician review versus standard reporting (with AI available).
Nick Woznitza, PhD, consultant radiographer and clinical academic at University College London Hospitals NHS Foundation Trust and Canterbury Christ Church University, will present and explain findings so far, along with David Baldwin, MD, chair of NHS England’s Clinical Expert Group for Lung Cancer and a respiratory consultant at Nottingham University Hospitals, cardiothoracic radiologist Indrajeet Das, MD, and others.
As of April 2024, researchers had randomized 46,360 chest x-rays, with a goal to randomize 78,220 by trial close, according to the session preview abstract. The team noted that the LungIMPACT trial is the largest multisite randomized trial of chest x-ray AI for lung cancer and was identified as one of the “11 clinical trials to shape medicine in 2024” by Nature Medicine.
Among the results to come, a health economic evaluation will estimate the cost-effectiveness of CXR AI in lung cancer diagnosis, including the difference in costs per patient screened, cost per patient diagnosed, and costs per percentage increase in early diagnosis.
Full results are expected soon. If positive results bear out, they could support a change in practice to include AI for lung chest x-rays in lung cancer detection. If not, it would warrant a better evaluation of AI products before they can be introduced into routine practice, according to the researchers.
Gain perspective on LungIMPACT and more about AI analysis of chest x-rays during this talk.