A London hospital will trial the use of artificial intelligence (AI) software to detect abnormalities in chest X-rays and speed up diagnosis of lung cancer.
The LungIMPACT trial, at University College Hospital (UCLH), will evaluate whether a technology called qXR could help flag up which patients need an urgent assessment before the disease progresses.
Patients flagged up by the system will have their scan reviewed by a radiographer, who can arrange for a same-day CT scan if their X-ray indicates possible lung cancer.
GPs in England request around two million chest X-rays every year. While most X-ray results come back as normal, some can contain early indications of lung cancer.
The qXR system produces a secondary image of each chest X-ray with an overlay to highlight abnormalities.
If the AI detects a problem, this will highlight the X-ray on the reporting worklist so that the radiographer can prioritise this for urgent reporting.
Researchers will evaluate whether use of the AI system can reduce diagnosis times.
More than 43,000 people are diagnosed with lung cancer every year in the UK, according to the NHS.
Just over three-quarters of people (77.5 per cent) of patients were seen by a specialist within two weeks of an urgent suspected cancer referral in July, the latest figures show.
The target is 93 per cent and was last met in May 2020.
The study is co-led by Dr Nick Woznitza, a consultant radiographer at UCLH, and Professor David Baldwin, honorary professor of medicine at Nottingham University Hospitals (NUH) and the University of Nottingham.
Dr Woznitza told the Standard: “The quicker we pick up on any potential anomalies on a chest X-ray, the better.â¯Weâ¯review X-ray results as quickly as possible, but if this technology can help us prioritise who would most benefit from a rapid review of their X-rays, this would help improve outcomes for our patients.”
Prof Baldwin said: “Studies evaluating the clinical impact of AI are urgently needed to ensure the safe and effective implementation that is needed to help the NHS and our patients. Doing these studies is a significant challenge but a worthwhile one.”
