Can Artificial Intelligence help diagnose lung cancer faster?
New research into faster diagnosis of lung disease
NUH is one of seven hospitals in England to begin research into artificial intelligence software which could speed up the diagnosis of lung cancer.
The software works by identifying unusual signs from a routine chest X-ray within minutes, so that patients who may have signs of lung cancer can be offered a CT-scan on the same day.
The LungIMPACT trial will evaluate AI technology called qXR which is designed to spot potential abnormalities on chest X-rays.
The AI system, developed by the company Qure.ai, is designed to flag which patients would benefit from an urgent review of their scan by a radiographer, who can arrange for a same-day CT scan.
In the study, the AI system will produce a secondary image for each chest X-ray to highlight certain abnormalities. If the AI detects a problem, the patient's X-ray will be flagged up so that an uregnt scan can be provided. The research team will evaluate whether use of this AI technology can successfully bring down time diagnosis times.
Professor David Baldwin, Chair of NHS England’s Clinical Expert Group for Lung Cancer and a respiratory consultant at NUH, who is leading the trial, said: “Speed of diagnosis is critical to achieve the best outcomes in lung cancer and to reduce stress and worry for patients. 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.”
This study was commissioned and funded by the NHS Cancer Programme, with the support of SBRI Healthcare and the NHS Accelerated Access Collaborative.
How do I take part?
For the study, the qXR software will analyse chest X-rays of adult patients referred to NUH by their GPs. Patients's chest X-rays will be randomly assigned to the research, so that the research team can compare the normal diagnosis with the x-rays that use AI.
