Artificial intelligence supported clinician review of chest x-rays from patients with suspected lung cancer

Artificial intelligence (AI) can be used to support clinicians with reviewing chest x-ray (CXR) images from patients with suspected lung cancer following referral from primary care. The intended use of AI in the clinical pathway is to read and flag higher risk CXR images so that clinicians can prioritise patients for urgent computerised tomography (CT).

The evidence for the use of AI supported clinical review of CXRs for patients with suspected lung cancer is emerging. No published evidence on the clinical effectiveness, cost-effectiveness, or safety of the AI use case was identified. No studies were identified that captured patient or staff views on the use of AI in this setting.

Interim analysis (n=41 reaching diagnosis stage, n=27 reaching treatment stage) from an ongoing service evaluation in NHS Grampian shows that use of AI alongside an adjusted clinical pathway shows promise in reducing time from CXR report to CT, reducing time to treatment, and increasing the identification of patients with treatable lung cancers.

We found limited or no published evidence on the clinical effectiveness, cost effectiveness, safety or patient and staff experience of artificial intelligence (AI)-assisted clinician review of chest X-rays (CXR) for patients with suspected lung cancer.

A 12-month service evaluation in NHS Grampian that used AI calibrated to match their pathway capacity indicated that:

• AI-assisted clinician review of CXRs as part of a clinical pathway change can support radiology workload prioritisation (for example, the triaging of urgent suspicion of cancer scans) and reduce time to CT scanning.
• AI-assisted clinician review of CXRs as part of a clinical pathway change may lead to quicker time to treatment and earlier identification of patients with treatable lung cancer, but the results are inconclusive.

Our resource impact analysis of the diagnostic pathway found that AI-assisted clinician review of CXRs incurred additional costs compared with the traditional radiology pathway, based on pathway changes as part of NHS Grampian’s service evaluation.

Ongoing research studies in the United Kingdom (UK), due for completion in the next 12 months, are expected to contribute meaningfully to the evidence base on clinical and cost effectiveness, AI performance and patient and staff experiences. One ongoing study is being conducted in NHS Greater Glasgow and Clyde (GGC), with data expected after study completion in April 2025.

NHSScotland may wish to consider commissioning a national evaluation to determine how the use of diagnostic AI tools could best add value in an agreed optimised national diagnostic pathway.

Future contributors to the evidence base should use our Evidence Framework for collecting relevant data to guide decision making, as well as research and evaluation recommendations for the topic outlined by the National Institute for Health and Care Excellence (NICE).