A new University of Oxford study will test whether artificial intelligence can speed up and improve the diagnosis of chronic obstructive pulmonary disease (COPD).
Announced on Thursday, the research will evaluate an AI breath test designed to spot the illness in just five minutes, offering an easier option for patients and doctors.
COPD affects about three million people in the UK and is the country’s third biggest killer. It costs the NHS an estimated £1.9 billion each year and contributes to more than 30,000 deaths annually. Despite the scale of the problem, diagnosing COPD remains slow and challenging in many GP surgeries.
The study will examine the N-Tidal Diagnose device, created by HealthTech firm TidalSense. The technology measures carbon dioxide patterns during normal breathing. It then uses AI to interpret those results, giving either a high or low likelihood of COPD within minutes. Researchers want to see how well it works in real-world NHS settings.
Traditionally, COPD is diagnosed through spirometry, a test where patients blow hard into a tube. This process can be uncomfortable and is often hard to perform correctly. It also requires equipment and staff training, which many GP practices lack. As a result, many people with COPD face delays in getting diagnosed and starting treatment.
Dr Helen Ashdown, an NHS GP and academic clinical lecturer at the University of Oxford, is leading the trial. She said the study is a chance to explore how AI can help doctors make better decisions in daily practice. Additionally, she stressed the importance of testing the tool at scale to assess its impact on patients, clinicians, and the wider health system.
Read more: Breath Diagnostics leaders promote their mission at Miami investment conference
Read more: Breath Diagnostics leader speaks at lung cancer education event in Louisville
Goal is to support its adoption across the NHS
The Oxford Community Diagnostic Centre became the first site to recruit patients on 12 September 2025. Other sites across the UK will join over the next 18 months. In total, 24 primary care centres will take part, including GP practices, diagnostic hubs, and community clinics.
The project is part of the larger CORMORANT program, funded by the National Institute for Health and Care Research. It will run as a prospective, multi-centre study, where participating sites integrate the device into routine spirometry appointments. Patients showing possible COPD symptoms will be invited to participate.
Dr Ameera Patel, chief executive of TidalSense, said the study will help validate the device’s safety and performance across a broad population. Furthermore, she noted that the technology already meets EU medical device regulations. The ultimate goal is to support its adoption across the NHS, providing more consistent access to testing and care.
The need is clear. A 2024 Asthma + Lung UK survey found that half of NHS integrated care boards lacked enough spirometry capacity to meet demand. Consequently, many patients face long waits for a test that is already difficult to deliver.
If successful, the AI breath test could transform how doctors identify COPD and ensure patients receive help sooner.
Companies are increasingly turning to breath analysis as a non-invasive diagnostic tool.
By detecting biomarkers in exhaled breath, firms aim to improve early detection of diseases ranging from cancer to respiratory illness.
Owlstone Medical, for example, develops breath biopsy technology for cancer and asthma research, while Breath Diagnostics Inc’s OneBreath platform analyzes volatile organic compounds to identify conditions like lung cancer and pneumonia.
.
