AI in PF-ILD
Research type
Research Study
Full title
A retrospective pilot study for the use of artificial intelligence (AI) in the prognostication of progressive fibrotic lung disease (PF-ILD)
IRAS ID
300745
Contact name
Shaney Barratt
Contact email
Sponsor organisation
North Bristol NHS Trust
Duration of Study in the UK
0 years, 6 months, 1 days
Research summary
Progressive pulmonary fibrosis is the term used for a group of progressive (worsening), often fatal, lung diseases, which affect up to 70,000 people in the UK.
Pulmonary fibrosis causes scarring of the lungs, which may worsen over time causing shortness of breath, a cough and tiredness. People suffering with this disease are often very unwell and are at risk of dying. Pulmonary fibrosis progresses differently in individual patients and predicting who is likely to get worse is challenging.
All patients with pulmonary fibrosis routinely undergo a medical imaging technique called high-resolution CT scans (HRCT) as part of their investigation. Radiologists examine HRCT scans but their opinions can differ on the extent and type of disease, limiting the use of HRCT to monitor changes in disease and responses to treatment.
We have designed a study to investigate how specialised computer software can help provide an accurate prediction of how an individual patient’s disease might progress. We hope this information will enable patients and clinicians to make informed decisions regarding drug treatments and supportive therapies. Lung Textural Analysis is a new artificial intelligence (AI) software that has been used in other lung diseases to support the analysis of CT scans to give a quantitative assessment of lung changes. Our study will assess of the role of Lung Textural Analysis in patients with a wide range of progressive lung fibrosis conditions.
We will apply the technology to historical CT scans of patients under the care of North Bristol NHS Trust who have pulmonary fibrosis and who have had a least two CT scans in the last 5 years. These patients will have also undergone lung function tests and exercise testing. Lung Textural Analysis will be used to re-analyse the scans and we will compare the findings with changes in their lung function tests and exercise capacity. This information may help provide a more accurate assessment of the progression of disease.
REC name
N/A
REC reference
N/A