Artificial Intelligence in Acute and Chronic Pulmonary Embolism
Research type
Research Study
Full title
Developing Artificial Intelligence Solutions to Improve Diagnosis and Risk Stratification in Acute Pulmonary Embolism and Chronic Thrombo-Embolic Pulmonary Hypertension
IRAS ID
311735
Contact name
Jonathan Rodrigues
Contact email
Sponsor organisation
Royal United Hospitals Bath NHS Foundation Trust
Clinicaltrials.gov Identifier
Duration of Study in the UK
3 years, 0 months, 1 days
Research summary
Pulmonary Embolism (PE) is a common condition where blood clots cause blockages in the lung arteries; a potentially life-threatening emergency if not noticed early and treated quickly. PE can also cause long-term problems when clots are left behind, a condition called Chronic Thrombo-Embolic Pulmonary Hypertension (CTEPH). CTEPH causes persistent breathlessness and can even be fatal. Potentially life-saving treatments exist; however, diagnosis is frequently very delayed, with many cases missed.
Three key steps in PE management are: 1) prompt diagnosis, 2) assessing risk, 3) picking up long-term complications. CT scans are most commonly used for all three steps.
We aim to use Artificial Intelligence (AI) to make each step faster and more reliable, to improve outcomes for patients.
1. Diagnosis: ‘AIDOC’ detects PE and alerts clinicians immediately, so treatment can be offered quicker.2. Assessing risk: ‘IMBIO’ measures the ratio between lower heart chambers (left and right ventricles). This can indicate increased pressure on the right ventricle. Guidelines recommend that this is measured and reported in every patient with PE to assess risk of deterioration but this is not reliably done currently.
3. Long-term complications: Pulmonary Hypertension Automated Screening Technology (PHAST) measures the width of the pulmonary artery, which carries blood into the lungs. This measurement is recommended to look for CTEPH, but currently is often not provided.
To assess the AI’s impact, we will collect data on patient outcomes for 6 months before AI is made available to doctors, and for 12 months afterwards. Scans will still be reported by human radiologists but AI will run in the background and ensure important findings aren’t missed. We will also collect data on AI’s cost effectiveness and feedback from doctors to ensure it’s helpful.
Separately, we will develop PHAST so that in future Doctors can also use this to assess for long-term complications of PE.
REC name
West of Scotland REC 3
REC reference
23/WS/0067
Date of REC Opinion
3 May 2023
REC opinion
Favourable Opinion