Artificial Intelligence in the Diagnosis of Pulmonary Hypertension
Research type
Research Study
Full title
The Role of Artificial Intelligence Techniques in Electrocardiogram (ECG) and Echocardiogram in Pulmonary Hypertension
IRAS ID
298343
Contact name
Daniel Augustine
Contact email
Sponsor organisation
Research and Development Department, Royal United Hospitals Bath NHS Foundation Trust
Duration of Study in the UK
10 years, 0 months, 0 days
Research summary
Pulmonary hypertension (PH) is a condition caused by high blood pressure in the blood vessels that carry blood to your lungs; it can cause severe breathlessness and failure of the right side of the heart. Sadly it is often fatal. PH can be caused by a number of different conditions and life expectancy varies with the underlying cause, ranging from months to years. For some subtypes of PH, effective treatments exist which can significantly improve life expectancy and quality of life. Accurate tools for the assessment of PH are therefore essential, so that we can better understand and predict life expectancy and so that life-saving medications can be started earlier.
Once Doctors suspect that somebody has PH, they refer them to a specialist PH centre for assessment and a procedure called right heart catheterisation (RHC), which will confirm the diagnosis. However, evidence for the suspicion of PH is frequently overlooked, leading to an average delay to diagnosis from onset of symptoms of 2-4 years. This late presentation negatively impacts survival for these patients and prevents them promptly starting the effective treatments which are available.
Electrocardiogram (ECG) and echocardiogram (echo) are quick, safe and well-tolerated tests which are often requested to investigate breathless patients and which can provide useful information about the suspicion of PH. However, outside of specialist PH centres, doctors may not routinely look for and comment on the presence of clues to possible PH on ECG or echo. We think that using Artificial Intelligence (AI) techniques to read the ECGs and Echos could make their interpretation faster and more reliable, to improve outcomes for patients and reduce the time to diagnosis. Also, there may be subtle clues to the presence or severity of PH on ECG or Echo, less recognisable to the human eye, which AI can identify.
REC name
South West - Frenchay Research Ethics Committee
REC reference
22/SW/0055
Date of REC Opinion
14 Apr 2022
REC opinion
Favourable Opinion