Tests AI heart tracing tools for detecting structural heart disease
Tests AI analysis of ECG recordings to detect heart valve, failure or lung pressure problems.
Key facts
- Who runs it
- Imperial College London
- Where
- Bristol and London, United KingdomSee the 6 sites
- Trial code
- Registry title
- Prospective Evaluation of AI-ECG for SHD Detection
- Status
- Recruiting
- People taking part
- 590 people, planned
- Started
- 4 Nov 2025
- Expected to end
- 2 Aug 2027
- Type of study
- Observational, 2 groups
- Treatments tested
- Traditional 12-lead Electrocardiogram
- Apple Watch Series 4 Single-lead Electrocardiogram
- Eko Core 500 Digital Stethoscope 3-lead Electrocardiogram
- AliveCor KardiaMobile Single- and 6-lead Electrocardiogram
- Phlebotomy for N-terminal pro-B-type natriuretic peptide
- Record updated
- 8 October 2026
Who can take part
AI summary
From the trial's eligibility criteria. Machine-read from the registry text on this page, so it can be wrong. The registry text below and the trial team decide who can take part.
The trial is looking for adults aged 18-90 who are waiting for a heart ultrasound (echocardiogram) as part of their normal care. It tests whether AI reading of ECG recordings can spot structural heart disease.
- Age
- 18-90 years
- Sex
- All sexes can join.
- Disease stage
- Adults who are awaiting a transthoracic echocardiogram on clinical grounds. People with known severe structural heart disease cannot join.
- Earlier treatment
- No previous structural heart procedure such as valve repair, valve replacement or surgical repair of a heart chamber or a congenital structural abnormality.
Main reasons for not taking part
- Severe arrhythmia or unstable cardiovascular disease
- Known severe structural heart disease (for example LVEF ≤35% or severe valve disease)
- A pacemaker or implantable cardioverter defibrillator in place
- Current or recent involvement in another research study
- Not able to give informed consent
The registry criteria, word for word
Show all 7 criteriaShow less
Who can take part
- Patients awaiting a transthoracic echocardiogram (TTE) based on clinical grounds as part of their standard care
- Age 18-90 years
- Able to provide informed consent
Who cannot take part
- Severe arrhythmia or unstable cardiovascular disease
- Cardiac implantable electronic device in situ, including a permanent pacemaker or implantable cardioverter defibrillator
- Known severe structural heart disease, defined as any of the following: severe left ventricular systolic dysfunction (LVEF ≤35%); severe valvular heart disease according to current British Society of Echocardiography criteria; high echocardiographic probability of pulmonary hypertension according to current British Society of Echocardiography criteria; or previous structural cardiac intervention, including valve repair, valve replacement/implantation, or surgical repair of a cardiac chamber or congenital structural abnormality
- Current or recent involvement in another research study
Check if you might fit
Answer for yourself. This is not a decision: only the study team can say whether you can take part.
- Are you between 18 and 90 years old?
Where in United Kingdom
- Bristol Royal InfirmaryBristol, United KingdomContact: Ahmed YM El-Medany, MBChB, MRCP, MSc, FHEATaking people
- Southmead HospitalBristol, United KingdomContact: Ahmed YM El-Medany, MBChB, MRCP, MSc, FHEATaking people
- Chelsea And Westminster HospitalLondon, United KingdomContact: Ahmed YM El-Medany, MBChB, MRCP, MSc, FHEATaking people
- Hammersmith HospitalLondon, United KingdomContact: Ahmed YM El-Medany, MBChB, MRCP, MSc, FHEATaking people
- St Mary's HospitalLondon, United KingdomContact: Ahmed YM El-Medany, MBChB, MRCP, MSc, FHEATaking people
- West Middlesex University HospitalLondon, United KingdomContact: Ahmed YM El-Medany, MBChB, MRCP, MSc, FHEATaking people
About the trial
What the trial wants to find out
AI-ECG-SHD is a multicentre prospective observational diagnostic accuracy study evaluating artificial intelligence-enhanced electrocardiography (AI-ECG) for the detection of structural heart disease in adults undergoing clinically indicated transthoracic echocardiography (TTE).
Read full original descriptionShow less
Participants undergo standard 12-lead ECG acquisition together with ECG recordings obtained using portable or wearable single-, 3-, and 6-lead devices. Established AI-ECG models will be evaluated for the detection of heart failure, pulmonary hypertension and valvular heart disease using TTE as the clinical reference standard, with performance compared across ECG acquisition modalities within the same prospective cohort.
AI-ECG predictions are generated offline and are not provided to treating clinicians or used to alter clinical care. The study will also compare AI-ECG performance with N-terminal pro-B-type natriuretic peptide (NT-proBNP) and evaluate the diagnostic performance of a combined AI-ECG and NT-proBNP approach.
The study aims to recruit 590 participants across six NHS hospital sites. A prespecified subgroup of 203 participants will undergo dedicated venous blood sampling for NT-proBNP; eligible same-day NT-proBNP measurements obtained as part of routine clinical care will also be included where available.
The 2 groups in the trial
- Echocardiography cohort
Adult inpatients and outpatients undergoing transthoracic echocardiography (TTE) as part of routine clinical care will be recruited prospectively. Participants will undergo study-specific 12-lead ECG acquisition and portable or wearable single-, 3-, and 6-lead ECG recordings. Patients with known severe structural heart disease are excluded, while patients with previously diagnosed structural abnormalities that do not meet the prespecified severe structural heart disease exclusion criteria may remain eligible. AI-ECG predictions will be generated offline and will not inform clinical care.
Treatment: Traditional 12-lead Electrocardiogram, Apple Watch Series 4 Single-lead Electrocardiogram, Eko Core 500 Digital Stethoscope 3-lead Electrocardiogram, and AliveCor KardiaMobile Single- and 6-lead Electrocardiogram
- N-terminal pro B-type natriuretic peptide subgroup
A prespecified subgroup of 203 participants from the overall 590-participant cohort will be selected by stratified randomisation to undergo dedicated venepuncture for measurement of serum NT-proBNP. In addition, eligible same-day NT-proBNP measurements obtained as part of routine clinical care will be included in the NT-proBNP analysis where available. The final NT-proBNP analysis population may therefore exceed the dedicated 203-participant phlebotomy subgroup.
Treatment: Traditional 12-lead Electrocardiogram, Apple Watch Series 4 Single-lead Electrocardiogram, Eko Core 500 Digital Stethoscope 3-lead Electrocardiogram, AliveCor KardiaMobile Single- and 6-lead Electrocardiogram, and Phlebotomy for N-terminal pro-B-type natriuretic peptide
Questions to ask the study team
- How often do I need to come in, and for how long each time?
- Are travel costs paid?
- Can I keep my own doctor?
- What happens if I want to stop?
Contact the study team: see the registry record → Contacts and Locations
Print a page for my doctorData and sources
- Registry record
- Listed on ClinicalTrials.gov.
- Official title
- Prospective Evaluation of Artificial Intelligence-enhanced Electrocardiography for Detection of Structural Heart Disease
- Plain-language title
- Tests AI heart tracing tools for detecting structural heart diseaseGenerated from the registry record. The registry title is the official one.
- AI summary
- From the trial's eligibility criteria. Read by machine on 12 November 2026.
- Fit questions
- Built from NCT07057466, who can take part
- Record updated
- 8 October 2026