Portable electronic stethoscope and machine-learning detection of heart valve disease
Official title: Clinical Validation of Portable Electronic Stethoscope for Detecting Valvular Heart Disease
Run by The University of Hong Kong · NCT07568795 · Data updated 2026-11-12
We will test whether a portable electronic stethoscope combined with a machine-learning algorithm can accurately detect valvular heart disease in people with known valve problems and in healthy volunteers.
Quick facts
| Study type | Observational |
|---|---|
| Ages | 18 Years and up |
| Sex | All |
| Enrollment | 125 (estimated) |
| Sponsor | The University of Hong Kong Academic / other |
| Locations | 1 site (Hong Kong, Pok Fu Lam Rd.) |
| Status | Recruiting |
| Started | July 3, 2024 |
| Main results expected | August 21, 2024 |
| Study ends | December 31, 2026 |
| Registry record updated | May 6, 2026 |
| Trial ID | NCT07568795 on ClinicalTrials.gov |
Is this trial a fit for you?
✓Likely a good fit
Adults who can give informed consent, have a prior echocardiogram within five years, and either have a diagnosed valvular heart condition or are healthy volunteers willing to attend Queen Mary Hospital are ideal candidates.
✕Probably not a fit
People with mechanical heart valves or adult congenital heart disease are excluded and are unlikely to benefit from this specific algorithm-based detection approach.
A plain-English reading of the study's rules. Only the study team can confirm whether you qualify.
What this trial studies
This observational study records heart sounds with two portable electronic stethoscopes (BPM Core and BeamO) and compares machine-learning algorithm predictions to clinicians' interpretations and echocardiogram results. Participants include 100 patients diagnosed with valvular heart disease and 25 healthy controls recruited at Queen Mary Hospital in Hong Kong. Each participant will undergo echocardiography (within the prior five years), an ECG using the BPM Core device, and auscultation recordings for algorithm analysis. The main outcome is diagnostic agreement and accuracy of the algorithms versus clinician readings and echocardiographic findings.
Why it matters
Potential benefit: If successful, this approach could provide a low-cost, portable screening tool to help detect valvular heart disease earlier and expand access to screening outside specialist centers.
How similar studies have gone: Prior research using electronic auscultation and machine-learning has shown promising but variable accuracy for detecting murmurs and valve lesions, with external validation still limited.
Who can join: the full rules
Show full inclusion / exclusion criteria
Inclusion Criteria: * Voluntarily agrees to participate by proving written informed consent * Have echocardiography done within 5 years Exclusion Criteria: * Mechanical heart valve * Adult congenital heart disease
Where it's running
-
Queen Mary Hospital
Hong Kong, Pok Fu Lam Rd., Hong Kong Recruiting
Study contacts
- Study coordinator: Chun Ka Wong, Clinical Assistant Professor
- Email: wongeck@hku.hk
- Phone: 852 2255 3597
Similar studies
Other studies for the same condition or treatment. Recruiting studies are listed first.
-
Transcatheter Tricuspid Valve Replacement for Severe Tricuspid Regurgitation
This trial tests the Laplace TTVR System to see if it safely and effectively treats adults with severe tricuspid regurgitation.
-
TRIFORMIS RESILIA heart valve real-world results in tricuspid disease
A real-world, observational study to see how the Edwards TRIFORMIS RESILIA tricuspid heart valve performs in adults needing tricuspid valve replacement.
-
Multimodal Cardiac MRI to See How the Heart Is Working
This study tests a comprehensive MRI approach to characterize heart structure and tissue in adults with suspected or confirmed cardiovascular disease.
-
Vyne TriNova Transcatheter Tricuspid Valve Replacement study for severe tricuspid regurgitation
This trial tests the VDyne TriNova system in adults with symptomatic severe tricuspid regurgitation to see if it is safe and helps heart symptoms compared with an alternative device.
-
AI-assisted screening for heart valve disease using routine non-contrast chest CT
This will test whether an AI program can spot moderate-to-severe heart valve disease on routine non-contrast chest CT scans in adults.
-
Global longitudinal strain to predict difficult separation from cardiopulmonary bypass
This will test whether a heart ultrasound measure called global longitudinal strain (GLS) can predict which adults having elective cardiac surgery will have trouble coming off cardiopulmonary bypass.
How to take part
- Review the eligibility criteria above with your treating physician.
- Check the official listing on ClinicalTrials.gov for the latest contact details and recruitment status.
- Contact the study coordinator or principal investigator to ask for pre-screening. Pre-screening is free and never obligates you to enroll.