AI-powered single-feature heart sound detector for heart failure patients
Official title: Development and Application of a Single-Feature Recognition Model for Heart Failure With Artificial Intelligence-Optimized Algorithms
Run by Vivalink · NCT07667452 · Data updated 2026-11-12
A machine-learning tool using wearable ECG patches tests whether it can reliably identify heart sounds (S1, S2, and sometimes S3/S4) in adults with heart failure.
Quick facts
| Study type | Observational |
|---|---|
| Ages | 18 Years and up |
| Sex | All |
| Enrollment | 50 (estimated) |
| Sponsor | Vivalink Industry-sponsored |
| Locations | 1 site (Hangzhou, Zhejiang) |
| Status | Recruiting |
| Started | July 16, 2026 |
| Main results expected | February 28, 2027 |
| Study ends | May 31, 2027 |
| Registry record updated | July 21, 2026 |
| Trial ID | NCT07667452 on ClinicalTrials.gov |
Is this trial a fit for you?
✓Likely a good fit
Adults 18 or older with NYHA II–IV heart failure.
✕Probably not a fit
Patients with conditions that prevent chest skin contact or cause data collection interference may not benefit.
A plain-English reading of the study's rules. Only the study team can confirm whether you qualify.
What this trial studies
This observational, single-center study collects synchronized data from wearable ECG patches and a digital stethoscope to train and validate a small-feature AI that detects heart sounds. Participants with NYHA II–IV heart failure will undergo a 2-minute paired recording session, then standard ECG, followed by another 2-minute session to build a dataset for algorithm development. The primary outcome is how accurately the AI-identifies heart sounds from the wearable patch data compared with the Eko CORE 500 stethoscope. The study uses training and validation phases to assess performance in acute HF settings and may inform future remote monitoring approaches.
Why it matters
Potential benefit: If successful, the approach could enable reliable, wearable-based heart sound monitoring for HF patients.
How similar studies have gone: Previous work with wearable patches and AI for cardiac signals shows promise, but this exact single-feature approach is relatively novel.
Who can join: the full rules
Show full inclusion / exclusion criteria
Inclusion Criteria: * Age ≥ 18 years old; * Body mass index (BMI) \< 35 kg/m²; * Diagnosed with heart failure: according to "Chinese Guidelines for Diagnosis and Treatment of Heart Failure in 2024", "ESC Guidelines for Diagnosis and Treatment of Acute and Chronic Heart Failure in 2021", and "AHA/ACC/HFSA Guidelines for Management of Heart Failure in 2022"; * NYHA classification II - IV; * Able to fully understand the purpose and process of the trial, and willing to sign the informed consent form. Exclusion Criteria: * Physical disabilities that prevent safe and thorough testing; * Open wounds on the chest or the skin is allergic to the patches; * Large amount of pericardial effusion, pericardial tamponade, pleural friction rub, pneumothorax, and a large amount of pleural effusion, which may affect data collection; * Patients with severe comorbidities or unstable conditions, which may interfere with data collection during the study period; * Other situations where the investigator believes the subject is not suitable to participate in this trial, such as those that may increase trial risk, affect the protocol compliance, or impair the subject's ability to complete the trial due to physical or psychological diseases or conditions.
Where it's running
-
Second Affiliated Hospital, School of Medicine, Zhejiang University
Hangzhou, Zhejiang, China Recruiting
Similar studies
Other studies for the same condition or treatment. Recruiting studies are listed first.
-
Mitral Valve Edge-to-Edge Repair for exercise-induced severe mitral regurgitation in heart failure patients
This trial tests whether adding mitral valve TEER to standard heart failure treatment helps people with exercise-triggered severe mitral regurgitation feel better and stay healthier.
-
Understanding Exacerbations in Heart Failure: Monitoring with Apple Watch
This study tests whether data from an Apple Watch, combined with clinical information, can help predict worsening heart failure in adults living with the condition.
-
Using urine sodium to guide IV diuretic dosing for hospitalized acute heart failure
This trial will test whether increasing IV diuretic doses to reach higher urine sodium levels helps hospitalized adults with acute decompensated heart failure remove more salt and fluid and have fewer readmissions.
-
Can liver stiffness testing help detect high central venous pressure in heart failure patients
A non-invasive FibroScan test is being used to see if liver stiffness can indicate elevated central venous pressure in adults with heart failure.
-
Left bundle branch area pacing versus conventional cardiac resynchronization therapy for heart failure
This study will test whether left bundle branch area pacing (LBBAP) works as well as or better than conventional cardiac resynchronization therapy (CRT) in adults with NYHA II–IV heart failure and reduced ejection fraction who are receiving a CRT‑D device.
-
Wearable chest patch that monitors heart mechanics for people with heart failure
This project will try a small wearable chest patch that records heart movement (seismocardiography) and ECG to see if it can detect early worsening in adults with NYHA class II–IV heart failure.
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.