The goal of this observational study is to develop and validate a single-feature artificial intelligence algorithm based on data from a wearable ECG patch in patients with heart failure (HF). The main question it aims to answer is:
Does the algorithm, using synchronized ECG and accelerometer signals from the patch, achieve accurate detection of heart sounds (S1, S2, and in some patients S3, S4) compared to the Eko CORE500 digital stethoscope in patients with acute exacerbation of HF?
Participants with confirmed HF (NYHA class II-IV) will undergo two 2-minute sessions of simultaneous ECG patch and digital stethoscope recordings, followed by standard 12-lead ECG. Data will be used for algorithm training and validation, with the primary endpoint being the sensitivity and specificity of heart sound detection against the reference device.
Age ≥ 18 years old;
Body mass index < 35 kg/m2;
Diagnosed with heart failure: according to "Chinese Guidelines for Diagnosis and Treatment of Heart Failure 2024", "2021 ESC Guidelines for Diagnosis and Treatment of Acute and Chronic Heart Failure", and "2022 AHA/ACC/HFSA Guidelines for Management of Heart Failure";
NYHA classification II - IV;
There are physical disabilities that prevent safe and thorough testing;
There are open wounds on the chest skin or the skin is allergic to the patches;
There is a large amount of pericardial effusion, pericardial tamponade, pleural friction rub, pneumothorax, and a large amount of pleural effusion, which may affect data collection;
The patient has severe comorbidities or unstable condition, which may interfere with data collection during the study period;