Deep Learning-Based Wearable Device Study Using Heart Sound and ECG Data for Screening Depressed Heart Function

What this Trial Is About

Researchers are studying a new wearable device that combines synchronized phonocardiography (PCG) and electrocardiogram (ECG) to help diagnose depressed left ventricular ejection fraction (dLVEF), a form of heart failure where the heart's pumping ability is reduced (ejection fraction less than 50%). This device aims to speed up diagnosis, reduce the need for costly ultrasound tests, and improve access to life-saving therapies by using artificial intelligence (AI) to analyze the collected heart sound and electrical data. The wearable cardiac patch wirelessly pairs with the WenXin Mobile application, allowing simultaneous recording and viewing of PCG and ECG signals. This study is a case-control design involving adults aged 18 to 100 years who are scheduled for ultrasound cardiography (UCG). The AI system will be developed by creating machine learning algorithms that learn from the synchronized PCG and ECG data of patients with dLVEF and then use these algorithms to identify such patients in clinical practice. Participants will have their heart failure status assessed once at the start of the study. The device collects acoustic and electrical heart data during regular care visits, and participants must have completed UCG and be able to record at least 8 consecutive cycles of sinus rhythm. The study involves cooperation with research procedures and informed consent. The main outcome is the determination of heart failure disease using the wearable device and AI analysis.

Artificial Intelligence (AI) Analysis of Synchronized Phonocardiography (PCG) and Electrocardiogram(ECG)