Use of Determine Learning-based Cardiodynamicsgram (CDG) for Rapid and Precise Stratification of Chest Pain in Emergency Department

Qilu Hospital of Shandong University8,000 enrolled

Overview

Chest pain accounts for 10-20 percent of all emergency department visits. The stratification of chest pain is always a challenge. Electrocardiograms (ECG) have been used in clinical practice for 100 years, which is too important to be replaced due to its advantages of non-invasive, simple, rapid and inexpensive. ECG contains numerous signals derived from depolarization and repolarization of cardiomyocytes. However, the interpretation of ECG hasn't improved much in a hundred years. Based on determine-learning, Cong W's team developed an technique called "cardiodynamicsgram (CDG)", which is an outstanding method to identify myocardial ischemia. This study will further investigate the accuracy of CDG in stratification of patients with chest pain in Emergency department.

Study Type

OBSERVATIONAL

Enrollment

8,000

Conditions

Chest Pain Acute Coronary Syndrome

Interventions

Cardiodynamicsgram (CDG)OTHER

Cardiodynamicsgram (CDG) technique

Eligibility

Sex: ALLMin age: 18 Years

Medical Language ↔ Plain English

Inclusion Criteria: * aged 18 years or older * Those with suspected ACS who have symptoms of acute chest pain, visiting in the emergency department Exclusion Criteria: * Those who diagnosed with ST-segment elevation myocardial infarction (STEMI) * Those with hemodynamic instability (cardiogenic shock, cardiac arrest) * Those with malignant arrhythmias(ventricular tachycardia, ventricular fibrillation, third-degree atrioventricular block) * Those with aortic coarctation, or acute pulmonary embolism * Those who has an unanalysable ECG report due to loosened leads, unstable baseline, or signal interference, etc.

Outcomes

Primary Outcomes

The efficacy of CDG in the risk stratification of patients who have symptoms of acute chest pain suspected with acute coronary syndrome （ACS)

Establishing an algorithm model of CDG in risk stratification in chest pain patients, the efficacy of the model was assessed by sensitivity, specificity, accuracy, positive predictive value, negative predictive value, and AUC, etc.

Time frame: from the date of enrollment until the date of discharge, up to 30 days