Skip to content

Development of A Novel Artificial Intelligence Method for Recognition of Atrial Fibrillation During Electrocardiographic Monitoring

Development of A Novel Artificial Intelligence Method for Recognition of Atrial Fibrillation During Electrocardiographic Monitoring

Status
Recruiting
Phases
Early Phase 1
Study type
Observational
Source
ChiCTR
Registry ID
ChiCTR2000029310
Enrollment
Unknown
Registered
2020-01-23
Start date
2020-05-25
Completion date
Unknown
Last updated
2021-06-07

For informational purposes only — not medical advice. Sourced from public registries and may not reflect the latest updates. Terms

Conditions

Atrial Fibrillation

Interventions

Training group:none

Sponsors

Department of Cardiovascular Surgery, General Hospital of Northern Theater Command
Lead Sponsor

Eligibility

Sex/Gender
All
Age
18 Years to 80 Years

Inclusion criteria

Inclusion criteria: 1. Adults aged 18 to 80 years; 2. Non-urgent or non-emergent off-pump coronary artery bypass grafting surgery (CABG) surgery and valvular surgery; 3. Left ventricular EF > 40%; 4. Patients undergoing heart surgery for the first time; 5. No history of adult congenital heart disease or valvular disease; 6. Good compliance and ability to complete follow-up; 7. Epicardial leads were implanted during hospitalization.

Exclusion criteria

Exclusion criteria: 1. History of prior cardiac surgery; 2. Heart surgery was accompanied by surgery of other organ system; 3. Liver and kidney function abnormality (results exceed the upper limit of normal value by 3 times); or with CABG or valvular surgery contraindications; 4. Patients suffering from other diseases who require radiotherapy, or chemotherapy, and/or long-term hormone treatment; 5. Patients who declined to consent to the surgical procedure; 6. Patient who were unable to have epicardial leads implanted during hospitalization; 7. Patients in need of other critical cares that the data collection became inconvenient or not applicable such as those requiring pressor agents or antiarrhythmic drugs.

Design outcomes

Primary

MeasureTime frame
Artificial intelligence based atrial fibrillation diagnostic performance;F1 score, Precision, Positive predictive value (PPV), Recall, Sensitivity, Specificity, False positive ratio (FNR), False negative ratio (FNR), Negative predictive value (NPV), Area under ROC curve (AUC);

Secondary

MeasureTime frame
Construct a novel database for computer-aided AF diagnosis by collecting surface ECG and its concurrent cardiac atrial epicardial signals (EGM) as TRUE AF diagnosis;

Countries

China

Contacts

Public ContactHui-Shan Wang

Department of Cardiovascular Surgery, General Hospital of Northern Theater Command

huishanwang@hotmail.com+86 13309885095

Outcome results

None listed

Source: ChiCTR (via WHO ICTRP) · Data processed: Feb 4, 2026