Separating maternal and fetal heart signals from abdominal ECG
The Development and Validation of Maternal and Fetal Electrocardiograms (ECG) Separation Algorithm Based on Artificial Intelligence Application
We will test a computer algorithm that extracts a baby's heartbeat from noninvasive belly ECG recordings in pregnant women during the second and third trimesters.
Quick facts
| Phase | Not applicable |
|---|---|
| Study type | Interventional |
| Enrollment | 350 (estimated) |
| Ages | 18 Years to 55 Years |
| Sex | Female |
| Sponsor | I.M. Sechenov First Moscow State Medical University Academic / other |
| Locations | 1 site (Moscow) |
| Trial ID | NCT07518550 on ClinicalTrials.gov |
What this trial studies
Researchers will collect at least 300 abdominal ECG recordings using wearable textile electrodes from women in their second and third trimesters, with each recording lasting 5–10 minutes under standardized conditions. Signal features will be analyzed by gestational stage and compared with clinical information to characterize maternal and fetal rhythm overlap. Machine learning methods and independent component analysis will be used to develop an adaptive algorithm tuned for trimester-specific physiology, followed by validation on a separate cohort of 50 patients. The goal is to improve the accuracy and reliability of automatic fetal heartbeat detection from noninvasive abdominal recordings.
Who should consider this trial
Good fit: Ideal candidates are pregnant women over 18 years old with a singleton pregnancy in the second or third trimester who can sit for at least 5 minutes and provide informed consent.
Not a fit: Women with multiple pregnancies, severe maternal or fetal conditions, those under 18, or those outside the second and third trimesters are unlikely to benefit from this protocol.
Why it matters
Potential benefit: If successful, the algorithm could enable faster and more accurate noninvasive detection of fetal heartbeats, improving routine fetal monitoring during pregnancy.
How similar studies have performed: Similar methods using independent component analysis and machine learning have shown promising but variable results in extracting fetal ECG noninvasively, and applying these techniques with wearable, trimester-adaptive algorithms is relatively novel.
Eligibility criteria
Show full inclusion / exclusion criteria
Inclusion Criteria: * Age over 18 years * Recordings obtained during the second or third trimester of pregnancy * Recording duration of at least 5 minutes * Singleton pregnancy * Signed informed consent Exclusion Criteria: * Age under 18 years; * Multiple pregnancy; * Recent medical procedures or interventions that could affect the quality of electrocardiographic data; * Severe maternal conditions (e.g., severe eclampsia, shock, severe organ failure, etc.); * Severe fetal conditions (e.g., significant hypoxia, severe placental-fetal syndrome, and other life-threatening states). Exclusion criteria: 1\. Patient's refusal to continue participation in the study.
Where this trial is running
Moscow
- V.F. Snegirev Clinic of Obstetrics and Gynecology of I.M. Sechenov First Moscow State Medical University — Moscow, Russia (Recruiting)
Study contacts
- Principal investigator: Philipp Yu Kopylov, Prof. — I.M. Sechenov First Moscow State Medical University (Sechenov University)
- Study coordinator: Philipp Yu Kopylov, Prof.
- Email: kopylov_f_yu@staff.sechenov.ru
- Phone: +7-903-687-72-64
How to participate
- Review the eligibility criteria above with your treating physician.
- Visit the official trial page on ClinicalTrials.gov for the most current contact information and recruitment status.
- Contact the listed study coordinator or principal investigator to request pre-screening. Pre-screening is free and never obligates you to enroll.