AI-guided chest compressions for personalized CPR

Utilizing Artificial Intelligence to Optimize Chest Compression Region During Cardio-pulmonary Resuscitation for Patients With Out-of-hospital Cardiac Arrest.

Observational Far Eastern Memorial Hospital · NCT07431710

This project will test an AI app that analyzes arterial pressure waveforms to guide where rescuers compress the chest for adults with out-of-hospital cardiac arrest.

Quick facts

Study typeObservational
Enrollment255 (estimated)
Ages20 Years and up
SexAll
SponsorFar Eastern Memorial Hospital Academic / other
Locations1 site (New Taipei City, Banqiao)
Trial IDNCT07431710 on ClinicalTrials.gov

What this trial studies

The study will develop a deep-learning pipeline (YOLO v8–based) that analyzes real-time arterial pressure waveforms and patient data to detect whether chest compressions are compressing the aortic valve. Researchers will collect synchronized transesophageal echocardiography (TEE) video and arterial pressure traces from 150 OHCA patients to train waveform- and compression-location models. An external test of 75 additional patients will validate model predictions against TEE as the gold standard, and a final feasibility phase will deploy a Resuscitation Support App in 30 real clinical CPR episodes. The goal is real-time guidance that shifts compressions off the aortic valve toward positions that maximize cardiac output in individual patients.

Who should consider this trial

Good fit: Adults aged 20 years or older with non‑traumatic out‑of‑hospital cardiac arrest who arrive to the emergency department and undergo CPR are the intended participants.

Not a fit: Patients with DNR orders, obvious signs of death, pregnancy, traumatic causes or contraindications to TEE or femoral arterial catheterization (or requiring ECPR/REBOA) would not be expected to benefit or be eligible.

Why it matters

Potential benefit: If successful, the system could increase the chance of return of spontaneous circulation and survival by personalizing compression location to improve blood flow during CPR.

How similar studies have performed: Prior work shows TEE can identify when compressions occlude the aortic valve and waveform features correlate with valve opening, but AI-guided, real-time compression repositioning is a novel approach with limited prior clinical evidence.

Eligibility criteria

Show full inclusion / exclusion criteria
Inclusion Criteria:

1. Adults aged 20 years or older.
2. Patients with out-of-hospital cardiac arrest (OHCA) undergoing 3.cardiopulmonary resuscitation (CPR) in the emergency department.

Cardiac arrest caused by non-traumatic factors.

Exclusion Criteria:

1. Pregnant patients.
2. Patients with obvious signs of death.
3. Patients with a signed "Do Not Resuscitate" (DNR) order.
4. Patients requiring extracorporeal cardio-pulmonary resuscitation (ECPR).
5. Patients requiring Resuscitative Endovascular Balloon Occlusion of the Aorta (REBOA).
6. Cardiac arrest caused by massive hemorrhage, aortic emergencies, tension pneumothorax, cardiac tamponade, or pulmonary embolism.
7. History of severe aortic valve disease or previous aortic valve surgery.
8. Patients for whom TEE or femoral arterial catheterization is contraindicated.
9. Situations where the medical team is unable to perform TEE or femoral arterial catheterization during CPR.

Where this trial is running

New Taipei City, Banqiao

Study contacts

How to participate

  1. Review the eligibility criteria above with your treating physician.
  2. Visit the official trial page on ClinicalTrials.gov for the most current contact information and recruitment status.
  3. Contact the listed study coordinator or principal investigator to request pre-screening. Pre-screening is free and never obligates you to enroll.
Conditions Out-of-hospital Cardiac ArrestCardiopulmonary ResuscitationAortic Valve CompressionPrecision ResuscitationArtificial IntelligenceTransesophageal EchocardiographyArterial Pressure WaveformChest Compression Location
Last reviewed 2026-06-09 by the Find a Trial editorial team. Information on this page is for educational purposes and is not medical advice. Always consult qualified healthcare professionals about clinical trial participation.