AI-guided chest compressions for personalized CPR
Official title: Utilizing Artificial Intelligence to Optimize Chest Compression Region During Cardio-pulmonary Resuscitation for Patients With Out-of-hospital Cardiac Arrest.
Run by Far Eastern Memorial Hospital · NCT07431710 · Data updated 2026-11-12
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 type | Observational |
|---|---|
| Ages | 20 Years and up |
| Sex | All |
| Enrollment | 255 (estimated) |
| Sponsor | Far Eastern Memorial Hospital Academic / other |
| Locations | 1 site (New Taipei City, Banqiao) |
| Status | Recruiting |
| Started | January 6, 2025 |
| Main results expected | December 31, 2027 |
| Study ends | December 31, 2027 |
| Registry record updated | February 24, 2026 |
| Trial ID | NCT07431710 on ClinicalTrials.gov |
Is this trial a fit for you?
✓Likely a 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.
✕Probably 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.
A plain-English reading of the study's rules. Only the study team can confirm whether you qualify.
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.
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 gone: 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.
Who can join: the full rules
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 it's running
-
Far Eastern Memorinal Hospital
New Taipei City, Banqiao, Taiwan Recruiting
Study contacts
- Study coordinator: Sheng-En Chu, physician
- Email: ianchu300@msn.com
- Phone: 886-2-7728-1843
Similar studies
Other studies for the same condition or treatment. Recruiting studies are listed first.
-
Augmented reality CPR feedback for pediatric resuscitation
This study tests whether AR-CPR feedback can help healthcare teams deliver high-quality chest compressions in simulated pediatric cardiac arrest, as compared with coaching from a CPR expert.
-
Prehospital femoral arterial access to monitor blood pressure during OHCA
This pilot study tests whether placing a femoral arterial sheath before hospital arrival is feasible and safe in adults with non-traumatic OHCA to enable invasive blood pressure monitoring and better vasopressor control.
-
Pain after out-of-hospital cardiac arrest and resuscitation
This study will see if how pain is measured and treated in adults brought back after out-of-hospital cardiac arrest relates to delirium, ICU resource use, and longer-term recovery.
-
Measuring airway opening during out-of-hospital cardiac arrest
This project tests whether the Airway Opening Index (AOI) measured from capnograms during CPR in adults with out-of-hospital cardiac arrest is common and linked to return of spontaneous circulation.
-
HEROS 4.0 mixed-reality CPR training
This trial will test whether HEROS 4.0 mixed-reality training can teach adults aged 18–50 to perform CPR as well as standard instructor-led courses.
-
Ventilation Feedback in EMS Resuscitation (ventilation during CPR)
This trial tests whether real-time visual feedback helps EMS rescuers deliver the right amount of air during CPR in simulated OHCA.
How to take part
- Review the eligibility criteria above with your treating physician.
- Check the official listing on ClinicalTrials.gov for the latest contact details and recruitment status.
- Contact the study coordinator or principal investigator to ask for pre-screening. Pre-screening is free and never obligates you to enroll.