Deep learning to clean CPR artifacts so AEDs can decide quickly
Official title: A deep learning artifact removal method for CPR continuity throughout the shock decision in AEDs
Funded at University of Connecticut Storrs · NIH-11345432 · Data updated 2026-11-12
A deep learning method will clean up ECG signals during CPR to help AEDs make faster, more accurate shock decisions for people with out-of-hospital cardiac arrest.
Quick facts
| Grant type | R01 grant |
|---|---|
| Study type | NIH-funded research |
| Funding institution | University of Connecticut Storrs NIH-funded |
| Lab location | 1 site (Storrs-Mansfield, United States) |
| Project start | June 1, 2025 |
| Project end | March 31, 2029 |
| Funding year | 2026 |
| Award (this year) | $696,353 |
| NIH project number | 5R01HL173935-02 |
| Project ID | NIH-11345432 on NIH RePORTER |
Who could benefit from this research
✓Could help
Adults with out-of-hospital cardiac arrest or related ECG data during CPR who could benefit from better AED decision-making.
✕Less likely to help
Patients without OHCA or those not encountering CPR artifacts in their data may see no direct benefit.
What this research studies
This project will collect CPR artifact data from defibrillators and hospital patients to train a deep learning model. The goal is to produce an algorithm that can accurately analyze ECG during chest compressions without pausing CPR. By reducing unwanted motion noise, the AED can provide timely shocks when indicated, potentially improving survival. Collaboration with U-M and Massachusetts General Hospital will help build a robust dataset and validate the approach.
Why it matters
Potential benefit: If successful, the method could enable more continuous CPR with timely, accurate shock decisions, improving outcomes after cardiac arrest.
How similar studies have gone: Prior work struggled with CPR-induced artifacts; this project advances a data-driven approach and builds on previous attempts with mixed results.
Where this research is happening
-
University of Connecticut Storrs
Storrs-Mansfield, United States Active
Researchers
- Principal investigator: Chon, Ki H — University of Connecticut Storrs
- Study coordinator: Chon, Ki H
Related research
Other NIH-funded projects on the same topics.
-
Improving CPR effectiveness during cardiac arrest with advanced technology
This study is working on a way to make CPR more effective during heart emergencies by improving how heart rhythm is read while chest compressions are happening, which could help save more lives when someone has a cardiac arrest.
-
Integrative histo-genomic analysis to guide cancer risk and targeted therapies with interpretable AI
Researchers are developing an advanced AI-powered approach to map genetic and cellular patterns across breast and cervical cancers to help tailor treatments.
-
Pragmatic midodrine trial to reduce ICU vasopressor use in septic shock
A practical, patient-focused trial tests whether taking oral midodrine can lessen the need for IV vasopressors and shorten ICU stays for people with sepsis-related low blood pressure.
-
Predicting how antimalarial drug resistance spreads with AI
A powerful AI model will be built to forecast how resistance to antimalarial drugs might spread in Africa and beyond, helping clinicians and public health teams stay ahead of outbreaks.
-
Understanding how small heat shock proteins protect our cells
A study from the University of Washington explores how tiny chaperone proteins protect eye and other cells from damage, which could help prevent conditions like cataracts and age-related macular degeneration.
-
Self-supervised deep learning for biological sequences
A deep learning project uses self-supervised methods to better understand biological sequences and related data, with the goal of advancing biology and medicine.
About this research
- This is an active NIH-funded research project — typically early-stage science, not a clinical trial accepting patient enrollment.
- Some NIH-funded labs run parallel clinical studies or seek volunteers for related work. To check, contact the principal investigator or institution listed above.
- For full project details, budget, and progress reports, visit the official NIH RePORTER page.