MACE-Alert: AI tools to help triage chest pain in the emergency department

Who could benefit from this research

What this research studies

In this project, researchers at UC San Diego will create two AI tools to help ED doctors better judge the risk of serious heart problems in people with chest pain. The first tool uses a machine-learning model fed by past ED data and real-time vital signs to predict 30-day risk of major adverse cardiac events. The second tool is a friendly chat assistant that collects patient-reported symptoms and links them to medical records to support clinical decisions. The team will test these tools with retrospective data and measure accuracy, safety, and usefulness in guiding ED disposition.

Why it matters

Where this research is happening

• University of California, San Diego
  La Jolla, United States Active

Researchers

• Principal investigator: Ramsis, Mattheus — University of California, San Diego
• Study coordinator: Ramsis, Mattheus

Related research

Other NIH-funded projects on the same topics.

• ECG-BASED smart tools to quickly classify chest pain in emergency care

  A patient-focused project to use advanced ECG analysis and machine learning to quickly identify heart problems in people with chest pain when they arrive at the ER.

  NIH research University of Rochester · Rochester, United States · NIH-11550067

• How emergency doctors’ decisions about chest pain affect testing and outcomes

  A study using Medicare data will see if doctors who tend to admit chest-pain patients to the hospital lead to more tests and different outcomes for those patients.

  NIH research University of California, San Francisco · San Francisco, United States · NIH-11371961

• Using ECGs to find hidden heart attacks in people with chest pain

  This project is creating smart ECG tools to quickly spot heart attacks that don't show the classic ST-elevation in people who come to the emergency room with chest pain.

  NIH research University of Rochester · Rochester, United States · NIH-11292312

• Electrocardiographic warning system to speed up chest-pain care (ECG-SMART 2)

  A research project is testing new ECG-based computer tools to quickly and safely identify patients with potentially serious chest pain in emergency departments.

  NIH research University of Rochester · Rochester, United States · NIH-11099852

• Evaluating a new approach for managing chest pain patients in outpatient settings

  This study is testing a new way to help people with chest pain who aren't at high risk by letting them go home from the emergency room instead of staying in the hospital, and then checking in with them within three days to make sure they're doing okay and to manage any heart health concerns.

  NIH research Wake Forest University Health Sciences · Winston-Salem, United States · NIH-11003318

• Improving ECG methods to quickly identify heart issues in chest pain patients

  This study is working on a new tool to help doctors quickly and accurately check patients with chest pain in the emergency room, using advanced technology to spot heart issues that might be missed by regular tests, so they can provide faster and better care for you.

  NIH research University of Pittsburgh at Pittsburgh · Pittsburgh, United States · NIH-10893324

About this research

1. This is an active NIH-funded research project — typically early-stage science, not a clinical trial accepting patient enrollment.
2. Some NIH-funded labs run parallel clinical studies or seek volunteers for related work. To check, contact the principal investigator or institution listed above.
3. For full project details, budget, and progress reports, visit the official NIH RePORTER page.