New AI model CoDE-ACS could help doctors diagnose heart attacks

UK researchers created an AI-based program CoDE-ACS that may help doctors diagnose heart attacks faster and more accurately.

The new algorithm, CoDE-ACS, from the University of Edinburgh, was able to rule out a heart attack in more than twice as many patients with 99.6% accuracy compared to current testing methods.

CoDE-ACS may reduce hospital admissions and quickly identify safe-to-go patients. Nature Medicine publishes results.”Early diagnosis and treatment save lives,” stated Prof. Nicholas Mills, who conducted the study.

Unfortunately, numerous illnesses cause these common symptoms, making diagnosis difficult.”Data and AI can improve patient care and efficiency in our busy Emergency Departments,” Mills said.

CoDE-ACS could also help clinicians determine if abnormal troponin (a protein released into the bloodstream during a heart attack) levels were caused by a heart attack.

“Chest pain is one of the most common reasons that people present to emergency departments,” said Prof. Sir Nilesh Samani, medical director of the British Heart Foundation.

“Every day, doctors around the world face the challenge of separating patients whose pain is due to a heart attack from those who are suffering from something less serious,” he said.

CoDE-ACS was established utilizing data from 10,038 Scottish hospitalized heart attack suspects. It predicts heart attack risk based on age, sex, ECG results, medical history, and troponin levels. Each patient receives a 0–100 likelihood score. Now Scotland is conducting clinical trials to see if the gadget might help doctors ease emergency department congestion.