Machine learning predicts heart attack with 94% accuracy

Twitter icon
Facebook icon
LinkedIn icon
e-mail icon
Google icon
 - heart attack

Chest pain is one of the most common reasons patients visit the emergency department (ED), but relatively few are eventually diagnosed with myocardial infarction (MI). New research found a machine learning algorithm can predict MI with 94 percent accuracy.

According to an American College of Cardiology press release, Daniel Lindholm, MD, PhD, a postdoctoral fellow at Uppsala University in Sweden, is set to present the research at the American College of Cardiology’s 67th Annual Scientific Session, March 10-12 in Orlando.

"The long-term goal is to identify those who are at highest risk and to treat those patients first," said Lindholm in the release. "If this work is further validated, hospitals could potentially use it to quickly pick out which patients are sickest when they arrive at the hospital, and that could lead to a shorter time to treatment for those who need it most."

Lindholm and his colleagues trained their algorithm against data collected from more than 8,200 ED visits in Stockholm between 2011 and 2013.

In the first phase of the study the algorithm used data from 5,800 patient visits to create decision trees identifying MI diagnosis using indicators such as blood test results, vital signs and patient medical history.

The second phase used similar patient data from a separate set of 2,400 visits but excluded the final heart attack diagnosis to determine the accuracy of the algorithm.

Results indicated the algorithm accurately predicted the diagnosis of MI 94 percent of the time. A 90 percent mark is typically considered high for these models, according to the release.

"In a broad sense, machine learning methods have been around for quite some time, but it's just in the last few years that we have gained the large data sets and computational capabilities to use them for clinical applications," Lindholm said. "I think that we will see more and more decision support systems based on machine learning. But even as machine learning can enhance medical practice, I do not think these algorithms will ultimately replace physicians but, rather, provide decision support based on the data at hand. Other things, such as empathy, human judgment and the patient-doctor relationship are crucial."