AI Algorithm Outperforms Human ECG Interpretation

MONTRÉAL – An artificial intelligence algorithm developed by a team at the Montreal Heart Institute performs as well as, or ⁣better than, humans when interpreting electrocardiograms.

The tool can even detect conditions invisible to the human eye,and whose first symptoms might not emerge for months,according to ⁢a project leader.

“We can detect (heart) failure…‍ or predict the risk of arrhythmia in people who aren’t currently experiencing it, but‍ coudl ⁢develop it in ‍the coming years, or detect genetic diseases,” said Dr. Robert avram, a ‍cardiologist at the ICM.

“These are diseases that can’t traditionally be detected from an ECG, but with our model, we’re able to detect them with very ⁤good accuracy.”

Developed by Alexis Nolin-Lapalme and Achille Sowa, the DeepECG⁢ model was trained on more ⁤than one million ECG results,⁤ then retrospectively validated in eleven centers internationally.

deepecg ⁣is the “first fully open-source ‘foundation’ ECG model in the world,” Dr.Avram said. This means hospitals and research centers globally can adapt it to their local populations to develop new cardiac biomarkers, even with limited data.

“from an electrocardiogram, a cardiologist can detect several diseases,” Dr.Avram said.⁢ “But by training a foundation model, we’re also able to teach the algorithm to detect diseases that are invisible to the naked eye and undetectable by conventional medical means.”

DeepECG can detect conditions that even experienced cardiologists might miss.