Algorithm spots AFib in seemingly normal EKGs
A study of more than 181,000 patients at the Mayo Clinic has proven the efficacy of an AI algorithm in spotting AFib on seemingly normal EKGs, the Daily Mail reports.
The work, led by Paul Friedman, chairman of the department of cardiovascular medicine at the Mayo Clinic, and published in the Lancet, involved comparing normal, clean EKGs to those from patients with atrial fibrillation. An AI algorithm was trained on the data to recognize subtle symptoms of AFib that would otherwise present much later in a patient’s life.
The algorithm was able to identify individuals with potentially undetected AFib with 79% accuracy with a single 10-second test and 83% accuracy with multiple tests.
“AI can provide powerful information about the invisible electrical signals that our bodies give off with each heartbeat—signals that have been hidden in plain sight,” Friedman told the Daily Mail. “An EKG will always show the heart’s electrical activity at the time of the test, but this is like looking at the ocean now and being able to tell that there were big waves yesterday.”
Read more below:
After graduating from Indiana University-Bloomington with a bachelor’s in journalism, Anicka joined TriMed’s Chicago team in 2017 covering cardiology. Close to her heart is long-form journalism, Pilot G-2 pens, dark chocolate and her dog Harper Lee.