The research team — led by graduate students Awni Hannun and Pranav Rajpurkar — collaborated with the heartbeat monitor company iRhythm to train the deep-learning algorithm on data from its wearable electrocardiogram device. After seven months, the algorithm was able to diagnose 14 types of heart arrhythmias from ECG signals.
To test the algorithm’s accuracy, the researchers asked six different cardiologists to diagnose 300 short ECG clips for arrhythmias. They compared these results with the diagnosis from the algorithm, to determine which more closely matched expert consensus. The researchers found the algorithm was able to outperform cardiologists on most arrhythmias.
The researchers hope the algorithm may help to monitor at-risk patients or to diagnose patients in remote areas.
More articles on health IT:
Alphabet relaunches Google Glass
DOD initiates 2nd Cerner EHR go-live
KLAS: Large organizations rank Epic No. 1 practice management IT vendor
At the Becker's 11th Annual IT + Revenue Cycle Conference: The Future of AI & Digital Health, taking place September 14–17 in Chicago, healthcare executives and digital leaders from across the country will come together to explore how AI, interoperability, cybersecurity, and revenue cycle innovation are transforming care delivery, strengthening financial performance, and driving the next era of digital health. Apply for complimentary registration now.
