In a collaboration between digital healthcare company iRhythm and the Stanford Machine Learning Group (SMLG), an algorithm has been developed to detect 14 different cardiac output classes, including 12 arrhythmias.
iRhythm manufactures wearable biosensor devices that detect cardiac arrhythmias and is based in San Francisco. The SMLG works to build large-scale algorithms in technical fields and is part of Stanford University in California.
In their research, they examined a data set of approximately 30,000 unique patients, and were able to develop a neural network that’s comparable to artificial intelligence models used in vision and speech recognition. They collected readings using iRhythm’s wearable monitors.
Some of the classifications included atrial fibrillation (AFib), atrial flutter, complete heart block, second degree AV block and ventricular tachycardia.
"As a digital health company, we are very pleased to leverage our large and unique cardiac data repository of over 200 million hours of labeled ECG data and our leadership in ECG analysis to enable this cutting edge deep learning research," said iRhythm CEO Kevin King in a statement. "This project is a continuation of iRhythm's exploration of state-of-the-art machine learning techniques as key to the future of healthcare delivery."