Biofourmis, a company with offices in Singapore and Boston, won FDA clearance for its RhythmAnalytics cloud-based software that uses artificial intelligence techniques to automate the interpretation of cardiac arrhythmias from ECG tracings. The system can detect more than fifteen different types of arrhytmias including using beat-by-beat morphology analysis to spot ventricular arrhythmias, ventricular ectopic beats, and all non-paced arrhythmias including atrial fibrillation (AFib).
The system was trained by feeding it over a million single-lead ECG recordings, harvested from a variety of wearable monitoring devices. Deep-learning algorithms were used to identify signature signs of arrhythmias in tracings of patients that were previously confirmed to have had the arrhythmias. This resulted in a convolutional neural network capable of detecting arrhythmias on par with trained cardiologists.
“Comprehensive diagnosis of a patient’s cardiac health requires longer continuous monitoring and full characterization of multiple arrhythmias. We are on a mission of predicting and preventing serious medical events using software-based therapeutic intervention and RhythmAnalyticsTM is an integral part of our Digital Therapeutics platform that would enable prescription of the right dose, to the right patient at the right time,” said Kuldeep Singh Rajput, Founder and Chief Executive Officer of Biofourmis, in a published press release. “We are excited about this milestone and look forward to using RhythmAnalyticsTM to enable clinicians to detect a wide range of cardiac arrhythmias and provide appropriate treatment and therapy.”
Related study: On Arrhythmia Detection by Deep Learning and Multidimensional Representation…
Link: Biofourmis homepage…
Via: Biofourmis…