It uses an enhanced deep-learning technique to detect over 15 types of cardiac arrhythmias along with beat-by-beat morphology computation which include ventricular arrhythmias, ventricular ectopic beats and all non-paced arrhythmias including Atrial Fibrillation (AFib). The AI-models were trained using over a million ECG recordings collected using various FDA-cleared ECG monitoring wearables.

Biofourmis currently works with leading hospitals like Mayo Clinic, Brigham and Women’s Hospital and has also secured partnerships with over 5 leading global pharmaceutical companies for its Digital Therapeutics platform.  The team has trained a densely connected convolutional neural network using more than a million single-lead ECG recordings collected from patients with a history of cardiac arrhythmias using a variety of ambulatory ECG monitoring devices, one of which is the ePatch extended holter monitor from BioTelemetry Inc., which was also used as a cardiac monitoring device in the Apple Heart Study.

In a recent arXiv paper, the company demonstrated cardiologist-level arrhythmia detection and classification using a novel-deep learning architecture, which was submitted to the FDA to demonstrate clinical evidence in addition to various other clinical trials data. Over 120,000 single-lead ECG episodes were used to train the neural network with over 30 distinctive cardiac arrhythmias. The company demonstrated that RhythmAnalytics outperforms two other similar deep learning systems as well as a panel of cardiologists with Sensitivity of 90.8%, Specificity of 98.2% and an overall F1 score of 0.834.

“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 RhythmAnalytics 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. “We are excited about this milestone and look forward to using RhythmAnalytics to enable clinicians to detect a wide range of cardiac arrhythmias and provide appropriate treatment and therapy.”

Traditional approaches to cardiac rhythm classification are prone to large false positives, leading to misdiagnosis, that significantly increases the healthcare utilization cost. Studies1 have also shown that the computerized arrhythmia interpretation error rates approach 50%. RhythmAnalytics supports analysis of electrocardiograms (ECG) captured from any FDA cleared devices or wearable sensors such as Holter monitors, event recorders, or other similar devices. It can either be integrated as a cloud-based API into existing cardiac monitoring solutions or directly integrated into a medical device or wearable sensor, which significantly improves the accuracy and scalability of ECG analysis, reducing the rate or misinterpretation and inappropriate patient management.

Biofourmis plans to offer RhythmAnalytics cloud-based API as Software-as-a-Service (SaaS) to cardiac monitoring organizations to improve accuracy and scalability of their ECG analysis, thereby improving throughput and efficiencies in their cardiac monitoring centers. According to Dr. Maulik Majmudar, cardiologist and a member of Biofourmis’ clinical advisory board, “Diagnostic interpretation of ambulatory ECGs are not only resource intensive but can also carry high rates of diagnostic errors. Given the interest in, and availability of, OTC consumer-focused ECG acquisition devices on the market today, there is a growing need for rapid, automated, and highly accurate interpretation of single-lead ECGs for a wide array of cardiac rhythm disorders. The FDA-cleared RhythmAnalytics platform directly addresses that need.”

Biofourmis also announced its partnership with Brigham and Women’s Hospital in November 2018, where RhythmAnalytics is currently being used to continuously monitor for cardiac arrhythmias and manage patients at home, at Brigham’s Home Hospital Program. The patient numbers have doubled on a month-on-month basis.

“The Biofourmis RhythmAnalytics platform ushers in a new era of computer-aided ECG interpretation – harnessing refined deep-learning techniques that I strongly feel will revolutionize care by improving throughput and reducing costs while maintaining accuracy. Biofourmis has built an incredibly strong in-house data science and clinical capabilities and we look forward to working with them,” said Dr. Christopher J. McLeod, Clinical Director for Cardiovascular Medicine at Mayo Clinic.

Source: Company Press Release