News | Artificial Intelligence | July 11, 2017

iRhythm and Stanford Researchers Develop Deep Learning-Based Cardiac Arrhthymia Detection Algorithm

Algorithm provides expert-level classification of 12 arrhythmias following training with dataset of 30,000 unique patients

iRhythm and Stanford Researchers Develop Deep Learning-Based Cardiac Arrhthymia Detection Algorithm

July 11, 2017 — iRhythm Technologies Inc. announced a collaboration with the Stanford Machine Learning Group that has resulted in the development of a deep learning algorithm capable of expert-level detection of 14 cardiac output classes, including 12 arrhythmias as well as sinus rhythm and noise from artifact. The collaboration leveraged the iRhythm data science and clinical teams’ expertise in electrocardiogram (ECG) analysis, as well as iRhythm’s expansive labeled electrocardiogram (ECG) dataset to produce an arrhythmia detection algorithm. The classifications include atrial fibrillation, atrial flutter, complete heart block, second degree AV block and ventricular tachycardia, among others.

Because deep learning models are dependent upon vast amounts of reliable data, iRhythm provided an annotated data set of about 30,000 unique patients, 500 times larger than standards-based databases utilized in previous studies. This enabled the Stanford researchers, in collaboration with iRhythm Machine Learning Specialist Masoumeh Haghpanahi, to develop the 34-layer convolutional neural network, comparable to artificial intelligence (AI) models used in computer vision and speech recognition.

Details about the algorithm have been published in a paper co-authored by Stanford and iRhythm researchers titled “Cardiologist-Level Arrhythmia Detection with Convolutional Neural Networks.”

For more information: www.irhythm.com

Related Content

FDA Clears Aidoc's AI Solution for Flagging Pulmonary Embolism
Technology | Artificial Intelligence | May 15, 2019
Artificial intelligence (AI) solutions provider Aidoc has been granted U.S. Food and Drug Administration (FDA)...
Basic artificial intelligence is already incorporated into several premium echocardiography systems. This example is from the Philips Epiq, which can take 3-D datasets and the AI automatically identifies and segments the cardiac anatomy. It then extracts the best images for each of the standard views for an echocardiogram to eliminate variation between operators. The next generation echo AI software will pull in data from the electronic medical records and imaging data to offer suggested diagnoses.

Basic artificial intelligence is already incorporated into several premium echocardiography systems. This example is from the Philips Epiq, where the AI takes 3-D datasets and automatically identifies and segments the cardiac anatomy. It then extracts the best images for each of the standard echocardiogram views to eliminate variation between operators. The next generation echo AI software will pull in data from the electronic medical records and imaging data to offer suggested diagnoses.

Feature | Artificial Intelligence | May 07, 2019 | Ross Upton
Artificial Intelligence has a multitude of impacts on our daily lives, from recommending movies based upon your Netfl
FDA Proposes New Review Framework for AI-based Medical Devices
News | Artificial Intelligence | April 02, 2019 | Jeff Zagoudis, Associate Editor
U.S. Food and Drug Administration (FDA) Commissioner Scott Gottlieb, M.D., announced Tuesday the agency is pursuing a...
New Consensus Document Explores Ethical Use of AI in Radiology
News | Artificial Intelligence | March 05, 2019 | Jeff Zagoudis, Associate Editor
The American College of Radiology (ACR) is one of seven professional societies behind a new consensus document on the...
RSNA Offers First U.S. Spotlight Course on Artificial Intelligence
News | Artificial Intelligence | March 05, 2019
The Radiological Society of North America (RSNA) announced an expansion of its artificial intelligence (AI) education...
ACC Future Hub

Presenter delivers pitch at last year’s ACC Future Hub. This year during ACC.19, entrepreneurs will pitch software and hardware specific to cardiology in two categories– artificial intelligence and digitally enabled medical devices. (Image courtesy of ACC)

Feature | Artificial Intelligence | March 01, 2019 | By Greg Freiherr
Entrepreneurs to pitch innovative ideas at ACC
Siemens Healthineers Demonstrates Artificial Intelligence, Healthcare Digitalization at HIMSS19
News | Artificial Intelligence | February 13, 2019
At the 2019 Healthcare Information and Management Systems Society (HIMSS) global conference and exhibition, Feb. 11-15...
Overlay Init