Ambiq Introduces AI-based HeartKit for Real-Time Heart Monitoring Applications

By Tiera Oliver

Associate Editor

Embedded Computing Design

May 02, 2023

News

Ambiq Introduces AI-based HeartKit for Real-Time Heart Monitoring Applications

AUSTIN, Texas, --  Ambiq announced Ambiq HeartKit, an open-source AI model built on Ambiq's AI SDK, neuralSPOT®, allowing AI developers to run multiple real-time heart monitoring applications, and utilize scripts and tools that add real-time ECG monitoring capabilities to health-tech applications.

Ambiq’s HeartKit helps healthcare providers identify irregular events through personalized health monitoring applications, from commercial-grade health and fitness applications. The reference AI model analyzes 1-lead ECG data to detect heart arrhythmias and capture heart rate variability metric, and analyze individual beats to identify irregular beats, such as premature and ectopic beats originating in the atrium or ventricles.

The AI model leverages a modern multi-head network architecture and Ambiq's low-power SoC, while the pre-trained model is ready to use on Ambiq platforms and includes software to train, convert, and deploy customized models.

"Ambiq's HeartKit may be the most comprehensive open-source TinyML™ implementation of AI-based heart monitoring for IoT endpoint devices," said Carlos Morales, the VP of AI at Ambiq. "The highly optimized AI model will help developers enable health-tech applications on Ambiq Apollo4 Plus SoC in a matter of minutes."

What makes this technology so impressive is that it runs on the company’s super low-power MCU, designed with subthreshold power-optimized technology, aka SPOT. The company laims that SPOT is 13X more power efficient compared to competitive MCUs.

The HeartKit has been released under the permissive BSD-3 license for ease of deployment and development.

HeartKit is available now for download as a technical preview at https://github.com/AmbiqAI/heartkit.

For more information, visit: www.ambiq.com

Tiera Oliver, Associate Editor for Embedded Computing Design, is responsible for web content edits, product news, and constructing stories. She also assists with newsletter updates as well as contributing and editing content for ECD podcasts and the ECD YouTube channel. Before working at ECD, Tiera graduated from Northern Arizona University where she received her B.S. in journalism and political science and worked as a news reporter for the university’s student led newspaper, The Lumberjack.

More from Tiera