This website uses cookies and similar technologies to understand visitors' experiences. By continuing to use this website, you accept our use of cookies and similar technologies,Terms of Use, and Privacy Policy.

Jul 08 2018 - 08:00pm
Cardiogram: The Wearable Health Screening AI

"When we talk about artificial intelligence in medicine, we often debate whether machines will replace tasks doctors do today. A more tantalizing possibility is performing tasks doctors can’t—using large data sets and modern computational tools like deep learning to recognize patterns too subtle for any human to discern." (Brandon Ballinger, Co-Founder, Cardiogram.)

Stories From the Heart

On average, the heart beats 102,000 times per day and reacts to everything that happens: what you're eating, how you exercise, a stressful moment, or a happy memory. On the basis of this data, healthtech startup Cardiogram built an app to help people make their cardio health meaningful, useful, and actionable. The technology operates through wearables like Android Wear, Fitbit, and Apple Watch, collecting and crunching a users’ data to help people analyze and graph their heart rate measurements. Their algorithm processes the data and shows users how their heart reacts during an intense workout. It tracks changes to the resting heart rate and stress-related spikes. Users can share graphs of their heart rate via email and on Twitter and Facebook.

Data Deus

Cardiogram’s founding goal was to use algorithms in wearable devices to predict and identify atrial fibrillation (an irregular, rapid heart rate that causes palpitations, fatigue, and shortness of breath) and to understand what normal heart health looks like. But its algorithm learned quickly, and in trials with the Apple Watch, it detected arrhythmia with 97% accuracy, sleep apnea with 90% accuracy, and hypertension with 82% accuracy. This led the Cardiogram team to build DeepHeart, a deep neural network to help create the future of preventive medicine. In one clinical study, DeepHeart used data from 14,000 Apple Watch users and detected diabetes in 462 of them using the device’s heart rate sensor. Given that an estimated 30.3 million Americans (9.4% of the population) suffer from diabetes, Cardiogram’s creators are looking at integrating the screening algorithm into the app to help those Americans who don’t know they have diabetes (approximately 25%) detect and treat the condition early.

Image: Heart Rate Monitor on an Apple Watch by Integrated Change via Flickr
Posted in: New Learning TimesNL Sector|By: Debra Lee|23 Reads