Cardiogram is a company building a personal healthcare assistant that turns wearable devices, such as Android Wear, Fitbit, and Apple Watch, into a continuous health monitor. The company is developing Deepheart, a novel deep neural network tested in multiple rigorous clinical studies. The semi-supervised deep neural network accurately predicts cardiovascular risk with 10x less labeled data than conventional deep learning techniques.
Cardiogram can now detect 4 medical conditions using consumer wearables: Sleep Apnea, High Blood Pressure, Atrial Fibrillation, and even Diabetes. DeepHeart can detect hypertension and sleep apnea with more 82% accuracy using consumer wearables alone. Atrial Fibrillation, the most common abnormal heart rhythm, causes 1 in 4 strokes. DeepHeart detected atrial fibrillation with 97% accuracy using optical heart rate sensors, this allows for cost-effective, broad screening of the condition.
Cardiogram has been running clinical studies with UCSF Cardiology since 2016, including the ongoing mRhythm study. The company aims to broadly implement preventive medicine by early disease detection and reduced missed diagnosis rates among prevalent conditions.
The company, which is based in San Francisco, was founded in 2016 by Brandon Ballinger and Johnson Hsieh. Both founders had previously worked as software engineers at Google with Ballinger going on to work for Sift Science, Healthcare.gov, and University of California, San Francisco - Cardiology, focusing on data science and machine learning.
Cardiogram raised $2M Seed round funding on October 20th 2016. The lead investor was Andreessen Horowitz, a prominent Silicon Valley VC firm that has made early investments in companies such as Facebook, Airbnb, Twitter, Pinterest, Skype, Lyft, Zynga, Groupon, and many others. The Seed round also had participation from Homebrew, Health Catalyst Capital Management, and multiple angel investors.
Senior Software Engineer
Director of Product & Business Development
Achieving High Retention in Mobile Health Research Using Design Principles Adopted From Widely Popular Consumer Mobile Apps
Geoffrey H Tison, Kaiyu Hsu, Johnson T Hsieh, Brandon M Ballinger, Mark J Pletcher, Gregory M Marcus, and Jeffrey E Olgin
June 9, 2018
Cardiovascular Risk Stratification Using Off-the-Shelf Wearables and a Multi-Task Deep Learning Algorithm
Geoffrey H Tison, Avesh C Singh, Daniel A Ohashi, Johnson T Hsieh, Brandon M Ballinger, Jeffrey E Olgin, Gregory M Marcus, and Mark J Pletcher
June 9, 2018
DeepHeart: Semi-Supervised Sequence Learning for Cardiovascular Risk Prediction
Brandon Ballinger, Johnson Hsieh, Avesh Singh, Nimit Sohoni, Jack Wang, Geoffrey H. Tison, Gregory M. Marcus, Jose M. Sanchez, Carol Maguire, Jeffrey E. Olgin, Mark J. Pletcher
February 7, 2018
Passive Detection of Atrial Fibrillation Using a Commercially Available Smartwatch
Geoffrey H. Tison; José M. Sanchez; Brandon Ballinger; et al