DeepHeart: Semi-Supervised Sequence Learning for Cardiovascular Risk Prediction

Authors

  • Brandon BallingerCardiogram
  • Johnson HsiehCardiogram
  • Avesh SinghCardiogram
  • Nimit SohoniCardiogram, Stanford
  • Jack WangCardiogram, University of Waterloo
  • Geoffrey TisonUniversity of California, California (UCSF)
  • Gregory MarcusUniversity of California, California (UCSF)
  • Jose SanchezUniversity of California, California (UCSF)
  • Carol MaguireUniversity of California, California (UCSF)
  • Jeffrey OlginUniversity of California, California (UCSF)
  • Mark PletcherUniversity of California, California (UCSF)

DOI:

https://doi.org/10.1609/aaai.v32i1.11891

Keywords:

Biomedical/Bioinformatics, Bio/Medicine, Semisupervised Learning

Abstract

We train and validate a semi-supervised, multi-task LSTM on 57,675 person-weeks of data from off-the-shelf wearable heart rate sensors, showing high accuracy at detecting multiple medical conditions, including diabetes (0.8451), high cholesterol (0.7441), high blood pressure (0.8086), and sleep apnea (0.8298). We compare two semi-supervised training methods, semi-supervised sequence learning and heuristic pretraining, and show they outperform hand-engineered biomarkers from the medical literature. We believe our work suggests a new approach to patient risk stratification based on cardiovascular risk scores derived from popular wearables such as Fitbit, Apple Watch, or Android Wear.

AAAI 2018 Proceedings Cover

Downloads

Published

2018-04-26

How to Cite

Ballinger, B., Hsieh, J., Singh, A., Sohoni, N., Wang, J., Tison, G., Marcus, G., Sanchez, J., Maguire, C., Olgin, J., & Pletcher, M. (2018). DeepHeart: Semi-Supervised Sequence Learning for Cardiovascular Risk Prediction.Proceedings of the AAAI Conference on Artificial Intelligence,32(1). https://doi.org/10.1609/aaai.v32i1.11891

Issue

Section

Main Track: Machine Learning Applications