End-to-end Deep Learning from Raw Sensor Data: Atrial Fibrillation Detection using Wearables (2018-07-27T00:00:00.000000Z)

TL;DR

This work uses a prototype multi-sensor wearable device to collect over 180h of photoplethysmography data sampled at 20Hz and end-to-end learning to achieve state-of-the-art results in detecting AFib from raw PPG data, bringing large-scale atrial fibrillation screenings within imminent reach.

Abstract

We present a convolutional-recurrent neural network architecture with long short-term memory for real-time processing and classification of digital sensor data. The network implicitly performs typical signal processing tasks such as filtering and peak detection, and learns time-resolved embeddings of the input signal. We use a prototype multi-sensor wearable device to collect over 180h of photoplethysmography (PPG) data sampled at 20Hz, of which 36h are during atrial fibrillation (AFib). We use end-to-end learning to achieve state-of-the-art results in detecting AFib from raw PPG data. For classification labels output every 0.8s, we demonstrate an area under ROC curve of 0.9999, with false positive and false negative rates both below $2\times 10^{-3}$. This constitutes a significant improvement on previous results utilising domain-specific feature engineering, such as heart rate extraction, and brings large-scale atrial fibrillation screenings within imminent reach.

Authors

Igor Gotlibovych

1 papers

Stuart Crawford

1 papers

Dileep Goyal

1 papers

TL;DR

Abstract

Authors

References52 items

Detection of Paroxysmal Atrial Fibrillation using Attention-based Bidirectional Recurrent Neural Networks

Passive Detection of Atrial Fibrillation Using a Commercially Available Smartwatch

The Building Blocks of Interpretability

Detecting atrial fibrillation by deep convolutional neural networks

Convolutional recurrent neural networks for electrocardiogram classification

Cardiologist-Level Arrhythmia Detection with Convolutional Neural Networks

Data augmentation of wearable sensor data for parkinson’s disease monitoring using convolutional neural networks

Experiments in Handwriting with a Neural Network

The great time series classification bake off: a review and experimental evaluation of recent algorithmic advances

Time series classification from scratch with deep neural networks: A strong baseline

Data Augmentation for Time Series Classification using Convolutional Neural Networks

WaveNet: A Generative Model for Raw Audio

Monitoring and detecting atrial fibrillation using wearable technology

A guide to convolution arithmetic for deep learning

A Theoretically Grounded Application of Dropout in Recurrent Neural Networks

Deep Residual Learning for Image Recognition

Fast and accurate recurrent neural network acoustic models for speech recognition

Training Very Deep Networks

Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift

Adam: A Method for Stochastic Optimization

Deep Speech: Scaling up end-to-end speech recognition

2014 AHA/ACC/HRS guideline for the management of patients with atrial fibrillation: a report of the American College of Cardiology/American Heart Association Task Force on practice guidelines and the Heart Rhythm Society.

ImageNet Large Scale Visual Recognition Challenge

Epidemiology of atrial fibrillation: European perspective

Return of the Devil in the Details: Delving Deep into Convolutional Nets

Data Augmentation for deep neural network acoustic modeling

Atrial fibrillation: profile and burden of an evolving epidemic in the 21st century.

On the importance of initialization and momentum in deep learning

Modern hierarchical, agglomerative clustering algorithms

Deep Sparse Rectifier Neural Networks

Scikit-learn: Machine Learning in Python

Evaluation of Pooling Operations in Convolutional Architectures for Object Recognition

Convolutional networks and applications in vision

Understanding the difficulty of training deep feedforward neural networks

Learning from Imbalanced Data

What is the best multi-stage architecture for object recognition?

Photoplethysmography and its application in clinical physiological measurement

A population-based study of the long-term risks associated with atrial fibrillation: 20-year follow-up of the Renfrew/Paisley study.

Fast optimal leaf ordering for hierarchical clustering

Learning to Forget: Continual Prediction with LSTM

Long Short-Term Memory

Learning long-term dependencies with gradient descent is difficult

Backpropagation Applied to Handwritten Zip Code Recognition

The validity and practicality of sun-reactive skin types I through VI.

Learning From Imbalanced Data

Machine Learning on Heterogeneous Systems

TensorFlow: Large-Scale Machine

2014 AHA/ACC/HRS guideline for the management of patients with atrial fibrillation: a report of the American College of Cardiology/American Heart Association Task Force on Practice Guidelines and the Heart Rhythm Society.

Machine learning - a probabilistic perspective

Gradient-based learning applied to document recognition

VERIFICATION OF FORECASTS EXPRESSED IN TERMS OF PROBABILITY

End-to-end Deep Learning from Raw Sensor Data: Atrial Fibrillation Detection using Wearables

Field of Study

Journal Information

Name

Volume

Venue Information

Name

Type

URL

Alternate Names