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

TL;DR

This paper introduces a deep learning model that processes raw wearable sensor data to accurately detect atrial fibrillation in real-time, eliminating the need for manual feature engineering and achieving near-perfect classification performance.

Contribution

The study presents an end-to-end convolutional-recurrent neural network that directly learns from raw sensor data for AFib detection, outperforming previous methods that relied on domain-specific features.

Findings

Achieved an AUC of 0.9999 in AFib detection

False positive and false negative rates below 0.2%

Demonstrated real-time classification from raw PPG data

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.