Cardiologist-Level Arrhythmia Detection with Convolutional Neural Networks

Abstract

We develop an algorithm which exceeds the performance of board certified cardiologists in detecting a wide range of heart arrhythmias from electrocardiograms recorded with a single-lead wearable monitor. We build a dataset with more than 500 times the number of unique patients than previously studied corpora. On this dataset, we train a 34-layer convolutional neural network which maps a sequence of ECG samples to a sequence of rhythm classes. Committees of board-certified cardiologists annotate a gold standard test set on which we compare the performance of our model to that of 6 other individual cardiologists. We exceed the average cardiologist performance in both recall (sensitivity) and precision (positive predictive value).

References in corpus (3)

• Adam: A Method for Stochastic Optimization
• Deep Speech 2: End-to-End Speech Recognition in English and Mandarin
• Achieving Human Parity in Conversational Speech Recognition

Cited by in corpus (54)

• CheXNet: Radiologist-Level Pneumonia Detection on Chest X-Rays with Deep Learning
• ECG arrhythmia classification using a 2-D convolutional neural network
• Deep Learning in Pharmacogenomics: From Gene Regulation to Patient Stratification
• Spinal cord gray matter segmentation using deep dilated convolutions
• Ultra Low-Power and Real-time ECG Classification Based on STDP and R-STDP Neural Networks for Wearable Devices
• Time Series Anomaly Detection Using Convolutional Neural Networks and Transfer Learning
• Detection of Inferior Myocardial Infarction using Shallow Convolutional Neural Networks
• UnsuperPoint: End-to-end Unsupervised Interest Point Detector and Descriptor
• Rethinking multiscale cardiac electrophysiology with machine learning and predictive modelling
• Topological Data Analysis for Arrhythmia Detection through Modular Neural Networks
• Convolutional-Recurrent Neural Networks on Low-Power Wearable Platforms for Cardiac Arrhythmia Detection
• Dropout Feature Ranking for Deep Learning Models
• Creating and concentrating quantum resource states in noisy environments using a quantum neural network
• Icentia11K: An Unsupervised Representation Learning Dataset for Arrhythmia Subtype Discovery
• ECG-Adv-GAN: Detecting ECG Adversarial Examples with Conditional Generative Adversarial Networks
• SynthEnsemble: A Fusion of CNN, Vision Transformer, and Hybrid Models for Multi-Label Chest X-Ray Classification
• RAIM: Recurrent Attentive and Intensive Model of Multimodal Patient Monitoring Data
• ECGadv: Generating Adversarial Electrocardiogram to Misguide Arrhythmia Classification System
• End-to-end Deep Learning from Raw Sensor Data: Atrial Fibrillation Detection using Wearables
• Model Assertions for Monitoring and Improving ML Models
• ANNETTE: Accurate Neural Network Execution Time Estimation with Stacked Models
• DeepRadiologyNet: Radiologist Level Pathology Detection in CT Head Images
• Classification of Cardiac Arrhythmias from Single Lead ECG with a Convolutional Recurrent Neural Network
• HALF: Holistic Auto Machine Learning for FPGAs
• Automatic Diagnosis of Pneumothorax from Chest Radiographs: A Systematic Literature Review
• Atrial Fibrillation Detection and ECG Classification based on CNN-BiLSTM
• On Arrhythmia Detection by Deep Learning and Multidimensional Representation
• Hybrid Gradient Boosting Trees and Neural Networks for Forecasting Operating Room Data
• Deep Convolutional Neural Networks for Noise Detection in ECGs
• XAI Methods for Neural Time Series Classification: A Brief Review
• Detection of Paroxysmal Atrial Fibrillation using Attention-based Bidirectional Recurrent Neural Networks
• Cardiac Arrhythmia Detection from ECG with Convolutional Recurrent Neural Networks
• Multilevel Wavelet Decomposition Network for Interpretable Time Series Analysis
• Detection of Premature Ventricular Contractions Using Densely Connected Deep Convolutional Neural Network with Spatial Pyramid Pooling Layer
• Integrative Analysis of Patient Health Records and Neuroimages via Memory-based Graph Convolutional Network
• RTFN: A Robust Temporal Feature Network for Time Series Classification
• Generalization Studies of Neural Network Models for Cardiac Disease Detection Using Limited Channel ECG
• Adversarial Examples for Electrocardiograms
• Automating Abnormality Detection in Musculoskeletal Radiographs through Deep Learning
• Anesthesiologist-level forecasting of hypoxemia with only SpO2 data using deep learning
• Representing and Denoising Wearable ECG Recordings
• Using Multitask Learning to Improve 12-Lead Electrocardiogram Classification
• Data-Adaptive Discriminative Feature Localization with Statistically Guaranteed Interpretation
• Collaborative Inference for Efficient Remote Monitoring
• ReNN: Rule-embedded Neural Networks
• Optimizing Neural Network Scale for ECG Classification
• Enhance CNN Robustness Against Noises for Classification of 12-Lead ECG with Variable Length
• SE-ECGNet: A Multi-scale Deep Residual Network with Squeeze-and-Excitation Module for ECG Signal Classification
• Auto-Classification of Retinal Diseases in the Limit of Sparse Data Using a Two-Streams Machine Learning Model
• Piece-wise Matching Layer in Representation Learning for ECG Classification
• Application of Adversarial Examples to Physical ECG Signals
• Advance Prediction of Ventricular Tachyarrhythmias using Patient Metadata and Multi-Task Networks
• Measuring the Stability of EHR- and EKG-based Predictive Models
• Noise-Resilient Automatic Interpretation of Holter ECG Recordings