A training pipeline of an arrhythmia classifier for atrial fibrillation detection using Photoplethysmography signal

Article Computer Science, Interdisciplinary Applications

Beyond Mutual Information: Generative Adversarial Network for Domain Adaptation Using Information Bottleneck Constraint

Jiawei Chen et al.

Summary: Medical images from multicentres often suffer from domain shift problem. To address this issue, a novel GAN called IB-GAN is proposed to preserve image-objects during cross-domain image-to-image adaptation.

IEEE TRANSACTIONS ON MEDICAL IMAGING (2022)

Add to Collection

Article Cardiac & Cardiovascular Systems

2020 ESC Guidelines for the diagnosis and management of atrial fibrillation developed in collaboration with the European Association for Cardio-Thoracic Surgery (EACTS)

Gerhard Hindricks et al.

EUROPEAN HEART JOURNAL (2021)

Add to Collection

Article Chemistry, Analytical

Atrial Fibrillation Classification with Smart Wearables Using Short-Term Heart Rate Variability and Deep Convolutional Neural Networks

Jayroop Ramesh et al.

Summary: This study aims to generalize AF classification across ECG and PPG modalities using a unified knowledge representation. A one-dimensional deep convolutional neural network is used to classify normal sinus rhythm or atrial fibrillation using HRV-derived features from both ECG and PPG sensors. The model achieved high classification performance on ECG datasets and also performed well on unseen PPG datasets, indicating promising results for AF detection with consumer wearable devices.

SENSORS (2021)

Add to Collection

Review Cardiac & Cardiovascular Systems

How machine learning is impacting research in atrial fibrillation: implications for risk prediction and future management

Ivan Olier et al.

Summary: The exponential growth of artificial intelligence and machine learning publications in the field of atrial fibrillation mainly focuses on utilizing deep neural networks and open access databases for ML applications, with particular attention on using ECGs for AF detection. AI/ML can expand the utility of AF detection and risk prediction, leading to improvement in clinical care for patients with AF.

CARDIOVASCULAR RESEARCH (2021)

Add to Collection

Article Physiology

Wrist Band Photoplethysmography Autocorrelation Analysis Enables Detection of Atrial Fibrillation Without Pulse Detection

Eemu-Samuli Valiaho et al.

Summary: This study evaluated ten robust photoplethysmography features for detection of atrial fibrillation and found that autocorrelation was the most significant feature, reliably detecting atrial fibrillation without the need of pulse detection. Autocorrelation combined with pulse wave morphology-based features could provide a computationally effective and reliable wearable monitoring method in screening of atrial fibrillation.

FRONTIERS IN PHYSIOLOGY (2021)

Add to Collection

Article Computer Science, Interdisciplinary Applications

The feasibility of predicting impending malignant ventricular arrhythmias by using nonlinear features of short heartbeat intervals

Zheng Chen et al.

Summary: The study introduced a method to predict malignant ventricular arrhythmias using signal complexity, which was validated through machine learning model experiments. This research provides important theoretical and practical implications for cardiac arrest prevention.

COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE (2021)

Add to Collection

Article Computer Science, Artificial Intelligence