Automatic screening of patients with atrial fibrillation from 24-h Holter recording using deep learning

A knowledge embedded multimodal pseudo-siamese model for atrial fibrillation detection

Atrial fibrillation (AF) is a common arrhythmia disease with a higher incidence rate. The diagnosis of AF is time-consuming. Although many ECG classification models have been proposed to assist in AF detection, they are prone to misclassifying indistinguishable noise signals, and the context information of long-term signals is also ignored, which impacts the performance of AF detection. Considering all the above problems, we propose a knowledge embedded multimodal pseudo-siamese model. The proposed model comprises a temporal-spatial pseudo-siamese network (TSPS-Net) and a knowledge embedded noise filter module. Firstly, a parallel siamese network architecture is proposed in TSPS-Net to process the multimodal representations. Secondly, a spatiotemporal collaborative fusion mechanism (STCFM) is proposed to fuse multimodal features. Finally, medical knowledge is introduced to design manual features, which are used to distinguish noise and fuse with deep features of ECG to obtain the accurate final result. The model's performance is verified on the CinC 2017 dataset and the MIT-BIH AF dataset. Experimental results showed that the average accuracy achieved 82.17% and 99.11%. The F1 score of our proposed model on the CinC 2017 dataset and MIT-BIH dataset was 0.787 and 0.970, respectively.

SeqAFNet: A Beat-Wise Sequential Neural Network for Atrial Fibrillation Classification in Adhesive Patch-Type Electrocardiographs

Due to their convenience, adhesive patch-type electrocardiographs are commonly used for arrhythmia screening. This study aimed to develop a reliable method that can improve the classification performance of atrial fibrillation (AF) using these devices based on the 2020 European Society of Cardiology (ESC) guidelines for AF diagnosis in clinical practice. We developed a deep learning model that utilizes RR interval frames for precise, beat-wise classification of electrocardiogram (ECG) signals. This model is specifically designed to sequentially classify each R peak on the ECG, considering the rhythms surrounding each beat. It features a two-stage bidirectional Recurrent Neural Network (RNN) with a many-to-many architecture, which is particularly optimized for processing sequential and time-series data. The structure aims to extract local features and capture long-term dependencies associated with AF. After inference, outputs which indicating either AF or non-AF, derived from various temporal sequences are combined through an ensembling technique to enhance prediction accuracy. We collected AF data from a clinical trial that utilized the MEMO Patch, an adhesive patch-type electrocardiograph. When trained on public databases, the model demonstrated high accuracy on the patch dataset (accuracy: 0.986, precision: 0.981, sensitivity: 0.979, specificity: 0.992, and F1 score: 0.98), maintaining consistent performance across public datasets. SeqAFNet was robust for AF classification, making it a potential tool in real-world applications.

Artificial-intelligence-based risk prediction and mechanism discovery for atrial fibrillation using heart beat-to-beat intervals

BACKGROUND

Early diagnosis of atrial fibrillation (AF) is important for preventing stroke and other complications. Predicting AF risk in advance can improve early diagnostic efficiency. Deep learning has been used for disease risk prediction; however, it lacks adherence to evidence-based medicine standards. Identifying the underlying mechanisms behind disease risk prediction is important and required.

METHODS

We developed an explainable deep learning model called HBBI-AI to predict AF risk using only heart beat-to-beat intervals (HBBIs) during sinus rhythm. We proposed a possible AF mechanism based on the model's explainability and verified this conjecture using confirmed AF risk factors while also examining new AF risk factors. Finally, we investigated the changes in clinicians' ability to predict AF risk using only HBBIs before and after learning the model's explainability.

FINDINGS

HBBI-AI consistently performed well across large in-house and external public datasets. HBBIs with large changes or extreme stability were critical predictors for increased AF risk, and the underlying cause was autonomic imbalance. We verified various AF risk factors and discovered that autonomic imbalance was associated with all these factors. Finally, cardiologists effectively understood and learned from these findings to improve their abilities in AF risk prediction.

CONCLUSIONS

HBBI-AI effectively predicted AF risk using only HBBI information through evaluating autonomic imbalance. Autonomic imbalance may play an important role in many risk factors of AF rather than in a limited number of risk factors.

FUNDING

This study was supported in part by the National Key R&D Program and the National Natural Science Foundation of China.