Clinical 12-lead electrocardiography (ECG) is one of the most widely encountered kinds of biosignals. Despite the increased availability of public ECG datasets, label scarcity remains a central challenge in the field. Self-supervised learning represents a promising way to alleviate this issue. This would allow to train more powerful models given the same amount of labeled data and to incorporate or improve predictions about rare diseases, for which training datasets are inherently limited. In this work, we put forward the first comprehensive assessment of self-supervised representation learning from clinical 12-lead ECG data. To this end, we adapt state-of-the-art self-supervised methods based on instance discrimination and latent forecasting to the ECG domain. In a first step, we learn contrastive representations and evaluate their quality based on linear evaluation performance on a recently established, comprehensive, clinical ECG classification task. In a second step, we analyze the impact of self-supervised pretraining on finetuned ECG classifiers as compared to purely supervised performance. For the best-performing method, an adaptation of contrastive predictive coding, we find a linear evaluation performance only 0.5% below supervised performance. For the finetuned models, we find improvements in downstream performance of roughly 1% compared to supervised performance, label efficiency, as well as robustness against physiological noise. This work clearly establishes the feasibility of extracting discriminative representations from ECG data via self-supervised learning and the numerous advantages when finetuning such representations on downstream tasks as compared to purely supervised training. As first comprehensive assessment of its kind in the ECG domain carried out exclusively on publicly available datasets, we hope to establish a first step towards reproducible progress in the rapidly evolving field of representation learning for biosignals.
Download full-text PDF |
Source |
|---|---|
| http://dx.doi.org/10.1016/j.compbiomed.2021.105114 | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
Enhancing waste classification accuracy with Channel and Spatial Attention-Based Multiblock Convolutional Network.
Environ Monit Assess
January 2025
Department of Computer Science and Engineering, Sathyabama Institute of Science and Technology, Shollinganallur, Chennai, India.
Municipal waste classification is significant for effective recycling and waste management processes that involve the classification of diverse municipal waste materials such as paper, glass, plastic, and organic matter using diverse techniques. Yet, this municipal waste classification process faces several challenges, such as high computational complexity, more time consumption, and high variability in the appearance of waste caused by variations in color, type, and degradation level, which makes an inaccurate waste classification process. To overcome these challenges, this research proposes a novel Channel and Spatial Attention-Based Multiblock Convolutional Network for accurately classifying municipal waste that utilizes a unique attention mechanism for enhancing feature learning and waste classification accuracy.
View Article and Find Full Text PDFA multiscale molecular structural neural network for molecular property prediction.
Mol Divers
January 2025
Key Laboratory for Macromolecular Science of Shaanxi Province, School of Chemistry and Chemical Engineering, Shaanxi Normal University, Xi'an, 710119, People's Republic of China.
Molecular Property Prediction (MPP) is a fundamental task in important research fields such as chemistry, materials, biology, and medicine, where traditional computational chemistry methods based on quantum mechanics often consume substantial time and computing power. In recent years, machine learning has been increasingly used in computational chemistry, in which graph neural networks have shown good performance in molecular property prediction tasks, but they have some limitations in terms of generalizability, interpretability, and certainty. In order to address the above challenges, a Multiscale Molecular Structural Neural Network (MMSNet) is proposed in this paper, which obtains rich multiscale molecular representations through the information fusion between bonded and non-bonded "message passing" structures at the atomic scale and spatial feature information "encoder-decoder" structures at the molecular scale; a multi-level attention mechanism is introduced on the basis of theoretical analysis of molecular mechanics in order to enhance the model's interpretability; the prediction results of MMSNet are used as label values and clustered in the molecular library by the K-NN (K-Nearest Neighbors) algorithm to reverse match the spatial structure of the molecules, and the certainty of the model is quantified by comparing virtual screening results across different K-values.
View Article and Find Full Text PDFIn the context of Chinese clinical texts, this paper aims to propose a deep learning algorithm based on Bidirectional Encoder Representation from Transformers (BERT) to identify privacy information and to verify the feasibility of our method for privacy protection in the Chinese clinical context. We collected and double-annotated 33,017 discharge summaries from 151 medical institutions on a municipal regional health information platform, developed a BERT-based Bidirectional Long Short-Term Memory Model (BiLSTM) and Conditional Random Field (CRF) model, and tested the performance of privacy identification on the dataset. To explore the performance of different substructures of the neural network, we created five additional baseline models and evaluated the impact of different models on performance.
View Article and Find Full Text PDFUnleashing the Potential of Pre-Trained Diffusion Models for Generalizable Person Re-Identification.
Sensors (Basel)
January 2025
College of Information Science and Electronic Engineering, Zhejiang University, Hangzhou 310027, China.
Domain-generalizable re-identification (DG Re-ID) aims to train a model on one or more source domains and evaluate its performance on unseen target domains, a task that has attracted growing attention due to its practical relevance. While numerous methods have been proposed, most rely on discriminative or contrastive learning frameworks to learn generalizable feature representations. However, these approaches often fail to mitigate shortcut learning, leading to suboptimal performance.
View Article and Find Full Text PDFZero-Shot Traffic Identification with Attribute and Graph-Based Representations for Edge Computing.
Sensors (Basel)
January 2025
School of Economics and Management, Beijing Information Science & Technology University, Beijing 100192, China.
With the proliferation of mobile terminals and the rapid growth of network applications, fine-grained traffic identification has become increasingly challenging. Methods based on machine learning and deep learning have achieved remarkable results, but they heavily rely on the distribution of training data, which makes them ineffective in handling unseen samples. In this paper, we propose AG-ZSL, a zero-shot learning framework based on traffic behavior and attribute representations for general encrypted traffic classification.
View Article and Find Full Text PDFWant AI Summaries of new PubMed Abstracts delivered to your In-box?
Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!