What does this research mean for the field?

The application of deep learning to 1-D biosignals is currently dominated by ECG pattern detection using convolutional neural networks, but exhibits large methodological variability that requires future architectural standardization and optimization. Novelty: ClaimNovelty.SYNTHESIS. Consensus alignment: ConsensusAlignment.NEUTRAL.

August 1, 2018Open Access

Deep Learning on 1-D Biosignals: a Taxonomy-based Survey

Structured PICO

Population

71 research papers applying deep learning to 1-D biosignals (selected from 437 reviewed), published between January 2010 and December 2017.

Intervention

Deep learning techniques (including convolutional neural networks, recurrent neural networks, auto-encoders, and restricted Boltzmann machines)

Outcome

Taxonomy and classification of deep learning models based on biosignal origin, dimension, type, application goal, ground truth data, learning schedule, and network topology

Deep learning, particularly using convolutional neural networks, is increasingly applied to 1-D biosignals like ECG for pattern detection, though standardization and robust training data remain key challenges.

Abstract

OBJECTIVES: Deep learning models such as convolutional neural networks (CNNs) have been applied successfully to medical imaging, but biomedical signal analysis has yet to fully benefit from this novel approach. Our survey aims at (i) reviewing deep learning techniques for biosignal analysis in computer- aided diagnosis; and (ii) deriving a taxonomy for organizing the growing number of applications in the field. METHODS: A comprehensive literature research was performed using PubMed, Scopus, and ACM. Deep learning models were classified with respect to the (i) origin, (ii) dimension, and (iii) type of the biosignal as input to the deep learning model; (iv) the goal of the application; (v) the size and (vi) type of ground truth data; (vii) the type and (viii) schedule of learning the network; and (ix) the topology of the model. RESULTS: Between January 2010 and December 2017, a total 71 papers were published on the topic. The majority (n = 36) of papers are on electrocariography (ECG) signals. Most applications (n = 25) aim at detection of patterns, while only a few (n = 6) at predection of events. Out of 36 ECG-based works, many (n = 17) relate to multi-lead ECG. Other biosignals that have been identified in the survey are electromyography, phonocardiography, photoplethysmography, electrooculography, continuous glucose monitoring, acoustic respiratory signal, blood pressure, and electrodermal activity signal, while ballistocardiography or seismocardiography have yet to be analyzed using deep learning techniques. In supervised and unsupervised applications, CNNs and restricted Boltzmann machines are the most and least frequently used, (n = 34) and (n = 15), respectively. CONCLUSION: Our key-code classification of relevant papers was used to cluster the approaches that have been published to date and demonstrated a large variability of research with respect to data, application, and network topology. Future research is expected to focus on the standardization of deep learning architectures and on the optimization of the network parameters to increase performance and robustness. Furthermore, application-driven approaches and updated training data from mobile recordings are needed.

Ask AI

Helpful

Bookmark

View Full Paper