ECG-based multi-class arrhythmia detection using spatio-temporal attention-based convolutional recurrent neural network.

Abstract:

:Automatic arrhythmia detection based on electrocardiogram (ECG) is of great significance for early prevention and diagnosis of cardiac diseases. Recently, deep learning methods have been applied to arrhythmia detection and obtained great success. Among them, convolutional neural network (CNN) is an effective method for extracting features due to its local connectivity and parameter sharing. In addition, recurrent neural network (RNN) is another commonly used method, which is applied to process time-series signal. The stacking of both CNN and RNN has been proved to be more effective in multi-class arrhythmia detection. However, these networks ignored the fact that different channels and temporal segments of a feature map extracted from the 12-lead ECG signal contribute differently to cardiac arrhythmia detection, and thus, the classification performance could be greatly improved. To address this issue, spatio-temporal attention-based convolutional recurrent neural network (STA-CRNN) is proposed to focus on representative features along both spatial and temporal axes. STA-CRNN consists of CNN subnetwork, spatio-temporal attention modules and RNN subnetwork. The experiment result shows that, STA-CRNN reaches an average F1 score of 0.835 in classifying 8 types of arrhythmias and normal rhythm. Compared with the state-of-the-art methods based on the same public dataset, STA-CRNN achieves an obvious improvement on identifying most of arrhythmias. Also, it is demonstrated by visualization that the learned features through STA-CRNN are in line with clinical judgement. STA-CRNN provides a promising method for automatic arrhythmia detection, which has a potential to assist cardiologists in the diagnosis of arrhythmias.

journal_name

Artif Intell Med

authors

Zhang J,Liu A,Gao M,Chen X,Zhang X,Chen X

doi

10.1016/j.artmed.2020.101856

subject

Has Abstract

pub_date

2020-06-01 00:00:00

pages

101856

eissn

0933-3657

issn

1873-2860

pii

S0933-3657(19)31260-6

journal_volume

106

pub_type

杂志文章
  • Modelling prognostic power of cardiac tests using rough sets.

    abstract::Rough sets (Pawlak Z. Rough Sets: Theoretical Aspects of Reasoning about Data, Dordrecht: Kluwer Academic Publishers, 1991) is a relatively new approach to representing and reasoning with incomplete and uncertain knowledge. This article introduces the basic concepts of rough sets and Boolean reasoning (Brown FM. Boole...

    journal_title:Artificial intelligence in medicine

    pub_type: 杂志文章

    doi:10.1016/s0933-3657(98)00051-7

    authors: Komorowski J,Ohrn A

    更新日期:1999-02-01 00:00:00

  • Pressure injury image analysis with machine learning techniques: A systematic review on previous and possible future methods.

    abstract::Pressure injuries represent a tremendous healthcare challenge in many nations. Elderly and disabled people are the most affected by this fast growing disease. Hence, an accurate diagnosis of pressure injuries is paramount for efficient treatment. The characteristics of these wounds are crucial indicators for the progr...

    journal_title:Artificial intelligence in medicine

    pub_type: 杂志文章

    doi:10.1016/j.artmed.2019.101742

    authors: Zahia S,Garcia Zapirain MB,Sevillano X,González A,Kim PJ,Elmaghraby A

    更新日期:2020-01-01 00:00:00

  • Analyzing depression tendency of web posts using an event-driven depression tendency warning model.

    abstract:OBJECTIVE:The Internet has become a platform to express individual moods/feelings of daily life, where authors share their thoughts in web blogs, micro-blogs, forums, bulletin board systems or other media. In this work, we investigate text-mining technology to analyze and predict the depression tendency of web posts. ...

    journal_title:Artificial intelligence in medicine

    pub_type: 杂志文章

    doi:10.1016/j.artmed.2015.10.003

    authors: Tung C,Lu W

    更新日期:2016-01-01 00:00:00

  • A hybrid expert system for the diagnosis of epileptic crisis.

    abstract::This work presents a hybrid expert system (HES) intended to minimise some complex problems pervasive to knowledge engineering such as: the knowledge elicitation process, known as the bottleneck of expert systems; the choice of a model for knowledge representation to codify human reasoning; the number of neurons in the...

    journal_title:Artificial intelligence in medicine

    pub_type: 杂志文章

    doi:10.1016/s0933-3657(00)00090-7

    authors: Brasil LM,de Azevedo FM,Barreto JM

    更新日期:2001-01-01 00:00:00

  • Towards a computer-aided diagnosis system for vocal cord diseases.

    abstract:OBJECTIVE:The objective of this work is to investigate a possibility of creating a computer-aided decision support system for an automated analysis of vocal cord images aiming to categorize diseases of vocal cords. METHODOLOGY:The problem is treated as a pattern recognition task. To obtain a concise and informative re...

    journal_title:Artificial intelligence in medicine

    pub_type: 杂志文章

    doi:10.1016/j.artmed.2004.11.001

    authors: Verikas A,Gelzinis A,Bacauskiene M,Uloza V

    更新日期:2006-01-01 00:00:00

  • Selection of patients for clinical trials: an interactive web-based system.

    abstract::The purpose of a clinical trial is to evaluate a new treatment procedure. When medical researchers conduct a trial, they recruit participants with appropriate health problems and medical histories. To select participants, they analyze medical records of the available patients, which has traditionally been a manual pro...

    journal_title:Artificial intelligence in medicine

    pub_type: 杂志文章

    doi:10.1016/j.artmed.2004.01.017

    authors: Fink E,Kokku PK,Nikiforou S,Hall LO,Goldgof DB,Krischer JP

    更新日期:2004-07-01 00:00:00

  • Automatic classification of epilepsy types using ontology-based and genetics-based machine learning.

    abstract:OBJECTIVES:In the presurgical analysis for drug-resistant focal epilepsies, the definition of the epileptogenic zone, which is the cortical area where ictal discharges originate, is usually carried out by using clinical, electrophysiological and neuroimaging data analysis. Clinical evaluation is based on the visual det...

    journal_title:Artificial intelligence in medicine

    pub_type: 杂志文章

    doi:10.1016/j.artmed.2014.03.001

    authors: Kassahun Y,Perrone R,De Momi E,Berghöfer E,Tassi L,Canevini MP,Spreafico R,Ferrigno G,Kirchner F

    更新日期:2014-06-01 00:00:00

  • Project INSIDE: towards autonomous semi-unstructured human-robot social interaction in autism therapy.

    abstract::This paper describes the INSIDE system, a networked robot system designed to allow the use of mobile robots as active players in the therapy of children with autism spectrum disorders (ASD). While a significant volume of work has explored the impact of robots in ASD therapy, most such work comprises remotely operated ...

    journal_title:Artificial intelligence in medicine

    pub_type: 杂志文章

    doi:10.1016/j.artmed.2018.12.003

    authors: Melo FS,Sardinha A,Belo D,Couto M,Faria M,Farias A,Gambôa H,Jesus C,Kinarullathil M,Lima P,Luz L,Mateus A,Melo I,Moreno P,Osório D,Paiva A,Pimentel J,Rodrigues J,Sequeira P,Solera-Ureña R,Vasco M,Veloso M,Vent

    更新日期:2019-05-01 00:00:00

  • A fuzzy cognitive map approach to differential diagnosis of specific language impairment.

    abstract::This paper presents a computer-based model for differential diagnosis of specific language impairment (SLI), a language disorder that, in many cases, cannot be easily diagnosed. This difficulty necessitates the development of a methodology to assist the speech therapist in the diagnostic process. The methodology tool ...

    journal_title:Artificial intelligence in medicine

    pub_type: 杂志文章

    doi:10.1016/s0933-3657(02)00076-3

    authors: Georgopoulos VC,Malandraki GA,Stylios CD

    更新日期:2003-11-01 00:00:00

  • Knowledge-assisted recognition of cluster boundaries in gene expression data.

    abstract:BACKGROUND AND MOTIVATION:DNA microarray technology has made it possible to determine the expression levels of thousands of genes in parallel under multiple experimental conditions. Genome-wide analyses using DNA microarrays make a great contribution to the exploration of the dynamic state of genetic networks, and furt...

    journal_title:Artificial intelligence in medicine

    pub_type: 杂志文章

    doi:10.1016/j.artmed.2005.02.007

    authors: Okada Y,Sahara T,Mitsubayashi H,Ohgiya S,Nagashima T

    更新日期:2005-09-01 00:00:00

  • A modular approach for representing and executing clinical guidelines.

    abstract::In this paper, we propose an approach for managing clinical guidelines. We outline a modular architecture, allowing us to separate two conceptually distinct aspects: the representation (and acquisition) of clinical guidelines and their execution. We propose an expressive formalism, which allows one to deal with the co...

    journal_title:Artificial intelligence in medicine

    pub_type: 杂志文章,评审

    doi:10.1016/s0933-3657(01)00087-2

    authors: Terenziani P,Molino G,Torchio M

    更新日期:2001-11-01 00:00:00

  • Adaptive dynamic programming algorithms for sequential appointment scheduling with patient preferences.

    abstract:OBJECTIVES:A well-developed appointment system can help increase the utilization of medical facilities in an outpatient department. This paper outlines the development of an appointment system that can make an outpatient department work more efficiently and improve patient satisfaction level. METHODS:A Markov decision...

    journal_title:Artificial intelligence in medicine

    pub_type: 杂志文章

    doi:10.1016/j.artmed.2014.12.002

    authors: Wang J,Fung RY

    更新日期:2015-01-01 00:00:00

  • Identification of sympathetic and parasympathetic nerves function in cardiovascular regulation using ANFIS approximation.

    abstract:OBJECTIVE:In this paper a new nonlinear system identification approach is developed for dynamical quantification of cardiovascular regulation. This approach is specifically focused on the identification of the heart rate (HR) baroreflex mechanism. The principal objective of this paper is to improve the model accuracy i...

    journal_title:Artificial intelligence in medicine

    pub_type: 杂志文章

    doi:10.1016/j.artmed.2011.01.002

    authors: Jalali A,Ghaffari A,Ghorbanian P,Nataraj C

    更新日期:2011-05-01 00:00:00

  • Heart murmur detection based on wavelet transformation and a synergy between artificial neural network and modified neighbor annealing methods.

    abstract::Early recognition of heart disease plays a vital role in saving lives. Heart murmurs are one of the common heart problems. In this study, Artificial Neural Network (ANN) is trained with Modified Neighbor Annealing (MNA) to classify heart cycles into normal and murmur classes. Heart cycles are separated from heart soun...

    journal_title:Artificial intelligence in medicine

    pub_type: 杂志文章

    doi:10.1016/j.artmed.2017.05.005

    authors: Eslamizadeh G,Barati R

    更新日期:2017-05-01 00:00:00

  • Using Arden Syntax for the creation of a multi-patient surveillance dashboard.

    abstract:OBJECTIVE:Most practically deployed Arden-Syntax-based clinical decision support (CDS) modules process data from individual patients. The specification of Arden Syntax, however, would in principle also support multi-patient CDS. The patient data management system (PDMS) at our local intensive care units does not native...

    journal_title:Artificial intelligence in medicine

    pub_type: 杂志文章

    doi:10.1016/j.artmed.2015.09.009

    authors: Kraus S,Drescher C,Sedlmayr M,Castellanos I,Prokosch HU,Toddenroth D

    更新日期:2018-11-01 00:00:00

  • Pattern identification of biomedical images with time series: Contrasting THz pulse imaging with DCE-MRIs.

    abstract:OBJECTIVE:We provide a survey of recent advances in biomedical image analysis and classification from emergent imaging modalities such as terahertz (THz) pulse imaging (TPI) and dynamic contrast-enhanced magnetic resonance images (DCE-MRIs) and identification of their underlining commonalities. METHODS:Both time and f...

    journal_title:Artificial intelligence in medicine

    pub_type: 杂志文章

    doi:10.1016/j.artmed.2016.01.005

    authors: Yin XX,Hadjiloucas S,Zhang Y,Su MY,Miao Y,Abbott D

    更新日期:2016-02-01 00:00:00

  • Brain-controlled applications using dynamic P300 speller matrices.

    abstract:OBJECTIVES:Access to the world wide web and multimedia content is an important aspect of life. We present a web browser and a multimedia user interface adapted for control with a brain-computer interface (BCI) which can be used by severely motor impaired persons. METHODS:The web browser dynamically determines the most...

    journal_title:Artificial intelligence in medicine

    pub_type: 杂志文章

    doi:10.1016/j.artmed.2014.12.001

    authors: Halder S,Pinegger A,Käthner I,Wriessnegger SC,Faller J,Pires Antunes JB,Müller-Putz GR,Kübler A

    更新日期:2015-01-01 00:00:00

  • Unveiling relevant non-motor Parkinson's disease severity symptoms using a machine learning approach.

    abstract:OBJECTIVE:Is it possible to predict the severity staging of a Parkinson's disease (PD) patient using scores of non-motor symptoms? This is the kickoff question for a machine learning approach to classify two widely known PD severity indexes using individual tests from a broad set of non-motor PD clinical scales only. ...

    journal_title:Artificial intelligence in medicine

    pub_type: 杂志文章

    doi:10.1016/j.artmed.2013.04.002

    authors: Armañanzas R,Bielza C,Chaudhuri KR,Martinez-Martin P,Larrañaga P

    更新日期:2013-07-01 00:00:00

  • Constructing explanatory process models from biological data and knowledge.

    abstract:OBJECTIVE:We address the task of inducing explanatory models from observations and knowledge about candidate biological processes, using the illustrative problem of modeling photosynthesis regulation. METHODS:We cast both models and background knowledge in terms of processes that interact to account for behavior. We a...

    journal_title:Artificial intelligence in medicine

    pub_type: 杂志文章

    doi:10.1016/j.artmed.2006.04.003

    authors: Langley P,Shiran O,Shrager J,Todorovski L,Pohorille A

    更新日期:2006-07-01 00:00:00

  • Extracting rules from pruned networks for breast cancer diagnosis.

    abstract::A new algorithm for neural network pruning is presented. Using this algorithm, networks with small number of connections and high accuracy rates for breast cancer diagnosis are obtained. We will then describe how rules can be extracted from a pruned network by considering only a finite number of hidden unit activation...

    journal_title:Artificial intelligence in medicine

    pub_type: 杂志文章

    doi:10.1016/0933-3657(95)00019-4

    authors: Setiono R

    更新日期:1996-02-01 00:00:00

  • From an expert-driven paper guideline to a user-centred decision support system: a usability comparison study.

    abstract:OBJECTIVE:To assess whether a user-centred prototype clinical decision support system (CDSS) providing patient-specific advice better supports healthcare practitioners in terms of (a) types of usability problems detected and (b) effective and efficient retrieval of childhood cancer survivor's follow-up screening proced...

    journal_title:Artificial intelligence in medicine

    pub_type: 杂志文章

    doi:10.1016/j.artmed.2013.04.004

    authors: Kilsdonk E,Peute LW,Riezebos RJ,Kremer LC,Jaspers MW

    更新日期:2013-09-01 00:00:00

  • A case-based reasoning system based on weighted heterogeneous value distance metric for breast cancer diagnosis.

    abstract:OBJECTIVE:We present the implementation and application of a case-based reasoning (CBR) system for breast cancer related diagnoses. By retrieving similar cases in a breast cancer decision support system, oncologists can obtain powerful information or knowledge, complementing their own experiential knowledge, in their m...

    journal_title:Artificial intelligence in medicine

    pub_type: 杂志文章

    doi:10.1016/j.artmed.2017.02.003

    authors: Gu D,Liang C,Zhao H

    更新日期:2017-03-01 00:00:00

  • Brain-computer interface controlled gaming: evaluation of usability by severely motor restricted end-users.

    abstract:OBJECTIVE:Connect-Four, a new sensorimotor rhythm (SMR) based brain-computer interface (BCI) gaming application, was evaluated by four severely motor restricted end-users; two were in the locked-in state and had unreliable eye-movement. METHODS:Following the user-centred approach, usability of the BCI prototype was ev...

    journal_title:Artificial intelligence in medicine

    pub_type: 杂志文章

    doi:10.1016/j.artmed.2013.08.001

    authors: Holz EM,Höhne J,Staiger-Sälzer P,Tangermann M,Kübler A

    更新日期:2013-10-01 00:00:00

  • Accessing complex patient data from Arden Syntax Medical Logic Modules.

    abstract:OBJECTIVE:Arden Syntax is a standard for representing and sharing medical knowledge in form of independent modules and looks back on a history of 25 years. Its traditional field of application is the monitoring of clinical events such as generating an alert in case of occurrence of a critical laboratory result. Arden S...

    journal_title:Artificial intelligence in medicine

    pub_type: 杂志文章

    doi:10.1016/j.artmed.2015.09.003

    authors: Kraus S,Enders M,Prokosch HU,Castellanos I,Lenz R,Sedlmayr M

    更新日期:2018-11-01 00:00:00

  • Evolving artificial neural networks for screening features from mammograms.

    abstract::Disagreement or inconsistencies in mammographic interpretation motivates utilizing computerized pattern recognition algorithms to aid the assessment of radiographic features. We have studied the potential for using artificial neural networks (ANNs) to analyze interpreted radiographic features from film screen mammogra...

    journal_title:Artificial intelligence in medicine

    pub_type: 杂志文章

    doi:10.1016/s0933-3657(98)00040-2

    authors: Fogel DB,Wasson EC 3rd,Boughton EM,Porto VW

    更新日期:1998-11-01 00:00:00

  • Development of systems for support of collaboration in health care: the design arenas.

    abstract::To explore the design of computer-supported collaborative work in health care, a case study is described addressing the social contexts and conditions influencing the development process. The data set covers 13 consecutive meetings held in a systems design group over a 2-year period, in total approximately 24 h of vid...

    journal_title:Artificial intelligence in medicine

    pub_type: 杂志文章

    doi:10.1016/s0933-3657(97)00046-8

    authors: Timpka T,Sjöberg C

    更新日期:1998-02-01 00:00:00

  • Automatic computation of mandibular indices in dental panoramic radiographs for early osteoporosis detection.

    abstract:AIM:A new automatic method for detecting specific points and lines (straight and curves) in dental panoramic radiographies (orthopantomographies) is proposed, where the human knowledge is mapped to the automatic system. The goal is to compute relevant mandibular indices (Mandibular Cortical Width, Panoramic Mandibular ...

    journal_title:Artificial intelligence in medicine

    pub_type: 杂志文章

    doi:10.1016/j.artmed.2020.101816

    authors: Aliaga I,Vera V,Vera M,García E,Pedrera M,Pajares G

    更新日期:2020-03-01 00:00:00

  • Owlready: Ontology-oriented programming in Python with automatic classification and high level constructs for biomedical ontologies.

    abstract:OBJECTIVE:Ontologies are widely used in the biomedical domain. While many tools exist for the edition, alignment or evaluation of ontologies, few solutions have been proposed for ontology programming interface, i.e. for accessing and modifying an ontology within a programming language. Existing query languages (such as...

    journal_title:Artificial intelligence in medicine

    pub_type: 杂志文章

    doi:10.1016/j.artmed.2017.07.002

    authors: Lamy JB

    更新日期:2017-07-01 00:00:00

  • Granular support vector machines with association rules mining for protein homology prediction.

    abstract:OBJECTIVE:Protein homology prediction between protein sequences is one of critical problems in computational biology. Such a complex classification problem is common in medical or biological information processing applications. How to build a model with superior generalization capability from training samples is an ess...

    journal_title:Artificial intelligence in medicine

    pub_type: 杂志文章

    doi:10.1016/j.artmed.2005.02.003

    authors: Tang Y,Jin B,Zhang YQ

    更新日期:2005-09-01 00:00:00

  • Bridge and brick network motifs: identifying significant building blocks from complex biological systems.

    abstract:OBJECTIVE:A major focus in computational system biology research is defining organizing principles that govern complex biological network formation and evolution. The task is considered a major challenge because network behavior and function prediction requires the identification of functionally and statistically impor...

    journal_title:Artificial intelligence in medicine

    pub_type: 杂志文章

    doi:10.1016/j.artmed.2007.07.006

    authors: Huang CY,Cheng CY,Sun CT

    更新日期:2007-10-01 00:00:00