CN107657318A - A kind of electrocardiogram sorting technique based on deep learning model - Google Patents

A kind of electrocardiogram sorting technique based on deep learning model Download PDF

Info

Publication number
CN107657318A
CN107657318A CN201711114287.0A CN201711114287A CN107657318A CN 107657318 A CN107657318 A CN 107657318A CN 201711114287 A CN201711114287 A CN 201711114287A CN 107657318 A CN107657318 A CN 107657318A
Authority
CN
China
Prior art keywords
data
electrocardiogram
model
deep learning
ecg
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN201711114287.0A
Other languages
Chinese (zh)
Inventor
蔡源涛
赵二超
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Chengdu Blue Scene Information Technology Co Ltd
Original Assignee
Chengdu Blue Scene Information Technology Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Chengdu Blue Scene Information Technology Co Ltd filed Critical Chengdu Blue Scene Information Technology Co Ltd
Priority to CN201711114287.0A priority Critical patent/CN107657318A/en
Publication of CN107657318A publication Critical patent/CN107657318A/en
Pending legal-status Critical Current

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/045—Combinations of networks
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/24—Detecting, measuring or recording bioelectric or biomagnetic signals of the body or parts thereof
    • A61B5/316—Modalities, i.e. specific diagnostic methods
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/24—Detecting, measuring or recording bioelectric or biomagnetic signals of the body or parts thereof
    • A61B5/316—Modalities, i.e. specific diagnostic methods
    • A61B5/318—Heart-related electrical modalities, e.g. electrocardiography [ECG]
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
    • A61B5/7235—Details of waveform analysis
    • A61B5/7264—Classification of physiological signals or data, e.g. using neural networks, statistical classifiers, expert systems or fuzzy systems
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/048—Activation functions
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/08—Learning methods

Landscapes

  • Health & Medical Sciences (AREA)
  • Engineering & Computer Science (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Physics & Mathematics (AREA)
  • Biomedical Technology (AREA)
  • Biophysics (AREA)
  • Theoretical Computer Science (AREA)
  • General Health & Medical Sciences (AREA)
  • Molecular Biology (AREA)
  • Artificial Intelligence (AREA)
  • Mathematical Physics (AREA)
  • Evolutionary Computation (AREA)
  • Software Systems (AREA)
  • Surgery (AREA)
  • General Physics & Mathematics (AREA)
  • Computing Systems (AREA)
  • Data Mining & Analysis (AREA)
  • Computational Linguistics (AREA)
  • Pathology (AREA)
  • Heart & Thoracic Surgery (AREA)
  • Medical Informatics (AREA)
  • General Engineering & Computer Science (AREA)
  • Animal Behavior & Ethology (AREA)
  • Public Health (AREA)
  • Veterinary Medicine (AREA)
  • Cardiology (AREA)
  • Fuzzy Systems (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Physiology (AREA)
  • Psychiatry (AREA)
  • Signal Processing (AREA)
  • Measurement And Recording Of Electrical Phenomena And Electrical Characteristics Of The Living Body (AREA)

Abstract

The present invention discloses a kind of electrocardiogram sorting technique based on deep learning model, it is characterised in that：Including steps such as data acquisition, data processing, model construction, optimized algorithm, model trainings.The present invention solves the technical problem of carrying out arrhythmia cordis differentiation by ECG data, auxiliary and reference are provided for doctor, it is serious uneven to solve some areas doctor supply, mistaken diagnosis, the problems such as rate of missed diagnosis is higher.By implementing, this method has the advantages that：The present invention uses depth method, and rhythm abnormality detection is carried out to ECG information by building extensive convolutional neural networks.Compare with for traditional approach, save cost and also the degree of accuracy it is higher.

Description

A kind of electrocardiogram sorting technique based on deep learning model
Technical field
The present invention relates to electrocardiogram classification association area, is especially a kind of electrocardiogram classification based on deep learning model Method.
Background technology
It is well known that electrocardiogram waveform data collection and electrocardiogram classification results are the important of diagnosis heart disease illness Supplementary means and reference information, usual electrocardiogram waveform data collection and classification are in hospital or medical center progress, inspection be present The shortcomings such as inconvenient, detection frequency is low are surveyed, and electrocardiogram classification information can not be supplied to doctor in time and be examined in real time to do It is disconnected, it is difficult to effectively prevention and in time treatment heart disease lesion.In recent years, with network, the popularization of intelligent movable mobile phone so that The release of portable type electrocardioscanner, household person motive electric wave monitor is possibly realized.This kind of prison released in the market Instrument is surveyed, the classification of its foundation is traditional measurement classification, is usually first measured after the cut-off of each waveform to waveform Classified, then select distinct methods to calculate required Characteristics of electrocardiogram parameter based on type of waveform again.By electrocardiogram The conventional ECG computer automatic sorting algorithm that characteristic parameter input is established based on medical knowledge, it is possible to obtain electrocardiogram Classification results.
But by analysis it is seen that, following shortcoming be present in existing mode of operation：
One：Existing mode of operation needs to do substantial amounts of Feature Engineering, expends substantial amounts of work energy；
Secondly：Existing mode of operation needs the expertise of medical domain, expends substantial amounts of human resources；
Thirdly：It is not very high for more than the ten kinds of arrhythmia cordis type classification degrees of accuracy when existing mode of operation is implemented.
The content of the invention
The present invention provides a kind of electrocardiogram sorting technique based on deep learning model herein；Its technology mainly solved is asked Topic is to carry out arrhythmia cordis differentiation by ECG data, and auxiliary and reference are provided for doctor, solves some areas doctor and supplies To serious imbalance, mistaken diagnosis, the problems such as rate of missed diagnosis is higher.
The present invention is achieved in that a kind of electrocardiogram sorting technique based on deep learning model of construction, and its feature exists In：Realize as follows；
Step 1, data acquisition：Gather substantial amounts of ECG data；Obtain original time span 30 seconds, sample frequency is 300HZ electrocardiogram electric potential signal data；
Step 2, data processing：Using single channel, the cycle is the electrocardiogram of 30 seconds, by native state potential digital signal data numerical value Change, be normalized；Corpus is divided into training set, checking collection, test set, ratio 8:1:1；Data prediction, to original Beginning potential value divided by voltage magnitude, then do normalized；
Step 3, model construction：Multilayer convolutional neural networks are built, last layer of model is the softmax for handling more classification tasks Layer；
Step 4, optimized algorithm：In order to optimize the network, data are made to can adapt to network, using residual error network, to each convolution Layer, using Batch Normalization, DropOut, MaxPooling and correct the technologies such as linear activation primitive；
Step 5, model training：Data after processing are imported into deep learning model, by dozens of cycle of training, search is compared Preferable parameter, the level close to even more than electrocardio expert doctor has been finally reached it；
Step 6, model exports：It will be input in the model trained, pass through after a unknown electrocardiogram (ECG) data pretreatment Model calculation draws the result of the electrocardiogram (ECG) data；Exception is determined whether, if abnormal belong to the arrhythmia cordis of which kind；Pass through Model exports, by the data input after processing into network, by the result predicted after calculating, for doctor's auxiliary treatment.
According to a kind of electrocardiogram sorting technique based on deep learning model of the present invention, it is characterised in that：It is wherein right For step 1, data acquisition includes the initial data of normal, noise and tens of kinds of arrhythmia cordis.
The invention has the advantages that：The present invention provides a kind of electrocardiogram classification side based on deep learning model herein Method；It provides auxiliary and ginseng mainly solving the technical problems that carry out arrhythmia cordis differentiation by ECG data, for doctor Examine, it is serious uneven to solve some areas doctor supply, mistaken diagnosis, the problems such as rate of missed diagnosis is higher.By implementing, this method tool Have the advantages that：This patent uses depth method, and ECG information is entered by building extensive convolutional neural networks Row rhythm abnormality detects.Compare and had the advantage that with conventional method：
（1）Save cost：Model is learning method end to end, it is not necessary to from extracting data complex characteristic, it is not necessary to by Medical expert knowledge.Only need to provide the mass data input convolutional neural networks marked, the knot that then output model judges Fruit.
（2）The degree of accuracy is higher：On the basis of having substantial amounts of data set, by Optimal Parameters, model can reach higher The degree of accuracy, approach the average level of even more than electrocardio expert doctor.
Brief description of the drawings
Fig. 1 is the implementing procedure block diagram of electrocardiogram sorting technique of the present invention；
Fig. 2 is instance graph corresponding to implementation steps 1 of the present invention；
Fig. 3 is instance graph corresponding to implementation steps 2 of the present invention；
Fig. 4 is instance graph corresponding to implementation steps 3 of the present invention；
Fig. 5 is instance graph corresponding to implementation steps 6 of the present invention.
Embodiment
Below in conjunction with accompanying drawing 1- Fig. 5, the present invention is described in detail, and the technical scheme in the embodiment of the present invention is entered Row clearly and completely describes, it is clear that described embodiment is only part of the embodiment of the present invention, rather than whole realities Apply example.Based on the embodiment in the present invention, those of ordinary skill in the art are obtained under the premise of creative work is not made Every other embodiment, belong to the scope of protection of the invention.
The present invention provides a kind of electrocardiogram sorting technique based on deep learning model herein by improving；According to such as lower section Formula is realized, referring to such as Fig. 1；
Step 1, data acquisition：Gather substantial amounts of ECG data, including normal, noise and tens of kinds of arrhythmia cordis is original Data；
Step 2, data processing：We use single channel, and the cycle is the electrocardiogram of 30 seconds, by native state potential digital signal data number Value, it is normalized.Corpus is divided into training set, checking collection, test set, ratio 8:1:1；
Step 3, model construction：Multilayer convolutional neural networks are built, last layer of model is the softmax for handling more classification tasks Layer；
Step 4, optimized algorithm：In order to optimize the network, data are made to can adapt to network, we use residual error network, to each Convolutional layer, using Batch Normalization, DropOut, MaxPooling and correct the technologies such as linear activation primitive；
Step 5, model training：Data after processing are imported into deep learning model, by dozens of cycle of training, search is compared Preferable parameter, the level close to even more than electrocardio expert doctor has been finally reached it.
Step 6, model exports：The model that we have trained is input to after one unknown electrocardiogram (ECG) data is pre-processed In, the result of the electrocardiogram (ECG) data is drawn by model calculation（It is whether abnormal, if abnormal belong to the arrhythmia cordis of which kind）.
By described above, this method has the advantages that：
This patent uses depth method, and rhythm abnormality inspection is carried out to ECG information by building extensive convolutional neural networks Survey.Compare and had the advantage that with conventional method：
（1）Save cost：Model is learning method end to end, it is not necessary to from extracting data complex characteristic, it is not necessary to by Medical expert knowledge.Only need to provide the mass data input convolutional neural networks marked, the knot that then output model judges Fruit.
（2）The degree of accuracy is higher：On the basis of having substantial amounts of data set, by Optimal Parameters, model can reach higher The degree of accuracy, approach the average level of even more than electrocardio expert doctor.
The foregoing description of the disclosed embodiments, professional and technical personnel in the field are enable to realize or using the present invention. A variety of modifications to these embodiments will be apparent for those skilled in the art, as defined herein General Principle can be realized in other embodiments without departing from the spirit or scope of the present invention.Therefore, it is of the invention The embodiments shown herein is not intended to be limited to, and is to fit to and principles disclosed herein and features of novelty phase one The most wide scope caused.

Claims (2)

  1. A kind of 1. electrocardiogram sorting technique based on deep learning model, it is characterised in that：Realize as follows；
    Step 1, data acquisition：Gather substantial amounts of ECG data；Obtain original time span 30 seconds, sample frequency is 300HZ electrocardiogram electric potential signal data；
    Step 2, data processing：Using single channel, the cycle is the electrocardiogram of 30 seconds, by native state potential digital signal data numerical value Change, be normalized；Corpus is divided into training set, checking collection, test set, ratio 8:1:1；Data prediction, to original Beginning potential value divided by voltage magnitude, then do normalized；
    Step 3, model construction：Multilayer convolutional neural networks are built, last layer of model is the softmax for handling more classification tasks Layer；
    Step 4, optimized algorithm：In order to optimize the network, data are made to can adapt to network, using residual error network, to each convolution Layer, using Batch Normalization, DropOut, MaxPooling and correct the technologies such as linear activation primitive；
    Step 5, model training：Data after processing are imported into deep learning model, by dozens of cycle of training, search is compared Preferable parameter, the level close to even more than electrocardio expert doctor has been finally reached it；
    Step 6, model exports：It will be input in the model trained, pass through after a unknown electrocardiogram (ECG) data pretreatment Model calculation draws the result of the electrocardiogram (ECG) data；Exception is determined whether, if abnormal belong to the arrhythmia cordis of which kind；Pass through Model exports, by the data input after processing into network, by the result predicted after calculating, for doctor's auxiliary treatment.
  2. A kind of 2. electrocardiogram sorting technique based on deep learning model according to claim 1, it is characterised in that：It is wherein right For step 1, data acquisition includes the initial data of normal, noise and tens of kinds of arrhythmia cordis.
CN201711114287.0A 2017-11-13 2017-11-13 A kind of electrocardiogram sorting technique based on deep learning model Pending CN107657318A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201711114287.0A CN107657318A (en) 2017-11-13 2017-11-13 A kind of electrocardiogram sorting technique based on deep learning model

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201711114287.0A CN107657318A (en) 2017-11-13 2017-11-13 A kind of electrocardiogram sorting technique based on deep learning model

Publications (1)

Publication Number Publication Date
CN107657318A true CN107657318A (en) 2018-02-02

Family

ID=61121212

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201711114287.0A Pending CN107657318A (en) 2017-11-13 2017-11-13 A kind of electrocardiogram sorting technique based on deep learning model

Country Status (1)

Country Link
CN (1) CN107657318A (en)

Cited By (29)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108564167A (en) * 2018-04-09 2018-09-21 杭州乾圆科技有限公司 The recognition methods of abnormal data among a kind of data set
CN108606798A (en) * 2018-05-10 2018-10-02 东北大学 Contactless atrial fibrillation intelligent checking system based on depth convolution residual error network
CN108852347A (en) * 2018-07-13 2018-11-23 京东方科技集团股份有限公司 For extracting the method for the characteristic parameter of cardiac arrhythmia, the device and computer-readable medium of cardiac arrhythmia for identification
CN108960050A (en) * 2018-05-25 2018-12-07 东软集团股份有限公司 Classification model training method, ECG data classifying method, device and equipment
CN108986913A (en) * 2018-07-13 2018-12-11 希蓝科技（北京）有限公司 A kind of optimization artificial intelligence cardiac diagnosis method and system
CN109044340A (en) * 2018-08-29 2018-12-21 北京航空航天大学 Electrocardiogram (ECG) data classification method, device, electronic equipment and storage medium
CN109222963A (en) * 2018-11-21 2019-01-18 燕山大学 A kind of anomalous ecg method for identifying and classifying based on convolutional neural networks
CN109480824A (en) * 2018-12-11 2019-03-19 武汉中旗生物医疗电子有限公司 Processing method, device and the server of EGC waveform data
CN109645983A (en) * 2019-01-09 2019-04-19 南京航空航天大学 A kind of uneven beat classification method based on multimode neural network
CN109846474A (en) * 2019-03-26 2019-06-07 深圳市理邦精密仪器股份有限公司 The processing method and processing device of electrocardiogram, the long-range processing method of electrocardiogram and system
CN109864714A (en) * 2019-04-04 2019-06-11 北京邮电大学 A kind of ECG Signal Analysis method based on deep learning
CN109886967A (en) * 2019-01-16 2019-06-14 成都蓝景信息技术有限公司 Lung anatomy position location algorithms based on depth learning technology
CN109948647A (en) * 2019-01-24 2019-06-28 西安交通大学 A kind of electrocardiogram classification method and system based on depth residual error network
CN109998532A (en) * 2019-06-04 2019-07-12 广州视源电子科技股份有限公司 Electrocardiosignal identification method and device based on multi-lead multi-structure aggregation network
CN110008674A (en) * 2019-03-25 2019-07-12 浙江大学 A kind of electrocardiosignal identity identifying method of high generalization
CN110046604A (en) * 2019-04-25 2019-07-23 成都信息工程大学 A kind of single lead ECG arrhythmia detection classification method based on residual error network
CN110141216A (en) * 2019-05-29 2019-08-20 清华大学深圳研究生院 A kind of recognition methods, training method and the system of electrocardiosignal QRS characteristic wave
WO2019205067A1 (en) * 2018-04-27 2019-10-31 Vita-Course Technologies Co., Ltd. Systems and methods for determining an arrhythmia type
CN110680278A (en) * 2019-09-10 2020-01-14 广州视源电子科技股份有限公司 Electrocardiosignal recognition device based on convolutional neural network
CN110731773A (en) * 2019-10-28 2020-01-31 浙江工业大学 abnormal electrocardiogram screening method based on fusion of global and local depth features of electrocardiogram
CN110974214A (en) * 2019-12-20 2020-04-10 华中科技大学 Automatic electrocardiogram classification method, system and equipment based on deep learning
CN111134662A (en) * 2020-02-17 2020-05-12 武汉大学 Electrocardio abnormal signal identification method and device based on transfer learning and confidence degree selection
CN111460951A (en) * 2020-03-25 2020-07-28 西安交通大学 Electrocardiosignal automatic analysis method based on deep learning
CN111557660A (en) * 2020-06-08 2020-08-21 东北大学 Arrhythmia identification method under sub-population deep learning framework
CN111956208A (en) * 2020-08-27 2020-11-20 电子科技大学 ECG signal classification method based on ultra-lightweight convolutional neural network
CN112232253A (en) * 2020-10-26 2021-01-15 南通大学 Fetal electrocardiogram abnormity detection method driven by rough and reasonable granularity
WO2021027224A1 (en) * 2019-08-12 2021-02-18 广州视源电子科技股份有限公司 Electrocardiosignal recognition apparatus and method based on group convolutional neural network
CN112804937A (en) * 2018-10-01 2021-05-14 雷诺兹·德尔加多 High frequency QRS in biometric identification
CN114159070A (en) * 2021-12-20 2022-03-11 武汉大学 Real-time cardiac arrest risk prediction method and system of convolutional neural network

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101411617A (en) * 2008-11-20 2009-04-22 杭州先控信息科技有限公司 Remote electrocardiogram monitor system based on wireless sensor network
CN101785670A (en) * 2009-01-22 2010-07-28 陈跃军 Intelligent blurry electrocardiogram on-line analyzer system
CN103886184A (en) * 2014-03-03 2014-06-25 浙江大学 Construction method for heart pathology recognition model
CN105726018A (en) * 2016-02-06 2016-07-06 河北大学 Automatic atrial fibrillation detection method irrelevant to RR interphase
CN105748063A (en) * 2016-04-25 2016-07-13 山东大学齐鲁医院 Intelligent arrhythmia diagnosis method based on multiple-lead and convolutional neural network

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101411617A (en) * 2008-11-20 2009-04-22 杭州先控信息科技有限公司 Remote electrocardiogram monitor system based on wireless sensor network
CN101785670A (en) * 2009-01-22 2010-07-28 陈跃军 Intelligent blurry electrocardiogram on-line analyzer system
CN103886184A (en) * 2014-03-03 2014-06-25 浙江大学 Construction method for heart pathology recognition model
CN105726018A (en) * 2016-02-06 2016-07-06 河北大学 Automatic atrial fibrillation detection method irrelevant to RR interphase
CN105748063A (en) * 2016-04-25 2016-07-13 山东大学齐鲁医院 Intelligent arrhythmia diagnosis method based on multiple-lead and convolutional neural network

Non-Patent Citations (3)

* Cited by examiner, † Cited by third party
Title
MOHAMAD M.ALRAHHAL: ""Deep Learning Approach for Active Classification of Electrocardiogram Signals"", 《INTFORMATION SCIENCE》 *
PRANAV RAJPURKAR ET AL.: ""Cardiologist-Level Arrhythmia Detection with Convolutional Neural Networks"", 《ARXIV》 *
谢秋玲: ""应用于心电图分类的两种数据输入模式的对比"", 《上海工程技术大学学报》 *

Cited By (41)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108564167A (en) * 2018-04-09 2018-09-21 杭州乾圆科技有限公司 The recognition methods of abnormal data among a kind of data set
CN108564167B (en) * 2018-04-09 2020-07-31 杭州乾圆科技有限公司 Method for identifying abnormal data in data set
CN112312836A (en) * 2018-04-27 2021-02-02 深圳市长桑技术有限公司 System and method for determining type of arrhythmia
WO2019205067A1 (en) * 2018-04-27 2019-10-31 Vita-Course Technologies Co., Ltd. Systems and methods for determining an arrhythmia type
US11534099B2 (en) 2018-04-27 2022-12-27 Vita-Course Technologies Co., Ltd. Systems and methods for determining an arrhythmia type
CN108606798A (en) * 2018-05-10 2018-10-02 东北大学 Contactless atrial fibrillation intelligent checking system based on depth convolution residual error network
CN108606798B (en) * 2018-05-10 2021-03-02 东北大学 Non-contact atrial fibrillation intelligent detection system based on deep convolution residual error network
CN108960050A (en) * 2018-05-25 2018-12-07 东软集团股份有限公司 Classification model training method, ECG data classifying method, device and equipment
US11389101B2 (en) 2018-07-13 2022-07-19 Boe Technology Group Co., Ltd. Method and device for identifying arrhythmia, and computer readable medium
CN108852347A (en) * 2018-07-13 2018-11-23 京东方科技集团股份有限公司 For extracting the method for the characteristic parameter of cardiac arrhythmia, the device and computer-readable medium of cardiac arrhythmia for identification
CN108986913A (en) * 2018-07-13 2018-12-11 希蓝科技（北京）有限公司 A kind of optimization artificial intelligence cardiac diagnosis method and system
CN109044340A (en) * 2018-08-29 2018-12-21 北京航空航天大学 Electrocardiogram (ECG) data classification method, device, electronic equipment and storage medium
CN112804937A (en) * 2018-10-01 2021-05-14 雷诺兹·德尔加多 High frequency QRS in biometric identification
CN109222963A (en) * 2018-11-21 2019-01-18 燕山大学 A kind of anomalous ecg method for identifying and classifying based on convolutional neural networks
CN109480824B (en) * 2018-12-11 2021-10-08 武汉中旗生物医疗电子有限公司 Method and device for processing electrocardio waveform data and server
CN109480824A (en) * 2018-12-11 2019-03-19 武汉中旗生物医疗电子有限公司 Processing method, device and the server of EGC waveform data
CN109645983A (en) * 2019-01-09 2019-04-19 南京航空航天大学 A kind of uneven beat classification method based on multimode neural network
CN109886967A (en) * 2019-01-16 2019-06-14 成都蓝景信息技术有限公司 Lung anatomy position location algorithms based on depth learning technology
CN109948647A (en) * 2019-01-24 2019-06-28 西安交通大学 A kind of electrocardiogram classification method and system based on depth residual error network
CN110008674A (en) * 2019-03-25 2019-07-12 浙江大学 A kind of electrocardiosignal identity identifying method of high generalization
CN110008674B (en) * 2019-03-25 2020-10-16 浙江大学 High-generalization electrocardiosignal identity authentication method
CN109846474B (en) * 2019-03-26 2022-04-05 深圳市理邦精密仪器股份有限公司 Processing method and device of electrocardiogram and remote processing method and system of electrocardiogram
CN109846474A (en) * 2019-03-26 2019-06-07 深圳市理邦精密仪器股份有限公司 The processing method and processing device of electrocardiogram, the long-range processing method of electrocardiogram and system
CN109864714A (en) * 2019-04-04 2019-06-11 北京邮电大学 A kind of ECG Signal Analysis method based on deep learning
CN110046604A (en) * 2019-04-25 2019-07-23 成都信息工程大学 A kind of single lead ECG arrhythmia detection classification method based on residual error network
CN110141216B (en) * 2019-05-29 2022-09-30 清华大学深圳研究生院 Identification method, training method and system for QRS (QRS) characteristic waves of electrocardiosignals
CN110141216A (en) * 2019-05-29 2019-08-20 清华大学深圳研究生院 A kind of recognition methods, training method and the system of electrocardiosignal QRS characteristic wave
CN109998532A (en) * 2019-06-04 2019-07-12 广州视源电子科技股份有限公司 Electrocardiosignal identification method and device based on multi-lead multi-structure aggregation network
WO2021027224A1 (en) * 2019-08-12 2021-02-18 广州视源电子科技股份有限公司 Electrocardiosignal recognition apparatus and method based on group convolutional neural network
CN110680278B (en) * 2019-09-10 2022-07-19 广州视源电子科技股份有限公司 Electrocardiosignal recognition device based on convolutional neural network
CN110680278A (en) * 2019-09-10 2020-01-14 广州视源电子科技股份有限公司 Electrocardiosignal recognition device based on convolutional neural network
CN110731773A (en) * 2019-10-28 2020-01-31 浙江工业大学 abnormal electrocardiogram screening method based on fusion of global and local depth features of electrocardiogram
CN110731773B (en) * 2019-10-28 2022-10-28 浙江工业大学 Abnormal electrocardiogram screening method based on fusion of global and local depth features of electrocardiogram
CN110974214A (en) * 2019-12-20 2020-04-10 华中科技大学 Automatic electrocardiogram classification method, system and equipment based on deep learning
CN111134662A (en) * 2020-02-17 2020-05-12 武汉大学 Electrocardio abnormal signal identification method and device based on transfer learning and confidence degree selection
CN111460951A (en) * 2020-03-25 2020-07-28 西安交通大学 Electrocardiosignal automatic analysis method based on deep learning
CN111557660A (en) * 2020-06-08 2020-08-21 东北大学 Arrhythmia identification method under sub-population deep learning framework
CN111956208A (en) * 2020-08-27 2020-11-20 电子科技大学 ECG signal classification method based on ultra-lightweight convolutional neural network
CN112232253B (en) * 2020-10-26 2021-11-09 南通大学 Fetal electrocardiogram abnormity detection method driven by rough and reasonable granularity
CN112232253A (en) * 2020-10-26 2021-01-15 南通大学 Fetal electrocardiogram abnormity detection method driven by rough and reasonable granularity
CN114159070A (en) * 2021-12-20 2022-03-11 武汉大学 Real-time cardiac arrest risk prediction method and system of convolutional neural network

Similar Documents

Publication Publication Date Title
CN107657318A (en) A kind of electrocardiogram sorting technique based on deep learning model
CN107837082A (en) Electrocardiogram automatic analysis method and device based on artificial intelligence self study
US20200015694A1 (en) Automatic method to delineate or categorize an electrocardiogram
Pecchia et al. Remote health monitoring of heart failure with data mining via CART method on HRV features
CN108647565A (en) A kind of data preprocessing method classified to electrocardiosignal based on deep learning model
CN109864714A (en) A kind of ECG Signal Analysis method based on deep learning
EP3614301A1 (en) Artificial intelligence-based interference recognition method for electrocardiogram
CN108186011A (en) Atrial fibrillation detection method, device and readable storage medium storing program for executing
de Chazal et al. Automatic classification of ECG beats using waveform shape and heart beat interval features
CN106815570A (en) A kind of T sections of recognition methods of electrocardiosignal ST based on dynamic pattern recognition
CN110638430B (en) Method for building cascade neural network ECG signal arrhythmia classification model
CN106725376B (en) Sign detection method and device
CN109222963A (en) A kind of anomalous ecg method for identifying and classifying based on convolutional neural networks
Chen et al. Edge2Analysis: a novel AIoT platform for atrial fibrillation recognition and detection
CN111956208B (en) ECG signal classification method based on ultra-lightweight convolutional neural network
CN103970975A (en) Electrocardio data processing method and electrocardio data processing system
CN107530015A (en) A kind of vital sign analysis method and system
CN105726013A (en) Electrocardiogram monitoring system with electrocardiosignal quality discrimination function
CN107072569A (en) Spike detection module based on frame
US11571161B2 (en) Systems and methods for electrocardiogram diagnosis using deep neural networks and rule-based systems
Zhou et al. Premature ventricular contraction detection from ambulatory ECG using recurrent neural networks
Vijaya et al. Artificial neural network based wave complex detection in electrocardiograms
CN104614663B (en) Detection tester for electronic circuit fault and method
Chia et al. Computationally generated cardiac biomarkers: Heart rate patterns to predict death following coronary attacks
CN115607167A (en) Lightweight model training method, atrial fibrillation detection method, device and system

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
RJ01 Rejection of invention patent application after publication
RJ01 Rejection of invention patent application after publication

Application publication date: 20180202