CN102129509B - Coronary heart disease self-diagnosis system based on electrocardiographic monitoring and back-propagation neural network - Google Patents
Coronary heart disease self-diagnosis system based on electrocardiographic monitoring and back-propagation neural network Download PDFInfo
- Publication number
- CN102129509B CN102129509B CN 201110042458 CN201110042458A CN102129509B CN 102129509 B CN102129509 B CN 102129509B CN 201110042458 CN201110042458 CN 201110042458 CN 201110042458 A CN201110042458 A CN 201110042458A CN 102129509 B CN102129509 B CN 102129509B
- Authority
- CN
- China
- Prior art keywords
- data
- electrocardiogram
- patient
- ecg
- heart disease
- 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.)
- Expired - Fee Related
Links
Images
Landscapes
- Measurement And Recording Of Electrical Phenomena And Electrical Characteristics Of The Living Body (AREA)
Abstract
The invention discloses a coronary heart disease self-diagnosis system based on electrocardiographic monitoring and back-propagation neural network, comprising an electrocardiographic collection terminal and a hospital monitoring center computer system, wherein the electrocardiographic collection terminal is composed of an electrocardiographic monitoring collector and a data transmission module based on wired or wireless data transmission. By means of multi-scale features of wavelet transformation, the system of the invention completes the extraction of wave peak points and the detection of ST segment in different scale decomposition coefficients by adopting a quadratic spline wavelet transformation method, thus the electrocardiographic waveform of the clinical patient can be accurately extracted. On the basis of correctively extracting characteristic points, an electrocardiogram ST segment pattern recognition model is set up by using a BP (Back-Propagation) neutral network in order to successfully recognize the pattern of the ST segment, and the initial weight and the threshold of the BP neutral network are optimized by using genetic algorithm and DNA (deoxyribonucleic acid) algorithm, thereby problem that the BP neutral network is liable to fall into local optimum in the process of training is solved, and the pattern recognition of ST segment and the diagnosis of coronary heart disease in the manner of artificial experience before are replaced.
Description
Technical field
The present invention relates to cardiac monitoring and coronary heart disease self-diagnosable system, especially carry out the cardiac monitoring of ECG Data Transmission Based and the coronary heart disease self-diagnosable system of reverse transmittance nerve network by Internet.
Background technology
According to the world Heart Federation analysis, the mortality ratio of coronary heart disease is higher than Other diseases far away, has become the principal disease that threatens human life's safety.The early diagnosis of coronary heart disease is very important to guiding treatment and evaluate its prognosis.At present, the Main Diagnosis method of coronary heart disease is coronarography and ECG (being cardiogram).Detect owing to the expensive of coronarography and for having to create, thereby become the most frequently used method based on the ECG without the wound determination and analysis.Wherein, the important indicator of sign myocardial ischemia is the degrees of offset of ST section under quiescent condition and load condition among the ECG.
On the Vehicles Collected from Market there be the cardiac monitoring equipment of main flow: electrocardio Holter, electrocardio beeper and ECG real-time monitor system, although they all occupy a part of market, but Shortcomings all: 1, electrocardio Holter is generally used for the premature beat patient, it can only record electrocardiosignal, there is not the real-time analysis function, can not carry out remote monitoring, after the patient uses every day, must arrive hospital by specialized equipment read, data in the playback, analysis Holter; 2, the relative Holter of electrocardio beeper has real-time detection function, but whole morbidity alarm procedure need to be pressed first " record " key of instrument, and to the other relief phone of putting through of telephone set, again phone is aimed at instrument, and press the sequence of operations such as " transmission " key and could realize monitoring, whole process steps is many and complicated, is not suitable for the cardiac; 3, although the ECG real-time monitor system has solved the real-time test problems of electrocardiosignal, but the LAN that only limits in the hospital is used among a small circle, do not possess movability, some accidental anomalous ecg waveform is difficult to find on one's sick bed, patient's long-term inpatients is observed work and the normal family life that can have a strong impact on again the patient, so its range of application and popularization all are very limited, and in reality, quite a lot of patient is in routine work, fall ill during life, transference cure during to examination in hospital, cause to detect abnormal electrocardiographic pattern in hospital, can't make diagnosis to the state of an illness, delayed the best opportunity for the treatment of; 4, above-mentioned various cardiac monitoring equipment is to rely on micro-judgment by the doctor to the analysis of ECG, and workload is large and time-consuming, loaded down with trivial details, and accuracy depends on doctor's individual professional skill and working sense of responsibility.
Summary of the invention
The object of the invention is to: the coronary heart disease self-diagnosable system of a kind of cardiac monitoring and reverse transmittance nerve network is provided, easy-to-use, simple to operate, can be implemented in rapidly and accurately different geographical the patient is carried out unremitting cardiac monitoring and coronary heart disease self diagnosis.
For achieving the above object, the present invention can take following technical proposals:
The coronary heart disease self-diagnosable system of cardiac monitoring of the present invention and reverse transmittance nerve network comprises electrocardiogram acquisition terminal and hospital monitoring center computer system; Described electrocardiogram acquisition terminal consists of by the cardiac monitoring Acquisition Instrument with based on the data transmission module of wired or wireless data transmission; Described hospital monitoring center computer system is by receiving from the electrocardiogram (ECG) data of described electrocardiogram acquisition terminal and being stored to the data communication module of system storage, for the user of system distributes login ID unitedly, password and authority and the subscriber information management module that patient identity is differentiated, for patient user sets up Profile and transfers to the patient information management module that medical personnel user manages, computer program is housed, extract the data analysis module that patient's electrocardiogram (ECG) data unique point union goes out the diagnosis of coronary heart disease data, reception is from patient or other consultants' mail, and the Email transceiver module of answer is provided and diagnostic result feedback patient's SMS administration module is consisted of.
Described data analysis module comprises following execution in step: the first step, utilize wavelet transformation to carry out electrocardiogram (ECG) data filtering, feature point extraction: extract patient's electrocardiogram (ECG) data from described system storage, by the porous algorithm this electrocardiogram (ECG) data is carried out quadratic spline small echo 5 Scale Decompositions; Take 2 seconds electrocardiogram (ECG) datas as one section, the wavelet decomposition high frequency coefficient segmentation on 4 yardsticks, and calculate the positive and negative module maximum point of wavelet decomposition; The every a pair of module maximum point that detects is carried out the time shift correction, and the less crest value point position of amplitude is eliminated in the position right according to revised module maximum, selects to have the crest value point of maximum amplitude as the crest value point; Second step, utilize error back propagation neural network (BP neural network) neural network computing to go out the diagnosis of coronary heart disease data: the unique point of at first extracting according to the first step, utilize the MATLAB instrument to carry out Characteristic Extraction, and with the recognition feature quantity set input BP neural network of extracting; According to genetic algorithm or DNA algorithm the BP neural network is carried out initial weight and the threshold optimization of network, then carry out network training, the BP neural network of described training is three-layer network, and concrete structure is as follows:
Ground floor position input layer is comprised of 5 neurons, is used for receiving 5 recognition feature amounts extracting; The second layer is hidden layer, formed by 11 neurons, in the network calculations process, play the effect of forming a connecting link, utilize the output valve of input layer to be input, according to the computation rule of error backpropagation algorithm, and result of calculation delivered to the neuronic input end of output layer; The 3rd layer is output layer, is comprised of 6 neurons, and its Output rusults namely gets patient's ECG ST section form corresponding to 6 kinds of forms of ST section.
The present invention adopts the quadratic spline Wavelet Transform by the multiple dimensioned characteristic of wavelet transformation, finishes the detection to the extraction of crest value point and ST section in the different scale coefficient of dissociation, can accurately extract the ecg wave form of clinical patients.On the correct basis of extracting of unique point, utilize BP neural metwork training method to make up the model of cognition of 6 kinds of forms of ECG ST section, successfully identified ST section form, and initial weight and the threshold value of BP neural network of having utilized genetic algorithm and DNA algorithm optimization, solve the problem that is easy to be absorbed in local optimum that the BP neural network occurs at training process, substituted the identification of ST section form and the diagnosis of coronary heart disease work undertaken by the artificial experience mode in the past.Towards the transmission of wireless or cable data, the information management of Internet, can be implemented in different geographical, without interruption the patient be carried out cardiac monitoring and coronary heart disease self diagnosis in addition, enlarge medical coverage rate, reduce medical expense.
Description of drawings
Fig. 1 is structural representation of the present invention.
Fig. 2 is the computer program schematic flow sheet of the data analysis module of Fig. 1.
Embodiment
As shown in Figure 1 and Figure 2, the coronary heart disease self-diagnosable system of cardiac monitoring of the present invention and reverse transmittance nerve network comprises electrocardiogram acquisition terminal and hospital monitoring center computer system; Described electrocardiogram acquisition terminal consists of by cardiac monitoring Acquisition Instrument 1 with based on the data transmission module 2 of wired or wireless data transmission; Described hospital monitoring center computer system is by receiving from the electrocardiogram (ECG) data of described electrocardiogram acquisition terminal and being stored to the data communication module 3 of system storage, for the user of system distributes login ID unitedly, password and authority and the subscriber information management module 4 that patient identity is differentiated, for patient user sets up Profile and transfers to the patient information management module 5 that medical personnel user manages, computer program is housed, extract the data analysis module 6 that patient's electrocardiogram (ECG) data unique point union goes out the diagnosis of coronary heart disease data, reception is from patient or other consultants' mail, and the Email transceiver module 7 of answer is provided and diagnostic result feedback patient's SMS administration module 8 is consisted of.
Described data analysis module 6 comprises following execution in step:
The first step, utilize wavelet transformation to carry out electrocardiogram (ECG) data filtering, feature point extraction:
Extract patient's electrocardiogram (ECG) data from described system storage, by the porous algorithm this electrocardiogram (ECG) data is carried out quadratic spline small echo 5 Scale Decompositions; Take 2 seconds electrocardiogram (ECG) datas as one section, the wavelet decomposition high frequency coefficient segmentation on 4 yardsticks, and calculate the positive and negative module maximum point of wavelet decomposition; The every a pair of module maximum point that detects is carried out the time shift correction, and the less crest value point position of amplitude is eliminated in the position right according to revised module maximum, selects to have the crest value point of maximum amplitude as the crest value point;
Second step, utilize the BP neural network computing to go out the diagnosis of coronary heart disease data;
The unique point of at first extracting according to the first step, carry out Characteristic Extraction in conjunction with the MATLAR instrument, and with the recognition feature quantity set error originated from input backpropagation BP neural network of extracting, the BP neural network is carried out initial weight and the threshold optimization of network according to genetic algorithm or DNA algorithm, then carry out network training, the BP neural net method that described training is adopted the steps include:
Ground floor position input layer is comprised of 5 neurons, is used for receiving 5 recognition feature amounts that come from extraction; The second layer is hidden layer, formed by 11 neurons, in the network calculations process, play the effect of forming a connecting link, utilize the output valve of input layer to be input, according to the computation rule of error backpropagation algorithm, and result of calculation delivered to the neuronic input end of output layer; The 3rd layer is output layer, is comprised of 6 neurons, and its Output rusults namely gets patient's ECG ST section form corresponding to 6 kinds of forms of ST section, and assist personnel realizes diagnosis of coronary heart disease.
Claims (1)
1. the coronary heart disease self-diagnosable system of a cardiac monitoring and reverse transmittance nerve network comprises electrocardiogram acquisition terminal and hospital monitoring center computer system; Described electrocardiogram acquisition terminal consists of by cardiac monitoring Acquisition Instrument (1) with based on the data transmission module (2) of wired or wireless data transmission; Described hospital monitoring center computer system is by receiving from the electrocardiogram (ECG) data of described electrocardiogram acquisition terminal and being stored to the data communication module (3) of system storage, for the user of system distributes login ID unitedly, password and authority and the subscriber information management module (4) that patient identity is differentiated, for patient user sets up Profile and transfers to the patient information management module (5) that medical personnel user manages, computer program is housed, extract the data analysis module (6) that patient's electrocardiogram (ECG) data unique point union goes out the diagnosis of coronary heart disease data, reception is from patient or other consultants' mail, and the Email transceiver module (7) of answer is provided and diagnostic result feedback patient's SMS administration module (8) is consisted of;
Described data analysis module (6) comprises following execution in step:
The first step, utilize wavelet transformation to carry out electrocardiogram (ECG) data filtering, feature point extraction;
Extract patient's electrocardiogram (ECG) data from described system storage, by the porous algorithm this electrocardiogram (ECG) data is carried out quadratic spline small echo 5 Scale Decompositions; Take 2 seconds electrocardiogram (ECG) datas as one section, the wavelet decomposition high frequency coefficient segmentation on 4 yardsticks, and calculate the positive and negative module maximum point of wavelet decomposition; The every a pair of module maximum point that detects is carried out the time shift correction, and the less crest value point position of amplitude is eliminated in the position right according to revised module maximum, selects to have the crest value point of maximum amplitude as the crest value point;
Second step, utilize the BP neural network computing to go out the diagnosis of coronary heart disease data;
The feature of at first extracting according to the first step constructs the BP neural network structure of realizing diagnosis of coronary heart disease, determines the input vector of diagnostic network; And according to genetic algorithm or DNA algorithm the BP neural network is carried out initial weight and the threshold optimization of network, and then carry out network training, the BP neural network of described training is three-layer network, concrete structure is as follows:
Ground floor position input layer is comprised of 5 neurons, is used for 5 recognition feature amounts that input comes from the unique point composition that extracts; The second layer is hidden layer, formed by 11 neurons, in the network calculations process, play the effect of forming a connecting link, utilize the output valve of input layer to be input, according to the computation rule of error backpropagation algorithm, and result of calculation delivered to the neuronic input end of output layer; The 3rd layer is output layer, is comprised of 6 neurons, and its Output rusults namely gets patient's ECG ST section form corresponding to 6 kinds of forms of ST section.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN 201110042458 CN102129509B (en) | 2011-02-22 | 2011-02-22 | Coronary heart disease self-diagnosis system based on electrocardiographic monitoring and back-propagation neural network |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN 201110042458 CN102129509B (en) | 2011-02-22 | 2011-02-22 | Coronary heart disease self-diagnosis system based on electrocardiographic monitoring and back-propagation neural network |
Publications (2)
Publication Number | Publication Date |
---|---|
CN102129509A CN102129509A (en) | 2011-07-20 |
CN102129509B true CN102129509B (en) | 2013-01-02 |
Family
ID=44267591
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN 201110042458 Expired - Fee Related CN102129509B (en) | 2011-02-22 | 2011-02-22 | Coronary heart disease self-diagnosis system based on electrocardiographic monitoring and back-propagation neural network |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN102129509B (en) |
Families Citing this family (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105590011B (en) * | 2014-10-20 | 2019-04-30 | 深圳市迈迪加科技发展有限公司 | A kind of ecg signal data modification method and system based on pulse regression model |
CN104398252A (en) * | 2014-11-05 | 2015-03-11 | 深圳先进技术研究院 | Electrocardiogram signal processing method and device |
CN104463326B (en) * | 2014-12-09 | 2017-02-22 | 浙江大学 | Standard 12-lead ecg signal reconstruction method |
CN104523264B (en) * | 2014-12-31 | 2017-01-18 | 深圳职业技术学院 | Electrocardiosignal processing method |
CN107688852A (en) * | 2017-09-15 | 2018-02-13 | 郑州云海信息技术有限公司 | One kind stimulates classification coding/decoding method and device |
CN108053883A (en) * | 2017-12-22 | 2018-05-18 | 北京鑫丰南格科技股份有限公司 | Patient advisory's opinion generating means and system |
CN109497992A (en) * | 2019-01-04 | 2019-03-22 | 济南汇医融工科技有限公司 | Coronary heart disease intelligence screening apparatus based on machine learning method |
CN109662689B (en) * | 2019-03-07 | 2021-07-27 | 姜炜炜 | Health early warning system based on electrocardiogram for hospital |
Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN1751656A (en) * | 2005-11-14 | 2006-03-29 | 深圳市岩尚科技有限公司 | Long-distance, radio-electrocardiogram real-time monitoring system, and method therefor |
CN101385644A (en) * | 2008-07-25 | 2009-03-18 | 沈阳中国医科大学医疗器械研制中心(有限公司) | 12 lead wireless remote electrocardiograph monitoring system |
-
2011
- 2011-02-22 CN CN 201110042458 patent/CN102129509B/en not_active Expired - Fee Related
Patent Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN1751656A (en) * | 2005-11-14 | 2006-03-29 | 深圳市岩尚科技有限公司 | Long-distance, radio-electrocardiogram real-time monitoring system, and method therefor |
CN101385644A (en) * | 2008-07-25 | 2009-03-18 | 沈阳中国医科大学医疗器械研制中心(有限公司) | 12 lead wireless remote electrocardiograph monitoring system |
Non-Patent Citations (4)
Title |
---|
基于BP神经网络的心电图ST段的模式识别;师黎等;《微计算机应用》;20071231;第23卷(第1-1期);275-277 * |
基于心电图的身份识别方法;师黎等;《计算机工程》;20110131;第37卷(第1期);175-177 * |
师黎等.基于BP神经网络的心电图ST段的模式识别.《微计算机应用》.2007,第23卷(第1-1期),275-277. |
师黎等.基于心电图的身份识别方法.《计算机工程》.2011,第37卷(第1期),175-177. |
Also Published As
Publication number | Publication date |
---|---|
CN102129509A (en) | 2011-07-20 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN102129509B (en) | Coronary heart disease self-diagnosis system based on electrocardiographic monitoring and back-propagation neural network | |
US11931154B2 (en) | Systems and methods for classifying ECG data | |
CN106214145B (en) | Electrocardiogram classification method based on deep learning algorithm | |
CN102429649B (en) | Continuous blood pressure measuring device | |
Martinek et al. | Advanced bioelectrical signal processing methods: Past, present and future approach—part i: Cardiac signals | |
US20110190598A1 (en) | Health Data Dynamics, Its Sources and Linkage with Genetic/Molecular Tests | |
CN106108889A (en) | Electrocardiogram classification method based on degree of depth learning algorithm | |
CN101791214A (en) | Community health-oriented portable monitoring system | |
CN109998522A (en) | A kind of exercise load detection device and method based on wearable dynamic electrocardiogram | |
CN101422362A (en) | Wireless cardiac bioelectricity monitoring system with motion artifact elimination function | |
CN106778016A (en) | A kind of remote health monitoring medical system | |
Zhang et al. | A wristband device for detecting human pulse and motion based on the Internet of Things | |
CN105581786A (en) | Health monitoring system | |
CN204520670U (en) | A kind of electrocardiogram monitor system based on Internet of Things | |
CN110537907B (en) | Electrocardiosignal compression and identification method based on singular value decomposition | |
CN107516019A (en) | Noninvasive health forecast system and method | |
CN113384277A (en) | Electrocardiogram data classification method and classification system | |
Sánchez-Tato et al. | Health@ Home: A telecare system for patients with chronic heart failure | |
CN201886480U (en) | Telemonitoring system | |
CN112037916A (en) | Shared multifunctional sudden death prevention physiological information detection system and method thereof | |
Kew et al. | Wearable patch-type ECG using ubiquitous wireless sensor network for healthcare monitoring application | |
CN102163257A (en) | Coronary heart disease self-diagnosis system with electrocardiographic monitoring and self-adaptive fuzzy reasoning network | |
CN109770851A (en) | A kind of health of heart condition monitoring system and method based on Bluetooth wireless communication | |
CN214433943U (en) | Toilet seat with physical sign monitoring function | |
CN206560437U (en) | A kind of stress assessment system |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
C14 | Grant of patent or utility model | ||
GR01 | Patent grant | ||
CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20130102 |
|
CF01 | Termination of patent right due to non-payment of annual fee |