CN103948387B - A kind of polymorphic reconstruct and optimization method realizing abnormal electrocardiogram template based on large data - Google Patents
A kind of polymorphic reconstruct and optimization method realizing abnormal electrocardiogram template based on large data Download PDFInfo
- Publication number
- CN103948387B CN103948387B CN201410097341.5A CN201410097341A CN103948387B CN 103948387 B CN103948387 B CN 103948387B CN 201410097341 A CN201410097341 A CN 201410097341A CN 103948387 B CN103948387 B CN 103948387B
- Authority
- CN
- China
- Prior art keywords
- template
- similarity
- kinds
- reconstruct
- polymorphic
- 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.)
- Active
Links
Abstract
A kind of polymorphic reconstruct and optimization method realizing abnormal electrocardiogram template based on large data, it is characterized in that described polymorphic reconstruct and optimization method are: first, according to the resolution parameter of standard cardioelectric waveform, set up the parameterized template data with two-dimensional characteristics, and establish the ecg wave form template be made up of multiple minutiae point; Secondly, utilize large data that are existing and edited dynamic electro-cardiac monitor, the pretreatment before comparing, namely carries out waveform merogenesis, then carries out waveform comparison one by one with ecg wave form template; Again, alignment algorithm uses misclassification rate (FRR), refuses to recognize rate (FAR), span: the success rate of finally mating is added up and assessed to these three critical quantity of the similarity (TH) of 0 ~ 1, and make polymorphic reconstruct or re-start the optimization of template data amount.
Description
Technical field
What the present invention relates to is a kind of polymorphic reconstruct and automatic optimization method of realizing abnormal electrocardiogram template based on large data, the large data mainly using dynamic electro-cardiac monitor to generate are carried out dynamic construction, are optimized the method for abnormal electrocardiogram data template variform, belong to Holter technical field.
Background technology
At present, in Holter medically, identification based on abnormal electrocardiographic pattern to carry out manual evaluation often by medical practitioner, not only efficiency is low but also manual labor amount is large for it, although some medical special electrocardio software or equipment also can realize dynamic pre-identification, but it is higher that misclassification rate and refusing recognizes rate, its reason abnormal electrocardiogram data template that to be most of electrocardio recognizer be based on conventional criteria, different individual humans is differed greatly, the individual variations such as such as old man, child, youngster, middle age, the display form of abnormal electrocardiogram can be different.Therefore for Holter, each action of human body then can present more significantly diversity, and in this case, obvious standard cardioelectric template is the actual needs that can not meet Holter.
Summary of the invention
The object of the invention is to the deficiency overcoming prior art existence, and provide a kind of large data mainly using dynamic electro-cardiac monitor to generate the polymorphic reconstruct and the optimization method that realize abnormal electrocardiogram template based on large data of dynamic construction, optimization abnormal electrocardiogram data template variform.
The object of the invention is to have come by following technical solution, the described polymorphic reconstruct and the optimization method that realize abnormal electrocardiogram template based on large data, it comprises the steps:
First, according to the resolution parameter of standard cardioelectric waveform, set up the parameterized template data with two-dimensional characteristics, and establish the ecg wave form template be made up of multiple minutiae point;
Secondly, utilize large data that are existing and edited dynamic electro-cardiac monitor, the pretreatment before comparing, namely carries out waveform merogenesis, then carries out waveform comparison one by one with ecg wave form template;
Again, alignment algorithm uses misclassification rate (FRR), refuses to recognize rate (FAR), span: the success rate of finally mating is added up and assessed to these three critical quantity of the similarity (TH) of 0 ~ 1, and make polymorphic reconstruct or re-start the optimization of template data amount.
Described ecg wave form template of having established comprises: 2 kinds of cardiac electric axis, 2 kinds of PR intervals, 2 kinds of QTc intervals, 3 kinds of R ripples, 3 kinds of S ripples, 5 kinds of P ripples, 5 kinds of T ripples, 12 kinds of Q ripples, 36 kinds of ST ripples, 30 kinds of ST-T associatings.Described ecg wave form mould
Comparison between plate and arbitrarily EGC waveform data, by by misclassification rate, refuse to recognize rate, three groups of threshold values of presetting of these three critical quantity of similarity carry out three times and calculate, and according to three statistical result, assess as follows:
(1) contrast according to the similarity TH in the th result calculated for the third time and last group, for the ecg wave form lower than threshold value, be reconstructed;
(2) the similarity TH in the th result calculated according to second time and second group contrasts, and for identifying but the very low template of discrimination, again enters the optimization of new template data volume;
(3) the similarity TH in the th result calculated according to first time and first group contrasts, and for identifying but the very low template of discrimination, again enters the optimization of new template data volume; For the waveform that discrimination is high, template does not then carry out any process.
The present invention is by the large data scanning to existing cardioelectric monitor, and EGC pattern variant class template can get more and more, classification is more and more thinner, and waveform template is also more and more accurate; Improve the quality of waveform template, nature can improve the accuracy of the structure of electrocardio disease template, and this accuracy rate for Holter can improve a lot.
Accompanying drawing explanation
Fig. 1 is ecg wave form template configuration of the present invention classification schematic diagram.
Fig. 2 is ecg wave form template of the present invention reconstruct and optimization schematic diagram.
Detailed description of the invention
Below in conjunction with drawings and Examples, the present invention will be further described: polymorphic reconstruct and the optimization method realizing abnormal electrocardiogram template based on large data of the present invention, it comprises the steps:
First, according to the resolution parameter of standard cardioelectric waveform, set up the parameterized template data with two-dimensional characteristics, and establish the ecg wave form template be made up of multiple minutiae point;
Secondly, utilize large data that are existing and edited dynamic electro-cardiac monitor, the pretreatment before comparing, namely carries out waveform merogenesis, then carries out waveform comparison one by one with ecg wave form template;
Again, alignment algorithm uses misclassification rate (FRR), refuses to recognize rate (FAR), span: the success rate of finally mating is added up and assessed to these three critical quantity of the similarity (TH) of 0 ~ 1, and make polymorphic reconstruct or re-start the optimization of template data amount.
The ecg wave form template of described establishment comprises: 2 kinds of cardiac electric axis, 2 kinds of PR intervals, 2 kinds of QTc intervals, 3 kinds of R ripples, 3 kinds of S ripples, 5 kinds of P ripples, 5 kinds of T ripples, 12 kinds of Q ripples, 36 kinds of ST ripples, 30 kinds of ST-T associatings.
Comparison between described ecg wave form template and arbitrarily EGC waveform data, by by misclassification rate, refuse to recognize rate, three groups of threshold values of presetting of these three critical quantity of similarity carry out three times and calculate, and according to three statistical result, assess as follows:
(1) contrast according to the similarity TH in the th result calculated for the third time and last group, for the ecg wave form lower than threshold value, be reconstructed;
(2) the similarity TH in the th result calculated according to second time and second group contrasts, and for identifying but the very low template of discrimination, again enters the optimization of new template data volume;
(3) the similarity TH in the th result calculated according to first time and first group contrasts, and for identifying but the very low template of discrimination, again enters the optimization of new template data volume; For the waveform that discrimination is high, template does not then carry out any process.
Embodiment: polymorphic reconstruct and the optimization method realizing abnormal electrocardiogram template based on large data of the present invention, it relates to structure electrocardio medical diagnosis on disease and ecg wave form two kinds of data templates; Wherein electrocardio medical diagnosis on disease template is made up of one group of multiple ecg wave form template forming a kind of genius morbi that have be associated; Described ecg wave form template is then made up of multiple minutiae point; The object of large data is utilized to be reconstruct new or optimize existing ecg wave form template data, as shown in Figure 1.
First according to the resolution parameter of standard cardioelectric waveform, set up the parameterized template data with two-dimensional characteristics, established following ecg wave form template at present: cardiac electric axis (2 kinds), PR interval (2 kinds), QTc interval (2 kinds), R ripple (3 kinds), S ripple (3 kinds), P ripple (5 kinds), T ripple (5 kinds), Q ripple (12 kinds), ST ripple (36 kinds), ST-T combine (30 kinds); By seeing the observation process of a large amount of heart patients, the templating species of waveform is not enough far away, therefore needs long-term constantly find and add, and for existing electro-cardiologic template, can more sophisticated category.
According to large data that are existing and the dynamic electro-cardiac monitor of edited (by effective waveform editing in 5 minutes), the pretreatment before first comparing, namely carries out waveform merogenesis, then carries out waveform comparison one by one with ecg wave form template.On alignment algorithm, we use misclassification rate (FRR), refuse to recognize rate (FAR), similarity (TH) (span: 0 ~ 1) three critical quantity are added up and assess the success rate of finally mating.Comparison between any EGC waveform data and waveform template, by by misclassification rate, refuse to recognize rate, the three groups of threshold values preset of similarity three critical quantity carry out three times and calculate, according to three statistical result, assess as follows:
(1) contrast according to the similarity TH in the th result calculated for the third time and last group, for the ecg wave form lower than threshold value, be reconstructed;
(2) the similarity TH in the th result calculated according to second time and second group contrasts, and for identifying but the very low template of discrimination, again enters the optimization of new template data volume;
(3) the similarity TH in the th result calculated according to first time and first group contrasts, and for identifying but the very low template of discrimination, again enters the optimization of new template data volume.For the waveform that discrimination is high, template does not then carry out any process.
Holter in Fig. 1, realized by various diseases diagnosis template, each medical diagnosis on disease template all has oneself 4 No. ID.Such as, we determine that No. ID of acute myocardial infarction is 8012.Comprise one group of ecg wave form template in each medical diagnosis on disease template, each ecg wave form template also forms by 6 No. ID, and front 2 is type code, and latter 4 is ecg wave form template code.Such as, ecg wave form template data in acute myocardial infarction is expressed as:
8012：T0003；
Q0501；
R0341；
PR0005；
ST2232；
……
Ecg wave form template in Fig. 1, then divided equidistant block with time shaft formed by multiple, each block is then made up of one group of minutiae point, and each minutiae point is then made up of a stack features value; Equidistant block, minutiae point and eigenvalue are distinguished by 6 No. ID, and explanatory content is the same.
The foundation of electrocardio medical diagnosis on disease template then needs expert doctor to come, automatically cannot be reconstructed by computer, therefore the present invention mainly refers to the structure of the new waveform template that ecg wave form template is carried out under the large data environment of dynamic ecg monitoring and the assessment of existing waveform template data and optimization, so following example, then with ecg wave form template for objective for implementation.
1) data structure of ecg wave form template is set up
2) to Electrocardiographic waveform pre-treatment step:
● baseline drift process
● cardiac electrical cycle divides second
● waveform partition
● block divides
●…...
3) realization of alignment algorithm: first we need the predetermined amount of determining to refuse to recognize rate (FAR), misclassification rate (FRR) and similarity (Similarity) three coupling to be three groups:
0.1％、0.02％、0.75％；
0.05％、0.06％、0.85％；
0.03%, 0.08%, 0.93%; Also needing the every important indicator in waveform, block, minutiae point simultaneously, setting up rational comparison threshold value by calculating in a large number,
Do not illustrate at this.
The ECGWaveVerify (WaveData, WaveTemplate, VerifyParameter) of alignment algorithm;
Alignment algorithm flow process is shown in that Fig. 2 is as shown:
Fig. 2 is ecg wave form template of the present invention reconstruct and Optimizing Flow figure;
4) ecg wave form template reconstruct:
Template reconstruction of function is called:
ECGWaveTemplateRefactoring(OldWaveTemplate,NewWaveTemplate,Parameter)；
5) ecg wave form is template optimized: mould
Plate majorized function is called:
ECGWaveTemplateOptimize (WaveTemplate, Parameter); Effect of the present invention just designs from the angle of electro-cardiologic template, can improve precision and the reliability of ecg wave form template to a certain extent, promotes the accuracy rate of Holter.
Claims (3)
1. realize polymorphic reconstruct and the optimization method of abnormal electrocardiogram template based on large data, it is characterized in that described polymorphic reconstruct and optimization method are:
First, according to the resolution parameter of standard cardioelectric waveform, set up the parameterized template data with two-dimensional characteristics, and establish the ecg wave form template be made up of multiple minutiae point;
Secondly, utilize the large data of existing dynamic electro-cardiac monitor, the pretreatment before comparing, namely carry out waveform merogenesis, then carry out waveform comparison one by one with ecg wave form template;
Again, alignment algorithm uses misclassification rate FRR, refuses to recognize rate FAR, span be 0 ~ 1 these three critical quantity of similarity TH add up and assess the success rate of finally mating, and make polymorphic reconstruct or re-start the optimization of template data amount.
2. polymorphic reconstruct and the optimization method realizing abnormal electrocardiogram template based on large data according to claim 1, the ecg wave form template of having established described in it is characterized in that comprises: 2 kinds of cardiac electric axis, 2 kinds of PR intervals, 2 kinds of QTc intervals, 3 kinds of R ripples, 3 kinds of S ripples, 5 kinds of P ripples, 5 kinds of T ripples, 12 kinds of Q ripples, 36 kinds of ST ripples and 30 kinds of ST-T associatings.
3. polymorphic reconstruct and the optimization method realizing abnormal electrocardiogram template based on large data according to claim 1, it is characterized in that described ecg wave form template and the comparison arbitrarily between EGC waveform data, by by misclassification rate, refuse to recognize rate, three groups of threshold values of presetting of these three critical quantity of similarity carry out three times and calculate, and according to three statistical result, assess as follows:
(1) contrast according to the similarity TH in the similarity result calculated for the third time and last group, for the ecg wave form lower than predetermined threshold value, be reconstructed;
(2) contrast according to the similarity TH in the similarity result calculated for the second time and second group, for similarity TH in the similarity calculated higher than similarity TH in second group but relatively second group, then regard as and can identify but the very low template of discrimination, re-start the optimization of new template data volume;
(3) contrast according to the similarity TH in the similarity result calculated for the first time and first group, for similarity TH in the similarity calculated higher than similarity TH in first group but relatively first group, then regard as and can identify but the very low template of discrimination, re-start the optimization of new template data volume; For the similarity calculated far above first group in similarity TH, then assert the high waveform of discrimination, template does not then carry out any process.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410097341.5A CN103948387B (en) | 2014-03-17 | 2014-03-17 | A kind of polymorphic reconstruct and optimization method realizing abnormal electrocardiogram template based on large data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410097341.5A CN103948387B (en) | 2014-03-17 | 2014-03-17 | A kind of polymorphic reconstruct and optimization method realizing abnormal electrocardiogram template based on large data |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN103948387A CN103948387A (en) | 2014-07-30 |
| CN103948387B true CN103948387B (en) | 2016-01-20 |
Family
ID=51325847
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201410097341.5A Active CN103948387B (en) | 2014-03-17 | 2014-03-17 | A kind of polymorphic reconstruct and optimization method realizing abnormal electrocardiogram template based on large data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN103948387B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104473633B (en) * | 2014-12-31 | 2017-01-25 | 广州视源电子科技股份有限公司 | Judging method and device of abnormal electrocardio data |
| CN110731762B (en) * | 2019-09-18 | 2022-02-08 | 平安科技（深圳）有限公司 | Method, device, computer system and readable storage medium for preprocessing pulse wave based on similarity |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1189320A (en) * | 1997-01-31 | 1998-08-05 | 惠普公司 | Method and system for fast determination of EKG waveform morphology |
| US7177674B2 (en) * | 2001-10-12 | 2007-02-13 | Javier Echauz | Patient-specific parameter selection for neurological event detection |
| CN101810476A (en) * | 2009-12-22 | 2010-08-25 | 李顶立 | Classification method of heart beat template of dynamic electrocardiogram |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8457724B2 (en) * | 2008-12-11 | 2013-06-04 | Siemens Medical Solutions Usa, Inc. | System for heart performance characterization and abnormality detection |
-
2014
- 2014-03-17 CN CN201410097341.5A patent/CN103948387B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1189320A (en) * | 1997-01-31 | 1998-08-05 | 惠普公司 | Method and system for fast determination of EKG waveform morphology |
| US7177674B2 (en) * | 2001-10-12 | 2007-02-13 | Javier Echauz | Patient-specific parameter selection for neurological event detection |
| CN101810476A (en) * | 2009-12-22 | 2010-08-25 | 李顶立 | Classification method of heart beat template of dynamic electrocardiogram |
Non-Patent Citations (2)
| Title |
|---|
| 动态心电图波形改进分类策略研究;曹国超;《中国优秀硕士学位论文全文数据库信息科技辑》;20100731;全文 * |
| 心电算法及其参数数据库的构建;杨洁;《中国优秀硕士学位论文全文数据库医药卫生科技辑》;20050131;全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN103948387A (en) | 2014-07-30 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109171712B (en) | Atrial fibrillation identification method, atrial fibrillation identification device, atrial fibrillation identification equipment and computer readable storage medium | |
| Park et al. | Hierarchical support vector machine based heartbeat classification using higher order statistics and hermite basis function | |
| CN109117730B (en) | Real-time electrocardiogram atrial fibrillation judgment method, device and system and storage medium | |
| US11617528B2 (en) | Systems and methods for reduced lead electrocardiogram diagnosis using deep neural networks and rule-based systems | |
| Zhang et al. | A multi-dimensional association information analysis approach to automated detection and localization of myocardial infarction | |
| CN104840186A (en) | Evaluation method of autonomic nervous function of patient suffering from CHF (Congestive Heart-Failure) | |
| CN108511055B (en) | Ventricular premature beat recognition system and method based on classifier fusion and diagnosis rules | |
| Dima et al. | On the detection of myocadial scar based on ECG/VCG analysis | |
| CN109276242A (en) | The method and apparatus of electrocardiosignal type identification | |
| KR101366101B1 (en) | System and method for classificating normal signal of personalized ecg | |
| CN104398254A (en) | Electrocardiogram analyzing system, electrocardiogram analyzing equipment and electrocardiogram predication model acquisition equipment | |
| Lyle et al. | Beyond HRV: Analysis of ECG signals using attractor reconstruction | |
| CN109887595A (en) | Heartbeat anomalous identification algorithm based on depth learning technology | |
| EP4041073A1 (en) | Systems and methods for electrocardiogram diagnosis using deep neural networks and rule-based systems | |
| CN103948387B (en) | A kind of polymorphic reconstruct and optimization method realizing abnormal electrocardiogram template based on large data | |
| Yang et al. | A novel method for automated congestive heart failure and coronary artery disease recognition using THC-Net | |
| Papadogiorgaki et al. | Heart rate classification using ECG signal processing and machine learning methods | |
| CN108338777A (en) | A kind of pulse signal determination method and device | |
| Spicher et al. | ECG delineation using a piecewise Gaussian derivative model with parameters estimated from scale-dependent algebraic expressions | |
| CN110363177A (en) | A kind of extracting method of human biological signal's chaos characteristic | |
| CN106778561B (en) | Identity recognition method and device of wearable equipment | |
| CN115392296A (en) | Abnormal brain wave type identification method, system, storage medium and equipment | |
| CN105769171A (en) | Arrhythmia detection method and device | |
| Vasu et al. | A survey on bipolar disorder classification methodologies using machine learning | |
| CN114287950A (en) | Heart disease computer-assisted classification method based on continuous coherence and Fourier transform |
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 |