CN109036503A - A kind of system and method generating electrocardiographic diagnosis report - Google Patents
A kind of system and method generating electrocardiographic diagnosis report Download PDFInfo
- Publication number
- CN109036503A CN109036503A CN201810770726.1A CN201810770726A CN109036503A CN 109036503 A CN109036503 A CN 109036503A CN 201810770726 A CN201810770726 A CN 201810770726A CN 109036503 A CN109036503 A CN 109036503A
- Authority
- CN
- China
- Prior art keywords
- information
- module
- statistical information
- heart rate
- statistical
- 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
Links
- 238000000034 method Methods 0.000 title claims abstract description 52
- 238000003745 diagnosis Methods 0.000 title abstract description 12
- 208000000418 Premature Cardiac Complexes Diseases 0.000 claims abstract description 36
- 230000033764 rhythmic process Effects 0.000 claims abstract description 30
- 230000008569 process Effects 0.000 claims abstract description 25
- 230000004048 modification Effects 0.000 claims abstract description 20
- 238000012986 modification Methods 0.000 claims abstract description 20
- 238000013527 convolutional neural network Methods 0.000 claims abstract 3
- 230000008859 change Effects 0.000 claims description 31
- 230000000903 blocking effect Effects 0.000 claims description 30
- 208000010496 Heart Arrest Diseases 0.000 claims description 15
- 238000005457 optimization Methods 0.000 claims description 15
- 238000013528 artificial neural network Methods 0.000 claims description 11
- 230000002028 premature Effects 0.000 claims description 7
- 230000000747 cardiac effect Effects 0.000 claims description 6
- 238000003062 neural network model Methods 0.000 claims description 5
- 230000014759 maintenance of location Effects 0.000 claims description 3
- 239000012634 fragment Substances 0.000 claims description 2
- 230000036471 bradycardia Effects 0.000 abstract 1
- 238000010586 diagram Methods 0.000 description 6
- 238000013473 artificial intelligence Methods 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000002035 prolonged effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H15/00—ICT specially adapted for medical reports, e.g. generation or transmission thereof
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
- G16H50/20—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for computer-aided diagnosis, e.g. based on medical expert systems
Landscapes
- Health & Medical Sciences (AREA)
- Engineering & Computer Science (AREA)
- Medical Informatics (AREA)
- Public Health (AREA)
- Epidemiology (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Biomedical Technology (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Pathology (AREA)
- Measurement And Recording Of Electrical Phenomena And Electrical Characteristics Of The Living Body (AREA)
Abstract
The invention discloses a kind of system and methods of generation electrocardiographic diagnosis report, the system of generation electrocardiographic diagnosis report, it include: rhythm of the heart classification identification module, block/stop identification module of fighting, statistical module is sorted out in premature beat, escape beat sorts out statistical module, ST-T changes statistical module and heart rate statistical module and generates rhythm of the heart classification information according to original electrocardiographicdigital data and convolutional neural networks model respectively, block/stop information of fighting, the statistical information of each premature beat type, the statistical information of each escape beat type, the statistical information of statistical information and most fast heart rate and most slow heart rate that ST-T changes；Integrated calibration module, the modification process for the doctor according to correction tracking module tracking is corrected above- mentioned information, and above- mentioned information after correction are exported to report generation module；Report generation module for above- mentioned information to be respectively corresponded report template, and generates report.
Description
Technical Field
The invention relates to the technical field of artificial intelligence data analysis, in particular to a system and a method for generating an electrocardiogram diagnosis report.
Background
The electrocardiogram reports on the market at present are generated based on templates and statistical data, the format is single, only the data statistics function is provided, if some data are inaccurate, a doctor needs to correct the data one by one, and therefore, the report compiling time of the doctor is prolonged. Therefore, there is a need for an automatic report generation system that optimizes statistical data in conjunction with physician calibration data.
Disclosure of Invention
The present invention is directed to a system and method for generating an electrocardiogram diagnostic report, which is used to solve the problems of the prior art.
In order to achieve the above object, an aspect of the present invention is a system for generating an electrocardiographic diagnostic report, including: the heart rhythm identification module, the blocking/asystole identification module, the premature beat classification statistical module, the escape classification statistical module, the ST-T change statistical module, the heart rate statistical module, the correction process tracking module, the comprehensive correction module and the report generation module; the heart rate type identification module, the blocking/stopping identification module, the premature classification statistical module, the escape classification statistical module, the ST-T change statistical module and the heart rate statistical module respectively generate heart rate type information, blocking/stopping information, statistical information of each premature type, statistical information of each escape type, statistical information of ST-T change and statistical information of a fastest heart rate and a slowest heart rate according to the original electrocardio data and the neural network model; the comprehensive correction module is used for correcting the heart rhythm type information, the blocking/asystole information, the statistical information of each premature beat type, the statistical information of each escape type, the statistical information of ST-T change and the statistical information of the fastest heart rate and the slowest heart rate according to the modification process of the doctor tracked by the correction tracking module; and the report generation module is used for respectively corresponding the corrected heart rhythm category information, the blocking/stopping information, the statistical information of each premature beat type, the statistical information of each escape type, the statistical information of ST-T change and the statistical information of the fastest heart rate and the slowest heart rate to a report template and generating a report.
Optionally, the system for generating an electrocardiogram report further includes: a segment graph-keeping decision module; and the fragment image-retaining decision module is used for retaining images of the heart rhythm events corresponding to the process information corrected by the doctor and the characteristic values of the original electrocardio data.
Optionally, the system for generating an electrocardiogram report further includes: a natural language correction algorithm module; and the natural language correction algorithm module is used for optimizing the output of the comprehensive correction module by adopting a natural language correction algorithm according to the knowledge graph.
Optionally, the system for generating an electrocardiogram report further includes: an update module; and the updating module is used for updating the natural language optimization library, and the natural language optimization library is used for storing the language optimization of the doctor.
Optionally, the comprehensive correction module is specifically configured to: and the system is used for correcting the heart rhythm category information, the blocking/asystole information, the statistical information of each premature beat type, the statistical information of each escape type, the statistical information of ST-T change and the statistical information of the fastest heart rate and the slowest heart rate by adopting a deep neural network according to the modification process of the doctor tracked by the correction tracking module.
In order to achieve the above object, an aspect of the present invention is a method for generating an electrocardiographic diagnostic report, including: generating heart rate category information, blocking/asystole information, statistical information of each premature beat type, statistical information of each escape type, statistical information of ST-T change and statistical information of the fastest heart rate and the slowest heart rate according to the original electrocardiogram data and the neural network model respectively; correcting the cardiac rhythm type information, the blocking/asystole information, the statistical information of each premature beat type, the statistical information of each escape type, the statistical information of ST-T change and the statistical information of the fastest heart rate and the slowest heart rate according to the modification process of the doctor tracked by the correction tracking module; and respectively corresponding the corrected heart rhythm type information, the blocking/stopping information, the statistical information of each premature beat type, the statistical information of each escape type, the statistical information of ST-T change and the statistical information of the fastest heart rate and the slowest heart rate to a report template, and generating a report.
Optionally, before correcting the cardiac rhythm category information, the block/rest information, the statistics of each premature beat type, the statistics of each escape type, the statistics of ST-T changes, and the statistics of the fastest heart rate and the slowest heart rate according to the physician's modification process tracked by the correction tracking module, the method further comprises: and (4) performing image retention and storage on the process information corrected by the doctor and the heart rhythm event corresponding to the characteristic value of the original electrocardiogram data.
Optionally, after correcting the cardiac rhythm category information, the block/rest information, the statistics of each premature beat type, the statistics of each escape type, the statistics of ST-T changes, and the statistics of the fastest heart rate and the slowest heart rate according to the physician's modification process tracked by the correction tracking module, the method further includes: and optimizing the corrected heart rhythm category information, the blocking/stopping information, the statistical information of each premature beat type, the statistical information of each escape type, the statistical information of ST-T change and the statistical information of the fastest heart rate and the slowest heart rate by adopting a natural language correction algorithm according to the knowledge graph.
Optionally, the method for generating an electrocardiogram report further includes: and updating a natural language optimization library, wherein the natural language optimization library is used for storing the language optimization of the doctor.
Optionally, the correcting the cardiac rhythm category information, the blocking/asystole information, the statistics of each premature beat type, the statistics of each escape type, the statistics of ST-T changes, and the statistics of the fastest heart rate and the slowest heart rate according to the doctor's modification process tracked by the correction tracking module includes: and the system is used for correcting the heart rhythm category information, the blocking/asystole information, the statistical information of each premature beat type, the statistical information of each escape type, the statistical information of ST-T change and the statistical information of the fastest heart rate and the slowest heart rate by adopting a deep neural network according to the modification process of the doctor tracked by the correction tracking module.
The invention has the following advantages:
the statistical data can be optimized according to the correction data of the tracked doctor, so that the doctor does not need to manually correct each time, the time for writing the report by the doctor is shortened, and the report is closer to the expected requirement of the doctor.
Drawings
Fig. 1 is a first schematic structural diagram of a system for generating an electrocardiogram diagnostic report according to an embodiment of the present invention.
Fig. 2 is a schematic structural diagram of a system for generating an electrocardiogram diagnostic report according to an embodiment of the present invention.
Fig. 3 is a schematic structural diagram of a system for generating an electrocardiogram diagnostic report according to an embodiment of the present invention.
FIG. 4 is a flow chart of a method of generating an ECG diagnostic report according to an embodiment of the present invention.
Detailed Description
The following examples are intended to illustrate the invention but are not intended to limit the scope of the invention.
Example 1
Fig. 1 is a first schematic structural diagram of a system for generating an electrocardiogram diagnostic report according to an embodiment of the present invention. As shown in fig. 1, the system for generating an electrocardiogram diagnostic report comprises: a heart rate category identification module 10, a block/rest recognition module 11, a premature classification statistical module 12, an escape classification statistical module 13, an ST-T change statistical module 14, a heart rate statistical module 15, a correction process tracking module 16, a comprehensive correction module 17, and a report generation module 18.
The heart rate type identification module 10, the block/rest identification module 11, the premature classification statistical module 12, the escape classification statistical module 13, the ST-T change statistical module 14 and the heart rate statistical module 15 respectively generate heart rate type information, block/rest information, statistical information of each premature type, statistical information of each escape type, statistical information of ST-T change and statistical information of a fastest heart rate and a slowest heart rate according to the original electrocardio data and the neural network model; the comprehensive correction module 17 is used for correcting the heart rate category information, the blocking/stopping information, the statistical information of each premature beat type, the statistical information of each escape type, the statistical information of ST-T change and the statistical information of the fastest heart rate and the slowest heart rate according to the modification process of the doctor tracked by the correction and tracking module 16, and outputting the corrected heart rate category information, the blocking/stopping information, the statistical information of each premature beat type, the statistical information of each escape type, the statistical information of ST-T change and the statistical information of the fastest heart rate and the slowest heart rate to the report generation module 18; and a report generating module 18, configured to respectively correspond the corrected cardiac rhythm category information, blocking/asystole information, statistical information of each premature beat type, statistical information of each escape type, statistical information of ST-T changes, and statistical information of the fastest heart rate and the slowest heart rate to a report template, and generate a report.
In the embodiment of the invention, the report template is arranged in the report, and the report templates corresponding to different types of electrocardiogram diagnosis reports are different.
The correction tracking module 16 is specifically configured to track correction of each item of operation data by a doctor, and store the corrected data and the corrected item after the correction is completed, so that the corrected data and the corrected item are directly used next time, and each item of operation data that is counted is automatically corrected, thereby reducing manual correction by the doctor.
Note that the automatic correction cannot be performed without manual correction, and in a place where the automatic correction is not performed, a doctor is required to perform manual correction, and data of the manual correction is stored so that the automatic correction can be performed later.
Optionally, the comprehensive correction module 17 is specifically configured to: according to the doctor's modification process tracked by the correction tracking module 16, the deep neural network is used to correct the heart rate category information, the blocking/halting information, the statistical information of each premature beat type, the statistical information of each escape type, the statistical information of the ST-T change and the statistical information of the fastest heart rate and the slowest heart rate, and the corrected heart rate category information, the blocking/halting information, the statistical information of each premature beat type, the statistical information of each escape type, the statistical information of the ST-T change and the statistical information of the fastest heart rate and the slowest heart rate are output to the report generating module 18. The deep neural network may be a layer 6 deep neural network, or a layer 8 deep neural network.
Example 2
Fig. 2 is a schematic structural diagram of a system for generating an electrocardiogram diagnostic report according to an embodiment of the present invention. As shown in fig. 2, the system for generating an electrocardiographic diagnosis report further includes, compared to fig. 1: a segment map-keeping decision module 19; and the segment image-keeping decision module 19 is used for storing the corrected process information of the doctor and the characteristic value of the original electrocardio data, and storing the more typical heart rhythm event in an image-keeping mode.
In practical use, the operation time of the doctor on the current operation data and the frequency of the operation are also combined, for example, if the doctor stays too long for the current segment, the stay time exceeds 5 minutes, and clicks the segment many times, the importance level of the segment needs to be increased, and the follow-up similar segment also needs to be considered preferentially.
Example 3
Fig. 3 is a schematic structural diagram of a system for generating an electrocardiogram diagnostic report according to an embodiment of the present invention. As shown in fig. 3, the system for generating an electrocardiographic diagnostic report further includes, compared to fig. 2: a natural language correction algorithm module 20; and the natural language correction algorithm module 20 is used for performing natural language expression and tuning on the output of the comprehensive correction module 17 by adopting a natural language correction algorithm according to the knowledge graph.
Optionally, the system for generating an electrocardiogram diagnosis report further includes: and the updating module (not shown in the attached drawings) is used for recording the optimized language of the doctor in the past and updating the natural language optimization library according to the own language habit of the doctor. And further, the report optimized by the natural language correction algorithm is more in line with the habits of doctors. Wherein, the natural language optimization library is used for storing the language optimized by the doctor. For example, if the physician optimizes the same part in the same language multiple times, the physician-optimized language may be stored.
It should be noted that, the natural language correction algorithm corrects the obviously wrong part according to the knowledge graph on one hand, and adjusts the mechanized report according to the personal word habits of doctors on the other hand, so as to facilitate reading.
Example 4
FIG. 4 is a flow chart of a method of generating an ECG diagnostic report according to an embodiment of the present invention. As shown in fig. 4, the method of generating an electrocardiogram diagnostic report comprises the steps of:
step S401: generating heart rate category information, blocking/asystole information, statistical information of each premature beat type, statistical information of each escape type, statistical information of ST-T change and statistical information of the fastest heart rate and the slowest heart rate according to the original electrocardiogram data and the neural network model respectively;
step S402: correcting the heart rate category information, the block/rest information, the statistical information of each premature beat type, the statistical information of each escape type, the statistical information of ST-T changes and the statistical information of the fastest heart rate and the slowest heart rate according to the tracked modification process of the doctor;
step S403: and respectively corresponding the corrected heart rhythm type information, the blocking/stopping information, the statistical information of each premature beat type, the statistical information of each escape type, the statistical information of ST-T change and the statistical information of the fastest heart rate and the slowest heart rate to a report template, and generating a report.
Specifically, according to the modification process of the tracked doctor, the deep neural network is used to correct the heart rate category information, the blocking/halting information, the statistical information of each premature beat type, the statistical information of each escape type, the statistical information of ST-T changes, and the statistical information of the fastest heart rate and the slowest heart rate, and the corrected heart rate category information, the blocking/halting information, the statistical information of each premature beat type, the statistical information of each escape type, the statistical information of ST-T changes, and the statistical information of the fastest heart rate and the slowest heart rate are output to the report generating module 18 (as shown in fig. 1). The deep neural network may be a layer 6 deep neural network, or a layer 8 deep neural network.
In the embodiment of the invention, the report template is arranged in the report, and the report templates corresponding to different types of electrocardiogram diagnosis reports are different.
Prior to step S402, the method of generating an electrocardiogram diagnostic report further comprises: the process information for doctor correction and the characteristic value of the original electrocardio data are stored, and the more typical heart rhythm event can be stored by adopting a pattern retention mode.
Optionally, the method for generating an electrocardiogram diagnosis report further includes: and performing natural language expression and optimization on the output of the comprehensive correction module 17 (shown in figure 1) by adopting a natural language algorithm according to the knowledge graph.
Optionally, after step S402, that is, after each natural language optimization of the generated report, the method for generating an electrocardiogram diagnosis report further includes: and updating the knowledge graph according to the self-expression habits of the doctor. And further, the report optimized by the natural language correction algorithm is more in line with the habits of doctors.
The system and the method for generating the electrocardiogram diagnosis report provided by the embodiment of the invention can optimize statistical data according to the correction data of the tracking doctor, so that the doctor does not need to manually correct each time, the time for writing the report by the doctor is shortened, and the report is closer to the expected requirement of the doctor.
Although the invention has been described in detail above with reference to a general description and specific examples, it will be apparent to one skilled in the art that modifications or improvements may be made thereto based on the invention. Accordingly, such modifications and improvements are intended to be within the scope of the invention as claimed.
Claims (10)
1. A system for generating an electrocardiographic diagnostic report, said system comprising: the heart rhythm identification module, the blocking/asystole identification module, the premature beat classification statistical module, the escape classification statistical module, the ST-T change statistical module, the heart rate statistical module, the correction process tracking module, the comprehensive correction module and the report generation module; wherein,
the heart rate category identification module, the block/rest identification module, the premature classification statistical module, the escape classification statistical module, the ST-T change statistical module and the heart rate statistical module respectively generate heart rate category information, block/rest information, statistical information of each premature type, statistical information of each escape type, statistical information of ST-T change and statistical information of a fastest heart rate and a slowest heart rate according to original electrocardio data and a convolutional neural network model;
the comprehensive correction module is used for correcting the heart rhythm type information, the blocking/asystole information, the statistical information of each premature beat type, the statistical information of each escape type, the statistical information of ST-T change and the statistical information of the fastest heart rate and the slowest heart rate according to the modification process of the doctor tracked by the correction tracking module;
and the report generation module is used for respectively corresponding the corrected heart rhythm category information, the blocking/stopping information, the statistical information of each premature beat type, the statistical information of each escape type, the statistical information of ST-T change and the statistical information of the fastest heart rate and the slowest heart rate to a report template and generating a report.
2. The system of claim 1, further comprising: a segment graph-keeping decision module;
and the fragment image-retaining decision module is used for retaining images of the process information corrected by the doctor and the heart rhythm events corresponding to the characteristic values of the original electrocardiogram data.
3. The system of claim 1, further comprising: a natural language correction algorithm module; and the natural language correction algorithm module is used for optimizing the output of the comprehensive correction module by adopting a natural language correction algorithm according to the knowledge graph.
4. The system of claim 3, further comprising: an update module;
the updating module is used for updating a natural language optimization library, and the natural language optimization library is used for storing the language optimization of doctors.
5. The system of claim 1, wherein the comprehensive correction module is specifically configured to:
and the system is used for correcting the heart rhythm category information, the blocking/asystole information, the statistical information of each premature beat type, the statistical information of each escape type, the statistical information of ST-T change and the statistical information of the fastest heart rate and the slowest heart rate by adopting a deep convolutional neural network according to the modification process of the doctor tracked by the correction tracking module.
6. A method of generating an electrocardiographic diagnostic report, the method comprising:
generating heart rate category information, blocking/asystole information, statistical information of each premature beat type, statistical information of each escape type, statistical information of ST-T change and statistical information of the fastest heart rate and the slowest heart rate according to the original electrocardiogram data and the neural network model respectively;
correcting the cardiac rhythm type information, the blocking/asystole information, the statistical information of each premature beat type, the statistical information of each escape type, the statistical information of ST-T change and the statistical information of the fastest heart rate and the slowest heart rate according to the modification process of the doctor tracked by the correction tracking module;
and respectively corresponding the corrected heart rhythm type information, the blocking/stopping information, the statistical information of each premature beat type, the statistical information of each escape type, the statistical information of ST-T change and the statistical information of the fastest heart rate and the slowest heart rate to a report template, and generating a report.
7. The method of claim 6, wherein before correcting the heart rhythm category information, block/rest information, statistics for each premature beat type, statistics for each escape type, statistics of ST-T changes, and statistics of fastest and slowest heart rates according to the physician's modification procedure tracked by the correction tracking module, the method further comprises:
and (4) performing image retention and storage on the process information corrected by the doctor and the heart rhythm event corresponding to the characteristic value of the original electrocardiogram data.
8. The method of claim 6, wherein after correcting the heart rate category information, the block/rest information, the statistics of each premature beat type, the statistics of each escape type, the statistics of ST-T changes, and the statistics of the fastest and slowest heart rates according to the physician's modification procedures tracked by the correction tracking module, the method further comprises:
and optimizing the corrected heart rhythm category information, the blocking/stopping information, the statistical information of each premature beat type, the statistical information of each escape type, the statistical information of ST-T change and the statistical information of the fastest heart rate and the slowest heart rate by adopting a natural language correction algorithm according to the knowledge graph.
9. The method of claim 8, further comprising: updating a natural language optimization library for storing the doctor's language optimizations.
10. The method of claim 6, wherein the correcting heart rate category information, block/rest information, statistics for each premature beat type, statistics for each escape type, statistics of ST-T changes, and statistics of fastest and slowest heart rates according to physician's modified procedures tracked by the correction tracking module comprises:
and the system is used for correcting the heart rhythm type information, the blocking/asystole information, the statistical information of each premature beat type, the statistical information of each escape type, the statistical information of ST-T change and the statistical information of the fastest heart rate and the slowest heart rate by adopting a deep neural network according to the modification process of the doctor tracked by the correction tracking module.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810770726.1A CN109036503A (en) | 2018-07-13 | 2018-07-13 | A kind of system and method generating electrocardiographic diagnosis report |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810770726.1A CN109036503A (en) | 2018-07-13 | 2018-07-13 | A kind of system and method generating electrocardiographic diagnosis report |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109036503A true CN109036503A (en) | 2018-12-18 |
Family
ID=64642186
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810770726.1A Pending CN109036503A (en) | 2018-07-13 | 2018-07-13 | A kind of system and method generating electrocardiographic diagnosis report |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109036503A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113707258A (en) * | 2021-07-23 | 2021-11-26 | 厦门纳龙科技有限公司 | Method for quickly revising electrocardiogram report, terminal equipment and storage medium |
| CN114533014A (en) * | 2020-11-26 | 2022-05-27 | 深圳市科瑞康实业有限公司 | Method for early warning according to heart rate ranges of different heart rhythm types |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104970789A (en) * | 2014-04-04 | 2015-10-14 | 中国科学院苏州纳米技术与纳米仿生研究所 | Electrocardiogram classification method and system |
| CN107451417A (en) * | 2017-09-08 | 2017-12-08 | 北京蓬阳丰业医疗设备有限公司 | Dynamic ECG analysis intelligent diagnosis system and method |
| CN107491632A (en) * | 2017-07-10 | 2017-12-19 | 成都琅瑞医疗技术股份有限公司 | Method of servicing after cardiac diagnosis |
| CN107510452A (en) * | 2017-09-30 | 2017-12-26 | 扬美慧普（北京）科技有限公司 | A kind of ECG detecting method based on multiple dimensioned deep learning neutral net |
-
2018
- 2018-07-13 CN CN201810770726.1A patent/CN109036503A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104970789A (en) * | 2014-04-04 | 2015-10-14 | 中国科学院苏州纳米技术与纳米仿生研究所 | Electrocardiogram classification method and system |
| CN107491632A (en) * | 2017-07-10 | 2017-12-19 | 成都琅瑞医疗技术股份有限公司 | Method of servicing after cardiac diagnosis |
| CN107451417A (en) * | 2017-09-08 | 2017-12-08 | 北京蓬阳丰业医疗设备有限公司 | Dynamic ECG analysis intelligent diagnosis system and method |
| CN107510452A (en) * | 2017-09-30 | 2017-12-26 | 扬美慧普（北京）科技有限公司 | A kind of ECG detecting method based on multiple dimensioned deep learning neutral net |
Non-Patent Citations (1)
| Title |
|---|
| 赵志刚等: "《科技强检人才讲演录 检察大数据》", 30 April 2018, 中国检察出版社 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114533014A (en) * | 2020-11-26 | 2022-05-27 | 深圳市科瑞康实业有限公司 | Method for early warning according to heart rate ranges of different heart rhythm types |
| CN113707258A (en) * | 2021-07-23 | 2021-11-26 | 厦门纳龙科技有限公司 | Method for quickly revising electrocardiogram report, terminal equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US9788796B2 (en) | System and method of adaptive interpretation of ECG waveforms | |
| WO2021143402A1 (en) | Heartbeat classification method for multi-tag ecg signal labeling, and device | |
| US20210042667A1 (en) | Adapting a machine learning model based on a second set of training data | |
| CN112164446B (en) | Medical image report generation method based on multi-network fusion | |
| CN109036503A (en) | A kind of system and method generating electrocardiographic diagnosis report | |
| JP2021514768A (en) | Methods for sleep stage detection, computing devices, and wearable devices | |
| CN103530840A (en) | Accurate and quick electronic medical record type-in system | |
| CN111798439A (en) | Medical image quality interpretation method and system for online and offline fusion and storage medium | |
| JP4589078B2 (en) | ECG classification device | |
| TWI833072B (en) | Speech recognition system and speech recognition method | |
| CN115470832A (en) | Electrocardiosignal data processing method based on block chain | |
| EP2115737B1 (en) | Method and system to improve automated emotional recognition | |
| CN111655142A (en) | Arrhythmia real-time analysis method, electrocardiogram monitoring device and storage medium | |
| US11423261B2 (en) | Electronic device and model updating method | |
| US20240215925A1 (en) | Method, system, and non-transitory computer-readable recording medium for estimating arrhythmia using composite artificial neural network | |
| CN110992198A (en) | Crop disease control scheme recommendation method, device, system, equipment and medium | |
| US20240206821A1 (en) | Apparatus and a method for predicting a physiological indicator | |
| CN112989971B (en) | Electrocardiogram data fusion method and device for different data sources | |
| Jaimes et al. | Future stress, forecasting physiological signals | |
| CN117059220A (en) | Patient follow-up method, follow-up system and follow-up device | |
| CN110786847B (en) | Electrocardiogram signal library building method and analysis method | |
| CN115399786A (en) | Cardiac rhythm recognition method and system, medical device, medical system, and storage medium | |
| US20220207382A1 (en) | Apparatus and method for refining data and improving performance of behavior recognition model by reflecting time-series characteristics of behavior | |
| US20220020478A1 (en) | System and method for identifying low clinical value telemetry cases | |
| CN111297348A (en) | Method for generating electrocardiogram analysis result, electrocardiograph and storage medium |
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 |
Application publication date: 20181218 |
|
| RJ01 | Rejection of invention patent application after publication |