CN120531402A - Remote ECG data monitoring and analysis method, device, equipment and medium for cardiology department - Google Patents

Remote ECG data monitoring and analysis method, device, equipment and medium for cardiology department

Info

Publication number
CN120531402A
CN120531402A CN202510621640.2A CN202510621640A CN120531402A CN 120531402 A CN120531402 A CN 120531402A CN 202510621640 A CN202510621640 A CN 202510621640A CN 120531402 A CN120531402 A CN 120531402A
Authority
CN
China
Prior art keywords
electrocardiographic
data
lead
channel
remote
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
CN202510621640.2A
Other languages
Chinese (zh)
Inventor
刘玚
王羽飞
薛佳慧
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.)
8th Medical Center of PLA General Hospital
Original Assignee
8th Medical Center of PLA General Hospital
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 8th Medical Center of PLA General Hospital filed Critical 8th Medical Center of PLA General Hospital
Priority to CN202510621640.2A priority Critical patent/CN120531402A/en
Publication of CN120531402A publication Critical patent/CN120531402A/en
Pending legal-status Critical Current

Links

Classifications

    • 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
    • A61B5/0002—Remote monitoring of patients using telemetry, e.g. transmission of vital signals via a communication network
    • A61B5/0004—Remote monitoring of patients using telemetry, e.g. transmission of vital signals via a communication network characterised by the type of physiological signal transmitted
    • A61B5/0006—ECG or EEG signals
    • 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
    • A61B5/25—Bioelectric electrodes therefor
    • A61B5/271—Arrangements of electrodes with cords, cables or leads, e.g. single leads or patient cord assemblies
    • A61B5/273—Connection of cords, cables or leads to electrodes
    • 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
    • A61B5/25—Bioelectric electrodes therefor
    • A61B5/279—Bioelectric electrodes therefor specially adapted for particular uses
    • A61B5/28—Bioelectric electrodes therefor specially adapted for particular uses for electrocardiography [ECG]
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/24—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]
    • A61B5/346—Analysis of electrocardiograms
    • A61B5/349—Detecting specific parameters of the electrocardiograph cycle
    • A61B5/366—Detecting abnormal QRS complex, e.g. widening
    • 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
    • A61B5/7267—Classification of physiological signals or data, e.g. using neural networks, statistical classifiers, expert systems or fuzzy systems involving training the classification device
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/24—Classification techniques
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/24—Classification techniques
    • G06F18/243—Classification techniques relating to the number of classes
    • G06F18/2433—Single-class perspective, e.g. one-against-all classification; Novelty detection; Outlier detection
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T17/00—Three-dimensional [3D] modelling for computer graphics
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T19/00—Manipulating three-dimensional [3D] models or images for computer graphics
    • G06T19/20—Editing of three-dimensional [3D] images, e.g. changing shapes or colours, aligning objects or positioning parts
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
    • G06F2218/12—Classification; Matching
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2219/00—Indexing scheme for manipulating 3D models or images for computer graphics
    • G06T2219/004—Annotating, labelling

Landscapes

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

Abstract

The application relates to a method, a device, equipment and a medium for monitoring and analyzing remote electrocardiographic data in a cardiology department. The method comprises the steps of obtaining electrocardiogram data, conducting channel matching on the electrocardiogram data to obtain channel marked electrocardiogram data, inputting the channel marked electrocardiogram data of each channel into each channel corresponding to the channel in a channel electrocardiograph abnormality identification model group to obtain electrocardiograph abnormality identification information of the channel with abnormality in the electrocardiogram data, generating remote electrocardiograph preliminary diagnosis information and remote electrocardiograph weight coefficient information corresponding to the remote electrocardiograph preliminary diagnosis information based on the electrocardiograph abnormality identification information of each channel, and adjusting data transmission parameters of the channel marked electrocardiogram data and acquisition precision parameters of the electrocardiograph data according to the remote electrocardiograph weight coefficient information. The method can realize the collaborative optimization of diagnosis precision, transmission efficiency and equipment efficiency through lead level processing and resource regulation.

Description

Intracardiac remote electrocardiograph data monitoring and analyzing method, device, equipment and medium
Technical Field
The invention belongs to the technical field of medical equipment, and particularly relates to a method, a device, equipment and a medium for monitoring and analyzing remote electrocardiographic data in a department of cardiology.
Background
In recent years, the cardiovascular disease causes the symptoms of urgent morbidity, high mortality, more complications, high recurrence rate and the like, and becomes one of the main causes of death of human beings, so the prevention and treatment of the cardiovascular disease become extremely important and challenging. In the diagnosis of cardiovascular diseases, electrocardiographic detection plays a central role. However, the traditional electrocardiographic detection developed in emergency treatment and clinic is poor in real-time performance and timeliness, and difficulty in monitoring and diagnosing in different places is difficult to overcome. Therefore, all-weather dynamic electrocardiographic monitoring and real-time online electrocardiographic monitoring data diagnosis of suspected patients and diagnosed patients with cardiovascular diseases are problems which are urgently needed to be solved.
In addition, when the traditional remote electrocardiograph monitoring equipment collects data, the traditional remote electrocardiograph monitoring equipment is easy to be interfered by the outside, and accuracy and usability of the data are affected. In addition, because of the numerous lead wires, the electrode plate is easy to fall off, so that the loss of key electrocardiograph information is possibly caused, and the accurate judgment of a doctor on an electrocardiogram is influenced. When the data transmission is carried out by the network, the unstable network signal can cause the delay or loss of the electrocardio data transmission, thereby affecting the timeliness and the reliability of remote diagnosis.
In the prior art with the authorization bulletin number of CN108512629B, an electrocardio monitoring data sending, receiving and controlling method and system are provided, but the prior art can only realize the transmission rate control of single-lead electrocardio data and lacks the mechanism of abnormal identification, weight calculation and differential parameter adjustment of a multi-lead channel.
Disclosure of Invention
Based on the above, it is necessary to provide a method, a device, equipment and a medium for monitoring and analyzing cardiac remote electrocardiographic data, which can realize lead-level collaborative optimization of diagnosis precision, transmission efficiency and equipment efficiency.
In a first aspect, the present application provides a method for monitoring and analyzing remote electrocardiographic data in a cardiology department, including:
Obtaining electrocardiogram data, and conducting channel matching on the electrocardiogram data to obtain conducting channel marked electrocardiogram data;
inputting the lead channel marking electrocardiographic data of each lead channel into each lead electrocardiographic anomaly identification model corresponding to the lead channel in the lead electrocardiographic anomaly identification model group to obtain electrocardiographic anomaly identification information of the lead channel with anomaly electrocardiographic data;
Generating remote electrocardiograph preliminary diagnosis information and remote electrocardiograph weight coefficient information corresponding to the remote electrocardiograph preliminary diagnosis information based on electrocardiograph abnormality identification information of each lead channel;
and adjusting data transmission parameters of the lead channel marked electrocardiogram data and acquisition precision parameters of the electrocardiogram data according to the remote electrocardio weight coefficient information, wherein the data transmission parameters are used for regulating and controlling the data quality and/or transmission efficiency of the lead channel marked electrocardiogram data.
In one embodiment, the intracardiac remote electrocardiographic data monitoring and analyzing method further comprises:
Conducting channel demand analysis is carried out on the remote electrocardiograph preliminary diagnosis information, and conducting channel guiding state information is generated and used for representing the working state of electrocardiograph sensing equipment of each conducting channel required by electrocardiograph data monitoring analysis corresponding to the remote electrocardiograph preliminary diagnosis information;
Conducting channel state identification is carried out on the conducting channel marked electrocardiograph data, and conducting channel actual state information is generated and used for representing the actual working state of electrocardiograph sensing equipment of each conducting channel;
Generating the channel state anomaly information and channel state anomaly class information corresponding to the channel state anomaly information based on the channel guide state information and the channel actual state information;
If the abnormal grade information exceeds a preset abnormal grade threshold of the state of the lead channel, corresponding lead channel state adjustment guide information is generated according to the abnormal information of the state of the lead channel in a matching mode, and the lead channel state adjustment guide information is used for guiding a remote electrocardiograph data monitoring operator of the department of cardiology to adjust the actual working state of electrocardiograph sensing equipment of the lead channel.
In one embodiment, generating remote electrocardiograph preliminary diagnosis information and remote electrocardiograph weight coefficient information corresponding to the remote electrocardiograph preliminary diagnosis information based on electrocardiograph abnormality identification information of each lead channel includes:
obtaining the electrocardiogram data of the lead channel template of the lead channel with abnormal electrocardiogram data of the electrocardiographic abnormality identification information;
Generating electrocardiographic data comparison lead electrocardiograph template coincidence degree scoring data of a lead channel with abnormality of electrocardiograph data of each electrocardiograph abnormality identification information based on electrocardiographic data comparison lead channel marking electrocardiograph data of the lead channel template;
According to the electrocardiogram data comparison lead electrocardiograph template coincidence degree scoring data and electrocardiograph abnormality identification information, comprehensive coincidence degree scoring and remote electrocardiograph weight coefficient information are obtained through calculation;
if the comprehensive coincidence degree score is larger than or equal to the comprehensive coincidence degree threshold value, the electrocardio abnormality identification information is used as remote electrocardio preliminary diagnosis information;
If the comprehensive coincidence degree score is smaller than the comprehensive coincidence degree threshold value, inputting the electrocardiographic anomaly identification information into the combined lead electrocardiographic anomaly identification model according to the corresponding lead channel with the anomaly of electrocardiographic data, generating remote electrocardiographic preliminary diagnosis information and combined remote electrocardiographic weight coefficient information, wherein the combined remote electrocardiographic weight coefficient information is used for correcting and updating the remote electrocardiographic weight coefficient information.
In one embodiment, the electrocardiographic anomaly identification information includes electrocardiographic anomaly severity scoring data, and the calculation formula of the remote electrocardiographic weight coefficient information is:
wherein, ψ RCM is remote electrocardiographic weight coefficient information, N is total number of conducting channels with abnormal electrocardiographic data, The data precision weight coefficient of the lead device for the ith lead channel with the abnormality of the electrocardiogram data, deltaQ i, the data quality offset coefficient of the ith lead channel with the abnormality of the electrocardiogram data, D i andThe label information and the fuzzy scoring function of the actual working state of the electrocardiograph sensing device of the ith lead channel with abnormal electrocardiograph data are respectively provided,For the weighted sum of the electrocardiographic data of the ith lead channel whose electrocardiographic data is abnormal and the electrocardiographic data of the lead channel template electrocardiographic data of the lead channels whose electrocardiographic data is abnormal and the lead electrocardiographic template coincidence degree scoring data, R i is the electrocardiographic abnormality severity degree scoring data of the ith lead channel whose electrocardiographic data is abnormal, N * is the total number of the lead channel template electrocardiographic data whose size is equal to the total number N of the lead channels whose electrocardiographic data is abnormal,AndAnd respectively obtaining the weight of the electrocardiographic data comparison lead electrocardiograph template coincidence degree scoring data and the electrocardiographic data comparison lead electrocardiograph template coincidence degree scoring data of the electrocardiograph data of the ith lead channel with abnormal electrocardiograph data comparison lead template electrocardiograph data of the jth lead channel with abnormal electrocardiograph data.
In one embodiment, the lead electrocardiographic anomaly identification model set includes a lead electrocardiographic anomaly classification sub-model set and a lead electrocardiographic anomaly identification sub-model set, and the lead channel marking electrocardiographic data of each lead channel is input into each lead electrocardiographic anomaly identification model corresponding to the lead channel in the lead electrocardiographic anomaly identification model set to obtain electrocardiographic anomaly identification information of the lead channel with an anomaly in electrocardiographic data, including:
Acquiring photoplethysmogram data;
Performing time sequence calibration and image segmentation on the lead channel marked electrocardiogram data based on the photoelectric volume pulse data to obtain a lead channel marked single electrocardiogram data set of each lead channel;
Inputting the lead channel marked single electrocardiogram data set into a lead electrocardiogram abnormal classification sub-model corresponding to each lead channel in the lead electrocardiogram abnormal classification sub-model group, and screening an electrocardiogram abnormal image to obtain an abnormal single electrocardiogram data set and a normal single electrocardiogram data set;
and inputting the abnormal single electrocardiogram data set into a lead electrocardiogram abnormal analysis sub-model which is in line with the lead channel corresponding to the abnormal single electrocardiogram data set in the lead electrocardiogram abnormal identification sub-model group, so as to generate the electrocardiogram abnormal identification information.
In one embodiment, the intracardiac remote electrocardiographic data monitoring and analyzing method further comprises:
Inputting the normal single electrocardiogram data set of each lead channel into a normal electrocardiogram image fusion model group to generate a normal electrocardiogram fusion image of each lead channel;
Verifying the normal single electrocardiogram data set based on the normal electrocardiogram fusion image, and identifying single electrocardiogram data which deviate from the normal electrocardiogram data and are used for representing statistically significant differences between the normal single electrocardiogram data set and the normal electrocardiogram fusion image;
Removing the deviating normal electrocardiogram data in the normal single electrocardiogram data set to obtain a calibrated normal single electrocardiogram data set, and constructing the deviating normal electrocardiogram data set based on the deviating normal electrocardiogram data;
Generating and updating intracardiac remote electrocardiographic data monitoring medical history information based on the abnormal single electrocardiographic data set, the calibrated normal single electrocardiographic data set and the deviation from the normal electrocardiographic data set.
In one embodiment, the intracardiac remote electrocardiographic data monitoring and analyzing method further comprises:
Acquiring and initializing an initial digital twin model of the heart;
if the remote electrocardio weight coefficient information exceeds a preset remote electrocardio weight coefficient threshold value, selecting electrocardio abnormal core identification information matched with remote electrocardio preliminary diagnosis information from electrocardio abnormal identification information of each guide channel;
generating heart abnormality visual annotation information based on the heart abnormality core identification information;
Labeling the heart abnormality visualization labeling information on the heart initial digital twin model, updating the heart initial digital twin model, and generating the heart abnormality labeling digital twin model.
In a second aspect, the present application further provides a device for monitoring and analyzing electrocardiographic data remotely in a cardiology department, including:
The electrocardiographic data acquisition module is used for acquiring electrocardiographic data, conducting channel matching on the electrocardiographic data, and obtaining conducting channel marked electrocardiographic data;
The electrocardiographic anomaly identification module is used for inputting the lead channel marking electrocardiographic data of each lead channel into each lead electrocardiographic anomaly identification model corresponding to the lead channel in the lead electrocardiographic anomaly identification model group to obtain electrocardiographic anomaly identification information of the lead channel with the electrocardiographic data anomaly;
The remote primary diagnosis module is used for generating remote electrocardiograph primary diagnosis information and remote electrocardiograph weight coefficient information corresponding to the remote electrocardiograph primary diagnosis information based on electrocardiograph abnormality identification information of each lead channel;
The remote parameter adjusting module is used for adjusting data transmission parameters of the lead channel marked electrocardiogram data and acquisition precision parameters of the electrocardiogram data according to the remote electrocardio weight coefficient information, wherein the data transmission parameters are used for adjusting and controlling the data quality and/or transmission efficiency of the lead channel marked electrocardiogram data.
In a third aspect, the present application also provides a computer device comprising a memory storing a computer program and a processor implementing the steps of the method according to any of the first aspects of the application when the computer program is executed by the processor.
In a fourth aspect, the present application also provides a computer-readable storage medium having stored thereon a computer program which, when executed by a processor, implements the steps of the method according to any of the first aspects of the application.
The method, the device, the computer equipment and the storage medium for monitoring and analyzing the electrocardiographic data in the cardiology department can accurately locate abnormal sources through the matching of the guide channels, improve the accuracy of remote electrocardiographic monitoring, capture the specific myocardial electrical activities of different guide channels through constructing an independent abnormal identification model for the guide channels, further effectively avoid the misjudgment of complex arrhythmia, dynamically regulate and control the data quality and the transmission efficiency of electrocardiographic monitoring data through a dynamic weight regulation mechanism, further preferentially guarantee the integrity and the accuracy of key guide data under the limited transmission condition, and support the real-time decision in a remote emergency scene.
Drawings
In order to more clearly illustrate the embodiments of the present application or the technical solutions in the related art, the drawings that are required to be used in the embodiments or the related technical descriptions will be briefly described, and it is apparent that the drawings in the following description are only some embodiments of the present application, and other drawings may be obtained according to the drawings without inventive effort for those skilled in the art.
Fig. 1 is a schematic view of an application environment of a method for monitoring and analyzing remote electrocardiographic data of a cardiology department according to an embodiment of the present application;
fig. 2 is a schematic flow chart of a method for monitoring and analyzing remote electrocardiographic data in a cardiology department according to an embodiment of the present application;
FIG. 3 is a flow chart of another method for monitoring and analyzing remote electrocardiographic data of cardiology according to an embodiment of the present application;
FIG. 4 is a flow chart of a remote preliminary diagnostic method according to an embodiment of the present application;
FIG. 5 is a schematic flow chart of an electrocardiographic anomaly identification method according to an embodiment of the present application;
fig. 6 is a schematic structural diagram of a remote electrocardiographic data monitoring and analyzing device for cardiology according to an embodiment of the present application.
Detailed Description
The present application will be described in further detail with reference to the drawings and examples, in order to make the objects, technical solutions and advantages of the present application more apparent. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the application.
The intracardiac remote electrocardiographic data monitoring and analyzing method provided by the embodiment of the application can be applied to an application environment shown in fig. 1. Wherein the sensing device 102 and the diagnosis and treatment terminal 103 can communicate with the server 104 through a network. Database 104 may store data that server 101 needs to process. Database 104 may be integrated on server 101 or may be located on the cloud or other network server. The sensing device 102 may collect remote electrocardiographic data of the user and send the data to the server 101 via a network. The server 101 may store the remote electrocardiograph data of the user acquired by the sensing device 102 in a database, and analyze the remote electrocardiograph data of the user acquired by the sensing device 102 through a cardiology remote electrocardiograph data monitoring and analyzing application program carried on the server 101, so as to generate a cardiology remote electrocardiograph data monitoring and analyzing report. The diagnosis and treatment terminal 103 can acquire the intracardiac remote electrocardiographic data monitoring analysis report generated by the server 101 through a network. The diagnosis terminal 103 may be, but not limited to, various desktop computers, all-in-one machines, notebook computers, smart phones, tablet computers, and medical computing platforms, the sensing device 102 may be, but not limited to, an internet of things sensing device and a portable wearable device, and the portable wearable device may be a smart watch, a smart bracelet, a smart electrocardiograph monitoring device, and the like. The server 101 may be implemented as a stand-alone server or as a server cluster composed of a plurality of servers.
In an exemplary embodiment of the present application, as shown in fig. 2, a method for monitoring and analyzing remote electrocardiographic data of a cardiology is provided, and the method is applied to the server 101 in fig. 1 for illustration, and includes the following steps S201 to S204. Wherein:
step S201, obtaining electrocardiogram data, and conducting channel matching on the electrocardiogram data to obtain conducting channel marked electrocardiogram data.
Specifically, the server 101 may acquire remote electrocardiographic data of the user acquired by the sensing device through a network, and perform channel matching on the electrocardiographic data according to a channel matching application program carried by the server 101, so as to obtain channel marked electrocardiographic data. The lead channels may include, but are not limited to, standard limb leads, monopolar chest leads, and monopolar limb leads, among others.
Illustratively, the I lead of the standard limb lead is used for acquiring electrocardiosignals from the space between the left upper limb and the right upper limb and mainly reflects the depolarization process of the left ventricle; the standard limb lead II leads acquire signals from the position between the right upper limb and the left lower limb and can better reflect the electric activity of the left ventricle; the III leads of the standard limb leads acquire signals from the position between the left upper limb and the left lower limb, reflect the electric activity of the left ventricle to a certain extent, and have different waveform characteristics from the II leads due to the relation of projection angles; the V1 lead of the unipolar chest lead is close to the right ventricle, can reflect the depolarization and repolarization process of the right ventricle, the QRS complex of the V1 lead is mainly of rS type and has relatively low R wave amplitude, the V2 lead of the unipolar chest lead is positioned between the fourth rib of the left edge of the sternum, can reflect the electric activity of the left ventricle and the right ventricle, the QRS complex of the V2 lead is usually mainly of rS type or Rs type, the V3 lead of the unipolar chest lead is positioned at the midpoint of the connecting line of the V2 lead and the V4 lead, is sensitive to the electric activity of the left ventricle, the QRS complex of the V3 lead is diversified, can be of rS type, rs type, qR type and the like, the V4 lead of the unipolar chest lead is positioned between the fifth rib of the left collarbone, can clearly display the electric activity of the left ventricle, the QRS complex of the V4 lead is usually mainly of R type and has relatively high R wave amplitude, the V5 lead of the unipolar chest lead is positioned between the fifth rib of the left ventricle, the QRS lead is usually of V5 lead has high amplitude, the V6 lead is mainly of the V2 lead is positioned between the fifth rib of the left ventricle, the V4 lead is normally has high amplitude, the V6 lead is high amplitude of the main arm of the V lead is normally has high amplitude of the main V lead, and the V lead is high amplitude of the main, and the V lead is high amplitude of the main, and is high amplitude of the main and is high amplitude, the aVL lead of the unipolar limb lead is a left arm unipolar lead and can reflect the electrical activity of the left ventricle, and the aVF lead of the unipolar limb lead is a left leg unipolar lead and is more sensitive to the observation of the lower wall myocardium.
Step S202, the lead channel marking electrocardio data of each lead channel is input into each lead electrocardio abnormality identification model corresponding to the lead channel in the lead electrocardio abnormality identification model group, and electrocardio abnormality identification information of the lead channel with abnormal electrocardiograph data is obtained.
Specifically, the server 101 may input the lead channel marked electrocardiograph data of each lead channel into each lead electrocardiograph abnormality identification model corresponding to the lead channel in the lead electrocardiograph abnormality identification model set carried by the server 101, if the lead electrocardiograph abnormality identification model carried by the server 101 identifies that the lead channel marked electrocardiograph data of the lead channel is abnormal, the server 101 may generate electrocardiograph abnormality identification information of the lead channel with abnormal electrocardiograph data, if the lead electrocardiograph abnormality identification model carried by the server 101 identifies that the lead channel marked electrocardiograph data of the lead channel is in a normal state, the server 101 may store the lead channel marked electrocardiograph data in a database.
Alternatively, the lead electrocardiographic anomaly recognition model may be trained based on a modified cyclic convolutional neural network in combination with a modified self-encoder constructed joint neural network model.
Step S203, remote electrocardiograph preliminary diagnosis information and remote electrocardiograph weight coefficient information corresponding to the remote electrocardiograph preliminary diagnosis information are generated based on electrocardiograph abnormality identification information of each lead channel.
Specifically, the server 101 may generate remote electrocardiograph preliminary diagnosis information based on electrocardiograph abnormality identification information of a lead channel with an abnormality generated by a lead electrocardiograph abnormality identification model according to a preset remote electrocardiograph preliminary diagnosis policy, and calculate remote electrocardiograph weight coefficient information corresponding to the remote electrocardiograph preliminary diagnosis information by combining with a remote electrocardiograph weight coefficient information generation algorithm. The remote electrocardio weight coefficient information may include, but is not limited to, a remote electrocardio critical weight coefficient for representing the critical degree of the disorder corresponding to the abnormal electrocardio data and a remote electrocardio lead weight coefficient for representing the importance degree of the data of each lead channel corresponding to the remote electrocardio preliminary diagnosis information.
Alternatively, the remote electrocardiographic primary diagnostic information may include, but is not limited to, atrial fibrillation, interstitial bundle branch block, intermittent pre-excitation, differential indoor conduction, and ventricular escape.
Step S204, data transmission parameters of the lead channel marked electrocardiogram data and acquisition precision parameters of the electrocardiogram data are adjusted according to the remote electrocardiogram weight coefficient information.
Specifically, the server 101 may adjust the data transmission parameters of the lead channel marker electrocardiographic data of all the lead channels and the acquisition accuracy parameters of the electrocardiographic data of all the lead channels according to the remote electrocardiographic critical weight coefficient. The server 101 may also adjust data transmission parameters of the lead marker electrocardiogram data of the specific lead channel and acquisition accuracy parameters of the electrocardiogram data of the specific lead channel according to the remote electrocardiogram lead weight coefficient.
Illustratively, the data transmission parameters may be used to regulate the data quality and/or transmission efficiency of the lead channel marker electrocardiographic data. The acquisition accuracy parameters of the electrocardiogram data can be used for improving the acquisition accuracy when the conducting channel is in a suspected abnormal condition to acquire more detailed, accurate and reliable electrocardiographic information.
Optionally, the data transmission parameters of the lead channel marker electrocardiographic data may include, but are not limited to, sample rate, sample size, packet size, signal-to-noise ratio, carrier frequency, data rate, bandwidth, and transmission power.
According to the method for monitoring and analyzing the electrocardiographic data in the intracardiac department, electrocardiographic data are acquired and the lead channels are matched, so that multi-mode data fusion can be achieved, further, comprehensive assessment of the electrocardiographic activity of the heart can be facilitated, diagnosis accuracy is improved, electrocardiographic abnormal characteristics can be accurately identified by combining electrocardiographic abnormal identification models with marked electrocardiographic data of all the lead channels, information of different lead channels is integrated, further, the electrocardiographic activity can be comprehensively assessed, possibility of missed diagnosis and misdiagnosis is reduced, accurate diagnosis is achieved, more transmission resources can be allocated to the lead channels with higher weight by adjusting data transmission parameters of the lead channel marked electrocardiographic data according to remote electrocardiographic weight coefficient information, high-quality transmission of key data is guaranteed, improvement of efficiency and reliability of data transmission can be facilitated, risk of loss and damage of important data is reduced, and electrocardiographic data acquisition processes can be dynamically optimized according to remote electrocardiographic weight coefficient information by adjusting acquisition accuracy parameters of electrocardiographic data, and diagnosis reliability can be improved.
In an alternative embodiment of the present application, please refer to fig. 3, the intracardiac remote electrocardiographic data monitoring and analyzing method may further include:
Step S305, conducting channel demand analysis on the remote electrocardiograph preliminary diagnosis information to generate channel guide state information.
Specifically, the channel guide state information may be used to characterize the working state of the electrocardiographic sensing device of each channel required for electrocardiographic data monitoring analysis corresponding to the remote electrocardiographic preliminary diagnosis information.
Step S306, conducting channel state identification is conducted on the conducting channel marked electrocardiograph data, and conducting channel actual state information is generated.
Specifically, the actual state information of the lead channels is used for representing the actual working state of the electrocardiographic sensing equipment of each lead channel.
Step S307, generating the channel state anomaly information and the channel state anomaly class information corresponding to the channel state anomaly information based on the channel guide state information and the channel actual state information.
Step S308, if the abnormal grade information exceeds the preset abnormal grade threshold value of the state of the guide channel, corresponding guide channel state adjustment guide information is generated according to the abnormal information of the state of the guide channel in a matching mode.
Specifically, the guide channel state adjustment guide information is used for guiding a intracardiac remote electrocardiograph data monitoring operator to adjust the actual working state of the electrocardiograph sensing equipment of the guide channel.
Illustratively, the lead electrode drop is taken as an example, and at this time, the lead channel state abnormality information may be, but is not limited to, lead electrode drop abnormality identification information including a lead channel from which the lead electrode drops. At this time, the lead channel state adjustment guide information may be used to guide the operator to place the electrode of the lead channel from which the lead electrode falls at a specified position in a specified manner to achieve normal operation of the lead channel.
According to the method for monitoring and analyzing the electrocardiographic data of the intracardiac branch of the heart, the electrocardiographic data of the guide channels are marked, so that the working state of each guide channel and the corresponding sensing equipment can be accurately detected, further, the abnormal working state of the sensing equipment can be timely found out and targeted adjustment can be carried out, the electrocardiographic sensing equipment can be ensured to operate according to the expected working state, the accuracy and the integrity of the electrocardiographic data of the heart are ensured, and misdiagnosis and missed diagnosis caused by poor equipment state are avoided.
Furthermore, when the guide channel is abnormal, the method for monitoring and analyzing the remote electrocardiographic data in the department of cardiology can rapidly and accurately locate fault information, provide clear fault processing direction for operators, reduce interruption time of patient monitoring, and enhance stability and reliability of a remote electrocardiographic monitoring system.
In an alternative embodiment of the present application, as shown in fig. 4, the generating remote electrocardiograph preliminary diagnosis information based on electrocardiograph abnormality identification information of each lead channel and remote electrocardiograph weight coefficient information corresponding to the remote electrocardiograph preliminary diagnosis information may include:
Step S401, acquiring lead channel template electrocardiographic data of a lead channel in which each electrocardiographic data of electrocardiographic abnormality identification information is abnormal.
Step S402, generating the electrocardiogram data comparison lead electrocardiograph template coincidence degree scoring data of the lead channels with abnormal electrocardiogram data of each electrocardiograph abnormal identification information based on the electrocardiogram data comparison lead channel template electrocardiograph data.
Specifically, the server may compare the lead channel marking electrocardiographic data based on the lead channel template electrocardiographic data in combination with a preset comparison rule, and generate electrocardiographic data comparison lead electrocardiographic template coincidence degree scoring data of the lead channels in which the electrocardiographic data of each electrocardiographic abnormality identification information is abnormal.
Optionally, the server may input the lead channel template electrocardiographic data and the lead channel marker electrocardiographic data into a lead electrocardiographic data comparison model carried on the server, and generate electrocardiographic data comparison lead electrocardiographic template coincidence degree scoring data of a lead channel in which electrocardiographic data of each electrocardiographic abnormality identification information is abnormal.
Step S403, according to the electrocardiogram data comparison lead electrocardio template coincidence degree scoring data and electrocardio abnormality identification information, comprehensive coincidence degree scoring and remote electrocardio weight coefficient information are obtained through calculation.
Specifically, the server may construct a coincidence degree scoring matrix based on the electrocardiogram data and the coincidence degree scoring data of the lead electrocardiograph template, and generate a coincidence degree scoring weight matrix of the coincidence degree scoring matrix based on the electrocardiograph anomaly identification information. The server may calculate a composite fitness score based on a Hadamard product (Hadamard product) of the fitness scoring matrix and the fitness scoring weight matrix. The server can also calculate and obtain remote electrocardio weight coefficient information by combining channel data quality information and channel equipment working state information based on electrocardiographic data comparison lead electrocardiograph template coincidence degree scoring data and electrocardiograph abnormality identification information.
Illustratively, the number of lead channels in which the electrocardiographic data is abnormal is three as an exampleCoincidence degree scoring weight matrixAnd comprehensive compliance scoreThe expression of (2) may be:
In the formula, In order to be a matrix of the score for the degree of conformity,For the coincidence scoring weight matrix, N is the total number of the conducting channels with the abnormality of the electrocardiogram data, N * is the total number of the conducting channel template electrocardiogram data, the size of which is equal to the total number N of the conducting channels with the abnormality of the electrocardiogram data,Electrocardiogram data of the ith lead channel whose electrocardiogram data is abnormal versus electrocardiogram data of the lead template electrocardiogram data of the jth lead channel whose electrocardiogram data is abnormal versus lead electrocardiogram template coincidence scoring data,The weight of the electrocardiogram data of the lead template electrocardiogram data of the ith lead channel with abnormal electrocardiogram data compared with the lead electrocardiogram template conformity scoring data of the jth lead channel with abnormal electrocardiogram data,Scoring matrix for based on coincidenceCoincidence degree scoring weight matrixThe overall conformity score was calculated, as well as the hadamard product, |·| F being the freude Luo Beini us norm (Frobenius norm).
And step S404, if the comprehensive coincidence degree score is greater than or equal to the comprehensive coincidence degree threshold value, the electrocardio abnormality identification information is used as remote electrocardio preliminary diagnosis information.
Step S405, if the comprehensive coincidence degree score is smaller than the comprehensive coincidence degree threshold, inputting the electrocardiographic anomaly identification information into the combined lead electrocardiographic anomaly identification model according to the corresponding lead channels with anomalies in electrocardiographic data, and generating remote electrocardiographic preliminary diagnosis information and combined remote electrocardiographic weight coefficient information.
Specifically, the combined remote electrocardiographic weight coefficient information can be used for correcting and updating the remote electrocardiographic weight coefficient information.
Alternatively, a joint lead electrocardiographic anomaly recognition model may be constructed based on a transducer model (transducer).
According to the method for monitoring and analyzing the electrocardio remote electrocardio data in the cardiology department, the difference between the electrocardio abnormality identification information and the preset template can be accurately quantified through generating the coincidence degree scoring data, the accuracy of diagnosis can be improved, reliable quantification basis can be provided for subsequent diagnosis decision, comprehensive evaluation of electrocardio abnormality can be achieved through comprehensive coincidence degree scoring and calculation of remote electrocardio weight coefficient information, the most representative electrocardio abnormality condition can be identified in a plurality of lead channels, the reliability of diagnosis can be improved, the electrocardio abnormality identification information can be further analyzed through introducing a combined lead electrocardio abnormality identification model, combined remote electrocardio weight coefficient information is generated, remote electrocardio weight coefficient information can be corrected and updated based on the combined remote electrocardio weight coefficient information, further accurate diagnosis information can be provided under complex or atypical electrocardio abnormality conditions, the diagnosis performance of remote electrocardio can be effectively improved through accurate comparison and comprehensive evaluation mechanisms, and further the technique for providing remote medical support can be provided for the cardiology department.
In an optional embodiment of the present application, the electrocardiographic anomaly identification information includes electrocardiographic anomaly severity scoring data, and the calculation formula of the remote electrocardiographic weight coefficient information may be:
wherein, ψ RCM is remote electrocardiographic weight coefficient information, N is total number of conducting channels with abnormal electrocardiographic data, The data precision weight coefficient of the lead device for the ith lead channel with the abnormality of the electrocardiogram data, deltaQ i, the data quality offset coefficient of the ith lead channel with the abnormality of the electrocardiogram data, D i andThe label information and the fuzzy scoring function of the actual working state of the electrocardiograph sensing device of the ith lead channel with abnormal electrocardiograph data are respectively provided,For the weighted sum of the electrocardiographic data of the ith lead channel whose electrocardiographic data is abnormal and the electrocardiographic data of the lead channel template electrocardiographic data of the lead channels whose electrocardiographic data is abnormal and the lead electrocardiographic template coincidence degree scoring data, R i is the electrocardiographic abnormality severity degree scoring data of the ith lead channel whose electrocardiographic data is abnormal, N * is the total number of the lead channel template electrocardiographic data whose size is equal to the total number N of the lead channels whose electrocardiographic data is abnormal,AndAnd respectively obtaining the weight of the electrocardiographic data comparison lead electrocardiograph template coincidence degree scoring data and the electrocardiographic data comparison lead electrocardiograph template coincidence degree scoring data of the electrocardiograph data of the ith lead channel with abnormal electrocardiograph data comparison lead template electrocardiograph data of the jth lead channel with abnormal electrocardiograph data.
Optionally, when the available computing power of the server meets a preset computing power threshold condition, the server may compare the influence coefficient of the weighted sum of the lead electrocardiographic template conformity scoring data based on the electrocardiographic data of the ith lead channel with abnormality in electrocardiographic dataAnd the Electrocardiogram abnormality severity scoring data influence coefficientFurther correcting the remote electrocardiographic weight coefficient information, at this time, a calculation formula of the remote electrocardiographic weight coefficient information may be:
wherein the influence coefficient of the electrocardiogram data of the ith lead channel with abnormal electrocardiogram data compared with the weighted sum of the lead electrocardiographic template coincidence degree scoring data And the Electrocardiogram abnormality severity scoring data influence coefficientThe weighted sum of the electrocardiogram data comparison lead electrocardiograph plate conformity scoring data of the lead electrocardiograph plate electrocardiograph data of the lead channels with abnormal electrocardiograph data can be respectively compared based on the electrocardiograph data of the ith lead channel with abnormal electrocardiograph dataAnd the electrocardio abnormality severity scoring data R i of the ith lead channel with abnormal electrocardiographic data are generated by combining a preset influence coefficient calculation rule. Wherein the influence coefficient calculation rule can be constructed based on a fuzzy control algorithm, but is not limited to the method.
In an alternative embodiment of the present application, the lead electrocardiographic anomaly identification model set includes a lead electrocardiographic anomaly classification sub-model set and a lead electrocardiographic anomaly identification sub-model set, please refer to fig. 5, and the method may include, inputting the lead channel marking electrocardiographic data of each lead channel into each lead electrocardiographic anomaly identification model corresponding to the lead channel in the lead electrocardiographic anomaly identification model set, to obtain electrocardiographic anomaly identification information of the lead channel in which electrocardiographic data is abnormal, where:
In step S501, photoplethysmography data is acquired.
Illustratively, photoplethysmography data (Photoplethysmography, PPG) is a non-invasive detection data for detecting blood volume changes.
Step S502, performing time sequence calibration and image segmentation on the lead channel marked electrocardiographic data based on the photoplethysmographic pulse data to obtain a lead channel marked single electrocardiographic data set of each lead channel.
Step S503, inputting the lead channel marked single electrocardiogram data set into the lead electrocardiogram abnormal classification sub-model corresponding to each lead channel in the lead electrocardiogram abnormal classification sub-model group, and screening the electrocardiogram abnormal images to obtain an abnormal single electrocardiogram data set and a normal single electrocardiogram data set.
Alternatively, the server may construct a lead electrocardiographic anomaly classification sub-model based on a clustering algorithm model, which may include, but is not limited to, a K-means clustering model, a hierarchical clustering model, a spectral clustering model, a random forest model, a self-organizing map network model, and a Gaussian mixture model.
Step S504, inputting the abnormal single electrocardiogram data set into a lead electrocardiogram abnormal analysis sub-model which is in line with a lead channel corresponding to the abnormal single electrocardiogram data set in the lead electrocardiogram abnormal identification sub-model group, and generating electrocardiogram abnormal identification information.
Illustratively, the lead electrocardiographic anomaly analysis sub-model can be trained based on a modified cyclic convolutional neural network in combination with a modified self-encoder constructed joint neural network model.
According to the method for monitoring and analyzing the remote electrocardiographic data in the department of cardiology, multi-modal fusion of the remote monitoring data can be achieved by combining the photoelectric volume pulse data and the lead channel marked electrocardiographic data, wherein the photoelectric volume pulse data can provide hemodynamic information, data noise and interference can be reduced, accuracy of electrocardiographic anomaly identification is improved, further functions and states of hearts can be comprehensively evaluated, accuracy of remote diagnosis is improved, electrocardiographic anomaly image screening is conducted on the lead channel marked single electrocardiographic data set through the lead electrocardiographic anomaly classification sub-model, abnormal electrocardiographic data and normal electrocardiographic data can be effectively distinguished, false report and false report can be reduced, reliability of anomaly identification is improved, the abnormal single electrocardiographic data set is input into the lead electrocardiographic anomaly identification sub-model group, targeted electrocardiographic anomaly analysis can be conducted, types and degrees of electrocardiographic anomalies can be accurately identified, more detailed diagnosis information can be provided, and further doctors can be supported to make more accurate remote diagnosis decisions.
In an alternative embodiment of the present application, please refer to fig. 5, the intracardiac remote electrocardiographic data monitoring and analyzing method further includes:
step S505, inputting the normal single electrocardiogram data set of each lead channel into the normal electrocardiogram image fusion model group to generate a normal electrocardiogram fusion image of each lead channel.
Step S506, checking the normal single electrocardiogram data set based on the normal electrocardiogram fusion image, and identifying deviation from the normal electrocardiogram data.
In particular, deviations from normal electrocardiographic data may be used to characterize single electrocardiographic data in a normal single electrocardiographic dataset that is statistically significantly different from a normal electrocardiographic fusion image.
Step S507, removing the deviating normal electrocardiogram data in the normal single electrocardiogram data set to obtain a calibrated normal single electrocardiogram data set, and constructing the deviating normal electrocardiogram data set based on the deviating normal electrocardiogram data set.
Step S508, generating and updating intracardiac remote electrocardiographic data monitoring medical history information based on the abnormal single electrocardiographic data set, the calibrated normal single electrocardiographic data set, and the deviation from the normal electrocardiographic data set.
Illustratively, the abnormal single electrocardiogram data set may include a real-time abnormal electrocardiogram data set and a historical abnormal electrocardiogram data set, the calibrated normal single electrocardiogram data set may include a real-time calibrated normal single electrocardiogram data set and a historical calibrated normal single electrocardiogram data set, and the off-normal electrocardiogram data set may include a real-time off-normal electrocardiogram data set and a historical off-normal electrocardiogram data set.
According to the method for monitoring and analyzing the remote electrocardiographic data of the cardiology, the normal single electrocardiographic data set is checked based on the normal electrocardiographic fusion image, deviation from the normal electrocardiographic data with statistically significant differences from the normal electrocardiographic fusion image can be accurately identified, the purity and consistency of the data can be further improved, a more reliable data basis is provided for subsequent analysis, misjudgment risks caused by abnormality of the electrocardiographic data can be effectively reduced by constructing the calibration normal single electrocardiographic data set, and further the accuracy of diagnosis can be improved, and the medical history information of a patient can be more comprehensive and accurate by generating and updating the remote electrocardiographic data monitoring medical history information of the cardiology based on the abnormal single electrocardiographic data set, the calibration normal single electrocardiographic data set and the deviation from the normal electrocardiographic data set, so that more accurate and comprehensive diagnostic information can be provided for doctors, and powerful support can be provided for long-term electrocardiographic remote monitoring and intracardiac treatment of the patient.
In an alternative embodiment of the present application, please refer to fig. 3, the intracardiac remote electrocardiographic data monitoring and analyzing method may further include:
step S309, an initial digital twin model of the heart is acquired and initialized.
Step S310, if the remote electrocardio weight coefficient information exceeds the preset remote electrocardio weight coefficient threshold value, selecting the electrocardio abnormal core identification information matched with the remote electrocardio preliminary diagnosis information from the electrocardio abnormal identification information of each guide channel.
Step S311, generating heart abnormality visualization annotation information based on the heart abnormality core identification information.
Step S312, marking the heart abnormality visualization marking information on the heart initial digital twin model, updating the heart initial digital twin model, and generating a heart abnormality marking digital twin model.
According to the intracardiac remote electrocardiograph data monitoring and analyzing method, the anatomical structure and electrophysiological information of the heart can be intuitively displayed, doctors can be helped to quickly identify abnormal areas, and more accurate diagnosis can be made. And doctors can intuitively explain the disease conditions to patients and family members thereof by using the model, and improve the understanding and treatment compliance of the patients on the diseases.
In an exemplary embodiment of the present application, as shown in fig. 3, another method for monitoring and analyzing electrocardiographic data remotely from a cardiology department is provided, which includes the following steps S301 to S312. Wherein:
step S301, obtaining electrocardiogram data, and conducting channel matching on the electrocardiogram data to obtain conducting channel marked electrocardiogram data.
Step S302, the lead channel marking electrocardio data of each lead channel is input into each lead electrocardio abnormality identification model corresponding to the lead channel in the lead electrocardio abnormality identification model group, and electrocardio abnormality identification information of the lead channel with abnormal electrocardiograph data is obtained.
Step S303, generating remote electrocardiograph preliminary diagnosis information and remote electrocardiograph weight coefficient information corresponding to the remote electrocardiograph preliminary diagnosis information based on electrocardiograph abnormality identification information of each lead channel.
Step S304, data transmission parameters of the lead channel marked electrocardiogram data and acquisition precision parameters of the electrocardiogram data are adjusted according to the remote electrocardiogram weight coefficient information.
Step S305, conducting channel demand analysis on the remote electrocardiograph preliminary diagnosis information to generate channel guide state information.
Step S306, conducting channel state identification is conducted on the conducting channel marked electrocardiograph data, and conducting channel actual state information is generated.
Step S307, generating the channel state anomaly information and the channel state anomaly class information corresponding to the channel state anomaly information based on the channel guide state information and the channel actual state information.
Step S308, if the abnormal grade information exceeds the preset abnormal grade threshold value of the state of the guide channel, corresponding guide channel state adjustment guide information is generated according to the abnormal information of the state of the guide channel in a matching mode.
Step S309, an initial digital twin model of the heart is acquired and initialized.
Step S310, if the remote electrocardio weight coefficient information exceeds the preset remote electrocardio weight coefficient threshold value, selecting the electrocardio abnormal core identification information matched with the remote electrocardio preliminary diagnosis information from the electrocardio abnormal identification information of each guide channel.
Step S311, generating heart abnormality visualization annotation information based on the heart abnormality core identification information.
Step S312, marking the heart abnormality visualization marking information on the heart initial digital twin model, updating the heart initial digital twin model, and generating a heart abnormality marking digital twin model.
According to the method for monitoring and analyzing the remote electrocardiographic data of the cardiology department, through technical means such as multi-lead collaborative diagnosis, deep learning model, dynamic data transmission adjustment, equipment state monitoring and adjustment, visualization of the cardiac digital twin model and the like, accurate collection, efficient transmission, intelligent analysis and visual display of electrocardiographic data can be achieved, accuracy, monitoring efficiency and medical service quality of remote diagnosis of the cardiology department can be effectively improved, personalized medical scheme formulation and remote medical cooperation can be supported, and configuration of remote medical resources is optimized.
It should be understood that, although the steps in the flowcharts related to the embodiments described above are sequentially shown as indicated by arrows, these steps are not necessarily sequentially performed in the order indicated by the arrows. The steps are not strictly limited to the order of execution unless explicitly recited herein, and the steps may be executed in other orders. Moreover, at least some of the steps in the flowcharts described in the above embodiments may include a plurality of steps or a plurality of stages, which are not necessarily performed at the same time, but may be performed at different times, and the order of the steps or stages is not necessarily performed sequentially, but may be performed alternately or alternately with at least some of the other steps or stages.
Based on the same inventive concept, the embodiment of the application also provides a device for monitoring and analyzing the intracardiac remote electrocardiographic data, which is used for realizing the method for monitoring and analyzing the intracardiac remote electrocardiographic data. The implementation scheme of the device for solving the problems is similar to that described in the above method, so the specific limitation in the embodiments of the device for monitoring and analyzing remote electrocardiographic data of the intracardiac department provided below can be referred to the limitation of the method for monitoring and analyzing remote electrocardiographic data of the intracardiac department hereinabove, and will not be repeated here.
In an exemplary embodiment, as shown in fig. 6, there is provided a intracardiac remote electrocardiographic data monitoring and analyzing apparatus 600, comprising:
The electrocardiographic data obtaining module 601 may be configured to obtain electrocardiographic data, and perform channel matching on the electrocardiographic data to obtain channel marked electrocardiographic data.
The electrocardiographic anomaly identification module 602 may be configured to input electrocardiographic channel marking electrocardiographic data of each lead channel into each lead electrocardiographic anomaly identification model corresponding to the lead channel in the lead electrocardiographic anomaly identification model set, so as to obtain electrocardiographic anomaly identification information of the lead channel with an anomaly in electrocardiographic data.
The remote preliminary diagnosis module 603 may be configured to generate remote electrocardiographic preliminary diagnosis information and remote electrocardiographic weight coefficient information corresponding to the remote electrocardiographic preliminary diagnosis information based on electrocardiographic abnormality identification information of each of the conductive channels.
The remote parameter adjustment module 604 may be configured to adjust a data transmission parameter of the channel-marking electrocardiograph data and an acquisition accuracy parameter of the electrocardiograph data according to the remote electrocardiograph weight coefficient information, where the data transmission parameter is used to regulate and control data quality and/or transmission efficiency of the channel-marking electrocardiograph data.
In an alternative embodiment of the present application, the intracardiac remote electrocardiographic data monitoring and analyzing apparatus 600 may be further used to:
Conducting channel demand analysis is carried out on the remote electrocardiograph preliminary diagnosis information, and conducting channel guiding state information is generated and used for representing the working state of electrocardiograph sensing equipment of each conducting channel required by electrocardiograph data monitoring analysis corresponding to the remote electrocardiograph preliminary diagnosis information;
Conducting channel state identification is carried out on the conducting channel marked electrocardiograph data, and conducting channel actual state information is generated and used for representing the actual working state of electrocardiograph sensing equipment of each conducting channel;
Generating the channel state anomaly information and channel state anomaly class information corresponding to the channel state anomaly information based on the channel guide state information and the channel actual state information;
If the abnormal grade information exceeds a preset abnormal grade threshold of the state of the lead channel, corresponding lead channel state adjustment guide information is generated according to the abnormal information of the state of the lead channel in a matching mode, and the lead channel state adjustment guide information is used for guiding a remote electrocardiograph data monitoring operator of the department of cardiology to adjust the actual working state of electrocardiograph sensing equipment of the lead channel.
In an alternative embodiment of the present application, the remote preliminary diagnostic module 603 may also be configured to:
obtaining the electrocardiogram data of the lead channel template of the lead channel with abnormal electrocardiogram data of the electrocardiographic abnormality identification information;
Generating electrocardiographic data comparison lead electrocardiograph template coincidence degree scoring data of a lead channel with abnormality of electrocardiograph data of each electrocardiograph abnormality identification information based on electrocardiographic data comparison lead channel marking electrocardiograph data of the lead channel template;
According to the electrocardiogram data comparison lead electrocardiograph template coincidence degree scoring data and electrocardiograph abnormality identification information, comprehensive coincidence degree scoring and remote electrocardiograph weight coefficient information are obtained through calculation;
if the comprehensive coincidence degree score is larger than or equal to the comprehensive coincidence degree threshold value, the electrocardio abnormality identification information is used as remote electrocardio preliminary diagnosis information;
If the comprehensive coincidence degree score is smaller than the comprehensive coincidence degree threshold value, inputting the electrocardiographic anomaly identification information into the combined lead electrocardiographic anomaly identification model according to the corresponding lead channel with the electrocardiographic data anomaly, generating remote electrocardiographic preliminary diagnosis information and combined remote electrocardiographic weight coefficient information, wherein the combined remote electrocardiographic weight coefficient information can be used for correcting and updating the remote electrocardiographic weight coefficient information.
In an alternative embodiment of the present application, the lead electrocardiographic anomaly recognition model set includes a lead electrocardiographic anomaly classification sub-model set and a lead electrocardiographic anomaly recognition sub-model set, and the electrocardiographic anomaly recognition module 602 may be further configured to:
Acquiring photoplethysmogram data;
Performing time sequence calibration and image segmentation on the lead channel marked electrocardiogram data based on the photoelectric volume pulse data to obtain a lead channel marked single electrocardiogram data set of each lead channel;
Inputting the lead channel marked single electrocardiogram data set into a lead electrocardiogram abnormal classification sub-model corresponding to each lead channel in the lead electrocardiogram abnormal classification sub-model group, and screening an electrocardiogram abnormal image to obtain an abnormal single electrocardiogram data set and a normal single electrocardiogram data set;
and inputting the abnormal single electrocardiogram data set into a lead electrocardiogram abnormal analysis sub-model which is in line with the lead channel corresponding to the abnormal single electrocardiogram data set in the lead electrocardiogram abnormal identification sub-model group, so as to generate the electrocardiogram abnormal identification information.
In an alternative embodiment of the present application, the intracardiac remote electrocardiographic data monitoring and analyzing apparatus 600 may be further used to:
Inputting the normal single electrocardiogram data set of each lead channel into a normal electrocardiogram image fusion model group to generate a normal electrocardiogram fusion image of each lead channel;
Verifying the normal single electrocardiogram data set based on the normal electrocardiogram fusion image, and identifying single electrocardiogram data which deviate from the normal electrocardiogram data and are used for representing statistically significant differences between the normal single electrocardiogram data set and the normal electrocardiogram fusion image;
Removing the deviating normal electrocardiogram data in the normal single electrocardiogram data set to obtain a calibrated normal single electrocardiogram data set, and constructing the deviating normal electrocardiogram data set based on the deviating normal electrocardiogram data;
Generating and updating intracardiac remote electrocardiographic data monitoring medical history information based on the abnormal single electrocardiographic data set, the calibrated normal single electrocardiographic data set and the deviation from the normal electrocardiographic data set.
In an alternative embodiment of the present application, the intracardiac remote electrocardiographic data monitoring and analyzing apparatus 600 may be further used to:
Acquiring and initializing an initial digital twin model of the heart;
if the remote electrocardio weight coefficient information exceeds a preset remote electrocardio weight coefficient threshold value, selecting electrocardio abnormal core identification information matched with remote electrocardio preliminary diagnosis information from electrocardio abnormal identification information of each guide channel;
generating heart abnormality visual annotation information based on the heart abnormality core identification information;
Labeling the heart abnormality visualization labeling information on the heart initial digital twin model, updating the heart initial digital twin model, and generating the heart abnormality labeling digital twin model.
In one embodiment, a computer device is provided comprising a memory storing a computer program and a processor implementing the steps of a method of endocardial remote electrocardiographic data monitoring analysis as described previously when the computer program is executed.
In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored which, when executed by a processor, implements the steps of the method embodiments described above.
For the device embodiments, reference is made to the description of the method embodiments for the relevant points, since they essentially correspond to the method embodiments. The above-described apparatus embodiments are merely illustrative, wherein the components illustrated as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, may be located in one place, or may be distributed over a plurality of network units. Some or all of the modules may be selected according to actual needs to achieve the objectives of the disclosed solution. Those of ordinary skill in the art will understand and implement the present invention without undue burden.
The above examples merely represent a few implementations of the examples of the present application, which are described in more detail and are not to be construed as limiting the scope of the claims of the examples. It should be noted that it will be apparent to those skilled in the art that various modifications and improvements can be made to the present application without departing from the spirit of the embodiments of the application.

Claims (10)

1. A method for monitoring and analyzing intracardiac remote electrocardiographic data, the method comprising:
Obtaining electrocardiogram data, and conducting channel matching on the electrocardiogram data to obtain conducting channel marked electrocardiogram data;
inputting the lead channel marked electrocardiographic data of each lead channel into each lead electrocardiographic abnormality identification model corresponding to the lead channel in a lead electrocardiographic abnormality identification model group to obtain electrocardiographic abnormality identification information of the lead channel with abnormality in electrocardiographic data;
generating remote electrocardiograph preliminary diagnosis information and remote electrocardiograph weight coefficient information corresponding to the remote electrocardiograph preliminary diagnosis information based on the electrocardiograph abnormality identification information of each lead channel;
And adjusting data transmission parameters of the lead channel marked electrocardiogram data and acquisition precision parameters of the electrocardiogram data according to the remote electrocardio weight coefficient information, wherein the data transmission parameters are used for regulating and controlling the data quality and/or transmission efficiency of the lead channel marked electrocardiogram data.
2. The method according to claim 1, wherein the method further comprises:
conducting channel demand analysis on the remote electrocardiograph preliminary diagnosis information to generate channel guide state information, wherein the channel guide state information is used for representing the working state of electrocardiograph sensing equipment of each channel required by electrocardiograph data monitoring analysis corresponding to the remote electrocardiograph preliminary diagnosis information;
conducting channel state identification is carried out on the conducting channel marked electrocardiograph data, and conducting channel actual state information is generated and used for representing the actual working state of electrocardiograph sensing equipment of each conducting channel;
Generating channel state anomaly information and channel state anomaly class information corresponding to the channel state anomaly information based on the channel guide state information and the channel actual state information;
If the abnormal grade information exceeds a preset abnormal grade threshold of the lead channel state, corresponding lead channel state adjustment guide information is generated according to the lead channel state abnormal information in a matching mode, and the lead channel state adjustment guide information is used for guiding a intracardiac remote electrocardiographic data monitoring operator to adjust the actual working state of the electrocardiographic sensing equipment of the lead channel.
3. The method of claim 1, wherein the generating remote electrocardiographic preliminary diagnosis information based on the electrocardiographic abnormality identification information of each of the lead channels and remote electrocardiographic weight coefficient information corresponding to the remote electrocardiographic preliminary diagnosis information includes:
Acquiring electrocardiogram data of a lead channel template of the lead channel in which each electrocardiogram data of the electrocardiogram abnormal identification information is abnormal;
generating electrocardiographic data comparison lead electrocardiographic template coincidence degree scoring data of the lead channels with abnormal electrocardiographic data of each electrocardiographic abnormality identification information based on the lead channel template electrocardiographic data comparison lead channel marking electrocardiographic data;
Calculating to obtain comprehensive coincidence degree score and the remote electrocardio weight coefficient information by combining the electrocardio abnormality identification information according to the electrocardiograph data comparison lead electrocardiograph template coincidence degree score data;
if the comprehensive coincidence degree score is larger than or equal to a comprehensive coincidence degree threshold value, the electrocardio abnormality identification information is used as the remote electrocardio preliminary diagnosis information;
If the comprehensive coincidence degree score is smaller than the comprehensive coincidence degree threshold, inputting the electrocardiographic anomaly identification information into a combined lead electrocardiographic anomaly identification model according to the corresponding guide channel with the electrocardiographic data anomaly, and generating the remote electrocardiographic preliminary diagnosis information and combined remote electrocardiographic weight coefficient information, wherein the combined remote electrocardiographic weight coefficient information is used for correcting and updating the remote electrocardiographic weight coefficient information.
4. The method of claim 3, wherein the electrocardiographic anomaly identification information comprises electrocardiographic anomaly severity scoring data, and the remote electrocardiographic weight coefficient information is calculated according to the formula:
Wherein, ψ RCM is the remote electrocardio weight coefficient information, N is the total number of the lead channels with abnormal electrocardiographic data, The data precision weight coefficient of the lead equipment for the ith lead channel with the abnormality of the electrocardiographic data, the delta Q i is the data quality offset coefficient of the ith lead channel with the abnormality of the electrocardiographic data, D i andThe label information and the fuzzy scoring function of the actual working state of the electrocardiographic sensing equipment of the ith lead channel with abnormal electrocardiographic data are respectively obtained,A weighted sum of the electrocardiographic data comparison lead electrocardiographic template electrocardiographic data of the ith lead channel with the electrocardiographic data abnormality, R i is electrocardiographic abnormality severity scoring data of the ith lead channel with the electrocardiographic data abnormality, N * is total number of the lead channel template electrocardiographic data with the same size as total number N of the lead channels with the electrocardiographic data abnormality,AndAnd respectively comparing the electrocardiographic data of the ith lead channel with the electrocardiographic data, and the electrocardiographic data of the lead channel template electrocardiographic data of the jth lead channel with the electrocardiographic data with the exception, wherein the electrocardiographic data of the lead electrocardiographic data of the jth lead channel with the exception is the weight of lead electrocardiographic template coincidence degree scoring data and electrocardiographic data comparison lead electrocardiographic template coincidence degree scoring data.
5. The method according to claim 1, wherein the lead electrocardiographic anomaly recognition model group includes a lead electrocardiographic anomaly classification sub-model group and a lead electrocardiographic anomaly recognition sub-model group, the inputting the lead channel marking electrocardiographic data of each lead channel into each lead electrocardiographic anomaly recognition model corresponding to the lead channel in the lead electrocardiographic anomaly recognition model group, obtaining electrocardiographic anomaly recognition information of the lead channel in which the electrocardiographic data is anomalous, includes:
Acquiring photoplethysmogram data;
Performing time sequence calibration and image segmentation on the lead channel marked electrocardiographic data based on the photoplethysmogram data to obtain a lead channel marked single electrocardiographic data set of each lead channel;
Inputting the lead channel marked single electrocardiogram data set into a lead electrocardiogram abnormal classification sub-model corresponding to each lead channel in the lead electrocardiogram abnormal classification sub-model group, and screening an electrocardiogram abnormal image to obtain an abnormal single electrocardiogram data set and a normal single electrocardiogram data set;
Inputting the abnormal single electrocardiogram data set into a lead electrocardiogram abnormal analysis submodel which is in line with a lead channel corresponding to the abnormal single electrocardiogram data set in the lead electrocardiogram abnormal identification submodel group, and generating the electrocardiogram abnormal identification information.
6. The method of claim 5, wherein the method further comprises:
Inputting the normal single electrocardiogram data set of each lead channel into a normal electrocardiogram image fusion model group to generate a normal electrocardiogram fusion image of each lead channel;
Verifying the normal single electrocardiogram data set based on the normal electrocardiogram fusion image, and identifying deviation normal electrocardiogram data therein, wherein the deviation normal electrocardiogram data is used for representing single electrocardiogram data in which the normal single electrocardiogram data set has statistically significant differences from the normal electrocardiogram fusion image;
Removing the off-normal electrocardiographic data in the normal single electrocardiographic data set to obtain a calibrated normal single electrocardiographic data set, and constructing the off-normal electrocardiographic data set based on the off-normal electrocardiographic data;
Generating and updating intracardiac remote electrocardiographic data monitoring medical history information based on the abnormal single electrocardiographic dataset, the calibrated normal single electrocardiographic dataset, and the off-normal electrocardiographic dataset.
7. The method according to any one of claims 1 to 6, further comprising:
Acquiring and initializing an initial digital twin model of the heart;
If the remote electrocardio weight coefficient information exceeds a preset remote electrocardio weight coefficient threshold value, selecting electrocardio abnormality core identification information matched with the remote electrocardio preliminary diagnosis information from the electrocardio abnormality identification information of each lead channel;
Generating heart abnormality visual annotation information based on the heart abnormality core identification information;
Labeling the heart abnormality visual labeling information on the heart initial digital twin model, updating the heart initial digital twin model, and generating a heart abnormality labeling digital twin model.
8. A intracardiac remote electrocardiographic data monitoring and analyzing device, characterized in that the device comprises:
the electrocardiographic data acquisition module is used for acquiring electrocardiographic data, and conducting channel matching on the electrocardiographic data to obtain conducting channel marked electrocardiographic data;
The electrocardiographic anomaly identification module is used for inputting the lead channel marked electrocardiographic data of each lead channel into each lead electrocardiographic anomaly identification model corresponding to the lead channel in the lead electrocardiographic anomaly identification model group to obtain electrocardiographic anomaly identification information of the lead channel with the anomaly of electrocardiographic data;
The remote primary diagnosis module is used for generating remote electrocardiograph primary diagnosis information and remote electrocardiograph weight coefficient information corresponding to the remote electrocardiograph primary diagnosis information based on the electrocardiograph abnormality identification information of each lead channel;
the remote parameter adjustment module is used for adjusting the data transmission parameters of the lead channel marked electrocardiogram data and the acquisition precision parameters of the electrocardiogram data according to the remote electrocardio weight coefficient information, and the data transmission parameters are used for adjusting and controlling the data quality and/or transmission efficiency of the lead channel marked electrocardiogram data.
9. A computer device comprising a memory and a processor, the memory storing a computer program, characterized in that the processor implements the method of any one of claims 1 to 7 when executing the computer program.
10. A computer readable storage medium, on which a computer program is stored, characterized in that the computer program, when being executed by a processor, implements the method of any of claims 1 to 7.
CN202510621640.2A 2025-05-15 2025-05-15 Remote ECG data monitoring and analysis method, device, equipment and medium for cardiology department Pending CN120531402A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202510621640.2A CN120531402A (en) 2025-05-15 2025-05-15 Remote ECG data monitoring and analysis method, device, equipment and medium for cardiology department

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202510621640.2A CN120531402A (en) 2025-05-15 2025-05-15 Remote ECG data monitoring and analysis method, device, equipment and medium for cardiology department

Publications (1)

Publication Number Publication Date
CN120531402A true CN120531402A (en) 2025-08-26

Family

ID=96784475

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202510621640.2A Pending CN120531402A (en) 2025-05-15 2025-05-15 Remote ECG data monitoring and analysis method, device, equipment and medium for cardiology department

Country Status (1)

Country Link
CN (1) CN120531402A (en)

Similar Documents

Publication Publication Date Title
US12186086B2 (en) Systems and methods for reduced lead electrocardiogram diagnosis using deep neural networks and rule-based systems
US11147500B2 (en) Electrocardiogram processing system for delineation and classification
US11517212B2 (en) Electrocardiogram information dynamic monitoring method and dynamic monitoring system
Murugesan et al. Ecgnet: Deep network for arrhythmia classification
US11350868B2 (en) Electrocardiogram information processing method and electrocardiogram workstation system
US11571161B2 (en) Systems and methods for electrocardiogram diagnosis using deep neural networks and rule-based systems
Shahriari et al. Electrocardiogram signal quality assessment based on structural image similarity metric
CN109411042B (en) ECG information processing method and ECG workstation
Liu et al. ECG-based heart arrhythmia diagnosis through attentional convolutional neural networks
CN112690802A (en) Method, device, terminal and storage medium for detecting electrocardiosignals
US20220104750A1 (en) Electrocardiogram processing system for delineation and classification
Yuan et al. Enhancing multi-label ecg classification via task-guided lead correlations in internet of medical things
US20250204866A1 (en) Apparatus and a method for a plurality of time series data
CN120531402A (en) Remote ECG data monitoring and analysis method, device, equipment and medium for cardiology department
Lomoio et al. AUTAN-ECG: An AUToencoder bAsed system for anomaly detectioN in ECG signals
De Roberto et al. Can ChatGPT-4o enhance ECG interpretation accuracy compared to cardiologists?
WO2017182622A1 (en) Adaptive visualization of electrocardiogram
US12329463B1 (en) System and method for visualization of vectorcardiograms for ablation procedures
Sun et al. Predicting spontaneous termination of atrial fibrillation based on the RR interval
Badnjević et al. Processing Cardiac Signals
CN120611325A (en) Method, device, equipment and medium for determining time series signal anomaly based on multi-dimensional trajectory graph
Napitupulu et al. Random Forest-Based Classification of Electrocardiogram Signals for Early Detection of Cardiac Abnormalities
Luangphasy et al. Efficient Arrhythmia Detection Using Progressive Resolution Shrinking
Cahyanto et al. IoT-Based Platform for Real-Time ECG Arrhythmia Detection Using Self-Supervised Learning with Masked Autoencoder
Yang et al. A geometric insight into ECG classification: leveraging phase space reconstruction and distance to measure

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