CN116130107A - Valve replacement early clinical evaluation method and system based on time domain analysis - Google Patents
Valve replacement early clinical evaluation method and system based on time domain analysis Download PDFInfo
- Publication number
- CN116130107A CN116130107A CN202310400695.1A CN202310400695A CN116130107A CN 116130107 A CN116130107 A CN 116130107A CN 202310400695 A CN202310400695 A CN 202310400695A CN 116130107 A CN116130107 A CN 116130107A
- Authority
- CN
- China
- Prior art keywords
- patient
- time domain
- early
- value
- clinical evaluation
- 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.)
- Withdrawn
Links
Images
Classifications
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
- G16H50/50—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for simulation or modelling of medical disorders
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B8/00—Diagnosis using ultrasonic, sonic or infrasonic waves
- A61B8/08—Detecting organic movements or changes, e.g. tumours, cysts, swellings
- A61B8/0883—Detecting organic movements or changes, e.g. tumours, cysts, swellings for diagnosis of the heart
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B8/00—Diagnosis using ultrasonic, sonic or infrasonic waves
- A61B8/52—Devices using data or image processing specially adapted for diagnosis using ultrasonic, sonic or infrasonic waves
- A61B8/5215—Devices using data or image processing specially adapted for diagnosis using ultrasonic, sonic or infrasonic waves involving processing of medical diagnostic data
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0012—Biomedical image inspection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/20—Analysis of motion
- G06T7/246—Analysis of motion using feature-based methods, e.g. the tracking of corners or segments
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/764—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using classification, e.g. of video objects
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/82—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using neural networks
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H30/00—ICT specially adapted for the handling or processing of medical images
- G16H30/20—ICT specially adapted for the handling or processing of medical images for handling medical images, e.g. DICOM, HL7 or PACS
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
- G16H50/30—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for calculating health indices; for individual health risk assessment
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
- G16H50/70—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for mining of medical data, e.g. analysing previous cases of other patients
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10132—Ultrasound image
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20084—Artificial neural networks [ANN]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30004—Biomedical image processing
- G06T2207/30048—Heart; Cardiac
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Public Health (AREA)
- General Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Biomedical Technology (AREA)
- Databases & Information Systems (AREA)
- Pathology (AREA)
- Epidemiology (AREA)
- Radiology & Medical Imaging (AREA)
- Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
- General Physics & Mathematics (AREA)
- Primary Health Care (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Multimedia (AREA)
- Surgery (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Veterinary Medicine (AREA)
- Artificial Intelligence (AREA)
- Biophysics (AREA)
- Heart & Thoracic Surgery (AREA)
- Software Systems (AREA)
- Animal Behavior & Ethology (AREA)
- Quality & Reliability (AREA)
- Cardiology (AREA)
- Automatic Analysis And Handling Materials Therefor (AREA)
- Medical Treatment And Welfare Office Work (AREA)
- Measuring And Recording Apparatus For Diagnosis (AREA)
Abstract
The invention relates to the field of postoperative prediction data processing, and particularly discloses a valve replacement early-stage clinical evaluation method and system based on time domain analysis.
Description
Technical Field
The invention relates to the field of post-operation prediction data processing, in particular to a valve replacement early-stage clinical evaluation method and system based on time domain analysis.
Background
Heart valve disease is a cardiovascular disease with abnormal structure and function, which causes hemodynamic disturbance, so that heart load is increased, myocardial function is damaged, valve replacement is a common operation type which effectively solves the problems of incapability of spontaneous regeneration and medicine restoration of valve tissues, effectively improves the disease symptoms of heart valve patients, improves the life quality of patients, and the traditional aortic valve replacement needs to perform aortic valve replacement through a sternum median incision, but the risk level of the operation is very high, strict requirements are on the operation of a surgeon and the self basic condition of the patient, and the patients often cannot endure the operation type because of serious basic diseases, so that in recent years, when the requirements of the traditional aortic valve replacement cannot be met, the problems of large wound surface, large quantity of bleeding valve and serious infection risk caused by the opening of a chest of the traditional aortic valve replacement can be effectively improved through the catheter aortic valve replacement.
Although the transcatheter aortic valve replacement has been better advanced and improved, the postoperative prognosis of the patient with abnormal left ventricle is worse, the risks of postoperative complications and poor prognosis of the patient still exist, and the postoperative long-term effect is poor, so that the clinical evaluation of the postoperative early prognosis of the patient becomes important, the traditional postoperative early poor prognosis risk monitoring method involves more factors, multiple physiological indexes are required to be analyzed and monitored, the monitoring data of the postoperative left ventricle of the patient is not subjected to targeted comprehensive analysis, the physiological indexes are required to be analyzed and monitored depending on the experience and the feeling of doctors, the subjective influence factors are larger, and a large amount of time and manpower resources are required, so that a rapid, accurate and reliable postoperative early clinical evaluation method and system are required to be provided, so that the multiple physiological indexes are subjected to combined analysis and monitoring in time, and the comprehensive evaluation indexes for the postoperative early monitoring evaluation of the left ventricle are acquired, and the accuracy, the pertinence and the efficiency of the evaluation are improved.
In order to solve the above problems, a technical solution is now provided.
Disclosure of Invention
In order to overcome the defects in the prior art, the method processes and analyzes the signals acquired by the two-dimensional speckle tracking imaging technology by utilizing a computer algorithm, extracts the time characteristics and the frequency characteristics of the signals by utilizing a time domain analysis technology, establishes a classification model of the postoperative clinical manifestation of the valvular patient, improves the pertinence of the postoperative left ventricular function analysis of the patient, and has higher reliability and stability in data processing so as to solve the problems in the background technology.
In order to achieve the above purpose, the present invention provides the following technical solutions:
a valve replacement early clinical evaluation method based on time domain analysis, comprising the steps of:
step S1, acquiring continuous 24-week two-dimensional ultrasonic examination of a patient after operation, performing one-time heart two-dimensional ultrasonic examination every other week, and storing data;
step S2, acquiring the whole left room and layered strain parameters of the patient 24 weeks after operation, acquiring the whole left room and layered strain parameters once every other week, and storing data;
step S3, extracting characteristic information from the echocardiogram according to a time domain analysis technology, acquiring the post-operation left ventricular ejection fraction from the characteristic information and substituting the post-operation left ventricular ejection fraction as an independent variable into a function
In (1) obtaining->
Of (2), wherein
And->
All are positive numbers;
step S4, extracting characteristic information from the echocardiogram according to a time domain analysis technology, acquiring left-chamber integral and layered strain parameters from the characteristic information, acquiring a post-operation left-chamber integral annular endocardial layer strain value and a left-chamber annular epicardial layer strain value, and substituting the values as independent variables into the values
In (1) obtaining->
Function value of>
And->
All are positive numbers;
s5, analyzing the whole left ventricle and layered strain parameters after the left ventricle abnormal function segment operation by a time domain analysis technology, obtaining a longitudinal strain value of a central inner membranous layer of the left ventricle movement abnormal function segment, and substituting the longitudinal strain value as an independent variable into a function
Obtain->
Function value of>
And->
All are positive numbers;
step S6, constructing a valve replacement operation patient postoperative early clinical evaluation model by using
、/>
And +.>
And acquiring the post-operation early-stage clinical evaluation index according to a formula of the post-operation early-stage clinical evaluation model.
As a further method of the present invention, in step S6, the formula of the post-operative early clinical evaluation model is:
wherein:
is an early clinical evaluation index after operation, and is->
Left ventricular ejection fraction after patient operation, < >>
For the strain value of the left chamber integral ring to the endocardial layer of the patient after operation, < ->
For the strain value of the epicardial layer of the left ventricular ring after the operation of the patient,
longitudinal strain value of central intima layer of left ventricular motor dysfunction segment after operation of patient>
Data acquisition period sequence number,/->
Is an integer greater than 1.
As a further method of the invention, in the steps S1-S4, the time sequence of data acquisition is respectively 1 week after operation, 4 weeks after operation, 8 weeks after operation, 12 weeks after operation, 16 weeks after operation, 20 weeks after operation and 24 weeks after operation, and the data acquisition time period sequence number thereof
1, 2, 3, 4, 5, 6 and 7, respectively.
As a further method of the present invention, the process of extracting features from an echocardiogram based on a time domain technique in step S3 and step S4 includes the steps of:
step A1, data acquisition: acquiring two-dimensional ultrasonic image signals of a patient in early postoperative period;
step A2, data preprocessing: preprocessing the acquired data, and performing noise removal, gaussian filtering and graying;
step A3, feature extraction: tracking a two-dimensional gray-scale image in real time by utilizing a two-dimensional speckle tracking imaging technology, acquiring a spatial motion track of a myocardial echo speckle, extracting myocardial strain, rotation and torsion angles, and forming a feature vector with time domain features;
step A4, feature vector classification: and classifying the feature vectors by using a cyclic neural network classifier to obtain an overall layered myocardial strain value and a layered myocardial strain value of the left ventricular dysfunctional segment.
As a further method of the present invention, in steps S3-S5
、/>
、/>
、/>
、/>
And->
Numerical analysis is carried out by inputting historical data, and the ∈1 is balanced>
、/>
And +.>
The order of magnitude between the function values is obtained.
As a further method of the present invention, in step S6, the method for classifying the post-operation early clinical evaluation index is as follows:
step B1, standardization: forming a sample data set by using the numerical value of the postoperative early clinical evaluation index, acquiring the mean value and the standard deviation of the sample data set, and normalizing the data in the sample data set by using the mean value and the standard deviation, wherein the normalization formula is as follows:
wherein:
for standard sample value, +.>
For values in the sample dataset, +.>
For the mean value of the sample dataset, +.>
Standard deviation for the sample dataset;
step B2, classification evaluation: using equations
Obtaining a classification result of a standard sample value, wherein a classification formula is as follows:
wherein:
the classification result for the standard sample value is a predictive probability of a class,>
the classification result of the sample value is two kindsIs used for the prediction probability of (1).
As a further method of the invention, the clinical cardiac performance of the patient is better than the clinical cardiac performance of the patient with the sample standard value classification result of the first class.
The valve replacement operation early clinical evaluation system based on the time domain analysis is used for realizing the valve replacement operation early clinical evaluation method based on the time domain analysis and comprises a processor, a data acquisition system, an intelligent analysis system, a user interface system and a database system, wherein the data acquisition system, the intelligent analysis system, the user interface system and the database system are in communication connection with the processor;
a processor for processing data from at least one component of a valve replacement patient post-operative early clinical assessment system based on time domain analysis;
the data acquisition system is used for acquiring a patient postoperative early-stage heart ultrasonic signal acquired by the patient postoperative early-stage heart ultrasonic, transmitting the acquired signal to the intelligent analysis system for analysis and processing, and transmitting the acquired information to the database system for storage through the intelligent analysis system;
after receiving the information sent by the data acquisition system, the intelligent analysis system invokes the data stored in the database system through the processor to carry out intelligent analysis processing on early clinical monitoring data of the patient after operation, so as to obtain different classification results, and the classification results are sent to the user interface system;
the user interface system analyzes and displays clinical monitoring data of early prognosis after operation of a patient according to the received classification result, provides a friendly user interface, and is convenient for medical staff to check the data acquisition and analysis result;
the database system is used for storing historical monitoring and analysis data of early postoperative period of patients.
The valve replacement early clinical evaluation method and the valve replacement early clinical evaluation system based on time domain analysis have the technical effects and advantages that: the method has the advantages that the signals acquired by the two-dimensional speckle tracking imaging technology are processed and analyzed by utilizing a computer algorithm, the time characteristics and the frequency domain characteristics of the signals are extracted by utilizing a time domain analysis technology, a classification model of the postoperative clinical manifestation of the valvular patient is established, the pertinence of the postoperative left ventricle function analysis of the patient is improved, the method has the advantages of high efficiency and automation, the data processing has higher reliability and stability, a large amount of time and manpower resources are saved, the physiological indexes of the patient can be monitored in real time, the numerical value of each real-time monitoring physiological index of the patient is acquired in time, and the evaluation of postoperative early clinical monitoring data is realized.
Drawings
FIG. 1 is a flow chart of a valve replacement early clinical evaluation method based on time domain analysis of the present invention;
fig. 2 is a schematic structural diagram of a valve replacement patient post-operation early clinical evaluation system based on time domain analysis according to the present invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Example 1. The valve replacement early clinical evaluation method and the valve replacement early clinical evaluation system based on time domain analysis are characterized in that signals acquired by a two-dimensional speckle tracking imaging technology are processed and analyzed by utilizing a computer algorithm, time features and frequency domain features of the signals are extracted by utilizing a time domain analysis technology, a classification model of clinical manifestation of a valve patient after operation is established, pertinence of left ventricular function analysis after operation of the patient is improved, and the valve replacement early clinical evaluation method and the valve replacement early clinical evaluation system have the advantages of high efficiency and automation, high reliability and stability in data processing, save a large amount of time and manpower resources, monitor physiological indexes of the patient in real time, acquire values of all real-time monitoring physiological indexes of the patient in time and realize evaluation of early clinical monitoring data after operation.
FIG. 1 presents a flow chart of the method of early post-operative clinical assessment of a valve replacement patient based on time-domain analysis of the present invention, comprising the steps of:
step S1, acquiring continuous 24-week two-dimensional ultrasonic examination of a patient after operation, performing one-time heart two-dimensional ultrasonic examination every other week, and storing data;
step S2, acquiring the whole left room and layered strain parameters of the patient 24 weeks after operation, acquiring the whole left room and layered strain parameters once every other week, and storing data;
step S3, extracting characteristic information from the echocardiogram according to a time domain analysis technology, acquiring the post-operation left ventricular ejection fraction from the characteristic information and substituting the post-operation left ventricular ejection fraction as an independent variable into a function
In (1) obtaining->
Of (2), wherein
And->
All are positive numbers;
step S4, extracting characteristic information from the echocardiogram according to a time domain analysis technology, acquiring left-chamber integral and layered strain parameters from the characteristic information, acquiring a post-operation left-chamber integral annular endocardial layer strain value and a left-chamber annular epicardial layer strain value, and substituting the values as independent variables into the values
In (1) obtaining->
Function value of>
And->
All are positive numbers;
s5, analyzing the whole left ventricle and layered strain parameters after the left ventricular dysfunctional segment operation by a time domain analysis technology to obtain the central inner membranous layer longitudinal of the left ventricular dysfunctional segmentTo the strain value and substituting it as an argument into a function
Obtain->
Function value of>
And->
All are positive numbers;
step S6, constructing a valve replacement operation patient postoperative early clinical evaluation model by using
、/>
And +.>
Acquiring a post-operation early-stage clinical evaluation index according to a formula of a post-operation early-stage clinical evaluation model, wherein the formula of the post-operation early-stage clinical evaluation model is as follows: />
Wherein:
is an early clinical evaluation index after operation, and is->
Left ventricular ejection fraction after patient operation, < >>
For the strain value of the left chamber integral ring to the endocardial layer of the patient after operation, < ->
For the strain value of the epicardial layer of the left ventricular ring after the operation of the patient,
longitudinal strain value of central intima layer of left ventricular motor dysfunction segment after operation of patient>
Data acquisition period sequence number,/->
Is an integer greater than 1.
Specifically, the detailed process of each step of the invention is as follows:
step S1:
the invention firstly periodically acquires two-dimensional ultrasonic examination of a patient for 24 weeks after operation, carries out two-dimensional ultrasonic examination of the heart once every other week, and stores data.
It should be noted that, the two-dimensional cardiac ultrasound can monitor the left atrial end systole inner diameter, the left ventricular end diastole, the left ventricular end systole solvent and the left ventricular ejection fraction of the patient, wherein the left ventricular ejection fraction is used as the most common index in the cardiac ultrasound examination, the cardiac pumping function can be displayed, the left ventricular ejection fraction is smaller than the normal value when the aortic valve is narrow, and the left ventricular ejection fraction of the normal person is 50% -70%, so that the application grabs the left ventricular ejection fraction to reflect the normal state of the cardiac pumping function so as to evaluate the clinical data representation of the heart of the patient after the valve replacement operation.
Step S2:
the invention acquires the whole left room and layered strain parameters of the patient 24 weeks after operation, acquires the whole left room and layered strain parameters once every other week, and stores the data.
It should be noted that, research shows that the whole left ventricle and layering strain parameters can be well monitored in the situation of layering strain of left ventricle cardiac muscle after aortic valve replacement operation of patients with left ventricular dysfunction, so that the invention grabs the layering strain parameters of left ventricle cardiac muscle as a key factor for evaluating patients with left ventricular dysfunction after aortic valve replacement operation.
Step S3:
the invention extracts characteristic information from echocardiography according to a time domain analysis technology, acquires the left ventricular ejection fraction after operation from the characteristic information and substitutes the left ventricular ejection fraction as an independent variable into a function
In (1) obtaining->
Function value of>
And->
All positive numbers were analyzed for left ventricular ejection fraction.
The invention uses linear function to adjust the change of left room ejection fraction, to obtain the information of change of index according to the linear change trend of data, to realize the machine learning algorithm identification of change index, to realize the parting and evaluation of data change.
Step S4:
in step S4, feature information is extracted from the echocardiogram according to time domain analysis technique, left-ventricular integral and layered strain parameters are obtained from the feature information, and post-operative left-ventricular integral annular endocardial layer strain value and left-ventricular annular epicardial layer strain value are obtained and substituted as independent variables
In (1) obtaining->
Function value of>
And
all are positive numbers. />
It is to be noted that the invention adopts parabolic change trend to describe the strain value of the left chamber integral ring to the inner membranous layer and the change condition of the strain value of the left chamber ring to the outer membranous layer, which is convenient to be larger than the change condition of the strain value of the left chamber integral ring to the inner membranous layer
The function value is adjusted in a speed-doubling mode, so that the distinction between the change of the function value and the change of the left ventricular ejection fraction is facilitated.
Step S5:
in step S5, the invention analyzes the whole left chamber and layered strain parameters after the left chamber abnormal function segment operation through a time domain analysis technology, obtains the longitudinal strain value of the inner membranous layer of the center of the left chamber movement abnormal function segment, and substitutes the longitudinal strain value as an independent variable into a function
Obtain->
Function value of>
And->
All are positive numbers.
It should be noted that, the invention adopts the form of the exponent power of e to adjust the longitudinal strain value of the endocardial layer in the center of the left ventricular dysfunctional segment, defines the myocardial dyskinesia before the evaluation, when the end diameter of the left ventricular contraction is more than or equal to-20% as the myocardial dyskinesia segment, then obtains the longitudinal strain value of the endocardial layer in the myocardial dyskinesia segment through the time domain feature analysis technology, because the research shows that the myocardial strain parameter obtained by the two-dimensional speckle tracking imaging technology can evaluate the postoperation cardiac function prognosis of the valve patient with sensibility, and simultaneously adjusts the numerical variation of the index by utilizing the exponent function of e, thereby being convenient for distinguishing the variation condition of the parameter through the variation range of the function value, and further being convenient for the multidimensional evaluation of the cardiac function of the postoperative patient according to the variety and range of the parameter variation.
Step S6:
in step S6, the invention constructs a model for early clinical evaluation of the valve replacement patient after operation, and utilizes
、/>
And +.>
Acquiring a post-operation early-stage clinical evaluation index according to a formula of a post-operation early-stage clinical evaluation model, wherein the formula of the post-operation early-stage clinical evaluation model is as follows:
wherein:
is an early clinical evaluation index after operation, and is->
Left ventricular ejection fraction after patient operation, < >>
For the strain value of the left chamber integral ring to the endocardial layer of the patient after operation, < ->
For the strain value of the epicardial layer of the left ventricular ring after the operation of the patient,
longitudinal strain value of central intima layer of left ventricular motor dysfunction segment after operation of patient>
Data acquisition period sequence number,/->
Is an integer greater than 1.
The method comprises the steps of obtaining the post-operation early clinical evaluation index by summing absolute values of function numerical differences of adjacent time sequences of function values corresponding to four indexes selected by the method, calculating, analyzing change types of the four indexes through multi-dimensional change and multi-threshold change of the post-operation early clinical evaluation index, evaluating change types and total change forms of the four indexes, and conveniently classifying and evaluating the four index changes after the aortic valve replacement operation of the patient with left ventricular dysfunction.
In the steps S1-S4, the time sequence of data acquisition is respectively 1 week after operation, 4 weeks after operation, 8 weeks after operation, 12 weeks after operation, 16 weeks after operation, 20 weeks after operation and 24 weeks after operation, and the data acquisition time period sequence is that
1, 2, 3, 4, 5, 6 and 7, respectively.
As a further method of the present invention, the process of extracting features from an echocardiogram based on a time domain technique in step S3 and step S4 includes the steps of:
step A1, data acquisition: acquiring two-dimensional ultrasonic image signals of a patient in early postoperative period;
step A2, data preprocessing: preprocessing the acquired data, and performing noise removal, gaussian filtering and graying;
step A3, feature extraction: tracking a two-dimensional gray-scale image in real time by utilizing a two-dimensional speckle tracking imaging technology, acquiring a spatial motion track of a myocardial echo speckle, extracting myocardial strain, rotation and torsion angles, and forming a feature vector with time domain features;
step A4, feature vector classification: and classifying the feature vectors by using a cyclic neural network classifier to obtain an overall layered myocardial strain value and a layered myocardial strain value of the left ventricular dysfunctional segment.
As a further method of the present invention, in steps S3-S5
、/>
、/>
、/>
、/>
And->
Numerical analysis is carried out by inputting historical data, and the ∈1 is balanced>
、/>
And +.>
The order of magnitude between the function values is obtained.
In step S6, the method for classifying the post-operation early clinical evaluation index is as follows:
step B1, standardization: forming a sample data set by using the numerical value of the postoperative early clinical evaluation index, acquiring the mean value and the standard deviation of the sample data set, and normalizing the data in the sample data set by using the mean value and the standard deviation, wherein the normalization formula is as follows:
wherein:
for standard sample value, +.>
For values in the sample dataset, +.>
As a mean value of the sample data set,/>
standard deviation for the sample dataset;
step B2, classification evaluation: using equations
Obtaining a classification result of a standard sample value, wherein a classification formula is as follows:
wherein:
the classification result for the standard sample value is a predictive probability of a class,>
the classification result for the specimen sample value is a predictive probability of the second class.
And when the sample standard value classification result is one type, the clinical cardiac performance of the patient is superior to the clinical cardiac performance of the sample standard value classification result is two types.
Example 2. Embodiment 2 of the present invention differs from embodiment 1 in that this embodiment is presented with respect to a valve replacement patient post-operative early clinical evaluation system based on time-domain analysis.
FIG. 2 is a schematic diagram of a time domain analysis-based valve replacement patient post-operative early clinical evaluation system of the present invention, including a processor and a data acquisition system, an intelligent analysis system, a user interface system, and a database system communicatively coupled to the processor;
the processor may be used to process data and/or information from at least one component of a valve replacement patient post-operative early clinical assessment system based on time-domain analysis or an external data source (such as a cloud data center). In some embodiments, the processor may be local or remote. For example, the processor may access information and/or data from the data storage device, the terminal device, and/or the data acquisition device via a network. As another example, the processor may be directly connected to the data storage device, the terminal device, and/or the data acquisition device to access information and/or data. In some embodiments, the processor may be implemented on a cloud platform.
The data acquisition system is used for acquiring a patient postoperative early-stage heart ultrasonic signal acquired by the patient postoperative early-stage heart ultrasonic, transmitting the acquired signal to the intelligent analysis system for analysis and processing, and transmitting the acquired information to the database system for storage through the intelligent analysis system;
after receiving the information sent by the data acquisition system, the intelligent analysis system invokes the data stored in the database system through the processor to carry out intelligent analysis processing on early clinical monitoring data of the patient after operation, so as to obtain different classification results, and the classification results are sent to the user interface system;
the user interface system analyzes and displays clinical monitoring data of early prognosis after operation of a patient according to the received classification result, provides a friendly user interface, and is convenient for medical staff to check the data acquisition and analysis result;
the database system is used for storing historical monitoring and analysis data of early postoperative period of patients.
The above formulas are all formulas with dimensionality removed and numerical calculation, the formulas are formulas with the latest real situation obtained by software simulation through collecting a large amount of data, and preset parameters and threshold selection in the formulas are set by those skilled in the art according to the actual situation.
The above embodiments may be implemented in whole or in part by software, hardware, firmware, or any other combination. When implemented in software, the above-described embodiments may be implemented in whole or in part in the form of a computer program product. The computer program product comprises one or more computer instructions or computer programs. When the computer instructions or computer program are loaded or executed on a computer, the processes or functions described in accordance with the embodiments of the present application are all or partially produced. The computer may be a general purpose computer, a special purpose computer, a computer network, or other programmable apparatus. The computer instructions may be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another computer-readable storage medium, for example, the computer instructions may be transmitted from one website site, computer, server, or data center to another website site, computer, server, or data center by wired (e.g., infrared, wireless, microwave, etc.). The computer readable storage medium may be any available medium that can be accessed by a computer or a data storage device such as a server, data center, etc. that contains one or more sets of available media. The usable medium may be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium. The semiconductor medium may be a solid state disk.
Those of ordinary skill in the art will appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware, or combinations of computer software and electronic hardware. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the solution. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present application.
It will be clear to those skilled in the art that, for convenience and brevity of description, specific working procedures of the above-described systems, apparatuses and units may refer to corresponding procedures in the foregoing method embodiments, and are not repeated herein.
The units described as separate units may or may not be physically separate, and units shown as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
In addition, each functional unit in each embodiment of the present application may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit.
The foregoing is merely specific embodiments of the present application, but the scope of the present application is not limited thereto, and any person skilled in the art can easily think about changes or substitutions within the technical scope of the present application, and the changes and substitutions are intended to be covered by the scope of the present application. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.
Finally: the foregoing description of the preferred embodiments of the invention is not intended to limit the invention to the precise form disclosed, and any such modifications, equivalents, and alternatives falling within the spirit and principles of the invention are intended to be included within the scope of the invention.
Claims (8)
1. A method for early clinical evaluation of valve replacement based on time domain analysis, comprising the steps of:
step S1, acquiring continuous 24-week two-dimensional ultrasonic examination of a patient after operation, performing one-time heart two-dimensional ultrasonic examination every other week, and storing data;
step S2, acquiring the whole left room and layered strain parameters of the patient 24 weeks after operation, acquiring the whole left room and layered strain parameters once every other week, and storing data;
step S3, extracting characteristic information from the echocardiogram according to a time domain analysis technology, acquiring the post-operation left ventricular ejection fraction from the characteristic information and substituting the post-operation left ventricular ejection fraction as an independent variable into a function
In (1) obtaining->
Function value of>
And
all are positiveA number;
step S4, extracting characteristic information from the echocardiogram according to a time domain analysis technology, acquiring left-chamber integral and layered strain parameters from the characteristic information, acquiring a post-operation left-chamber integral annular endocardial layer strain value and a left-chamber annular epicardial layer strain value, and substituting the values as independent variables into the values
In (1) obtaining->
Function value of>
And->
All are positive numbers;
s5, analyzing the whole left ventricle and layered strain parameters after the left ventricle abnormal function segment operation by a time domain analysis technology, obtaining a longitudinal strain value of a central inner membranous layer of the left ventricle movement abnormal function segment, and substituting the longitudinal strain value as an independent variable into a function
Obtain->
Function value of>
And->
All are positive numbers;
step S6, constructing a valve replacement operation patient postoperative early clinical evaluation model by using
、/>
And +.>
And acquiring the post-operation early-stage clinical evaluation index according to a formula of the post-operation early-stage clinical evaluation model.
2. The time domain analysis based valve replacement early clinical evaluation method according to claim 1, wherein: the formula of the postoperative early clinical evaluation model is as follows:
wherein:
is an early clinical evaluation index after operation, and is->
Left ventricular ejection fraction after patient operation, < >>
For the strain value of the left chamber integral ring to the endocardial layer of the patient after operation, < ->
For the patient's postoperative left ventricular ring epicardial strain value,/->
Longitudinal strain value of central intima layer of left ventricular motor dysfunction segment after operation of patient>
Data acquisition period sequence number,/->
Is an integer greater than 1.
3. The time domain analysis based valve replacement early clinical evaluation method according to claim 1, wherein: in the steps S1-S4, the time sequence of data acquisition is respectively 1 week after operation, 4 weeks after operation, 8 weeks after operation, 12 weeks after operation, 16 weeks after operation, 20 weeks after operation and 24 weeks after operation, and the data acquisition time period sequence is that
1, 2, 3, 4, 5, 6 and 7, respectively.
4. The time domain analysis based valve replacement early clinical evaluation method according to claim 1, wherein: the process of extracting features from the echocardiogram based on the time domain technique in step S3 and step S4 includes the steps of:
step A1, data acquisition: acquiring two-dimensional ultrasonic image signals of a patient in early postoperative period;
step A2, data preprocessing: preprocessing the acquired data, and performing noise removal, gaussian filtering and graying;
step A3, feature extraction: tracking a two-dimensional gray-scale image in real time by utilizing a two-dimensional speckle tracking imaging technology, acquiring a spatial motion track of a myocardial echo speckle, extracting myocardial strain, rotation and torsion angles, and forming a feature vector with time domain features;
step A4, feature vector classification: and classifying the feature vectors by using a cyclic neural network classifier to obtain an overall layered myocardial strain value and a layered myocardial strain value of the left ventricular dysfunctional segment.
5. The time domain analysis based valve replacement early clinical evaluation method according to claim 1, wherein: in steps S3-S5
、/>
、/>
、/>
、/>
And->
Numerical analysis is carried out by inputting historical data, and the ∈1 is balanced>
、/>
and 
The order of magnitude between the function values is obtained.
6. The method for early clinical evaluation of valve replacement based on time domain analysis according to claim 2, wherein: the method for classifying the postoperative early clinical evaluation indexes comprises the following steps:
step B1, standardization: forming a sample data set by using the numerical value of the postoperative early clinical evaluation index, acquiring the mean value and the standard deviation of the sample data set, and normalizing the data in the sample data set by using the mean value and the standard deviation, wherein the normalization formula is as follows:
wherein:
for standard sample value, +.>
For values in the sample dataset, +.>
For the mean value of the sample dataset, +.>
Standard deviation for the sample dataset;
step B2, classification evaluation: using equations
Obtaining a classification result of a standard sample value, wherein a classification formula is as follows:
wherein:
the classification result for the standard sample value is a predictive probability of a class,>
the classification result for the specimen sample value is a predictive probability of the second class.
7. The time domain analysis based valve replacement early clinical evaluation method according to claim 6, wherein: and when the sample standard value classification result is one type, the clinical cardiac performance of the patient is superior to the clinical cardiac performance of the sample standard value classification result is two types.
8. A valve replacement patient post-operative early clinical evaluation system based on time domain analysis for implementing the valve replacement early clinical evaluation method based on time domain analysis of any one of claims 1-7, characterized in that: the system comprises a processor, and a data acquisition system, an intelligent analysis system, a user interface system and a database system which are in communication connection with the processor;
a processor for processing data from at least one component of a valve replacement patient post-operative early clinical assessment system based on time domain analysis;
the data acquisition system is used for acquiring a patient postoperative early-stage heart ultrasonic signal acquired by the patient postoperative early-stage heart ultrasonic, transmitting the acquired signal to the intelligent analysis system for analysis and processing, and transmitting the acquired information to the database system for storage through the intelligent analysis system;
after receiving the information sent by the data acquisition system, the intelligent analysis system invokes the data stored in the database system through the processor to carry out intelligent analysis processing on early clinical monitoring data of the patient after operation, so as to obtain different classification results, and the classification results are sent to the user interface system;
the user interface system analyzes and displays clinical monitoring data of early prognosis after operation of the patient according to the received classification result;
the database system is used for storing historical monitoring and analysis data of early postoperative period of patients.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310400695.1A CN116130107A (en) | 2023-04-14 | 2023-04-14 | Valve replacement early clinical evaluation method and system based on time domain analysis |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310400695.1A CN116130107A (en) | 2023-04-14 | 2023-04-14 | Valve replacement early clinical evaluation method and system based on time domain analysis |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116130107A true CN116130107A (en) | 2023-05-16 |
Family
ID=86306599
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310400695.1A Withdrawn CN116130107A (en) | 2023-04-14 | 2023-04-14 | Valve replacement early clinical evaluation method and system based on time domain analysis |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116130107A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116312929A (en) * | 2023-05-25 | 2023-06-23 | 四川互慧软件有限公司 | OKR-based pressure sore management method, system, equipment and medium |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20040193035A1 (en) * | 2003-03-31 | 2004-09-30 | Morteza Gharib | Noninvasive methods for assessing valvular and ventricular dysfunction |
| US20050020903A1 (en) * | 2003-06-25 | 2005-01-27 | Sriram Krishnan | Systems and methods for automated diagnosis and decision support for heart related diseases and conditions |
| CN109360273A (en) * | 2018-11-28 | 2019-02-19 | 同济大学 | A kind of cardiac valve replacement optimization method and system |
| CN109377470A (en) * | 2018-03-20 | 2019-02-22 | 任昊星 | A kind of heart disease risk forecasting system |
| CN113384293A (en) * | 2021-06-12 | 2021-09-14 | 北京医院 | Integrated machine learning method for coronary heart disease screening based on two-dimensional spot tracking technology |
| CN114121278A (en) * | 2021-11-04 | 2022-03-01 | 广西医科大学第一附属医院 | Prediction model of AKI risk after heart valve replacement based on age and clinical index |
| CN114203299A (en) * | 2021-12-13 | 2022-03-18 | 浙江大学 | Patient similarity-based congenital heart disease postoperative risk visualization evaluation method |
| CN115775629A (en) * | 2023-02-10 | 2023-03-10 | 北京海思瑞格科技有限公司 | Method for assessing PPCs risk based on sub-polar motion test before operation |
-
2023
- 2023-04-14 CN CN202310400695.1A patent/CN116130107A/en not_active Withdrawn
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20040193035A1 (en) * | 2003-03-31 | 2004-09-30 | Morteza Gharib | Noninvasive methods for assessing valvular and ventricular dysfunction |
| US20050020903A1 (en) * | 2003-06-25 | 2005-01-27 | Sriram Krishnan | Systems and methods for automated diagnosis and decision support for heart related diseases and conditions |
| CN109377470A (en) * | 2018-03-20 | 2019-02-22 | 任昊星 | A kind of heart disease risk forecasting system |
| CN109360273A (en) * | 2018-11-28 | 2019-02-19 | 同济大学 | A kind of cardiac valve replacement optimization method and system |
| CN113384293A (en) * | 2021-06-12 | 2021-09-14 | 北京医院 | Integrated machine learning method for coronary heart disease screening based on two-dimensional spot tracking technology |
| CN114121278A (en) * | 2021-11-04 | 2022-03-01 | 广西医科大学第一附属医院 | Prediction model of AKI risk after heart valve replacement based on age and clinical index |
| CN114203299A (en) * | 2021-12-13 | 2022-03-18 | 浙江大学 | Patient similarity-based congenital heart disease postoperative risk visualization evaluation method |
| CN115775629A (en) * | 2023-02-10 | 2023-03-10 | 北京海思瑞格科技有限公司 | Method for assessing PPCs risk based on sub-polar motion test before operation |
Non-Patent Citations (4)
| Title |
|---|
| 段宇龙;段峰;石真桂;马红;: "二维斑点追踪技术对主动脉瓣狭窄患者瓣膜置换前后左心室收缩功能的评价作用研究", 武警后勤学院学报(医学版), no. 10 * |
| 雷佳瑞;胡波;周青;陈金玲;谭团团;谭娅;郭瑞强;: "心肌应变评估瓣膜病患者瓣膜置换术后临床短期疗效的研究", 临床超声医学杂志, vol. 20, no. 04, pages 229 - 230 * |
| 雷佳瑞;郭瑞强;: "超声心动图评价心脏瓣膜病患者心功能与心肌受损的研究进展", 临床超声医学杂志, no. 02, pages 229 - 230 * |
| 黄慧;郭瑞强;刘琨;何艳;张春莉;郝美嘉;刘刚;: "二维斑点追踪技术定量评价风湿性二尖瓣狭窄患者瓣膜置换术后左心功能变化的临床应用", 武汉大学学报(医学版), no. 01 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116312929A (en) * | 2023-05-25 | 2023-06-23 | 四川互慧软件有限公司 | OKR-based pressure sore management method, system, equipment and medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| JP7262452B2 (en) | ECG-based Cardiac Ejection Fraction Screening | |
| CN106251880B (en) | Method and system for recognizing physiological sound | |
| US20220093216A1 (en) | Discovering novel features to use in machine learning techniques, such as machine learning techniques for diagnosing medical conditions | |
| Wang et al. | Arrhythmia classification algorithm based on multi-head self-attention mechanism | |
| CN108577883A (en) | A kind of Screening for coronary artery disease device, screening system and signal characteristic extracting methods | |
| CN112971802B (en) | Method and system for detecting heart sound signals based on deep learning model | |
| US20190026431A1 (en) | Discovering genomes to use in machine learning techniques | |
| CN107440679A (en) | For detecting the method and correspondence system of electrocardiographic abnormality | |
| Sedighian et al. | Pediatric heart sound segmentation using Hidden Markov Model | |
| Fattah et al. | Stetho-phone: Low-cost digital stethoscope for remote personalized healthcare | |
| CN116130107A (en) | Valve replacement early clinical evaluation method and system based on time domain analysis | |
| CN109497991A (en) | Heart failure detection device based on machine learning | |
| Demrozi et al. | B-HAR: an open-source baseline framework for in depth study of human activity recognition datasets and workflows | |
| Zhu et al. | Feature extraction from a novel ECG model for arrhythmia diagnosis | |
| CN110575178A (en) | Diagnosis and monitoring integrated medical system for judging motion state and judging method thereof | |
| Bhowmick et al. | Iot assisted real time ppg monitoring system for health care application | |
| CN111528900A (en) | Heart sound segmentation method and device based on Butterworth filter and Shannon entropy method | |
| KR102149748B1 (en) | Method and apparatus for obtaining heart and lung sounds | |
| CN116327181A (en) | Comprehensive evaluation method and device for real-time noninductive monitoring of heart and electronic equipment | |
| CN110491500A (en) | A kind of identification system and method based on cardiac function dynamic monitoring and analysis | |
| Karan et al. | Heart Sound Abnormality Detection using Wavelet Packet Features and Machine Learning | |
| CN115177260A (en) | Intelligent electrocardio-heart sound diagnosis method and device based on artificial neural network | |
| CN111345815B (en) | Method, device, equipment and storage medium for detecting QRS wave in electrocardiosignal | |
| CN115316985B (en) | Heart information detection method, device and equipment based on physiological signals | |
| Moukadem et al. | Automatic heart sound analysis module based on Stockwell transform |
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 | ||
| WW01 | Invention patent application withdrawn after publication | ||
| WW01 | Invention patent application withdrawn after publication |
Application publication date: 20230516 |