Risk assessment method, system and equipment based on three-dimensional prognosis model

Abstract

The invention discloses a risk assessment method, system and device based on a three-dimensional prognosis model, and relates to the technical field of medical data processing, and the method comprises the steps: obtaining clinical basic data and image data of a user; determining the cardiac hypertrophy degree of the left ventricular structure of the user according to the clinical basic data and the image data; determining a Cut-Off value of each part in the left ventricular structure of the user according to the cardiac hypertrophy degree of the left ventricular structure of the user; constructing a three-dimensional prognosis model according to the Cut-Off value of each part in the left ventricle structure of the user; the three-dimensional prognosis model is a three-dimensional simulation model for simulating a left ventricular structure of a user; performing prognosis risk assessment on the user by using the three-dimensional simulation model to obtain a prognosis risk assessment result; the prognosis risk assessment result is used for representing the risk level of the poor recurrence prognosis of the user. The accuracy of postoperative recurrence risk assessment can be improved, and guidance is provided for doctors.

Description

Technical Field

[0001] The present application relates to the technical field of medical data processing, and in particular to a risk assessment method, system and device based on a three-dimensional prognostic model. Background Art

[0002] Hypertrophic cardiomyopathy is a type of cardiomyopathy in children. Its main feature is that it can easily cause left ventricular outflow tract obstruction, forming obstructive cardiomyopathy, which can cause children to experience chest tightness, shortness of breath and even heart failure. Some users still have adverse recurrences such as obstruction after surgery.

[0003] At present, the risk assessment of postoperative recurrence of users is usually made by doctors based entirely on their personal experience, and the users are assessed as high-risk users or low-risk users. High-risk users have a higher risk level of postoperative recurrence and a higher probability of recurrence; low-risk users have a lower risk level of postoperative recurrence and a lower probability of recurrence. However, this risk assessment method based on the doctor's personal experience often produces inaccurate and unreliable risk results. Summary of the invention

[0004] The purpose of this application is to provide a risk assessment method, system and device based on a three-dimensional prognostic model, which can improve the accuracy of risk assessment of postoperative recurrence and provide guidance for doctors.

[0005] Improve the accuracy and efficiency of medical data analysis and processing, and improve prognosis.

[0006] To achieve the above objectives, this application provides the following solutions:

[0007] In a first aspect, the present application provides a risk assessment method based on a three-dimensional prognostic model, the risk assessment method based on a three-dimensional prognostic model comprising:

[0008] Obtaining the user's basic clinical data and imaging data; the user is a postoperative patient suffering from hypertrophic obstructive cardiomyopathy.

[0009] The degree of myocardial hypertrophy of the user's left ventricular structure is determined according to the basic clinical data and the image data; the degree of myocardial hypertrophy includes the thickness of various parts of the user's left ventricular structure.

[0010] According to the degree of myocardial hypertrophy of the user's left ventricular structure, the Cut-Off value of each part in the user's left ventricular structure is determined; the Cut-Off value is the lowest critical value that leads to a poor prognosis.

[0011] A three-dimensional prognostic model is constructed according to the Cut-Off values ​​of various parts in the left ventricular structure of the user; the three-dimensional prognostic model is a three-dimensional simulation model that simulates the left ventricular structure of the user.

[0012] The three-dimensional simulation model is used to perform a prognostic risk assessment on the user to obtain a prognostic risk assessment result; the prognostic risk assessment result is used to indicate the risk level of the user's poor recurrence prognosis.

[0013] Optionally, obtain the user's basic clinical data and imaging data, including:

[0014] The basic clinical data of the user is obtained by utilizing the EMR system.

[0015] The image data of the user is acquired by using a PACS system.

[0016] Optionally, the basic clinical data include age, weight, admission records, examination records and medical records; the imaging data include CT images and / or MRI images.

[0017] Optionally, before the step of determining the degree of myocardial hypertrophy of the user's left ventricular structure according to the basic clinical data and the image data, the risk assessment method based on the three-dimensional prognostic model further includes:

[0018] The basic clinical data and the image data are respectively subjected to missing value processing, One-Hot processing and Scaling processing to obtain pre-processed basic clinical data and image data; the pre-processed basic clinical data and image data are used to determine the degree of myocardial hypertrophy of the user's left ventricular structure.

[0019] Optionally, constructing a three-dimensional prognostic model according to the Cut-Off values ​​of various parts in the left ventricular structure of the user specifically includes:

[0020] The three-dimensional prognostic model is constructed using three-dimensional modeling software according to the Cut-Off values ​​of various parts in the left ventricular structure of the user.

[0021] Optionally, the three-dimensional prognostic model includes three layers: base, middle and apex, and each layer is divided into different longitudinal regions in the order of anterior wall, ventricular septum, posterior wall and lateral wall. The base includes the basal anterior wall, basal anterior septum, basal posterior septum, basal posterior wall, basal posterior lateral wall and basal anterior lateral wall; the middle includes the middle anterior wall, middle anterior septum, middle posterior septum, middle posterior wall, middle posterior lateral wall and middle anterior lateral wall; the apex includes the apical anterior wall, apical septum, apical lateral wall, apical posterior wall and apex.

[0022] Optionally, after the step of using the three-dimensional simulation model to perform a prognostic risk assessment on the user to obtain a prognostic risk assessment result, the risk assessment method based on the three-dimensional prognostic model further includes:

[0023] The user is followed up to obtain a follow-up result.

[0024] The three-dimensional prognostic model is modified according to the follow-up results to obtain a modified three-dimensional prognostic model.

[0025] The three-dimensional simulation model is used to perform a prognostic risk assessment on the user again to obtain a revised prognostic risk assessment result.

[0026] In a second aspect, the present application provides a risk assessment system based on a three-dimensional prognostic model, wherein the risk assessment system based on a three-dimensional prognostic model comprises:

[0027] The data acquisition module is used to acquire the user's basic clinical data and imaging data; the user is a postoperative patient suffering from hypertrophic obstructive cardiomyopathy.

[0028] The myocardial hypertrophy degree determination module is used to determine the myocardial hypertrophy degree of the user's left ventricular structure based on the clinical basic data and the image data; the myocardial hypertrophy degree includes the thickness of various parts in the user's left ventricular structure.

[0029] The Cut-Off value determination module is used to determine the Cut-Off value of each part in the left ventricular structure of the user according to the degree of myocardial hypertrophy of the left ventricular structure of the user; the Cut-Off value is the lowest critical value that leads to a poor prognosis.

[0030] The three-dimensional prognostic model construction module is used to construct a three-dimensional prognostic model according to the Cut-Off values ​​of various parts in the left ventricular structure of the user; the three-dimensional prognostic model is a three-dimensional simulation model that simulates the left ventricular structure of the user.

[0031] The prognostic risk assessment module is used to use the three-dimensional simulation model to perform a prognostic risk assessment on the user to obtain a prognostic risk assessment result; the prognostic risk assessment result is used to indicate the risk level of the user's poor recurrence prognosis.

[0032] Optionally, the risk assessment system based on the three-dimensional prognostic model further includes:

[0033] The correction module is used to follow up the user and obtain the follow-up results; according to the follow-up results, the three-dimensional prognostic model is corrected to obtain a corrected three-dimensional prognostic model; and using the three-dimensional simulation model, the prognostic risk assessment of the user is performed again to obtain a corrected prognostic risk assessment result.

[0034] In a third aspect, the present application provides a computer device comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the risk assessment method based on the three-dimensional prognostic model described in the first aspect.

[0035] According to the specific embodiments provided in this application, this application discloses the following technical effects:

[0036] The present application provides a risk assessment method, system and device based on a three-dimensional prognostic model, which determines the degree of myocardial hypertrophy of the user's left ventricular structure by obtaining the user's basic clinical data and imaging data, thereby determining the Cut-Off value of each part of the user's left ventricular structure, and then constructing a three-dimensional prognostic model that simulates the user's left ventricular structure. The three-dimensional simulation model is used to conduct a prognostic risk assessment on the user, thereby assessing the risk level of the user's recurrence of poor prognosis. Compared with the traditional assessment method that relies entirely on personal subjective experience, the present application uses the user's basic clinical data and imaging data as basic data, combined with the degree of myocardial hypertrophy and Cut-Off value of each part of the left ventricle to establish a three-dimensional prognostic model, so that the three-dimensional prognostic model assesses the risk level of the user's recurrence of poor prognosis based on the degree of myocardial hypertrophy and Cut-Off value, which is more accurate and reliable, effectively improves the accuracy of risk assessment, can provide guidance for doctors, and is conducive to improving the overall prognosis of users. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0038] Figure 1 This is a diagram of an application environment of a risk assessment method based on a three-dimensional prognostic model provided in one embodiment of the present application.

[0039] Figure 2 A schematic flow chart of a risk assessment method based on a three-dimensional prognostic model provided in one embodiment of the present application.

[0040] Figure 3 A schematic diagram of the structure of a three-dimensional prognostic model provided in one embodiment of the present application.

[0041] Figure 4 A schematic diagram of the structure of a risk assessment system based on a three-dimensional prognostic model provided in one embodiment of the present application.

[0042] Figure 5 A schematic diagram of the structure of a computer device provided in one embodiment of the present application.

[0043] Reference numerals:

[0044] 1-basal anterior wall; 2-basal anterior septum; 3-basal posterior septum; 4-basal posterior wall; 5-basal posterior lateral wall; 6-basal anterior lateral wall; 7-middle anterior wall; 8-middle anterior septum; 9-middle posterior septum; 10-middle posterior wall; 11-middle posterior lateral wall; 12-middle anterior lateral wall; 13-apical anterior wall; 14-apical septal wall; 15-apical lateral wall; 16-apical posterior wall; 17-apex; 102-terminal; 104-server. DETAILED DESCRIPTION

[0045] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0046] In order to make the above-mentioned objects, features and advantages of the present application more obvious and easy to understand, the present application is further described in detail below in conjunction with the accompanying drawings and specific implementation methods.

[0047] The risk assessment method based on the three-dimensional prognostic model provided in the embodiments of the present application can be applied to Figure 1In the application environment shown, the terminal 102 communicates with the server 104 through a network. The data storage system can store data that the server 104 needs to process. The data storage system can be set up separately, integrated on the server 104, or placed on the cloud or other servers. The terminal 102 can send the data to be processed to the server 104. After the server 104 receives the data to be processed, the server 104 obtains the user's basic clinical data and imaging data for the data to be processed; the user is a postoperative patient suffering from hypertrophic obstructive cardiomyopathy; based on the basic clinical data and the imaging data, the degree of myocardial hypertrophy of the user's left ventricular structure is determined; the degree of myocardial hypertrophy includes the thickness of each part of the user's left ventricular structure; based on the degree of myocardial hypertrophy of the user's left ventricular structure, the Cut-Off value of each part of the user's left ventricular structure is determined; the Cut-Off value is the lowest critical value that leads to poor prognosis; based on the Cut-Off values ​​of each part of the user's left ventricular structure, a three-dimensional prognostic model is constructed; the three-dimensional prognostic model is a three-dimensional simulation model that simulates the user's left ventricular structure; using the three-dimensional simulation model, the user is evaluated for prognostic risk to obtain a prognostic risk assessment result; the prognostic risk assessment result is used to indicate the risk level of the user's recurrence of poor prognosis.

[0048] The server 104 may feed back the obtained prognostic risk assessment result to the terminal 102. In addition, in some embodiments, the risk assessment method based on the three-dimensional prognostic model may also be implemented by the server 104 or the terminal 102 alone, such as the terminal 102 may directly build a three-dimensional prognostic model and perform risk assessment on the data to be processed, or the server 104 may obtain the data to be processed from the data storage system, and build a three-dimensional prognostic model and perform risk assessment on the data to be processed.

[0049] The terminal 102 may be, but is not limited to, various desktop computers, laptop computers, smart phones, tablet computers, IoT devices, and portable wearable devices. The IoT devices may be smart vehicle-mounted devices, etc. The portable wearable devices may be smart watches, smart bracelets, head-mounted devices, etc. The server 104 may be implemented by an independent server or a server cluster consisting of multiple servers, or may be a cloud server.

[0050] In an exemplary embodiment, Figure 2 As shown, a risk assessment method based on a three-dimensional prognostic model is provided. The method is executed by a computer device, and can be executed by a computer device such as a terminal or a server alone, or by a terminal and a server together. In the embodiment of the present application, the method is applied to Figure 1The server 104 in the example is used as an example to illustrate the method, which includes the following steps S1 to S5. Among them:

[0051] Step S1, obtaining basic clinical data and imaging data of the user. In this embodiment, the user mainly refers to postoperative patients with hypertrophic obstructive cardiomyopathy, especially pediatric patients.

[0052] Step S2: Determine the degree of myocardial hypertrophy of the user's left ventricular structure based on the basic clinical data and the image data. The degree of myocardial hypertrophy includes the thickness of each part of the user's left ventricular structure.

[0053] Step S3: Determine the Cut-Off value of each part of the left ventricular structure of the user according to the degree of myocardial hypertrophy of the left ventricular structure of the user. The Cut-Off value is the lowest critical value that leads to a poor prognosis.

[0054] Step S4: construct a three-dimensional prognostic model according to the Cut-Off values ​​of various parts in the left ventricular structure of the user. The three-dimensional prognostic model is a three-dimensional simulation model that simulates the left ventricular structure of the user.

[0055] Step S5: using the three-dimensional simulation model to perform a prognostic risk assessment on the user to obtain a prognostic risk assessment result.

[0056] In this embodiment, the prognostic risk assessment result is used to indicate the risk level of the user's poor prognosis of recurrence, which may include a high risk level and a low risk level, wherein the risk level of postoperative recurrence of a high risk level user is higher and the probability of recurrence is greater; the risk level of postoperative recurrence of a low risk level user is lower and the probability of recurrence is lower. It may also include a medium risk level between the high risk level and the low risk level, wherein the risk level and the probability of recurrence of postoperative recurrence of a medium risk level user are lower than those of a low risk level user, but higher than those of a low risk level user.

[0057] In this embodiment, step S1 obtains the user's basic clinical data and imaging data, which specifically includes the following steps:

[0058] Step S11: using an EMR (Electronic Medical Record) system to obtain the basic clinical data of the user.

[0059] Step S12: using PACS (Picture Archiving and Communication Systems) to obtain the image data of the user.

[0060] In this embodiment, the basic clinical data include age, weight, admission record, examination record, case data, etc. The image data include CT (Computed Tomography) images and / or MRI (Magnetic Resonance Imaging) images, etc.

[0061] In this embodiment, before determining the degree of myocardial hypertrophy of the user's left ventricular structure according to the basic clinical data and the image data in step S2, the risk assessment method based on the three-dimensional prognostic model further includes a data preprocessing step, which is as follows:

[0062] The clinical basic data and the image data are respectively subjected to missing value processing, One-Hot (one-bit effective coding) processing and Scaling (feature scaling) processing to obtain preprocessed clinical basic data and image data; the preprocessed clinical basic data and image data are used to determine the degree of myocardial hypertrophy of the user's left ventricular structure.

[0063] In this embodiment, step S4 constructs a three-dimensional prognostic model according to the Cut-Off values ​​of various parts in the left ventricular structure of the user, and specifically includes the following steps:

[0064] The three-dimensional prognostic model is constructed using three-dimensional modeling software according to the Cut-Off values ​​of various parts in the left ventricular structure of the user.

[0065] like Figure 3 As shown, the three-dimensional prognostic model in this embodiment includes three layers, namely, the base, the middle and the apex. Each layer is divided into different longitudinal regions in the order of the anterior wall, the ventricular septum, the posterior wall and the lateral wall. The base includes the basal anterior wall 1, the basal anterior septum 2, the basal posterior septum 3, the basal posterior wall 4, the basal posterior lateral wall 5 and the basal anterior lateral wall 6. The middle includes the middle anterior wall 7, the middle anterior septum 8, the middle posterior septum 9, the middle posterior wall 10, the middle posterior lateral wall 11 and the middle anterior lateral wall 12. The apex includes the apical anterior wall 13, the apical septum 14, the apical lateral wall 15, the apical posterior wall 16 and the apex 17.

[0066] In this embodiment, after the step of using the three-dimensional simulation model to perform prognostic risk assessment on the user and obtaining a prognostic risk assessment result in step S5, the risk assessment method based on the three-dimensional prognostic model further includes step S6, i.e., a model correction step, which specifically includes the following steps:

[0067] Step S61: Follow up the user to obtain a follow-up result.

[0068] Step S62: According to the follow-up results, the three-dimensional prognostic model is modified to obtain a modified three-dimensional prognostic model.

[0069] Step S63: using the three-dimensional simulation model, perform a prognostic risk assessment on the user again to obtain a revised prognostic risk assessment result.

[0070] This embodiment performs risk assessment of hypertrophic cardiomyopathy based on a three-dimensional prognostic model, mainly including the collection of basic clinical data and imaging data, combining the basic clinical data and imaging data to analyze the hypertrophic degree of hypertrophic myocardium in multiple dimensions, building a three-dimensional prognostic model according to the Cut-Off value, assessing the risk of poor prognosis of the user, and modifying the three-dimensional prognostic model according to the long-term follow-up results of the user, etc., as follows:

[0071] (1) Collection of basic clinical data and imaging data.

[0072] In this embodiment, the risk assessment system based on the three-dimensional prognostic model can be directly connected to the hospital database, and the key data parameters for building the model can be collected through the defined inclusion and exclusion conditions. For example, users with confirmed hypertrophic cardiomyopathy are included, and some users with other complex congenital heart diseases are excluded. The collected data types include the user's basic clinical information and imaging data.

[0073] In this embodiment, during the collection of model data, the risk assessment system based on the three-dimensional prognostic model can automatically capture key information, embed the program into the case system through programming, and focus on collecting data including the user's diagnosis, age, weight, echocardiography, CT imaging data, etc. Specific search keywords include "children", "hypertrophic cardiomyopathy", "obstructive", etc. Image data include left ventricular structure thickness, flow rate, pressure difference and other related imaging data. In particular, the thickness of the left ventricular posterior wall of the user's left ventricle is directly related to adverse events such as postoperative obstruction recurrence of the user.

[0074] In this embodiment, the risk assessment system based on the three-dimensional prognostic model can be well compatible with the hospital's EMR, HIS (Hospital Information System, hospital outpatient billing system), PACS and other systems to achieve seamless interoperability of user information. The captured information types can be divided into the following types:

[0075] 1) Structured information. For example, user laboratory tests, hospital admission records and other information are mostly stored in a structured form. This type of data can be directly used for model construction through simple processing.

[0076] 2) Text information (unstructured information). For example, user text, medical records, etc. This type of data is recorded in natural language and needs to be extracted and post-processed before it can be used.

[0077] 3) Image information. For example, user CT, MRI and other image information. This type of data needs to extract useful information from the image before it can be combined with the above two parts of information for subsequent analysis and modeling.

[0078] (2) Combine basic clinical data and imaging data to analyze the degree of hypertrophic myocardium in multiple dimensions.

[0079] In this embodiment, the imaging data and basic clinical data are analyzed, and a three-dimensional model of the ventricle of hypertrophic cardiomyopathy in children is constructed using three-dimensional software. The hypertrophic left ventricle is divided into three layers from top to bottom, namely, the base, the middle, and the apex, by the three-dimensional analysis software. Each layer is further divided into different longitudinal regions according to the anterior wall, the ventricular septum, the posterior wall, and the lateral wall. Finally, the left ventricle is divided into 17 parts, including basal anterior wall 1, basal anterior septum 2, basal posterior septum 3, basal posterior wall 4, basal posterior lateral wall 5, basal anterior lateral wall 6, middle anterior wall 7, middle anterior septum 8, middle posterior septum 9, middle posterior wall 10, middle posterior lateral wall 11, middle anterior lateral wall 12, apical anterior wall 13, apical septum 14, apical lateral wall 15, apical posterior wall 16, and apex 17. The thickness of each part is measured and compared with the average thickness of the same layer. The result of the ratio is associated with the user's prognosis, so as to obtain the lowest ratio number (lowest critical value) that leads to a poor prognosis as the Cut-Off value. The degree of myocardial hypertrophy in different parts of the left ventricle is related to the user's poor prognosis. Therefore, this embodiment focuses on the thickness of the left ventricular posterior wall, which is directly related to the user's postoperative prognosis, and builds a three-dimensional prognostic model based on this.

[0080] In this embodiment, the construction of the three-dimensional prognostic model includes the processes of data preprocessing, data set division, model construction, model selection, etc. Data preprocessing: The risk assessment system based on the three-dimensional prognostic model performs missing value, One-Hot, Scaling and other processing on the data after feature engineering to prepare for subsequent modeling and analysis. Data set division: The risk assessment system based on the three-dimensional prognostic model divides the data set into a development set and a test set according to 7:3 by default, wherein the development set is used to build and select the three-dimensional prognostic model, and the test set is used to test and evaluate the performance of the three-dimensional prognostic model. The risk assessment system based on the three-dimensional prognostic model has built-in algorithms such as XGBoost (distributed gradient boosting library), ITK-SNAP (medical image processing software), and Deep Learning (deep learning), which can automatically select different algorithms or objective functions according to the type of dependent variable. Finally, a three-dimensional prognostic model of left ventricular structure is constructed, and the preoperative users are stratified for prognostic risk by the degree of hypertrophy in different parts of the ventricle of hypertrophic cardiomyopathy in children.

[0081] (3) Construct a three-dimensional prognostic model based on the Cut-Off value.

[0082] In this embodiment, based on the characteristic parameters in (2), a large amount of basic clinical data and imaging data are analyzed to stratify the prognosis risk of preoperative users and establish a three-dimensional prognosis model. Since the three-dimensional prognosis model is constructed based on basic clinical data and imaging data, the three-dimensional prognosis model is mainly used to conduct risk assessment on whether the postoperative prognosis of users with hypertrophic cardiomyopathy is poor, and to determine the risk level of the postoperative prognosis of the user, which includes a high risk level and a low risk level, so as to guide doctors to formulate countermeasures, such as whether active intervention treatment is needed to reduce the risk of poor prognosis of the user.

[0083] In this embodiment, the degree of hypertrophy of different parts of the user's left ventricle can also be evaluated based on the three-dimensional prognostic model, and correlated with the user's postoperative prognosis, incorporating postoperative complications, death and other events, and dividing the users into high-risk users and low-risk users with poor prognosis.

[0084] In this embodiment, the risk assessment system based on the three-dimensional prognostic model uses a trained and selected model, i.e., a three-dimensional prognostic model based on the Cut-Off value. The Cut-Off value in this embodiment refers to the minimum ratio number that leads to a poor prognosis. If the subsequent results deviate from the Cut-Off value, the Cut-Off value will be continuously adjusted and evaluated on the test set, using indicators such as AUC (Area Under Curve, the area under the ROC curve and the coordinate axis), error square sum, RUC (recall rate-false positive rate) curve, PR (Precision-Recall, precision rate-recall rate) curve and other graphics to evaluate the accuracy of the three-dimensional prognostic model. The user decides whether to use it as a three-dimensional prognostic model based on these evaluation indicators (corrected Cut-Off value).

[0085] (4) Assess the user's risk of poor prognosis.

[0086] In this embodiment, a three-dimensional prognostic model is used to determine the risk of poor prognosis based on characteristic quantities such as the thickness of the left ventricular posterior wall of each user in combination with the Cut-Off value, thereby providing guidance for clinicians.

[0087] (5) Modify the three-dimensional prognostic model based on long-term follow-up user results.

[0088] In this embodiment, based on the user's feedback on the actual follow-up results after surgery, the relevant characteristic variables and Cut-Off values ​​of the three-dimensional prognostic model are corrected. The relevant characteristic variables include left ventricular outflow tract pressure gradient, ventricular septum thickness, etc., so as to continuously improve the overall fit of the prognostic model and continuously optimize the model accuracy.

[0089] This embodiment updates and optimizes the three-dimensional prognostic model, specifically including the ability of deep learning and automatic correction of the three-dimensional prognostic model, and regularly follows up the postoperative users, including whether the user has died, whether ventricular hypertrophy has recurred, whether arrhythmia complications have occurred, etc. If the follow-up user was originally judged as a low-risk user, if the above adverse events recur after surgery, the user's left ventricular hypertrophy level is re-evaluated and the Cut-off value is lowered, so that such users are reclassified as high-risk users, thereby correcting the three-dimensional prognostic model. With the continuous addition and update of user data sets, the weights and correctness of the characteristic parameters in the three-dimensional prognostic model are reversely re-judged according to the actual user prognosis results, further improving the accuracy and effectiveness of the prediction of the prognostic model.

[0090] In an exemplary embodiment, a corresponding risk assessment system based on a three-dimensional prognostic model is provided, such as Figure 4 As shown, the various functional modules and main functions of the risk assessment system based on the three-dimensional prognostic model are as follows:

[0091] The data acquisition module M1 is used to acquire the basic clinical data and imaging data of the user; the user is a postoperative patient suffering from hypertrophic obstructive cardiomyopathy.

[0092] The myocardial hypertrophy degree determination module M2 is used to determine the myocardial hypertrophy degree of the user's left ventricular structure based on the clinical basic data and the image data; the myocardial hypertrophy degree includes the thickness of each part of the user's left ventricular structure.

[0093] The Cut-Off value determination module M3 is used to determine the Cut-Off value of each part in the left ventricular structure of the user according to the degree of myocardial hypertrophy of the left ventricular structure of the user; the Cut-Off value is the lowest critical value that leads to a poor prognosis.

[0094] The three-dimensional prognostic model construction module M4 is used to construct a three-dimensional prognostic model according to the Cut-Off values ​​of various parts in the left ventricular structure of the user; the three-dimensional prognostic model is a three-dimensional simulation model that simulates the left ventricular structure of the user.

[0095] The prognostic risk assessment module M5 is used to use the three-dimensional simulation model to perform a prognostic risk assessment on the user to obtain a prognostic risk assessment result; the prognostic risk assessment result is used to indicate the risk level of the user's poor recurrence prognosis.

[0096] The correction module M6 is used to follow up the user and obtain follow-up results; according to the follow-up results, the three-dimensional prognostic model is corrected to obtain a corrected three-dimensional prognostic model; and using the three-dimensional simulation model, the prognostic risk assessment of the user is performed again to obtain a corrected prognostic risk assessment result.

[0097] In an exemplary embodiment, a computer device is provided. The computer device may be a server or a terminal. The internal structure diagram thereof may be as follows: Figure 5 As shown. The computer device includes a processor, a memory, an input / output interface (Input / Output, referred to as I / O) and a communication interface. Among them, the processor, the memory and the input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store the user's clinical basic data, imaging data and other modeling data of the three-dimensional prognosis model. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a risk assessment method based on a three-dimensional prognosis model is implemented.

[0098] Those skilled in the art will understand that Figure 5 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0099] The users of this embodiment are mainly children. The risk assessment process based on the three-dimensional prognostic model mainly includes the collection of basic clinical data before surgery, the use of deep machine learning combined with imaging data to analyze the degree of hypertrophic myocardium in multiple dimensions, the construction of a prognostic prediction model based on the threshold of the degree of hypertrophy, the assessment of the user's poor prognosis risk, and the correction of the prognostic model based on the long-term follow-up results of the user. By establishing a model that can predict the postoperative prognosis of the user's hypertrophic cardiomyopathy, combined with a variety of data such as the user's clinical data and imaging data, the accuracy of the model prediction can be ensured, and the model can also be automatically corrected continuously, providing a strong guiding role in the analysis, processing and judgment of hypertrophic cardiomyopathy. By mining data, analyzing data, finding the left ventricular candidate thickness feature, constructing a three-dimensional prognostic model, and feedback-correcting the three-dimensional prognostic model, the risk level of the user's hypertrophic obstructive cardiomyopathy can be distinguished, thereby improving the accuracy of risk assessment and improving the prognosis of the user's hypertrophic obstructive cardiomyopathy.

[0100] Those of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM may be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM).

[0101] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0102] This article uses specific examples to illustrate the principles and implementation methods of this application. The description of the above embodiments is only used to help understand the method and core ideas of this application. At the same time, for those skilled in the art, according to the ideas of this application, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as limiting this application.

Claims

1. A risk assessment method based on a three-dimensional prognostic model, characterized in that: The risk assessment method based on the three-dimensional prognostic model includes: Acquiring basic clinical data and imaging data of a user; the user is a postoperative patient suffering from hypertrophic obstructive cardiomyopathy; Determine the degree of myocardial hypertrophy of the user's left ventricular structure according to the basic clinical data and the image data; the degree of myocardial hypertrophy includes the thickness of various parts of the user's left ventricular structure; Determining a Cut-Off value of each part of the left ventricular structure of the user according to the degree of myocardial hypertrophy of the left ventricular structure of the user; the Cut-Off value is the lowest critical value that leads to a poor prognosis; Constructing a three-dimensional prognostic model according to the Cut-Off values ​​of various parts in the left ventricular structure of the user; the three-dimensional prognostic model is a three-dimensional simulation model that simulates the left ventricular structure of the user; The three-dimensional simulation model is used to perform a prognostic risk assessment on the user to obtain a prognostic risk assessment result; the prognostic risk assessment result is used to indicate the risk level of the user's poor recurrence prognosis.

2. The risk assessment method based on the three-dimensional prognostic model according to claim 1, characterized in that: Obtain the user's basic clinical data and imaging data, including: Using the EMR system, obtaining the basic clinical data of the user; The image data of the user is acquired by using a PACS system.

3. The risk assessment method based on the three-dimensional prognostic model according to claim 2, characterized in that: The basic clinical data include age, weight, admission records, examination records and medical records; the image data include CT images and / or MRI images.

4. The risk assessment method based on the three-dimensional prognostic model according to claim 1, characterized in that: Before the step of determining the degree of myocardial hypertrophy of the user's left ventricular structure according to the basic clinical data and the image data, the risk assessment method based on the three-dimensional prognostic model further includes: The basic clinical data and the image data are respectively subjected to missing value processing, One-Hot processing and Scaling processing to obtain pre-processed basic clinical data and image data; the pre-processed basic clinical data and image data are used to determine the degree of myocardial hypertrophy of the user's left ventricular structure.

5. The risk assessment method based on the three-dimensional prognostic model according to claim 1, characterized in that: According to the Cut-Off values ​​of various parts in the left ventricular structure of the user, a three-dimensional prognostic model is constructed, specifically including: The three-dimensional prognostic model is constructed using three-dimensional modeling software according to the Cut-Off values ​​of various parts in the left ventricular structure of the user.

6. The risk assessment method based on the three-dimensional prognostic model according to claim 1, characterized in that: The three-dimensional prognostic model includes three layers, namely, the base, the middle and the apex. Each layer is divided into different longitudinal regions in the order of the anterior wall, the ventricular septum, the posterior wall and the lateral wall. The base includes the basal anterior wall, the basal anterior septum, the basal posterior septum, the basal posterior wall, the basal posterior lateral wall and the basal anterior lateral wall. The middle includes the middle anterior wall, the middle anterior septum, the middle posterior septum, the middle posterior wall, the middle posterior lateral wall and the middle anterior lateral wall. The apex includes the apical anterior wall, the apical septum, the apical lateral wall, the apical posterior wall and the apex.

7. The risk assessment method based on a three-dimensional prognostic model according to claim 1, characterized in that: After the step of using the three-dimensional simulation model to perform prognostic risk assessment on the user to obtain a prognostic risk assessment result, the risk assessment method based on the three-dimensional prognostic model further includes: Follow up the user and obtain follow-up results; According to the follow-up results, the three-dimensional prognostic model is modified to obtain a modified three-dimensional prognostic model; The three-dimensional simulation model is used to perform a prognostic risk assessment on the user again to obtain a revised prognostic risk assessment result.

8. A risk assessment system based on a three-dimensional prognostic model, characterized in that: The risk assessment system based on the three-dimensional prognostic model includes: A data acquisition module, used to acquire basic clinical data and imaging data of a user; the user is a postoperative patient suffering from hypertrophic obstructive cardiomyopathy; A myocardial hypertrophy degree determination module, used to determine the myocardial hypertrophy degree of the user's left ventricular structure according to the clinical basic data and the image data; the myocardial hypertrophy degree includes the thickness of each part of the user's left ventricular structure; A Cut-Off value determination module, for determining the Cut-Off value of each part of the left ventricular structure of the user according to the degree of myocardial hypertrophy of the left ventricular structure of the user; the Cut-Off value is the lowest critical value that leads to a poor prognosis; A three-dimensional prognostic model building module, used to build a three-dimensional prognostic model according to the Cut-Off values ​​of various parts in the left ventricular structure of the user; the three-dimensional prognostic model is a three-dimensional simulation model that simulates the left ventricular structure of the user; The prognostic risk assessment module is used to use the three-dimensional simulation model to perform a prognostic risk assessment on the user to obtain a prognostic risk assessment result; the prognostic risk assessment result is used to indicate the risk level of the user's poor recurrence prognosis.

9. The risk assessment system based on the three-dimensional prognostic model according to claim 8, characterized in that: The risk assessment system based on the three-dimensional prognostic model also includes: The correction module is used to follow up the user and obtain the follow-up results; according to the follow-up results, the three-dimensional prognostic model is corrected to obtain a corrected three-dimensional prognostic model; and using the three-dimensional simulation model, the prognostic risk assessment of the user is performed again to obtain a corrected prognostic risk assessment result.

10. A computer device comprising: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the risk assessment method based on a three-dimensional prognostic model according to any one of claims 1 to 7.

Images