A subclinical diagnostic model for atherosclerosis and its construction method and system
By constructing a subclinical atherosclerosis diagnostic model based on physical examination data, the problems of invasiveness and high cost in existing technologies have been solved, enabling rapid and accurate diagnosis of subclinical atherosclerosis, which is suitable for large-scale screening.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- JIMEI UNIV
- Filing Date
- 2022-11-03
- Publication Date
- 2026-07-17
AI Technical Summary
Existing methods for diagnosing subclinical atherosclerosis rely on invasive medical imaging techniques and physicians’ subjective judgment, making them difficult to apply on a large scale for screening and costly.
By collecting physical examination data from multiple cases, a diagnostic model integrating a first-order linear regression component and a second-order feature cross component is constructed. Supervised data transformation and dimensionality reduction are performed using the physical examination data to establish a fast and accurate diagnostic model.
It enables non-invasive, quantitative, and objective diagnosis of subclinical atherosclerosis, reduces human and material costs, and is suitable for large-scale screening.
Smart Images
Figure CN115798704B_ABST
Abstract
Description
Technical Field
[0001] This application relates to the field of computer software technology, specifically to a subclinical atherosclerosis diagnostic model and its construction method and system. Background Technology
[0002] According to the World Health Organization, cardiovascular disease is the leading cause of death worldwide. Subclinical atherosclerosis is a chronic, progressive inflammatory disease with a long asymptomatic period. Its progression eventually leads to acute cardiovascular events, seriously endangering people's lives and placing a heavy burden on healthcare systems. Therefore, early diagnosis and treatment of subclinical atherosclerosis are essential.
[0003] Existing diagnostic devices for subclinical atherosclerosis are mainly based on coronary angiography and medical imaging technologies such as B-mode, CT, and MRI. However, coronary angiography is somewhat invasive, while medical imaging relies on the subjective judgment of physicians, and the human, material, and time costs required for these two diagnostic devices are not suitable for large-scale screening. Summary of the Invention
[0004] The purpose of this application is to provide a subclinical atherosclerosis diagnostic model and its construction method and system.
[0005] The first aspect of this application provides a method for constructing a subclinical atherosclerosis diagnostic model, comprising:
[0006] Collect physical examination data from multiple cases, including cases of subclinical atherosclerosis; the physical examination data includes data from multiple physical examination items and diagnostic results, the diagnostic results indicating whether or not a patient has subclinical atherosclerosis.
[0007] The physical examination data of the multiple cases are aggregated based on the physical examination items to obtain a multivariate feature matrix;
[0008] Based on the diagnostic results, the multivariate feature matrix is transformed into supervised data;
[0009] The supervised data is subjected to dimensionality reduction processing;
[0010] A preliminary diagnostic model for subclinical atherosclerosis integrating different features is constructed, and an objective function is set; wherein, the preliminary diagnostic model for subclinical atherosclerosis consists of a first-order linear regression component and a second-order feature cross component;
[0011] Based on the dimensionality-reduced supervised data, the model is iteratively trained using multiple physical examination items of the case as input and the diagnosis result of the case as output, until the objective function converges, and finally the subclinical atherosclerosis diagnostic model is obtained.
[0012] In some embodiments, before converting the multivariate feature matrix into supervised data based on the diagnostic results, the method further includes:
[0013] The multivariate feature matrix is normalized to obtain the normalized multivariate feature matrix.
[0014] Accordingly, the process of converting the multivariate feature matrix into supervised data based on the diagnostic results includes:
[0015] Based on the diagnostic results, the normalized multivariate feature matrix is transformed into supervised data.
[0016] In some embodiments, the normalization process for the multivariate feature matrix includes:
[0017] The multivariate feature matrix was normalized using the Min-Max algorithm.
[0018] In some embodiments, the dimensionality reduction processing of the supervised data includes:
[0019] The supervised data is dimensionality reduced using a feature selection algorithm.
[0020] In some embodiments, the feature selection algorithm employs analysis of variance.
[0021] In some embodiments, the first-order linear regression component includes a linear layer and an activation function ReLU; the second-order feature cross component includes a latent vector matrix.
[0022] In some embodiments, the objective function is set to the BCEwithLogitsLoss function.
[0023] In some embodiments, the collection of physical examination data from multiple cases includes:
[0024] The cases were statistically analyzed, resulting in a total of T cases and Q examination items. Let i represent the physical examination data of a case, where i∈[1,2,…,T].
[0025] The second aspect of this application provides a system for constructing a subclinical atherosclerosis diagnostic model, comprising:
[0026] At least one processor;
[0027] At least one memory for storing at least one program;
[0028] When the at least one program is executed by the at least one processor, the at least one processor implements the method for constructing the subclinical atherosclerosis diagnostic model as described in the first aspect.
[0029] The third aspect of this application provides a subclinical atherosclerosis diagnostic model, which is created using the method for constructing a subclinical atherosclerosis diagnostic model described in the first aspect.
[0030] The beneficial effects of this application are as follows: This application trains a diagnostic model for subclinical atherosclerosis using collected physical examination data of cases. The diagnostic model consists of a first-order linear regression component and a second-order feature cross component. It takes multiple physical examination data of the case as the input of the model and the diagnostic result of the case as the output of the model. This allows the model to quickly and accurately diagnose and predict subclinical atherosclerosis using physical examination data, and can be widely applied in the field of automated processing of medical data. Attached Figure Description
[0031] Various other advantages and benefits will become apparent to those skilled in the art upon reading the following detailed description of preferred embodiments. The accompanying drawings are for illustrative purposes only and are not intended to limit the scope of this application. Furthermore, the same reference numerals denote the same parts throughout the drawings. In the drawings:
[0032] Figure 1 A flowchart illustrating a method for constructing a subclinical atherosclerosis diagnostic model provided in an embodiment of this application is shown;
[0033] Figure 2 A schematic diagram illustrating the construction and prediction process of the subclinical atherosclerosis diagnostic model provided in the embodiments of this application is shown.
[0034] Figure 3 A schematic diagram of a system for constructing a subclinical atherosclerosis diagnostic model provided in an embodiment of this application is shown. Detailed Implementation
[0035] Exemplary embodiments of this application will now be described in more detail with reference to the accompanying drawings. While exemplary embodiments of this application are shown in the drawings, it should be understood that this application may be implemented in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided to enable a more thorough understanding of this application and to fully convey the scope of this application to those skilled in the art.
[0036] It should be noted that, unless otherwise stated, the technical or scientific terms used in this application shall have the ordinary meaning as understood by one of ordinary skill in the art to which this application pertains.
[0037] Furthermore, the terms "first" and "second," etc., are used to distinguish different objects, not to describe a specific order. Additionally, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or apparatus that includes a series of steps or units is not limited to the listed steps or units, but may optionally include steps or units not listed, or may optionally include other steps or units inherent to those processes, methods, products, or apparatuses.
[0038] Subclinical atherosclerosis refers to a condition in which there is evidence of atherosclerotic plaques but no obvious clinical symptoms. Subclinical atherosclerosis is a dynamic process; the degree of coronary artery calcification increases at an average rate of 15% to 25% per year. The presence of subclinical atherosclerosis indicates a high risk of cardiovascular events.
[0039] Since this disease can potentially be reversed or at least have limited consequences if diagnosed early, it is of great significance to provide the medical field with new tools that allow for such early, rapid, and accurate diagnosis.
[0040] This application provides a subclinical atherosclerosis diagnostic model and its construction method and system, which can be used to quickly and accurately diagnose subclinical atherosclerosis. The following description is in conjunction with the accompanying drawings.
[0041] Please refer to Figure 1 The document illustrates a flowchart of a method for constructing a subclinical atherosclerosis diagnostic model according to some embodiments of this application. The method can be implemented by medical diagnostic equipment, etc. For ease of understanding, this application also provides... Figure 2 The diagram shows the construction and prediction process of the subclinical atherosclerosis diagnostic model.
[0042] like Figure 1 As shown, the method for constructing the subclinical atherosclerosis diagnostic model may include the following steps:
[0043] S101. Collect physical examination data from multiple cases, including cases of subclinical atherosclerosis; the physical examination data includes data from multiple physical examination items and diagnostic results, the diagnostic results indicating whether or not a patient has subclinical atherosclerosis.
[0044] Specifically, physical examination data from multiple cases can be collected from the hospital's medical record database, such as... Figure 2The data shown is from ETL. ETL is an abbreviation for Extract-Transform-Load, used to describe the process of extracting, transforming, and loading data from the source to the destination.
[0045] The physical examination data includes multiple examination items, such as the patient's age, body mass index, complete blood count, blood biochemistry, and urine test data.
[0046] In this embodiment, in step S101, the cases are counted to obtain a total of T cases and Q examination items. Let i represent the physical examination data of a case, where i∈[1,2,…,T].
[0047] S102. Aggregate the physical examination data of the multiple cases based on the physical examination items to obtain a multivariate feature matrix.
[0048] In this embodiment, since the data ranges of different physical examination items are significantly different, after obtaining the multivariate feature matrix, the multivariate feature matrix can be normalized to obtain the normalized multivariate feature matrix.
[0049] Specifically, the Min-Max algorithm can be used to normalize the multivariate feature matrix to [0,1].
[0050] The normalization formula is as follows:
[0051]
[0052] in, This represents the quantitative data of a certain physical examination item, z represents the normalized physical examination item data, and min(·) and max(·) represent the minimum and maximum values of the input physical examination item data, respectively.
[0053] S103. Based on the diagnostic results, the multivariate feature matrix is transformed into supervised data.
[0054] Specifically, the normalized multivariate feature matrix can be transformed into supervised data.
[0055] To capture the relationship between different features and diseases from physical examination data, this application transforms the data into supervised data. Given the physical examination data of a case, during the transformation process, several physical examination data variables are used as input variables of the model, and the diagnostic results are used as the output of the model.
[0056] The high-dimensional data is transformed into supervised data as follows:
[0057]
[0058] Among them, y i ∈[0,1], where 0 represents not having subclinical atherosclerosis and 1 represents having subclinical atherosclerosis.
[0059] S104. Perform dimensionality reduction processing on the supervised data.
[0060] In this embodiment, in order to prevent irrelevant data from disturbing the model, the data is filtered to reduce dimensionality. Specifically, a feature selection algorithm can be used to perform dimensionality reduction on the normalized supervised data.
[0061] Specifically, the feature selection algorithm employs the ANOVA algorithm. This application uses the F-value of ANOVA to filter the data to reduce dimensionality, sorts the data according to the F-value, and filters out the top C features. The formula for calculating the F-value is as follows:
[0062]
[0063] Where f is the F-value matrix, A physical examination result representing a case without subclinical atherosclerosis. A specific piece of medical examination data representing a patient's condition.
[0064] S105. Construct an initial diagnostic model for subclinical atherosclerosis that integrates different features, and set an objective function; wherein the initial diagnostic model for subclinical atherosclerosis consists of a first-order linear regression component and a second-order feature cross component.
[0065] Specifically, the first-order linear regression component includes a linear layer and an activation function ReLU; the linear layer is used to establish a mapping between feature variables and prediction results, and the activation function ReLU is used to make the features linearly separable.
[0066] The formula for generating a linear representation using the first-order linear regression component is as follows:
[0067]
[0068] For each original element in the ReLU(·) function, we have:
[0069]
[0070] in, It is a first-order linear representation. It is the feature matrix after feature selection. It is the weight matrix of the linear layer, and ⊙ represents the Hadamard product. It is a bias term.
[0071] The second-order feature crossing component mainly consists of a latent vector matrix v, which is used to learn the relationships between different features. The formula for generating the crossing feature representation using the second-order feature crossing component is as follows:
[0072]
[0073] in, It is a second-order cross feature representation. It is an implicit vector matrix.
[0074] like Figure 2 As shown, the above two representations are added together to generate the output representation, and the formula is as follows:
[0075] o=r 1 +r 2 ;
[0076] in,
[0077] Then, the sigmoid function is used to compress the output to [0,1]. The formula is as follows:
[0078] y = sigmoid(o);
[0079] in, This represents the output of the model. For any element of y in the model:
[0080]
[0081] Where exp(·) represents the exponential function, o i This represents an element in o.
[0082] Finally, the output is binarized using the following formula:
[0083]
[0084] in, It is the model output, that is, the model prediction result.
[0085] In this embodiment, the objective function can be set as the Binary Cross Entropy with Logits Loss (BCEwithLogitsLoss) function.
[0086] S106. Based on the supervised data after dimensionality reduction, the model is iteratively trained using multiple physical examination items of the case as input and the diagnosis result of the case as output, until the objective function converges, and finally the subclinical atherosclerosis diagnostic model is obtained.
[0087] In this embodiment, BCEwithLogitsLoss is used to calculate the loss function, and gradient descent algorithm is used to optimize the model until the loss function converges, thus obtaining the optimal parameters of the diagnostic model and finally obtaining the subclinical atherosclerosis diagnostic model.
[0088] Finally, based on the final subclinical atherosclerosis diagnostic model, and by inputting the patient's physical examination data, a rapid diagnosis of whether or not the patient has subclinical atherosclerosis can be obtained. Compared with existing technologies, this method has the following advantages:
[0089] 1. Non-invasive: This application collects patients' physical examination data and uses this data to make an accurate diagnosis of subclinical atherosclerosis. Unlike traditional methods such as coronary angiography that require minimally invasive surgery, this application will not cause any trauma to the patient.
[0090] 2. Quantitative and objective: Unlike traditional medical imaging diagnostic techniques that rely on doctors' subjective judgment, this application uses physical examination data for diagnosis. Its essence is to find the connection between human metabolic data and the disease, so as to establish a mapping between the two and thus accurately predict whether the patient has subclinical atherosclerosis.
[0091] 3. It can be applied on a large scale; this application can diagnose subclinical atherosclerosis through physical examination data, unlike coronary angiography and other medical imaging technologies, and does not require a lot of manpower and material resources.
[0092] This application trains a diagnostic model for subclinical atherosclerosis using collected physical examination data from cases. The diagnostic model consists of a first-order linear regression component and a second-order feature cross component. It takes multiple physical examination data of the case as input to the model and the diagnostic result of the case as output. This allows the model to quickly and accurately diagnose and predict subclinical atherosclerosis using physical examination data, and can be widely applied in the field of automated medical data processing.
[0093] This application also provides a construction system corresponding to the method for constructing a subclinical atherosclerosis diagnostic model provided in the foregoing embodiments. The construction system can be an electronic device for a client, such as a mobile phone, laptop, tablet computer, desktop computer, etc., to execute the above-described method for constructing a subclinical atherosclerosis diagnostic model.
[0094] Please refer to Figure 3 This illustration shows a schematic diagram of a system for constructing a subclinical atherosclerosis diagnostic model, provided by some embodiments of this application. For example... Figure 3 As shown, the construction system 20 includes:
[0095] At least one processor 200;
[0096] At least one memory 201 is used to store at least one program;
[0097] When the at least one program is executed by the at least one processor 200, the at least one processor 200 implements the method for constructing a subclinical atherosclerosis diagnostic model according to the above embodiments.
[0098] like Figure 3 As shown, the construction system 20 may also include a bus 202 and a communication interface 203, and the processor 200, the communication interface 203 and the memory 201 are connected through the bus 202.
[0099] The memory 201 may include high-speed random access memory (RAM) or non-volatile memory, such as at least one disk storage device. Communication between this system network element and at least one other network element is achieved through at least one communication interface 203 (which can be wired or wireless), such as the Internet, wide area network, local area network, or metropolitan area network.
[0100] Bus 202 can be an ISA bus, PCI bus, or EISA bus, etc. The bus can be divided into an address bus, a data bus, a control bus, etc. Memory 201 is used to store programs. After receiving an execution instruction, processor 200 executes the program. The method for constructing the subclinical atherosclerosis diagnostic model disclosed in any of the foregoing embodiments of this application can be applied to processor 200, or implemented by processor 200.
[0101] The processor 200 may be an integrated circuit chip with signal processing capabilities. In implementation, each step of the above method can be completed by the integrated logic circuitry in the hardware of the processor 200 or by instructions in software form. The processor 200 may be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it may also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), an off-the-shelf programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. It can implement or execute the methods, steps, and logic block diagrams disclosed in the embodiments of this application. The general-purpose processor may be a microprocessor or any conventional processor. The steps of the methods disclosed in the embodiments of this application can be directly embodied in the execution of a hardware decoding processor, or executed by a combination of hardware and software modules in the decoding processor. The software modules may reside in random access memory, flash memory, read-only memory, programmable read-only memory, electrically erasable programmable memory, registers, or other mature storage media in the art. The storage medium is located in memory 201. The processor 200 reads the information in memory 201 and, in conjunction with its hardware, completes the steps of the above method.
[0102] The system for constructing a subclinical atherosclerosis diagnostic model provided in this application embodiment and the method for constructing a subclinical atherosclerosis diagnostic model provided in this application embodiment are based on the same inventive concept and have the same beneficial effects as the methods they employ, operate, or implement.
[0103] Another embodiment of this application provides a subclinical atherosclerosis diagnostic model, which is created using the construction method of the subclinical atherosclerosis diagnostic model described in this application. It can quickly and accurately diagnose and predict subclinical atherosclerosis using physical examination data and can be widely applied in the field of automated processing of medical data.
[0104] It should be noted that the flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this application. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions marked in the blocks may occur in a different order than those marked in the drawings. For example, two consecutive blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or action, or using a combination of dedicated hardware and computer instructions.
[0105] Those skilled in the art will understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.
[0106] In the several embodiments provided in this application, it should be understood that the disclosed apparatus and methods can be implemented in other ways. The apparatus embodiments described above are merely illustrative. For example, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. Furthermore, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Additionally, the displayed or discussed mutual couplings, direct couplings, or communication connections may be through some communication interfaces; indirect couplings or communication connections between devices or units may be electrical, mechanical, or other forms.
[0107] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.
[0108] In addition, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.
[0109] If the aforementioned functions are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.
[0110] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some or all of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of this application, and they should all be covered within the scope of the claims and specification of this application.
Claims
1. A method for constructing a subclinical atherosclerosis diagnostic model, characterized in that, include: Collect physical examination data from multiple cases, including cases of subclinical atherosclerosis; the physical examination data includes data from multiple physical examination items and diagnostic results, the diagnostic results indicating whether or not a patient has subclinical atherosclerosis. The physical examination data of the multiple cases are aggregated based on the physical examination items to obtain a multivariate feature matrix; Based on the diagnostic results, the multivariate feature matrix is transformed into supervised data; The supervised data is subjected to dimensionality reduction processing; A preliminary diagnostic model for subclinical atherosclerosis integrating different features is constructed, and an objective function is set; wherein, the preliminary diagnostic model for subclinical atherosclerosis consists of a first-order linear regression component and a second-order feature cross component; Based on the dimensionality-reduced supervised data, the model is iteratively trained using multiple physical examination items of the case as input and the diagnosis result of the case as output, until the objective function converges, and finally the subclinical atherosclerosis diagnostic model is obtained.
2. The method according to claim 1, characterized in that, Before converting the multivariate feature matrix into supervised data based on the diagnostic results, the process further includes: The multivariate feature matrix is normalized to obtain the normalized multivariate feature matrix. Accordingly, the process of converting the multivariate feature matrix into supervised data based on the diagnostic results includes: Based on the diagnostic results, the normalized multivariate feature matrix is transformed into supervised data.
3. The method according to claim 2, characterized in that, The normalization process for the multivariate feature matrix includes: The multivariate feature matrix was normalized using the Min-Max algorithm.
4. The method according to claim 1, characterized in that, The dimensionality reduction process for the supervised data includes: The supervised data is dimensionality reduced using a feature selection algorithm.
5. The method according to claim 4, characterized in that, The feature selection algorithm employs analysis of variance.
6. The method according to claim 1, characterized in that, The first-order linear regression component includes a linear layer and the ReLU activation function; the second-order feature cross component includes a latent vector matrix.
7. The method according to claim 1, characterized in that, The objective function is set to BCEwithLogitsLoss.
8. The method according to claim 1, characterized in that, The collection of physical examination data from multiple cases includes: The cases were statistically analyzed, resulting in a total of T cases and Q examination items. Let i represent the physical examination data of a case, where i∈[1,2,…,T].
9. A system for constructing a subclinical atherosclerosis diagnostic model, characterized in that, include: At least one processor; At least one memory for storing at least one program; When the at least one program is executed by the at least one processor, the at least one processor implements the method for constructing a subclinical atherosclerosis diagnostic model as described in any one of claims 1-8.
10. A subclinical atherosclerosis diagnostic model, characterized in that, The subclinical atherosclerosis diagnostic model is created using the method for constructing a subclinical atherosclerosis diagnostic model as described in any one of claims 1-8.