Cardiovascular and cerebrovascular risk prediction method, device and equipment

Abstract

The invention provides a cardiovascular and cerebrovascular risk prediction method, device and equipment. The method comprises the following steps: acquiring multi-dimensional data; based on carotid artery image data, biochemical index data and blood pressure medical history data in the multi-dimensional data, weight coefficients corresponding to the multi-dimensional data are determined, and the weight coefficients change along with changes of the multi-dimensional data; based on the weight coefficients corresponding to the multi-dimensional data, heart and cerebral vessel risk prediction is conducted on the multi-dimensional data, a corresponding prediction result is obtained, and the prediction result comprises the corresponding risk level of the target user suffering from heart and cerebral vessels and corresponding diagnosis and treatment suggestions. Therefore, the technical problem that heart and cerebral vessels cannot be comprehensively and accurately predicted and diagnosed in the prior art can be solved.

Description

Technical Field

[0001] This application relates to the field of medical technology, specifically to a method, device, and equipment for predicting cardiovascular and cerebrovascular risks. Background Technology

[0002] Cardiovascular and cerebrovascular diseases are the leading cause of death worldwide, and my country has now entered a period of high incidence of these diseases. However, current prevention and treatment methods primarily focus on treatment, emphasizing disease management and post-mortem care. Patients typically only seek medical attention after the onset of symptoms, neglecting early diagnosis and intervention.

[0003] Many countries have developed assessment tools for various cardiovascular and cerebrovascular diseases. However, these assessments rely on single-dimensional data, such as limited static indicators like blood pressure, blood lipids, or blood sugar, and cannot accurately analyze or predict corresponding cardiovascular and cerebrovascular diseases. This is especially true for patients with complex cases, where comprehensive and accurate prediction and diagnosis of cardiovascular and cerebrovascular diseases are even more difficult. Therefore, there is an urgent need to develop a better cardiovascular and cerebrovascular risk prediction scheme. Summary of the Invention

[0004] In view of this, the embodiments of this application are committed to providing a method, device and equipment for predicting cardiovascular and cerebrovascular risks, which can solve the technical problem that the prior art cannot perform cardiovascular and cerebrovascular prediction and diagnosis in a comprehensive and accurate manner.

[0005] Firstly, this application provides a method for predicting cardiovascular and cerebrovascular risks, including: Acquire multidimensional data, including the target user's carotid artery imaging data, biochemical index data, and blood pressure history data; Based on the carotid artery imaging data, biochemical index data, and blood pressure history data in the multidimensional data, the weight coefficients corresponding to each of the multidimensional data are determined, and the weight coefficients change with the changes in the multidimensional data; Based on the weight coefficients corresponding to each of the multidimensional data, the cardiovascular and cerebrovascular risks of the multidimensional data are predicted to obtain the corresponding prediction results. The prediction results include the risk level of the target user having cardiovascular and cerebrovascular diseases and the corresponding diagnosis and treatment suggestions.

[0006] In some embodiments, the step of predicting cardiovascular and cerebrovascular risks based on the weight coefficients corresponding to each of the multidimensional data, and obtaining the corresponding prediction results, includes: Based on the carotid artery imaging data, biochemical index data, and blood pressure history data in the multidimensional data, normalization processing is performed to obtain the processed data corresponding to each of the multidimensional data. Based on the weight coefficients corresponding to each of the multidimensional data and the processed data, a comprehensive risk prediction is performed to obtain the corresponding prediction results.

[0007] In some embodiments, acquiring multidimensional data includes: In response to the request information from the target user, multi-source data is acquired asynchronously, and the multi-source data and the multi-dimensional data correspond one-to-one. The multi-source data is preprocessed to obtain the feature data corresponding to each of the multi-source data. The preprocessing includes at least standardization and scoring calculation. The feature data corresponding to each of the multiple sources are collected to obtain the multidimensional data.

[0008] In some embodiments, the request information carries a task identifier, and the multi-source data and the feature data corresponding to each of the multi-source data are obtained in parallel from different modules based on the task identifier. The step of aggregating the feature data corresponding to each of the multi-source data to obtain the multi-dimensional data includes: Based on the task identifier, the middleware aggregates and integrates the feature data corresponding to the multi-source data in the different modules to obtain the multi-dimensional data.

[0009] In some embodiments, the weighting coefficients corresponding to each of the multidimensional data include: Where i represents the i-th data in the multidimensional data. This represents the weight coefficient corresponding to the i-th data point. Indicates the clinical significance coefficient. Indicates the enhancement factor of medical history. This indicates a medical history indicator function. It is at least related to the blood pressure history data in the multidimensional data.

[0010] In some embodiments, The coefficients for calculating the importance of random forest features are obtained based on the i-th data in the multidimensional data.

[0011] In some embodiments, the step of predicting cardiovascular and cerebrovascular risks based on the weight coefficients corresponding to each of the multidimensional data, and obtaining the corresponding prediction results, further includes: Display a modal window, in which different risk levels are marked with different colors; and When the risk level is high, the risk level is displayed by flashing at a preset frequency and an audible alarm is triggered.

[0012] In some embodiments, the biochemical data includes low-density lipoprotein cholesterol data.

[0013] Secondly, this application provides a cardiovascular and cerebrovascular risk prediction device, comprising: The acquisition module is used to acquire multidimensional data, which includes the target user's carotid artery imaging data, biochemical index data, and blood pressure history data. The processing module is used to determine the weight coefficients corresponding to each of the multidimensional data based on the carotid artery imaging data, biochemical index data, and blood pressure history data in the multidimensional data, wherein the weight coefficients change with the changes in the multidimensional data; The processing module is further configured to perform cardiovascular and cerebrovascular risk prediction on the multidimensional data based on the weight coefficients corresponding to each of the multidimensional data, and obtain the corresponding prediction results. The prediction results include the risk level of the target user having cardiovascular and cerebrovascular disease and the corresponding diagnosis and treatment recommendations.

[0014] For any content not introduced or described in the embodiments of this application, please refer to the relevant descriptions in the foregoing method embodiments; they will not be repeated here.

[0015] Thirdly, this application provides an electronic device, including: a processor; and a memory for storing processor-executable instructions; wherein the processor is configured to execute the executable instructions to implement the steps of the above-described cardiovascular and cerebrovascular risk prediction method.

[0016] Fourthly, this application provides a computer-readable storage medium storing computer program instructions thereon, which, when executed by a processor, implement the steps of the above-described cardiovascular and cerebrovascular risk prediction method.

[0017] The technical solution provided in this application embodiment can include the following beneficial effects: This application acquires multidimensional data, including carotid artery imaging data, biochemical index data, and blood pressure history data of the target user; based on the carotid artery imaging data, biochemical index data, and blood pressure history data in the multidimensional data, it determines the weight coefficients corresponding to each of the multidimensional data, and the weight coefficients change with the changes in the multidimensional data; based on the weight coefficients corresponding to each of the multidimensional data, it performs cardiovascular and cerebrovascular risk prediction on the multidimensional data to obtain corresponding prediction results, and the prediction results include the risk level of the target user having cardiovascular and cerebrovascular diseases and corresponding diagnostic and treatment recommendations. In this way, dynamic weight coefficients can be determined according to the individualized multidimensional data of the target user, and then the risk level of the target user having cardiovascular and cerebrovascular diseases and diagnostic and treatment recommendations can be predicted and evaluated based on the dynamic weight coefficients, thereby effectively improving the comprehensiveness and accuracy of cardiovascular and cerebrovascular prediction. At the same time, it can also solve the technical problem that the prior art cannot perform cardiovascular and cerebrovascular prediction and diagnosis in a comprehensive and accurate manner.

[0018] The above description is only an overview of the technical solution of this application. In order to better understand the technical means of this application and to implement it in accordance with the contents of the specification, and to make the above and other objects, features and advantages of this application more obvious and understandable, specific embodiments of this application are given below. Attached Figure Description

[0019] 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.

[0020] Figure 1 This is a flowchart illustrating a method for predicting cardiovascular and cerebrovascular risks provided in an embodiment of this application.

[0021] Figure 2 This is a schematic diagram illustrating the comparison of weighting coefficients provided in an embodiment of this application.

[0022] Figure 3 This is a schematic diagram of the structure of a cardiovascular and cerebrovascular risk prediction device provided in an embodiment of this application.

[0023] Figure 4 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Detailed Implementation

[0024] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0025] Unless otherwise defined, the technical or scientific terms used in the embodiments of this specification shall have the ordinary meaning understood by one of ordinary skill in the art to which this specification pertains. The terms "first," "second," and similar terms used in the embodiments of this specification do not indicate any order, quantity, or importance, but are merely used to avoid confusion of constituent elements.

[0026] Unless the context otherwise requires, throughout this specification, "a plurality of" means "at least two," and "including" is interpreted as open-ended or encompassing, that is, "including, but not limited to." In the description of this specification, terms such as "one embodiment," "some embodiments," "exemplary embodiment," "example," "specific example," or "some examples" are intended to indicate that a particular feature, structure, material, or characteristic associated with that embodiment or example is included in at least one embodiment or example of this specification. The illustrative representations of the above terms do not necessarily refer to the same embodiment or example.

[0027] Exemplary embodiments of the present application will now be described in more detail with reference to the accompanying drawings. While exemplary embodiments of the present application are shown in the drawings, it should be understood that the present application may be implemented in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this application will be thorough and complete, and will fully convey the scope of the present application to those skilled in the art.

[0028] In the process of filing this application, the applicant also discovered that existing assessment tools, such as the Framingham scoring model, use fixed weights and cannot dynamically adjust the importance of indicators based on individual differences (e.g., plaque instability, comorbidities), leading to missed diagnoses of high-risk cardiovascular and cerebrovascular diseases. Furthermore, existing technologies do not integrate imaging, biochemical indicators, and medical history data, making it difficult to comprehensively and accurately assess complex cases, such as unstable plaques combined with diabetes. Existing technologies typically support offline batch risk assessment, which cannot support real-time clinical intervention. To address these issues, this application proposes a method, device, equipment, and medium for predicting cardiovascular and cerebrovascular risks.

[0029] Please see Figure 1 This is a flowchart illustrating a method for predicting cardiovascular and cerebrovascular risks provided in an embodiment of this application. Figure 1 The method shown can be applied to electronic devices, and the method may include the following implementation steps: S101. Obtain multidimensional data, including the target user's carotid artery imaging data, biochemical index data, and blood pressure history data.

[0030] The aforementioned multidimensional data in this application may refer to multi-source data used to influence the prediction or assessment of cardiovascular and cerebrovascular diseases. This may include, but is not limited to, carotid artery imaging data (such as carotid ultrasound images), biochemical index data (such as low-density lipoprotein cholesterol LDL-C), blood pressure history data (such as history of hypertension), or other data used to influence the assessment of the user's cardiovascular and cerebrovascular diseases. This application does not impose further limitations or details on this.

[0031] This application does not limit the implementation method for acquiring the aforementioned multidimensional data. For example, it can be obtained directly from a local database, manually entered, or through a communication interface. Alternatively, an application (APP) can take a picture to recognize the test report and then use Optical Character Recognition (OCR) technology to parse and obtain biochemical indicator data, such as LDL-C data. This application does not limit the implementation method in this regard. In another possible embodiment, this application can respond to a request from a target user, asynchronously acquire multi-source data, and then preprocess the multi-source data to obtain the feature data corresponding to each of the multi-source data. The multi-source data and the multidimensional data correspond one-to-one, which will not be elaborated further here. In practical applications, to solve the system blocking problem caused by the difference in the acquisition speed of multi-source data, this application adopts an asynchronous processing framework based on message queues. In specific implementation, when this application receives a request from a target user, such as a request for cardiovascular and cerebrovascular risk assessment, the central scheduler of the system will generate a globally unique task identifier ID for the request. Subsequently, the scheduler can send data request information in parallel and asynchronously to different modules, such as the carotid artery imaging DICOM module, the clinical laboratory information management LIS module, and the electronic health record (EHR) module. Each request carries the aforementioned task identifier for collecting corresponding multidimensional data. For example, the DICOM module is used to collect carotid artery imaging data. The LIS module is used to collect biochemical indicator data, such as LDL-C data. The EHR module is used to collect blood pressure history data, such as hypertension history data. After receiving the corresponding request information, each module works independently and in parallel to obtain the raw multi-source data from the system. Then, each module preprocesses the aforementioned multi-source data stored locally to obtain the corresponding feature data. This preprocessing can refer to data processing pre-defined by the system according to actual conditions, which may include, but is not limited to, standardization processing, scoring calculation, or other custom processing, etc. This application does not impose further limitations or details on this.

[0032] For example, for carotid artery imaging data, this application can use the plaque segmentation ITK-SNAP algorithm to calculate the instability score of the carotid artery imaging data. The calculation formula is: Score = 0.3 × Area + 0.5 × Irregularity + 0.2 × Calcification Ratio. The instability score of the carotid artery imaging data can be a value between 1 and 10, and this application does not impose any restrictions on this. For biochemical index data, this application can perform unit statistical processing, such as processing LDL-C data from mmol / L to mg / dL, where 1 mmol / L = 38.67 mg / dL, and this application does not impose any restrictions on this. For blood pressure history data, this application can perform disease duration quantification, such as disease duration = current date - date of first diagnosis, etc., and this application does not impose any restrictions on this.

[0033] After preprocessing, each module can package the processed feature data and the task identifier into a message body and publish it to a unified middleware, such as a designated topic in Kafka or RabbitMQ. The weighted scoring engine can monitor the middleware in real time or periodically. It can aggregate multiple feature data from different sources belonging to the same task identifier based on the task identifier to obtain the aforementioned multidimensional data. The weighted scoring engine will only trigger a cardiovascular risk prediction or assessment for the target user after all three multidimensional data corresponding to a certain task identifier (such as carotid artery imaging data, biochemical index data, and blood pressure history data) have arrived or been acquired. In this way, the slow image processing will not block the fast acquisition and preprocessing of biochemical index data, maximizing the utilization of system resources. Loose coupling and scalability: The modules interact with each other through message queues and the scoring engine. The modules are independent of each other. In the future, adding new data sources (such as genomic data) only requires adding new processing modules without changing the core system architecture, thus enabling the system to have loose coupling and scalability. Message queues have persistence capabilities, so even if the scoring engine crashes briefly, the data will not be lost and can continue to be processed after a restart, thereby enhancing the reliability of the system.

[0034] S102. Based on the carotid artery imaging data, biochemical index data, and blood pressure history data in the multidimensional data, determine the weight coefficients corresponding to each of the multidimensional data, and the weight coefficients change with the changes in the multidimensional data.

[0035] This application can use a weight function that is pre-defined according to the actual needs of the system to calculate the weight coefficients corresponding to the above multidimensional data. For example, the specific calculation is shown in the following formula (1): Formula (1) Where i represents the i-th data in the multidimensional data. This represents the weight coefficient corresponding to the i-th data. This represents the clinical significance coefficient. This represents the history enhancement factor, such as the weight amplification factor under specific medical history conditions. This indicates a medical history indicator function. It is at least related to the blood pressure medical history data in the multidimensional data. Specifically, its value is 1 when the preset medical history conditions are met (such as the duration of the disease being greater than 10 years), and 0 otherwise. This application does not make any further limitations or details in this regard.

[0036] In practical applications, the above clinical significance coefficients This can refer to the fundamental importance of the corresponding multidimensional data, with values ​​ranging from 0 to 1, such as plaque instability. =0.9, etc. Alternatively, this application may also utilize a random forest algorithm to calculate feature importance instead of / as the aforementioned clinical significance coefficient. The calculation formula is: RF feature importance score / sum of all scores. This allows for dynamic importance allocation by combining individualized data, improving the diagnostic accuracy for patients with cardiovascular and cerebrovascular diseases. For example, the weight of plaque instability increases non-linearly with risk. This application will not elaborate further on this aspect. For example, please refer to... Figure 2 This is a schematic diagram illustrating the comparison of weighting coefficients provided in an embodiment of this application. For example... Figure 2 As shown, curve 1 represents the weighting coefficients corresponding to the patch instability data, and curve 2 gives the weighting coefficients corresponding to the LDL-C data.

[0037] S103. Based on the weight coefficients corresponding to each of the multidimensional data, perform cardiovascular and cerebrovascular risk prediction on the multidimensional data to obtain the corresponding prediction results. The prediction results include the risk level of the target user having cardiovascular and cerebrovascular disease and the corresponding diagnosis and treatment suggestions.

[0038] This application does not limit the specific implementation method of the above-mentioned cardiovascular and cerebrovascular risk prediction. For example, this application can perform normalization processing on the carotid artery imaging data, biochemical index data and blood pressure history data in the above-mentioned multidimensional data to obtain the processed data corresponding to each of the above-mentioned multidimensional data. Among them, the normalization function or processing formula corresponding to the normalization processing is shown in the following formula (2): Formula (2) in, This represents the i-th data point in the corresponding multidimensional data. This represents the minimum value in the corresponding multidimensional data. This represents the maximum value in the corresponding multidimensional data. For example, the range of LDL-C data is [70, 200]. The LDL-C data in the above multidimensional data is 158. Then the normalized LDL-C data g(158) = (158-70) / (200-70) = 0.677.

[0039] Next, this application performs a comprehensive risk prediction based on the weight coefficients and processed data corresponding to the above multidimensional data, and obtains the corresponding prediction results. The above prediction results may include a comprehensive risk score, the corresponding risk level, diagnostic and treatment recommendations, or other custom diagnostic results information, which this application does not limit or elaborate on. The calculation formula or scoring function corresponding to the above comprehensive risk prediction can be shown in the following formula (3): Formula (3) Wherein, S represents the comprehensive risk score. This application can determine the risk level of the target user suffering from cardiovascular and cerebrovascular diseases based on the range of the comprehensive risk score; for example, when S is less than 4.0, the risk level can be determined as low risk; when S is greater than or equal to 4 and less than 7, the risk level can be determined as medium risk; when S is greater than or equal to 7, the risk level can be determined as high risk, etc. This application does not impose further limitations on this.

[0040] The following describes some optional embodiments related to this application.

[0041] In some optional embodiments, after obtaining the above prediction results, this application can display a modal window, in which different colors are used to mark and display different risk levels. For example, when the above risk level is high-risk, this application can automatically pop up a modal window, requiring the doctor to confirm reading and record the treatment measures, and use a preset frequency to flash the above risk level, such as flashing red and displaying the word "high-risk". Optionally, it can also be accompanied by a continuous sound alarm to remind the target user that they are a high-risk cardiovascular and cerebrovascular patient, etc. This application does not limit or elaborate on this. The above diagnostic and treatment suggestions can be diagnostic or treatment suggestions for doctors, which may include, but are not limited to, for example (1) immediate examination: for example, it is recommended to repeat carotid ultrasound (to assess whether plaque rupture signs), electrocardiogram or myocardial enzyme spectrum within 24 hours. (2) consultation and referral: for example, the system automatically prompts "It is recommended to consult a cardiologist / neurologist immediately" or "It is recommended to assess the indications for vascular interventional treatment", etc. (3) Patient management: For example, suggestions such as "It is recommended to be hospitalized immediately" or "Increase the frequency of home blood pressure / blood glucose monitoring to 3 times a day".

[0042] When the above risk level is intermediate, this application can automatically pop up a modal window, requiring the doctor to confirm reading and record the treatment measures, displaying a stable yellow label and the word intermediate risk, etc. The above diagnostic and treatment recommendations can be diagnostic or treatment recommendations for doctors, which may include, but are not limited to, for example (1) optimizing the existing plan: for example, recommending a follow-up visit within 1-2 weeks, adjusting the existing drug dosage or type (such as increasing the intensity of statins from moderate to high), etc. (2) intensified lifestyle intervention: for example, the system provides specific recommendation texts, such as "strictly implement a low-sodium diet (<5g / day)" and "increase moderate-intensity aerobic exercise to 150 minutes per week", etc. (3) targeted examinations: for example, recommending a follow-up examination of biochemical indicators such as blood lipids, blood glucose, and homocysteine ​​within 1 month to assess the effectiveness of the current treatment, etc.

[0043] When the above risk level is low, this application can automatically pop up a modal window, displaying a green logo and low-profile text. The above diagnostic and treatment recommendations can be diagnostic or treatment recommendations for doctors, which may include, but are not limited to, for example: (1) Maintenance and prevention: affirming the effectiveness of the current treatment or lifestyle, and recommending to maintain the existing plan, etc. (2) Long-term risk management: for example, recommending "a comprehensive cardiovascular and cerebrovascular risk assessment once a year". (3) Health education: for example, providing links to educational materials such as "low-salt and low-fat diet" and "exercise guidance" for doctors to promote to patients.

[0044] It should be noted that the above diagnostic and treatment suggestions are merely examples and do not constitute limitations. They can be adjusted and set according to the actual needs of the system or the patient, and this application will not impose further limitations or details on this. It can be seen that this application achieves individualized allocation of indicator importance by calculating dynamic weight coefficients (or dynamic weight functions), thereby improving the identification rate of high-risk groups; by integrating data such as imaging, biochemistry, and medical history to generate a comprehensive risk score and obtain the corresponding risk level, it is beneficial to improve the accuracy of cardiovascular and cerebrovascular diagnosis.

[0045] To aid in understanding this application, an example is provided below. Assume a patient has a plaque stability score of 0.82, a preprocessed LDC-C score of 0.677, and a history enhancement factor corresponding to the duration of hypertension of 1.5. The weighting coefficients are assigned as shown in Table 1 below: Table 1

[0046] Based on Table 1 above, the contribution of plaque stability is 1.35 × 0.82 = 1.107, and the contribution of LDL-C is 0.9 × 0.677 = 0.609. Therefore, the overall risk score S = 1.107 + 0.609 = 1.716, which is at the medium-risk level. In contrast, the traditional scheme uses static weights. Assuming the weight coefficient for plaque stability is 0.8 and the weight coefficient for LDL-C is 0.5, the overall risk score is 0.82 × 0.8 + 0.677 × 0.5 = 1.028, which is at the low-risk level. Therefore, the scheme in this application, using dynamic weight coefficients, can more sensitively and accurately identify the risk level of a user suffering from cardiovascular and cerebrovascular diseases.

[0047] By implementing the embodiments of this application, multidimensional data is obtained, including carotid artery imaging data, biochemical index data, and blood pressure history data of the target user. Based on the carotid artery imaging data, biochemical index data, and blood pressure history data in the multidimensional data, a weight coefficient corresponding to each of the multidimensional data is determined, and the weight coefficient changes with the multidimensional data. Based on the weight coefficients corresponding to each of the multidimensional data, cardiovascular and cerebrovascular risk is predicted, and a corresponding prediction result is obtained. The prediction result includes the risk level of the target user having cardiovascular and cerebrovascular diseases and corresponding diagnostic and treatment recommendations. In this way, dynamic weight coefficients can be determined based on the individualized multidimensional data of the target user, and then the risk level of the target user having cardiovascular and cerebrovascular diseases and the diagnostic and treatment recommendations can be predicted and evaluated based on the dynamic weight coefficients, thereby effectively improving the comprehensiveness and accuracy of cardiovascular and cerebrovascular prediction. At the same time, it can also solve the technical problem that the prior art cannot perform comprehensive and accurate cardiovascular and cerebrovascular prediction and diagnosis.

[0048] Based on the above embodiments, please refer to Figure 3 This is a schematic diagram of the structure of a cardiovascular and cerebrovascular risk prediction device provided in an embodiment of this application. Figure 3 The illustrated device 300 can be applied in an electronic device, and the device may include an acquisition module 301 and a processing module 302, wherein: The acquisition module 301 is used to acquire multidimensional data, which includes the target user's carotid artery imaging data, biochemical index data, and blood pressure history data. The processing module 302 is used to determine the weight coefficients corresponding to each of the multidimensional data based on the carotid artery imaging data, biochemical index data, and blood pressure history data in the multidimensional data. The weight coefficients change with the changes in the multidimensional data. The processing module 302 is further configured to perform cardiovascular and cerebrovascular risk prediction on the multidimensional data based on the weight coefficients corresponding to each of the multidimensional data, and obtain the corresponding prediction results. The prediction results include the risk level of the target user having cardiovascular and cerebrovascular disease and the corresponding diagnosis and treatment recommendations.

[0049] In some embodiments, the processing module 302 is specifically used for: Based on the carotid artery imaging data, biochemical index data, and blood pressure history data in the multidimensional data, normalization processing is performed to obtain the processed data corresponding to each of the multidimensional data. Based on the weight coefficients corresponding to each of the multidimensional data and the processed data, a comprehensive risk prediction is performed to obtain the corresponding prediction results.

[0050] In some embodiments, the acquisition module 301 is specifically used for: In response to the request information from the target user, multi-source data is acquired asynchronously, and the multi-source data and the multi-dimensional data correspond one-to-one. The multi-source data is preprocessed to obtain the feature data corresponding to each of the multi-source data. The preprocessing includes at least standardization and scoring calculation. The feature data corresponding to each of the multiple sources are collected to obtain the multidimensional data.

[0051] In some embodiments, the request information carries a task identifier, and the multi-source data and the feature data corresponding to each of the multi-source data are obtained in parallel from different modules based on the task identifier. The acquisition module 301 is specifically used for: Based on the task identifier, the middleware aggregates and integrates the feature data corresponding to the multi-source data in the different modules to obtain the multi-dimensional data.

[0052] In some embodiments, the weighting coefficients corresponding to each of the multidimensional data include: Where i represents the i-th data in the multidimensional data. This represents the weight coefficient corresponding to the i-th data point. Indicates the clinical significance coefficient. Indicates the enhancement factor of medical history. This indicates a medical history indicator function. It is at least related to the blood pressure history data in the multidimensional data.

[0053] In some embodiments, The coefficients for calculating the importance of random forest features are obtained based on the i-th data in the multidimensional data.

[0054] In some embodiments, the processing module 302 is further configured to: Display a modal window, in which different risk levels are marked with different colors; and When the risk level is high, the risk level is displayed by flashing at a preset frequency and an audible alarm is triggered.

[0055] In some embodiments, the biochemical data includes low-density lipoprotein cholesterol data.

[0056] By implementing the embodiments of this application, the device described above can acquire multidimensional data, including carotid artery imaging data, biochemical index data, and blood pressure history data of a target user. Based on the carotid artery imaging data, biochemical index data, and blood pressure history data in the multidimensional data, a weight coefficient corresponding to each of the multidimensional data is determined, and the weight coefficient changes with the multidimensional data. Based on the weight coefficients corresponding to each of the multidimensional data, cardiovascular and cerebrovascular risk prediction is performed on the multidimensional data to obtain corresponding prediction results. The prediction results include the risk level of the target user having cardiovascular and cerebrovascular diseases and corresponding diagnostic and treatment recommendations. In this way, dynamic weight coefficients can be determined based on the individualized multidimensional data of the target user, and then the risk level of the target user having cardiovascular and cerebrovascular diseases and diagnostic and treatment recommendations can be predicted and evaluated based on the dynamic weight coefficients, thereby effectively improving the comprehensiveness and accuracy of cardiovascular and cerebrovascular prediction. At the same time, it can also solve the technical problem that the prior art cannot perform comprehensive and accurate cardiovascular and cerebrovascular prediction and diagnosis.

[0057] Please see Figure 4 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. For example... Figure 4 The electronic devices shown can be mobile phones, computers, digital broadcasting terminals, messaging devices, game consoles, tablets, medical devices, fitness equipment, personal digital assistants, etc.

[0058] Reference Figure 4 The electronic device 400 may include one or more of the following components: processing component 402, memory 404, power supply component 406, multimedia component 408, audio component 410, input / output interface 412, sensor component 414, and communication component 416.

[0059] Processing component 402 typically controls the overall operation of electronic device 400, such as operations associated with display, telephone calls, data communication, camera operation, and recording. Processing component 402 may include one or more processors 420 to execute instructions to complete all or part of the steps of the aforementioned cardiovascular risk prediction method. Furthermore, processing component 402 may include one or more modules to facilitate interaction between processing component 402 and other components. For example, processing component 402 may include a multimedia module to facilitate interaction between multimedia component 408 and processing component 402.

[0060] Memory 404 is configured to store various types of data to support the operation of electronic device 400. Examples of such data include instructions for any application or method operating on electronic device 400, contact data, phonebook data, messages, pictures, videos, etc. Memory 404 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk.

[0061] Power supply component 406 provides power to various components of electronic device 400. Power supply component 406 may include a power management system, one or more power supplies, and other components associated with generating, managing, and distributing power to electronic device 400.

[0062] Multimedia component 408 includes a screen that provides an output interface between the electronic device 400 and the user. In some embodiments, the screen may include a liquid crystal display (LCD) and a touch panel (TP). If the screen includes a touch panel, the screen may be implemented as a touchscreen to receive input signals from the user. The touch panel includes one or more touch sensors to sense touches, swipes, and gestures on the touch panel. The touch sensors may sense not only the boundaries of the touch or swipe action but also the duration and pressure associated with the touch or swipe operation. In some embodiments, multimedia component 408 includes a front-facing camera and / or a rear-facing camera. When the electronic device 400 is in an operating mode, such as a shooting mode or a video mode, the front-facing camera and / or the rear-facing camera may receive external multimedia data. Each front-facing camera and rear-facing camera may be a fixed optical lens system or have focal length and optical zoom capabilities.

[0063] Audio component 410 is configured to output and / or input audio signals. For example, audio component 410 includes a microphone (MIC) configured to receive external audio signals when electronic device 400 is in an operating mode, such as call mode, recording mode, and voice recognition mode. The received audio signals may be further stored in memory 404 or transmitted via communication component 416. In some embodiments, audio component 410 also includes a speaker for outputting audio signals.

[0064] Input / output interface 412 provides an interface between processing component 402 and peripheral interface modules, which may be keyboards, click wheels, buttons, etc. These buttons may include, but are not limited to, home buttons, volume buttons, start buttons, and lock buttons.

[0065] Sensor assembly 414 includes one or more sensors for providing state assessments of various aspects of electronic device 400. For example, sensor assembly 414 may detect the on / off state of electronic device 400, the relative positioning of components such as the display and keypad of electronic device 400, changes in position of electronic device 400 or a component of electronic device 400, the presence or absence of user contact with electronic device 400, orientation or acceleration / deceleration of electronic device 400, and temperature changes of electronic device 400. Sensor assembly 414 may include a proximity sensor configured to detect the presence of nearby objects without any physical contact. Sensor assembly 414 may also include a light sensor, such as a CMOS or CCD image sensor, for use in imaging applications. In some embodiments, sensor assembly 414 may also include an accelerometer, gyroscope, magnetometer, pressure sensor, or temperature sensor.

[0066] Communication component 416 is configured to facilitate wired or wireless communication between electronic device 400 and other devices. Electronic device 400 can access wireless networks based on communication standards, such as WiFi, 2G, or 3G, or combinations thereof. In one exemplary embodiment, communication component 416 receives broadcast signals or broadcast-related information from an external broadcast management system via a broadcast channel. In one exemplary embodiment, communication component 416 also includes a near-field communication (NFC) module to facilitate short-range communication. For example, the NFC module may be implemented based on radio frequency identification (RFID) technology, Infrared Data Association (IrDA) technology, ultra-wideband (UWB) technology, Bluetooth (BT) technology, and other technologies.

[0067] In an exemplary embodiment, the electronic device 400 may be implemented by one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field-programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors, or other electronic components to perform the above-described cardiovascular and cerebrovascular risk prediction method.

[0068] Understandably, the processor 420 in this application embodiment can be an integrated circuit chip with signal processing capabilities. During implementation, each step of the above method embodiment can be completed by integrated logic circuits in the processor's hardware or by instructions in software form. The processor described above can be a general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components.

[0069] Understandably, the memory 404 in the embodiments of this application can be volatile memory or non-volatile memory, or may include both volatile and non-volatile memory. The non-volatile memory can be read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), or flash memory. The volatile memory can be random access memory (RAM), which is used as an external cache. By way of example, but not limitation, many forms of RAM are available, such as static random access memory (SRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDRSDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous linked dynamic random access memory (SLDRAM), and direct rambus RAM (DR RAM). It should be noted that the memory used in the systems and methods described herein is intended to include, but is not limited to, these and any other suitable types of memory.

[0070] In an exemplary embodiment, a non-transitory computer-readable storage medium including instructions is also provided, such as a memory 404 including instructions, which can be executed by a processor 420 of an electronic device 400 to complete the aforementioned upper-level cardiovascular and cerebrovascular risk prediction method. For example, the non-transitory computer-readable storage medium may be a ROM, random access memory (RAM), CD-ROM, magnetic tape, floppy disk, and optical data storage device, etc.

[0071] The aforementioned device can be a standalone electronic device or a part of a standalone electronic device. For example, in one embodiment, the device can be an integrated circuit (IC) or a chip, wherein the integrated circuit can be a single IC or a collection of multiple ICs; the chip can include, but is not limited to, the following types: GPU (Graphics Processing Unit), CPU (Central Processing Unit), FPGA (Field Programmable Gate Array), DSP (Digital Signal Processor), ASIC (Application Specific Integrated Circuit), SOC (System on Chip), etc. The aforementioned integrated circuit or chip can be used to execute executable instructions (or code) to implement the aforementioned cardiovascular and cerebrovascular risk prediction method. The executable instructions can be stored in the integrated circuit or chip or obtained from other devices or equipment. For example, the integrated circuit or chip includes a processor, memory, and an interface for communicating with other devices. The executable instructions can be stored in the memory, and when the executable instructions are executed by the processor, the above-mentioned cardiovascular and cerebrovascular risk prediction method can be implemented; or, the integrated circuit or chip can receive the executable instructions through the interface and transmit them to the processor for execution to implement the above-mentioned cardiovascular and cerebrovascular risk prediction method.

[0072] This application embodiment can divide the electronic device into functional modules according to the above method embodiment. For example, each function can be assigned to a separate module, or two or more functions can be integrated into a processing module. The integrated module can be implemented in hardware. It should be noted that the module division in this embodiment is illustrative and only represents one logical functional division. In actual implementation, there may be other division methods. When dividing each functional module according to its corresponding function, the vehicle may include a processing module and a communication module, etc.

[0073] It should be noted that all relevant content of each step involved in the above method embodiments can be referenced from the functional description of the corresponding functional module, and will not be repeated here. The electronic device provided in this embodiment is used to execute the above-described cardiovascular and cerebrovascular risk prediction method, and therefore can achieve the same effect as the above-described implementation method.

[0074] In another exemplary embodiment, a computer program product is also provided, the computer program product comprising a computer program executable by a programmable device, the computer program having a code portion for performing the above-described cardiovascular and cerebrovascular risk prediction method when executed by the programmable device.

[0075] It should be noted that the descriptions of the above embodiments of storage media, devices, and equipment are similar to the descriptions of the above method embodiments, and have similar beneficial effects. For technical details not disclosed in the embodiments of storage media, devices, and equipment of this application, please refer to the descriptions of the method embodiments of this application for understanding.

[0076] Other embodiments of this application will readily occur to those skilled in the art upon consideration of the specification and practice of this application. This application is intended to cover any variations, uses, or adaptations of this application that follow the general principles of this application and include common knowledge or customary techniques in the art not disclosed in this application. The specification and embodiments are to be considered exemplary only, and the true scope and spirit of this application are indicated by the following claims.

[0077] The above description is merely a preferred embodiment of this application and is not intended to limit this application. Any modifications or equivalent substitutions made within the spirit and principles of this application should be included within the protection scope of this application.

Claims

1. A method for predicting cardiovascular and cerebrovascular risks, characterized in that, include: Acquire multidimensional data, including the target user's carotid artery imaging data, biochemical index data, and blood pressure history data; Based on the carotid artery imaging data, biochemical index data, and blood pressure history data in the multidimensional data, the weight coefficients corresponding to each of the multidimensional data are determined, and the weight coefficients change with the changes in the multidimensional data; Based on the weight coefficients corresponding to each of the multidimensional data, the cardiovascular and cerebrovascular risks of the multidimensional data are predicted to obtain the corresponding prediction results. The prediction results include the risk level of the target user having cardiovascular and cerebrovascular diseases and the corresponding diagnosis and treatment suggestions.

2. The method according to claim 1, characterized in that, The method of predicting cardiovascular and cerebrovascular risks based on the weight coefficients corresponding to each of the multidimensional data to obtain the corresponding prediction results includes: Based on the carotid artery imaging data, biochemical index data, and blood pressure history data in the multidimensional data, normalization processing is performed to obtain the processed data corresponding to each of the multidimensional data. Based on the weight coefficients corresponding to each of the multidimensional data and the processed data, a comprehensive risk prediction is performed to obtain the corresponding prediction results.

3. The method according to claim 1, characterized in that, The acquisition of multidimensional data includes: In response to the request information from the target user, multi-source data is acquired asynchronously, and the multi-source data and the multi-dimensional data correspond one-to-one. The multi-source data is preprocessed to obtain the feature data corresponding to each of the multi-source data. The preprocessing includes at least standardization and scoring calculation. The feature data corresponding to each of the multiple sources are collected to obtain the multidimensional data.

4. The method according to claim 3, characterized in that, The request information carries a task identifier. The multi-source data and the corresponding feature data of each multi-source data are obtained in parallel from different modules based on the task identifier. The process of aggregating the feature data corresponding to each of the multi-source data to obtain the multi-dimensional data includes: Based on the task identifier, the middleware aggregates and integrates the feature data corresponding to the multi-source data in the different modules to obtain the multi-dimensional data.

5. The method according to claim 1, characterized in that, The weighting coefficients corresponding to each of the multidimensional data include: Where i represents the i-th data in the multidimensional data. This represents the weight coefficient corresponding to the i-th data point. The clinical significance coefficient is represented by the coefficient of significance. Indicates the enhancement factor of medical history. This indicates a medical history indicator function. It is at least related to the blood pressure history data in the multidimensional data.

6. The method according to claim 5, characterized in that, The coefficients for calculating the importance of random forest features are obtained based on the i-th data in the multidimensional data.

7. The method according to claim 1, characterized in that, The method of predicting cardiovascular and cerebrovascular risks based on the weight coefficients corresponding to each of the multidimensional data, and obtaining the corresponding prediction results, further includes: Display a modal window, in which different risk levels are marked with different colors; and When the risk level is high, the risk level is displayed by flashing at a preset frequency and an audible alarm is triggered.

8. The method according to any one of claims 1-7, characterized in that, The biochemical data includes low-density lipoprotein cholesterol data.

9. A cardiovascular and cerebrovascular risk prediction device, characterized in that, include: The acquisition module is used to acquire multidimensional data, which includes the target user's carotid artery imaging data, biochemical index data, and blood pressure history data. The processing module is used to determine the weight coefficients corresponding to each of the multidimensional data based on the carotid artery imaging data, biochemical index data, and blood pressure history data in the multidimensional data, wherein the weight coefficients change with the changes in the multidimensional data; The processing module is further configured to perform cardiovascular and cerebrovascular risk prediction on the multidimensional data based on the weight coefficients corresponding to each of the multidimensional data, and obtain the corresponding prediction results. The prediction results include the risk level of the target user having cardiovascular and cerebrovascular disease and the corresponding diagnosis and treatment recommendations.

10. An electronic device, characterized in that, include: processor; A memory for storing processor-executable instructions; wherein the processor is configured to execute the executable instructions to implement the steps of the method according to any one of claims 1 to 7.

Images