A method for constructing a medical information data system

Abstract

The present invention relates to the field of medical information data processing technology, and in particular to a method for constructing a medical information data system. The content includes: collecting and preprocessing multi-source medical information data from different medical data sources, intelligently processing the preprocessed multi-source medical information data, analyzing the multi-source medical information data after intelligent processing using a spatiotemporal coupling analysis algorithm, and proposing diagnosis and treatment suggestions based on the analysis results; encrypting and storing the multi-source medical information data after intelligent processing, the analysis results and diagnosis and treatment suggestions, and defining the data range and permissions accessible to users, limiting different users to access only the data they have permission to view. The technical problems of the inability to accurately integrate and process multi-source heterogeneous medical information data and the low security in the medical data processing process are solved in the construction of the medical information data system.

Description

Technical Field

[0001] The present invention relates to the technical field of medical information data processing, and in particular to a method for constructing a medical information data system. Background Art

[0002] With the in-depth application of information technology in the medical field, the types and sources of medical data are becoming increasingly diversified, showing the coexistence of structured, semi-structured and unstructured data, such as electronic medical records, laboratory test results, diagnostic reports, imaging data, etc. These medical data have the characteristics of large data volume, complex types, and diverse formats, which makes the medical information data system face huge challenges in processing these multi-source heterogeneous data. At the same time, data security and privacy protection issues are also receiving increasing attention, especially in the process of medical data processing involving sensitive patient information. How to ensure the safe storage and transmission of data and how to prevent unauthorized access have become important issues that must be solved in medical information data systems.

[0003] In summary, in the construction of medical information data systems, there are problems such as the inability to accurately integrate and process multi-source heterogeneous medical information data and low security in the medical data processing process. Summary of the invention

[0004] The present invention provides a method for constructing a medical information data system to solve the technical problems of the inability to accurately integrate and process multi-source heterogeneous medical information data and the low security in the medical data processing process during the construction of the medical information data system.

[0005] A method for constructing a medical information data system comprises the following steps:

[0006] S1. Collect and preprocess multi-source medical information data from different medical data sources, perform intelligent processing on the pre-processed multi-source medical information data, analyze the multi-source medical information data after intelligent processing using a spatiotemporal coupling analysis algorithm, and make diagnosis and treatment recommendations based on the analysis results;

[0007] S2. Encrypt and store the intelligently processed multi-source medical information data, analysis results, and treatment recommendations, and define the data scope and permissions that users can access, limiting different users to only access data that they are authorized to view.

[0008] Preferably, the S1 specifically includes:

[0009] The pre-processed multi-source medical information data is intelligently processed using a hierarchical recursive polymorphic medical information processing algorithm.

[0010] Preferably, the S1 specifically includes:

[0011] In the process of implementing the hierarchical recursive polymorphic medical information processing algorithm, the pre-processed multi-source medical information data is mapped based on hierarchical recursive processing to obtain a high-dimensional feature representation after mapping processing; the hierarchical recursive processing formula is:

[0012] ,

[0013] in, It is The output vector after layer recursive processing represents the high-dimensional feature representation after mapping processing; is a nonlinear activation function; It is The data source is in The weight matrix during layer recursive processing; It is The data source is in Output vector after layer recursive processing; is the total number of data sources; is the coupling coefficient, indicating the When recursively processing the layer Data source for Contribution of data sources; After preprocessing Medical information data from various data sources; is the base of natural logarithms; It is When recursively processing the layer Time-related tuning parameters for each data source; is a time variable.

[0014] Preferably, the S1 specifically includes:

[0015] After hierarchical recursive processing, the high-dimensional feature representation after mapping is coupled and analyzed through the polymorphic coupling method to obtain multi-source medical information data after intelligent processing. The specific formula is as follows:

[0016] ,

[0017] in, After intelligent processing Medical information data from various data sources; It is The total number of all features after hierarchical recursive processing of the data sources; It is Data source The linear weight coefficient of each feature; It is Data source The feature in The recursive processing results of the layer; It is Data source Adaptive adjustment coefficient of the sinusoidal function of the feature; It is Data source Adaptive adjustment coefficients for the logarithmic transformation of features; It is Data source Features and The coupling coefficient between the features; It is Data source The feature in The recursive processing result of the layer.

[0018] Preferably, the S1 specifically includes:

[0019] The specific implementation formula of the time-space coupling analysis algorithm is as follows:

[0020] ,

[0021] in, It's time and spatial location The health quantitative status under represents the analysis result; It is Data source The coupling weight of each feature; is the Gaussian decay function; It is Data source The time diffusion coefficient of each feature; is the current time point; It is Data source The timestamp of each feature; is the spatial attenuation function; is the current spatial position; It is The spatial position corresponding to each feature, the spatial position is the patient's geographical location or the location where medical information data is collected; is the weight of nonlinear spatiotemporal coupling; It is The spatial position corresponding to each feature; It is Data source Features in time The value is taken from the first Medical information data from various data sources ; is the total number of data sources.

[0022] Preferably, the S2 specifically includes:

[0023] The intelligently processed medical information data, intelligent analysis results and treatment recommendations are converted into data to be encrypted, and the converted data to be encrypted is encrypted through multi-layer dynamic adaptive hash encryption and recursive nonlinear mapping algorithm.

[0024] Preferably, the S2 specifically includes:

[0025] In the process of implementing multi-layer dynamic adaptive hash encryption and recursive nonlinear mapping algorithm, the data to be encrypted is divided into different data blocks, and each data block is subjected to multi-layer dynamic hash mapping processing to obtain the hash encrypted result.

[0026] Preferably, the S2 specifically includes:

[0027] After completing the multi-layer dynamic hash mapping process, the hash encryption result is used as the input of the recursive nonlinear encryption mapping to generate the recursive encryption result. The specific formula is as follows:

[0028] ,

[0029] in, is a recursive encryption function; Indicates the result of hash encryption No. The result after recursive encryption; It is Tuning parameters in sub-recursive encryption; It is Parameters controlling decay in recursive encryption; Indicates that the result of the last recursive encryption is used as the input for the next one; It is Parameters that control the amplitude of the cosine function in recursive encryption; It is In the recursive encryption, control The slope of .

[0030] Preferably, the S2 specifically includes:

[0031] Based on the result of hash encryption, a dynamic key generation mechanism is introduced to generate dynamic keys for different data blocks; and the result of recursive encryption is encrypted with the dynamic key and then stored in blocks.

[0032] The beneficial effects of the technical solution of the present invention are:

[0033] 1. The polymorphic coupling method is adopted, combined with nonlinear transformation and adaptive adjustment mechanism, which can fully explore the complex nonlinear interaction relationship between features after hierarchical recursive processing, improve the depth and accuracy of data analysis, and adaptively adjust the mutual influence of features through hierarchical recursive processing, providing a more accurate basis for subsequent diagnosis and treatment recommendations.

[0034] 2. Through the spatiotemporal coupling analysis algorithm, it is possible to combine the patient's historical medical information data and spatial location to accurately analyze the patient's health status and provide patients with personalized diagnosis and treatment recommendations.

[0035] 3. It adopts multi-layer dynamic adaptive hash encryption and recursive non-linear mapping algorithm to ensure high security of data during storage and transmission, and ensures that even if part of the encrypted data is cracked, the overall data cannot be decrypted, thereby improving data security; through the dynamic key generation mechanism, it can ensure that the key for each encryption changes with the data. Even if the same data is encrypted at different times, the key will be different, which greatly enhances the protection of encryption and reduces the potential security risks brought by traditional fixed keys. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] Figure 1 This is a flow chart of a method for constructing a medical information data system described in the present invention. DETAILED DESCRIPTION

[0037] In order to further explain the technical means and effects adopted by the present invention to achieve the predetermined invention purpose, the technical scheme in the embodiment of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiment of the present invention. Obviously, the described embodiment is only a part of the embodiment of the present invention, not all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0038] Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.

[0039] The following is a detailed description of a method for constructing a medical information data system provided by the present invention in conjunction with the accompanying drawings.

[0040] Refer to the attached Figure 1 , which shows a flow chart of a method for constructing a medical information data system provided by an embodiment of the present invention, the method comprising the following steps:

[0041] S1. Collect and preprocess multi-source medical information data from different medical data sources, perform intelligent processing on the pre-processed multi-source medical information data, analyze the multi-source medical information data after intelligent processing using a spatiotemporal coupling analysis algorithm, and make diagnosis and treatment recommendations based on the analysis results;

[0042] Multi-source medical information data is collected from different medical data sources, such as electronic medical records, diagnostic reports, laboratory test results, etc. The multi-source medical information data includes structured, semi-structured and unstructured data. The multi-source medical information data is preprocessed by methods such as denoising, cleaning, and standardization to obtain preprocessed multi-source medical information data. The above preprocessing methods are technical means well known to those skilled in the art and will not be elaborated here. The features contained in each data source in the preprocessed multi-source medical information data can be two-dimensional (such as electronic medical records and laboratory result data) or high-dimensional (such as three-dimensional imaging data). The preprocessed multi-source medical information data is intelligently processed using a hierarchical recursive polymorphic medical information processing algorithm. The specific implementation process is as follows:

[0043] When processing preprocessed multi-source heterogeneous medical information data, that is, preprocessed multi-source medical information data, firstly, the preprocessed medical information data of each data source is mapped to a unified high-dimensional feature space. In the mapping process, due to the significant differences in the features of different data sources, hierarchical recursive processing is required. At the same time, in order to ensure that the hierarchical recursive processing process can capture the dynamic changes of time and handle the interaction between the features of different data sources after preprocessing, the hierarchical recursive processing formula consists of linear combination, nonlinear mapping and time dependency. The hierarchical recursive processing formula is:

[0044] ,

[0045] in, It is The output vector after layer recursive processing represents the The data source is in Feature representation after layer recursive processing, that is, high-dimensional feature representation after mapping processing; It is a nonlinear activation function, which is used to introduce nonlinear processing. or ; It is The data source is in The weight matrix during layer recursive processing; It is The data source is in The output vector after recursive processing of the previous layer is the feature information extracted after recursive processing of the previous layer; is the total number of data sources; is the coupling coefficient, indicating the When recursively processing the layer Data source for Contribution of data sources; After preprocessing Medical information data from various data sources; is a time dependency; is the base of natural logarithms; It is When recursively processing the layer The time-related adjustment parameters of each data source control the influence of time factors in recursive processing and reflect the influence of time factors on the changes in data source characteristics. It is a time variable, which is used to capture the dynamic changes of medical data over time.

[0046] After layered recursive processing, the final output vector , contains the feature information of all data sources, and makes adaptive adjustments with the dynamic changes over time, laying the foundation for the subsequent polymorphic coupling processing of features; among them, is the total number of recursive layers, defined according to the specific scenario.

[0047] After completing the hierarchical recursive processing, it is necessary to perform coupling analysis on the high-dimensional feature representation after mapping. The feature representation corresponding to each data source It contains a combination of different medical features in order to explore the complex nonlinear interactions between features. It uses a polymorphic coupling method, combined with nonlinear transformation and adaptive adjustment mechanism, to generate new feature representations. The polymorphic coupling formula of the feature is:

[0048] ,

[0049] in, is the characteristic vector after polymorphic coupling, representing the The final feature representation of the data source, that is, the first Medical information data from various data sources; It is The total number of all features after hierarchical recursive processing of the data sources; It is Data source The linear weight coefficient of each feature; It is Data source The feature in The recursive processing results of the layer; It is Data source Adaptive adjustment coefficient of the sinusoidal function of each feature to control the influence of sinusoidal nonlinear transformation; It is Data source Adaptive adjustment coefficients for the logarithmic transformation of features; It is Data source Features and The coupling coefficient between the features controls the interaction between different features; It is Data source The feature in The recursive processing result of the layer.

[0050] The multi-source medical information data after intelligent processing is analyzed using the spatiotemporal coupling analysis algorithm, and diagnosis and treatment suggestions are put forward based on the analysis results. The specific implementation process is as follows:

[0051] Based on intelligent processing Medical information data from various data sources , combined with the patient's historical medical information data and spatial location, such as the patient's geographical location or the location where the medical information data was collected, to analyze future health trends. The time-space coupling analysis formula is:

[0052] ,

[0053] in, It's time and spatial location The quantitative health status under the condition of specific time and space, that is, the analysis results, reflects the health results under specific time and space conditions; It is Data source The coupling weight of a feature indicates the effect of this feature on the analysis results. The contribution degree of each feature is different, and the coupling weight of each feature is different, reflecting its influence on the health status; is a Gaussian decay function, which is used to capture the Data source The change of a feature in the time dimension; It is Data source The time diffusion coefficient of each feature controls the speed of time decay; is the current time point; It is Data source The timestamp of a feature indicates the time point of the feature in the historical medical information data; is the spatial attenuation function, which indicates the influence of spatial distance on the analysis results; is the current spatial position; It is The spatial location corresponding to each feature can be the patient's geographical location or the location where medical information data is collected; is the weight of nonlinear spatiotemporal coupling, indicating the Data source The contribution of each feature to the analysis results is used to adjust the influence of the feature in complex spatiotemporal coupling; It is The spatial position corresponding to each feature; It is Data source Features in time The value is taken from the first Medical information data from various data sources .

[0054] Finally, the threshold is preset based on expert experience. , , and analyze the results Compared with the preset threshold, When , it is a low risk interval, indicating that the patient is in a healthy state and has no risk of serious disease in the short term; When , it is a medium risk interval, indicating that the patient has certain health risks and preventive measures should be taken; when When the patient's health status is higher than the normal range, it is a high-risk range, indicating that the patient's health status is at a high risk and further examination and intervention are required. At the same time, the doctor will generate diagnosis and treatment recommendations based on the patient's risk range. When the patient is in a low-risk range, it means that the patient is in good health, but regular physical examinations and daily health monitoring are still required. Specifically: a comprehensive physical examination is conducted once a year, focusing on the cardiovascular system, metabolic function, etc., to ensure that the health status is maintained in good condition; maintain the current healthy lifestyle, including a reasonable diet, moderate exercise and adequate sleep; continue to monitor basic health indicators (such as blood pressure, blood sugar, blood lipids), and share the monitored results with the doctor regularly, especially for patients with a family history of genetic diseases. When in the medium-risk range, preventive intervention and lifestyle adjustments are required. Specifically: increase the frequency of physical examinations. It is recommended to have a detailed physical examination every 6 months, especially for special examinations of current risk factors, such as heart health, kidney function and blood sugar levels. When in a high-risk range, urgent examinations and treatment interventions are required. Specifically: immediate in-depth physical examinations and special examinations are conducted, focusing on specific health problems related to high risks; for example, patients with a high risk of cardiovascular disease need to undergo in-depth examinations such as cardiac ultrasound and coronary angiography.

[0055] S2. Encrypt and store the intelligently processed multi-source medical information data, analysis results, and treatment recommendations, and define the data scope and permissions accessible to users, limiting different users to access only the data they are authorized to view.

[0056] First, the multi-source medical information data, analysis results and treatment recommendations after intelligent processing are converted into data forms to be encrypted. For example, for text data encryption of treatment recommendations, the text data is converted into a binary data stream to adapt to the input of the encryption algorithm; such as data encryption of multi-source medical information data after intelligent processing, the data is directly converted into binary format to adapt to the input of the encryption algorithm.

[0057] The converted data to be encrypted is encrypted through multi-layer dynamic adaptive hash encryption and recursive non-linear mapping algorithm. The multi-layer dynamic adaptive hash encryption and recursive non-linear mapping algorithm ensures that even if part of the encryption result is cracked, the overall data cannot be decrypted through the combination of multi-layer dynamic hash mapping and recursive non-linear encryption mapping. The specific implementation process is as follows:

[0058] First, in order to reduce the amount of data for a single encryption target and enhance the ability to resist partial data leakage, the data to be encrypted is divided into data blocks, each of which represents a part of the data to be encrypted, ensuring that when a single data block is leaked, other parts of the data to be encrypted cannot be decrypted because they are encrypted independently.

[0059] Furthermore, multi-layer dynamic adaptive hash encryption is performed for each part of the data to be encrypted, and the data to be encrypted is converted into a hash value of a fixed length through a multi-layer hash mapping function. The specific formula is as follows:

[0060] ,

[0061] in, It is The layer hash mapping function is Data blocks The result of hash mapping, that is, the result after hash encryption; It is The layer hash mapping function is Data blocks The result of hash mapping recursively depends on the output of the previous layer; It is a data block Timestamp is used to introduce time dynamics and ensure that each encryption is different; It is The adaptive coefficient of the layer is used to adjust the complexity of the hash map; It is The hash transformation adjustment parameters of the layer hash mapping function control the frequency of the cosine function; It is The specific hash mapping function of the layer is randomly selected, such as SHA-256, SHA-512 and other hash functions; in the above multi-layer dynamic hash mapping processing, since the hash mapping result of each layer depends on the output of the previous layer and contains time, data content of the data block and adaptive coefficient, the hash mapping result is extremely complex and difficult to crack.

[0062] After completing the multi-layer dynamic hash mapping process, the hash mapping result is used as the input of the recursive nonlinear encryption mapping to generate the recursive encrypted result. The specific formula is as follows:

[0063] ,

[0064] in, is a recursive encryption function; Indicates the result of hash encryption No. The result after recursive encryption; It is The adjustment parameters in the recursive encryption control the offset of the internal data of the sine function and affect the amplitude of the result after recursive encryption; It is The parameters that control attenuation in recursive encryption control the slope of the exponential decay function, affecting the decay speed of the data and ensuring that the result after recursive encryption does not increase infinitely; Indicates that the result of the last recursive encryption is used as the input for the next one, ensuring the complexity of each encryption superposition; It is In the recursive encryption, the parameters of the cosine function amplitude are controlled to increase the nonlinear perturbation of the result after recursive encryption; It is In the recursive encryption, control Function (here Function refers to ) slope, affecting The smoothness of the function in the data transformation process.

[0065] Furthermore, in order to enhance data security, a dynamic key generation mechanism is introduced. Unlike traditional static keys, dynamic keys are not generated before encryption begins, but are recursively generated during the encryption process based on data changes. Dynamic keys are not only related to the data to be encrypted, but also closely related to the intermediate results of multi-layer dynamic adaptive hash encryption. The generation process of dynamic keys depends on the hash mapping results and the data content of the data block. The formula is as follows:

[0066] ,

[0067] in, It is Data blocks Dynamic key of It is Layer control Function (here Function refers to )’s slope coefficient; It is the total number of layers of dynamic adaptive hash encryption; the adaptive characteristic of the dynamic key generation mechanism is that the key changes with the change of the data block and the hash mapping result, ensuring the uniqueness of each encryption process. Even if it is the same data block, the key will be different when encrypted at different times, which increases the security and protection of the data.

[0068] Finally, the recursively encrypted result is encrypted using a dynamic key through an existing encryption function and then stored in blocks.

[0069] Ensure that different users can only access data that they have permission to view. Based on the existing role-based permission control mechanism, define the data scope and permissions that they can access, limit user access rights, and ensure the security of stored data. The details are as follows:

[0070] Doctors: They have the highest authority and can access all patients' data, including intelligently processed multi-source medical information data, analysis results, and diagnosis and treatment recommendations.

[0071] Nurse: Has medium authority and can only access basic data and nursing recommendations for some patients, but cannot view detailed diagnosis and treatment plans.

[0072] Patients: Can only access their own treatment recommendations and basic information, and cannot view other patients' data.

[0073] Administrator: Responsible for managing user permissions, but cannot directly view the data of specific patients.

[0074] In summary, a method for constructing a medical information data system has been completed.

[0075] The order of the embodiments of the invention is for description only and does not represent the advantages and disadvantages of the embodiments. The processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0076] The various embodiments in this specification are described in a progressive manner, and the same or similar parts between the various embodiments can be referenced to each other, and each embodiment focuses on the differences from other embodiments.

[0077] The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the above embodiments, those skilled in the art should understand that the technical solutions described in the above embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention, and should be included in the protection scope of the present invention.

Claims

1. A method for constructing a medical information data system. It is characterized in that The following steps are involved: S1. Collect and preprocess multi-source medical information data from different medical data sources, use a hierarchical recursive polymorphic medical information processing algorithm to intelligently process the preprocessed multi-source medical information data, and in the process of implementing the hierarchical recursive polymorphic medical information processing algorithm, perform mapping processing based on hierarchical recursive processing on the preprocessed multi-source medical information data to obtain a high-dimensional feature representation after mapping processing; The hierarchical recursive processing formula is: ， in, It is The output vector after layer recursive processing represents the high-dimensional feature representation after mapping processing; is a nonlinear activation function; It is The data source is in The weight matrix during layer recursive processing; It is The data source is in Output vector after layer recursive processing; is the total number of data sources; is the coupling coefficient, indicating the When recursively processing the layer Data source for Contribution of data sources; After preprocessing Medical information data from various data sources; is the base of natural logarithms; It is When recursively processing the layer Time-related tuning parameters for each data source; is a time variable; After hierarchical recursive processing, the high-dimensional feature representation after mapping is coupled and analyzed through the polymorphic coupling method to obtain multi-source medical information data after intelligent processing. The specific formula is as follows: ， in, After intelligent processing Medical information data from various data sources; It is The total number of all features after hierarchical recursive processing of the data sources; It is Data source The linear weight coefficient of each feature; It is Data source The feature in The recursive processing results of the layer; It is Data source Adaptive adjustment coefficient of the sinusoidal function of the feature; It is Data source Adaptive adjustment coefficients for the logarithmic transformation of features; It is Data source Features and The coupling coefficient between the features; It is Data source The feature in The recursive processing results of the layer; The multi-source medical information data after intelligent processing is analyzed using the spatiotemporal coupling analysis algorithm, and diagnosis and treatment recommendations are made based on the analysis results; the specific implementation formula of the spatiotemporal coupling analysis algorithm is as follows: ， in, It's time and spatial location The health quantitative status under represents the analysis result; It is Data source The coupling weight of each feature; is the Gaussian decay function; It is Data source The time diffusion coefficient of each feature; is the current time point; It is Data source The timestamp of the feature; is the spatial attenuation function; is the current spatial position; It is The spatial position corresponding to each feature, the spatial position is the patient's geographical location or the location where medical information data is collected; is the weight of nonlinear spatiotemporal coupling; It is The spatial position corresponding to each feature; It is Data source Features in time The value is taken from the first Medical information data from various data sources ; is the total number of data sources; S2. Encrypt and store the intelligently processed multi-source medical information data, analysis results, and treatment recommendations, and define the data scope and permissions that users can access, limiting different users to only access data that they are authorized to view.

2. The method for constructing a medical information data system according to claim 1, It is characterized in that The S2 specifically includes: The medical information data, intelligent analysis results and treatment recommendations after intelligent processing are converted into data forms to be encrypted, and the converted data to be encrypted is encrypted through multi-layer dynamic adaptive hash encryption and recursive nonlinear mapping algorithm. In the process of implementing the multi-layer dynamic adaptive hash encryption and recursive nonlinear mapping algorithm, the data to be encrypted is divided into different data blocks, and each data block is subjected to multi-layer dynamic hash mapping processing to obtain the result after hash encryption; after completing the multi-layer dynamic hash mapping processing, the result after hash encryption is used as the input of the recursive nonlinear encryption mapping to generate the result after recursive encryption. The specific formula is as follows: ， in, is a recursive encryption function; Indicates the result of hash encryption; No. The result after recursive encryption; It is Tuning parameters in sub-recursive encryption; It is Parameters controlling decay in recursive encryption; Indicates that the result of the last recursive encryption is used as the input for the next one; It is Parameters that control the amplitude of the cosine function in recursive encryption; It is In the recursive encryption, control The slope of .

3. The method for constructing a medical information data system according to claim 2, It is characterized in that The S2 specifically includes: Based on the result of hash encryption, a dynamic key generation mechanism is introduced to generate dynamic keys for different data blocks; and the result of recursive encryption is encrypted with the dynamic key and then stored in blocks.

Images