Medical data comprehensive utilization method and system based on trusted data space

Abstract

The invention provides a medical data comprehensive utilization method and system based on a credible data space, and the method comprises the steps: storing standard medical data generated by preprocessing initial medical data obtained from a plurality of data sources into the credible data space, and placing high-sensitivity invisible data into a sandbox; a first medical analysis model is generated according to data circulation information of circulation of the standard medical data and then is placed in the sandbox, and a standard analysis result and desensitized sample data are generated by performing model calculation on the high-sensitivity invisible data; and inputting the desensitized sample data into a second medical data analysis model for calculation to obtain a prediction analysis result, comparing the prediction analysis result with a standard analysis result for calculation, and optimizing the second medical data analysis model to construct a medical data comprehensive utilization model. According to the method and the system, full-life-cycle data tracing is realized, the data authenticity is ensured, the worry of customer data leakage prevention is solved, and the worry of data stealing after data out of a domain is solved by utilizing a sandbox technology.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of data supervision utilization, and more particularly, to a medical data comprehensive utilization method and system based on a trusted data space. BACKGROUND

[0002] The trusted data space is a data circulation utilization infrastructure based on consensus rules, connecting multiple parties, and realizing data resource sharing and common use. For data with extremely wide application range but extremely strong privacy, such as medical data, on the one hand, a large amount of data is needed to establish a medical data analysis model to analyze the medical data in actual application, and through the analysis result, the quality and efficiency of related services are improved, on the other hand, under the condition of ensuring data authenticity, the data is not leaked during circulation and analysis. How to ensure data authenticity and privacy not to be leaked in the process of medical data utilization, and at the same time, establish a medical data comprehensive utilization model to improve the quality and efficiency of medical services has become a problem to be solved. SUMMARY

[0003] In order to solve the technical problem of how to make the utilization of medical data ensure data authenticity and privacy not to be leaked, and at the same time, establish a medical data comprehensive utilization model to improve the quality and efficiency of medical services in the prior art, the present application provides a medical data comprehensive utilization method and system based on a trusted data space.

[0004] According to an aspect of the present application, the present application provides a medical data comprehensive utilization method based on a trusted data space, comprising:

[0005] The initial medical data obtained from a plurality of data sources is preprocessed to generate standard medical data, and then stored in a trusted data space, wherein the standard medical data includes an attribute identifier, and high-sensitivity invisible data in the standard medical data is placed in a sandbox at the bottom layer of the trusted data space;

[0006] When the standard medical data is circulated in the trusted data space, a hash value is generated by performing hash calculation on data circulation information, and the hash value is uploaded to a block chain in the form of a block as a data circulation evidence, wherein the data circulation information includes a data receiver, a data provider, a timestamp, related core field data of the standard medical data, and the attribute identifier;

[0007] Based on the attribute identifier, a first medical data analysis model is generated according to the standard medical data and the data circulation information, and the first medical data analysis model is placed in the sandbox;

[0008] The highly sensitive and invisible data placed in the sandbox is input into the first medical data analysis model for calculation, standard analysis results are obtained, and corresponding desensitized sample data is generated.

[0009] The desensitized sample data is input into a second medical data analysis model established outside the sandbox for calculation, generating predictive analysis results.

[0010] The predicted analysis results are compared with the standard analysis results to obtain the deviation of the results;

[0011] When the deviation of the result is less than the custom result threshold, the second medical data analysis model is determined as the output medical data comprehensive utilization model.

[0012] According to another aspect of the present invention, the present invention provides a comprehensive medical data utilization system based on a trusted data space, the system comprising:

[0013] The data preprocessing module is used to preprocess the initial medical data obtained from multiple data sources, generate standard medical data, and store it in the trusted data space. The standard medical data includes attribute identifiers, and the highly sensitive and invisible data in the standard medical data is placed in the bottom sandbox of the trusted data space.

[0014] The data transfer module is used to perform hash calculations on the data transfer information to generate hash values ​​when the standard medical data is transferred in a trusted data space, and upload the hash values ​​to the blockchain in the form of blocks as evidence of the data transfer. The data transfer information includes the data recipient, data provider, timestamp, relevant core field-level data of the standard medical data, and the attribute identifier.

[0015] The first model module is used to generate a first medical data analysis model based on the attribute identifier, the standard medical data, and the data flow information, and to place the first medical data analysis model in a sandbox.

[0016] The first calculation module is used to input highly sensitive and invisible data placed in the sandbox into the first medical data analysis model for calculation, obtain standard analysis results, and generate corresponding desensitized sample data.

[0017] The second calculation module is used to input the desensitized sample data into the second medical data analysis model established outside the sandbox for calculation and to generate predictive analysis results.

[0018] The result comparison module is used to compare the predictive analysis results with the standard analysis results to obtain the result deviation.

[0019] The second model module is used to determine the second medical data analysis model as the output medical data comprehensive utilization model when the deviation of the result is less than the custom result threshold.

[0020] According to another aspect of the present invention, a computer-readable storage medium is provided, the storage medium storing a computer program that, when executed by a processor, implements the methods described in any of the above aspects of the present invention.

[0021] According to another aspect of the present invention, an electronic device is provided, the electronic device comprising: a processor; a memory for storing executable instructions of the processor; the processor being configured to read the executable instructions from the memory and execute the instructions to implement the method described in any of the preceding aspects of the present invention.

[0022] The present invention discloses a method and system for comprehensive utilization of medical data based on a trusted data space. The method includes: preprocessing initial medical data from multiple data sources to generate standard medical data, which is then stored in a trusted data space; placing highly sensitive and invisible data in a sandbox; generating a first medical analysis model based on the data flow information of the standard medical data, which is also placed in the sandbox; generating standard analysis results and desensitized sample data through model calculations on the highly sensitive and invisible data; comparing the predicted analysis results obtained by inputting the desensitized sample data into a second medical data analysis model with the standard analysis results, optimizing the second medical data analysis model, and thus constructing a comprehensive medical data utilization model. The method and system utilize a trusted data space for full lifecycle data traceability, ensuring data authenticity. A hash algorithm is used to store data on the blockchain, ensuring traceability as data flows and addressing customer concerns about data leakage. For data computation, sandbox technology is used to ensure that data and models do not leave the domain, thus addressing concerns about data theft after leaving the domain. Finally, the predictive analysis results obtained by calculating the second medical analysis model built outside the sandbox based on anonymized data are iteratively compared with the standard analysis results obtained by the first medical analysis model inside the sandbox. This process makes the second medical analysis model infinitely close to the model inside the sandbox, thereby constructing a more accurate comprehensive medical data utilization model and improving the quality and efficiency of medical services. Attached Figure Description

[0023] Exemplary embodiments of the present invention can be more fully understood by referring to the following figures:

[0024] Figure 1 A flowchart illustrating a method for comprehensive utilization of medical data based on a trusted data space according to a preferred embodiment of the present invention;

[0025] Figure 2This is a schematic diagram of the structure of a medical data comprehensive utilization system based on a trusted data space according to a preferred embodiment of the present invention;

[0026] Figure 3 This is a schematic diagram of the structure of an electronic device according to a preferred embodiment of the present invention. Detailed Implementation

[0027] Exemplary embodiments of the invention will now be described with reference to the accompanying drawings. However, the invention may be embodied in many different forms and is not limited to the embodiments described herein. These embodiments are provided to fully and completely disclose the invention and to fully convey its scope to those skilled in the art. The terminology used in the exemplary embodiments illustrated in the drawings is not intended to limit the invention. In the drawings, the same units / elements are referred to by the same reference numerals.

[0028] Unless otherwise stated, the terms used herein (including technical terms) have their common meaning as understood by one of ordinary skill in the art. Furthermore, it is understood that terms defined in commonly used dictionaries should be understood to have a meaning consistent with the context of their relevant field, and not to be interpreted as having an idealized or overly formal meaning.

[0029] Exemplary method

[0030] Figure 1 This is a flowchart illustrating a preferred embodiment of a method for comprehensive utilization of medical data based on a trusted data space according to the present invention. Figure 1 As shown, the medical data comprehensive utilization method based on trusted data space described in this preferred embodiment starts from step 101.

[0031] In step 101, the initial medical data obtained from multiple data sources is preprocessed to generate standard medical data, which is then stored in a trusted data space. The standard medical data includes attribute identifiers, and highly sensitive, invisible data in the standard medical data is placed in the underlying sandbox of the trusted data space.

[0032] Preferably, the initial medical data obtained from multiple data sources is preprocessed to generate standard historical medical data, which is then stored in a trusted data space, including:

[0033] Acquire initial medical data from multiple sources that simultaneously comply with regulatory requirements and healthcare industry data standards, including clinical decision support institutions, epidemiological research institutions, and hospital management institutions, and the initial medical data includes electronic medical records, imaging data, genomic data, and wearable device data;

[0034] The initial medical data is tagged, classified, and then standard medical data is generated and stored in a trusted data space. The field-level data of the standard medical data carries their respective attribute identifiers.

[0035] In this preferred embodiment, data preparation is performed using a data governance device. Data from sources such as electronic medical records (EMR), imaging data, genomic data, and wearable device data, originating from clinical decision support, epidemiological research, and hospital management, are tagged, classified, and graded in accordance with GDPR, HIPAA, and the Personal Data Protection Act. Simultaneously, the data conforms to medical data standards such as HL7FHIR, DICOM, and OMOPCDM. Relevant data is obtained, classified, and categorized, with each field-level data having its own attribute identifier to prevent data tampering during multiple transfers and uses.

[0036] In step 102, when the standard medical data is transferred in the trusted data space, a hash value is generated by hash calculation on the data transfer information, and the hash value is uploaded to the blockchain in the form of a block as a proof of the data transfer. The data transfer information includes the data recipient, data provider, timestamp, relevant core field-level data of the standard medical data, and the attribute identifier.

[0037] Preferably, the method further includes, when the standard medical data flows within a trusted data space, the data recipient obtains the evidence storage result from the blockchain, performs calculations, comparisons, and verifications to complete the traceability process, including:

[0038] The receiving terminal sends the public key and the operator's identity information to the verification terminal on the blockchain;

[0039] After successfully verifying the operator's identity information, the verification terminal sends its public key to the detection terminal, and at the same time sends the detection terminal's public key and the verification terminal's private key to the receiving terminal.

[0040] The detection terminal will send the encrypted data to the receiving terminal using a private key;

[0041] The receiving terminal uses a fixed-stored public key to verify the signature. After successful verification, it decrypts the data information using the private key of the verifying terminal and then sends a notification of successful reception to the verifying terminal to complete the data verification.

[0042] In step 103, based on the attribute identifier, a first medical data analysis model is generated according to the standard medical data and the data flow information, and the first medical data analysis model is placed in a sandbox.

[0043] Preferably, based on the attribute identifier, a first medical data analysis model is generated according to the standard medical data and the data flow information, including:

[0044] Using the attribute identifiers, the entire process of data flow information is statistically traced, calculated, and categorized. Based on the frequency of data demand from the data recipients, a multi-dimensional data demand model is established using the standard medical data.

[0045] The data demand multidimensional model is optimized using data whose demand frequency is greater than a custom frequency threshold. The first medical data analysis model is generated by obtaining the source time, institution name, data source frequency, data type, data usage destination, and data utilization frequency of the above data based on the data flow information and the standard medical data.

[0046] In step 104, the highly sensitive and invisible data placed in the sandbox is input into the first medical data analysis model for calculation, standard analysis results are obtained, and corresponding desensitized sample data is generated.

[0047] In this preferred embodiment,

[0048] In step 105, the desensitized sample data is input into the second medical data analysis model established outside the sandbox for calculation, generating predictive analysis results.

[0049] In step 106, the predicted analysis results are compared with the standard analysis results to obtain the result deviation.

[0050] In step 107, when the deviation of the result is less than the custom result threshold, the second medical data analysis model is determined as the output medical data comprehensive utilization model.

[0051] Preferably, the method further includes performing model iterative optimization on the second medical data analysis model when the result deviation is not less than a custom result threshold, comparing the predicted analysis results based on the optimized second medical data analysis model with the standard analysis results, and using the optimized second medical data analysis model with a result deviation less than the custom result threshold as the output medical data comprehensive utilization model.

[0052] In this preferred embodiment, data is controlled through data space sandbox technology and data strategy technology. Data requests are distributed according to policy control to prevent data loss or loss of control during the process. Highly sensitive and invisible data is placed in the underlying sandbox of the data space, where it is invisible to users based on access control. Once the data enters the sandbox, it becomes a black box. Data within the sandbox undergoes model calculations to derive standard analysis results and generate anonymized sample data. Users outside the sandbox use the sample data to calculate and compare the results with the model. If the calculation deviation is too large, the data can be adjusted with new data or the model's calculation dimensions can be adjusted. The results are continuously compared with those within the sandbox until they converge, yielding the desired data and expected model, thus obtaining the analysis results. By constructing a comprehensive medical data utilization model, it is possible to analyze medical data usage patterns, the data demand and frequency of various medical institutions, the data usage tendencies of research institutions, and generate medical data usage reports. Furthermore, it enables effective data control and privacy protection.

[0053] The preferred embodiment of this medical data comprehensive utilization method based on a trusted data space utilizes a trusted data space for full lifecycle data traceability, ensuring data authenticity. A hash algorithm is used to store data on the blockchain, ensuring traceability as data flows and addressing concerns about data leakage. For data computation, sandbox technology is used to prevent data and models from leaving their domains, alleviating concerns about data theft after data leaves the domain. Finally, the predictive analysis results obtained by calculating using a second medical analysis model built outside the sandbox based on anonymized data input is iteratively compared with the standard analysis results obtained using a first medical analysis model within the sandbox. This process ensures that the second medical analysis model closely approximates the model within the sandbox, thereby constructing a more accurate medical data comprehensive utilization model and improving the quality and efficiency of medical services.

[0054] Exemplary system

[0055] Figure 2 This is a schematic diagram of the structure of a medical data comprehensive utilization system based on a trusted data space according to a preferred embodiment of the present invention. Figure 2 As shown, the medical data comprehensive utilization system 200 based on trusted data space according to this preferred embodiment includes:

[0056] The data preprocessing module 201 is used to preprocess the initial medical data obtained from multiple data sources, generate standard medical data, and store it in the trusted data space. The standard medical data includes attribute identifiers, and the highly sensitive and invisible data in the standard medical data is placed in the bottom sandbox of the trusted data space.

[0057] The data transfer module 202 is used to perform hash calculation on the data transfer information to generate a hash value when the standard medical data is transferred in the trusted data space, and upload the hash value to the blockchain in the form of a block as the storage result of the data transfer. The data transfer information includes the data recipient, data provider, timestamp, relevant core field-level data of the standard medical data, and the attribute identifier.

[0058] The first model module 203 is used to generate a first medical data analysis model based on the attribute identifier, the standard medical data and the data flow information, and place the first medical data analysis model in a sandbox.

[0059] The first calculation module 204 is used to input highly sensitive and invisible data placed in the sandbox into the first medical data analysis model for calculation, obtain standard analysis results, and generate corresponding desensitized sample data.

[0060] The second calculation module 205 is used to input the desensitized sample data into the second medical data analysis model established outside the sandbox for calculation and to generate predictive analysis results.

[0061] The result comparison module 206 is used to compare the predictive analysis results with the standard analysis results to obtain the result deviation.

[0062] The second model module 207 is used to determine the second medical data analysis model as the output medical data comprehensive utilization model when the deviation of the result is less than the custom result threshold.

[0063] Preferably, the data preprocessing module 201 preprocesses the initial medical data obtained from multiple data sources, generates standard historical medical data, and stores it in a trusted data space, including:

[0064] Acquire initial medical data from multiple sources that simultaneously comply with regulatory requirements and healthcare industry data standards, including clinical decision support institutions, epidemiological research institutions, and hospital management institutions, and the initial medical data includes electronic medical records, imaging data, genomic data, and wearable device data;

[0065] The initial medical data is tagged, classified, and then standard medical data is generated and stored in a trusted data space. The field-level data of the standard medical data carries their respective attribute identifiers.

[0066] Preferably, the system further includes a data traceability module, used to complete the traceability process when the standard medical data flows within a trusted data space, by having the data recipient obtain the evidence storage results from the blockchain, perform calculations, comparisons, and verifications, including:

[0067] The receiving terminal sends the public key and the operator's identity information to the verification terminal on the blockchain;

[0068] After successfully verifying the operator's identity information, the verification terminal sends its public key to the detection terminal, and at the same time sends the detection terminal's public key and the verification terminal's private key to the receiving terminal.

[0069] The detection terminal will send the encrypted data to the receiving terminal using a private key;

[0070] The receiving terminal uses a fixed-stored public key to verify the signature. After successful verification, it decrypts the data information using the private key of the verifying terminal and then sends a notification of successful reception to the verifying terminal to complete the data verification.

[0071] Preferably, the first model module 203 generates a first medical data analysis model based on the attribute identifier, according to the standard medical data and the data flow information, including:

[0072] Using the attribute identifiers, the entire process of data flow information is statistically traced, calculated, and categorized. Based on the frequency of data demand from the data recipients, a multi-dimensional data demand model is established using the standard medical data.

[0073] The data demand multidimensional model is optimized using data whose demand frequency is greater than a custom frequency threshold. The first medical data analysis model is generated by obtaining the source time, institution name, data source frequency, data type, data usage destination, and data utilization frequency of the above data based on the data flow information and the standard medical data.

[0074] Preferably, the second model module is further used to perform model iterative optimization on the second medical data analysis model when the result deviation is not less than a custom result threshold, compare the predicted analysis results based on the optimized second medical data analysis model with the standard analysis results, and use the optimized second medical data analysis model with a result deviation less than the custom result threshold as the output medical data comprehensive utilization model.

[0075] The steps for determining the medical data comprehensive utilization model outside the sandbox in the medical data comprehensive utilization system based on trusted data space described in this preferred embodiment are the same as those in the medical data comprehensive utilization method based on trusted data space, and the technical effects achieved are also the same, so they will not be repeated here.

[0076] Exemplary electronic device

[0077] Figure 3 This is a schematic diagram of the structure of an electronic device according to a preferred embodiment of the present invention. Figure 3 As shown, the electronic device includes one or more processors 301 and memory 302.

[0078] The processor 301 may be a central processing unit (CPU) or other form of processing unit with data processing capabilities and / or instruction execution capabilities, and may control other components in the electronic device to perform desired functions.

[0079] The memory 302 may include one or more computer program products, which may include various forms of computer-readable storage media, such as volatile memory and / or non-volatile memory. The volatile memory may include, for example, random access memory (RAM) and / or cache memory. The non-volatile memory may include, for example, read-only memory (ROM), hard disk, flash memory, etc. One or more computer program instructions may be stored on the computer-readable storage medium, and the processor 301 may execute the program instructions to implement the medical data comprehensive utilization method based on trusted data space of the various embodiments disclosed above, and / or other desired functions. In one example, the electronic device may also include an input device 303 and an output device 304, these components being interconnected via a bus system and / or other forms of connection mechanism (not shown).

[0080] In addition, the input device 303 may also include, for example, a keyboard, a mouse, etc.

[0081] The output device 304 can output various information to the outside. The output device 304 may include, for example, a display, a speaker, a printer, and a communication network and its connected remote output devices, etc.

[0082] Of course, for the sake of simplicity, Figure 3 Only some of the components of the electronic device relevant to this disclosure are shown, omitting components such as buses, input / output interfaces, etc. In addition, the electronic device may include any other suitable components depending on the specific application.

[0083] Exemplary computer program product and computer readable storage medium

[0084] In addition to the methods and apparatus described above, embodiments of this disclosure may also be computer program products comprising computer program instructions that, when executed by a processor, cause the processor to perform the steps in the methods for comprehensive utilization of medical data based on a trusted data space according to various embodiments of this disclosure as described in the "Exemplary Methods" section of this specification.

[0085] The computer program product can be written in any combination of one or more programming languages ​​to perform the operations of the embodiments of this disclosure. The programming languages ​​include object-oriented programming languages ​​such as Java and C++, as well as conventional procedural programming languages ​​such as C or similar languages. The program code can be executed entirely on a user's computing device, partially on a user's computing device, as a standalone software package, partially on a user's computing device and partially on a remote computing device, or entirely on a remote computing device or server.

[0086] Furthermore, embodiments of this disclosure may also be computer-readable storage media storing computer program instructions that, when executed by a processor, cause the processor to perform the steps in the comprehensive utilization method of medical data based on a trusted data space according to various embodiments of this disclosure as described in the "Exemplary Methods" section above.

[0087] The computer-readable storage medium may be any combination of one or more readable media. A readable medium may be a readable signal medium or a readable storage medium. A readable storage medium may, for example, include, but is not limited to, electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatuses, or devices, or any combination thereof. More specific examples of readable storage media (a non-exhaustive list) include: electrical connections having one or more wires, portable disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0088] The basic principles of this disclosure have been described above with reference to specific embodiments. However, it should be noted that the advantages, benefits, and effects mentioned in this disclosure are merely examples and not limitations, and should not be considered as essential features of each embodiment of this disclosure. Furthermore, the specific details disclosed above are for illustrative and facilitative purposes only, and are not limitations. These details do not limit the scope of this disclosure to the necessity of employing the aforementioned specific details for implementation.

[0089] The various embodiments in this specification are described in a progressive manner, with each embodiment focusing on its differences from other embodiments. Similar or identical parts between embodiments can be referred to interchangeably. For system embodiments, since they largely correspond to method embodiments, the description is relatively simple; relevant parts can be referred to the descriptions in the method embodiments.

[0090] The block diagrams of devices, apparatuses, devices, and systems disclosed herein are merely illustrative examples and are not intended to require or imply that they must be connected, arranged, or configured in the manner shown in the block diagrams. As those skilled in the art will recognize, these devices, apparatuses, devices, and systems can be connected, arranged, and configured in any manner. Words such as “comprising,” “including,” “having,” etc., are open-ended terms meaning “including but not limited to,” and are used interchangeably with them. The terms “or” and “and” as used herein refer to the terms “and / or,” and are used interchangeably with them unless the context clearly indicates otherwise. The term “such as” as used herein refers to the phrase “such as but not limited to,” and is used interchangeably with it.

[0091] The apparatus and methods of this disclosure may be implemented in many ways. For example, they may be implemented by software, hardware, firmware, or any combination of software, hardware, and firmware. The above-described order of steps for the methods is for illustrative purposes only, and the steps of the methods of this disclosure are not limited to the order specifically described above unless otherwise specifically stated. Furthermore, in some embodiments, this disclosure may also be implemented as a program recorded on a recording medium, the program including machine-readable instructions for implementing the methods according to this disclosure. Thus, this disclosure also covers recording media storing programs for performing the methods according to this disclosure.

[0092] It should also be noted that in the apparatus, devices, and methods of this disclosure, the components or steps are decomposable and / or recombinable. Such decomposition and / or recombination should be considered equivalent to the present disclosure. The above description of the disclosed aspects is provided to enable any person skilled in the art to make or use this disclosure. Various modifications to these aspects will be readily apparent to those skilled in the art, and the general principles defined herein can be applied to other aspects without departing from the scope of this disclosure. Therefore, this disclosure is not intended to be limited to the aspects shown herein, but rather to be carried out within the widest scope consistent with the principles and novel features disclosed herein.

[0093] The above description has been given for purposes of illustration and description. Furthermore, this description is not intended to limit the embodiments of this disclosure to the forms disclosed herein. Although numerous exemplary aspects and embodiments have been discussed above, those skilled in the art will recognize certain variations, modifications, alterations, additions, and sub-combinations therein.

Claims

1. A method for comprehensive utilization of medical data based on a trusted data space, characterized in that, The method includes: Initial medical data obtained from multiple data sources is preprocessed to generate standard medical data, which is then stored in a trusted data space. The standard medical data includes attribute identifiers, and highly sensitive, invisible data in the standard medical data is placed in the underlying sandbox of the trusted data space. When the standard medical data is transferred in a trusted data space, a hash value is generated by hash calculation on the data transfer information, and the hash value is uploaded to the blockchain in the form of a block as a proof of the data transfer. The data transfer information includes the data recipient, data provider, timestamp, relevant core field-level data of the standard medical data, and the attribute identifier. Based on the attribute identifier, a first medical data analysis model is generated according to the standard medical data and the data flow information, and the first medical data analysis model is placed in a sandbox. The highly sensitive and invisible data placed in the sandbox is input into the first medical data analysis model for calculation, standard analysis results are obtained, and corresponding desensitized sample data is generated. The desensitized sample data is input into a second medical data analysis model established outside the sandbox for calculation, generating predictive analysis results. The predicted analysis results are compared with the standard analysis results to obtain the deviation of the results; When the deviation of the result is less than the custom result threshold, the second medical data analysis model is determined as the output medical data comprehensive utilization model.

2. The method according to claim 1, characterized in that, Initial medical data obtained from multiple data sources is preprocessed to generate standard historical medical data, which is then stored in a trusted data space, including: Acquire initial medical data from multiple sources that simultaneously comply with regulatory requirements and healthcare industry data standards, including clinical decision support institutions, epidemiological research institutions, and hospital management institutions, and the initial medical data includes electronic medical records, imaging data, genomic data, and wearable device data; The initial medical data is tagged, classified, and then standard medical data is generated and stored in a trusted data space. The field-level data of the standard medical data carries their respective attribute identifiers.

3. The method according to claim 1, characterized in that, The method further includes, when the standard medical data flows within a trusted data space, the data recipient obtains the evidence storage result from the blockchain, performs calculations, comparisons, and verifications to complete the traceability process, including: The receiving terminal sends the public key and the operator's identity information to the verification terminal on the blockchain; After successfully verifying the operator's identity information, the verification terminal sends its public key to the detection terminal, and at the same time sends the detection terminal's public key and the verification terminal's private key to the receiving terminal. The detection terminal will send the encrypted data to the receiving terminal using a private key; The receiving terminal uses a fixed-stored public key to verify the signature. After successful verification, it decrypts the data information using the private key of the verifying terminal and then sends a notification of successful reception to the verifying terminal to complete the data verification.

4. The method according to claim 1, characterized in that, Based on the attribute identifier, a first medical data analysis model is generated according to the standard medical data and the data flow information, including: Using the attribute identifiers, the entire process of data flow information is statistically traced, calculated, and categorized. Based on the frequency of data demand from the data recipients, a multi-dimensional data demand model is established using the standard medical data. The data demand multidimensional model is optimized using data whose demand frequency is greater than a custom frequency threshold. The first medical data analysis model is generated by obtaining the source time, institution name, data source frequency, data type, data usage destination, and data utilization frequency of the above data based on the data flow information and the standard medical data.

5. The method according to claim 1, characterized in that, The method further includes iteratively optimizing the second medical data analysis model when the deviation of the result is not less than a custom result threshold, comparing the predicted analysis results based on the optimized second medical data analysis model with the standard analysis results, and using the optimized second medical data analysis model with a result deviation less than the custom result threshold as the output medical data comprehensive utilization model.

6. A comprehensive medical data utilization system based on a trusted data space, characterized in that, The system includes: The data preprocessing module is used to preprocess the initial medical data obtained from multiple data sources, generate standard medical data, and store it in the trusted data space. The standard medical data includes attribute identifiers, and the highly sensitive and invisible data in the standard medical data is placed in the bottom sandbox of the trusted data space. The data transfer module is used to perform hash calculations on the data transfer information to generate hash values ​​when the standard medical data is transferred in a trusted data space, and upload the hash values ​​to the blockchain in the form of blocks as evidence of the data transfer. The data transfer information includes the data recipient, data provider, timestamp, relevant core field-level data of the standard medical data, and the attribute identifier. The first model module is used to generate a first medical data analysis model based on the attribute identifier, the standard medical data, and the data flow information, and to place the first medical data analysis model in a sandbox. The first calculation module is used to input highly sensitive and invisible data placed in the sandbox into the first medical data analysis model for calculation, obtain standard analysis results, and generate corresponding desensitized sample data. The second calculation module is used to input the desensitized sample data into the second medical data analysis model established outside the sandbox for calculation and to generate predictive analysis results. The result comparison module is used to compare the predictive analysis results with the standard analysis results to obtain the result deviation. The second model module is used to determine the second medical data analysis model as the output medical data comprehensive utilization model when the deviation of the result is less than the custom result threshold.

7. The system according to claim 6, characterized in that, The data preprocessing module preprocesses initial medical data obtained from multiple data sources, generates standard medical data, and stores it in a trusted data space, including: Acquire initial medical data from multiple sources that simultaneously comply with regulatory requirements and healthcare industry data standards, including clinical decision support institutions, epidemiological research institutions, and hospital management institutions, and the initial medical data includes electronic medical records, imaging data, genomic data, and wearable device data; The initial medical data is tagged, classified, and then standard medical data is generated and stored in a trusted data space. The field-level data of the standard medical data carries their respective attribute identifiers.

8. The system according to claim 6, characterized in that, The system also includes a data traceability module, used to complete traceability by having the data recipient obtain the evidence storage results from the blockchain, perform calculations, comparisons, and verifications when the standard medical data flows within a trusted data space. This includes: The receiving terminal sends the public key and the operator's identity information to the verification terminal on the blockchain; After successfully verifying the operator's identity information, the verification terminal sends its public key to the detection terminal, and at the same time sends the detection terminal's public key and the verification terminal's private key to the receiving terminal. The detection terminal will send the encrypted data to the receiving terminal using a private key; The receiving terminal uses a fixed-stored public key to verify the signature. After successful verification, it decrypts the data information using the private key of the verifying terminal and then sends a notification of successful reception to the verifying terminal to complete the data verification.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the program is executed by the processor, it implements the steps of the method as described in any one of claims 1-5.

10. An electronic device, characterized in that, include: processor; Memory used to store the processor's executable instructions; The processor is configured to read the executable instructions from the memory and execute the instructions to implement the method described in any one of claims 1-5.

Images