Medical data aggregation statistical analysis system and method

By generating and processing anonymized x-ID identifiers, the privacy protection issue when aggregating and analyzing personal health data across multiple medical institutions is resolved, enabling secure data aggregation and analysis, and supporting scientific research and diagnostic guidance.

CN113722379BActive Publication Date: 2024-11-22SHANGHAI INT HUMAN PHENOTYPIC RES INST
View PDF 0 Cites 1 Cited by

Patent Information

Application Number
CN202111026859.6
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2021-09-02
Publication Date
2024-11-22
Estimated Expiration
2041-09-02

AI Technical Summary

Technical Problem

How can we utilize medical data for scientific research and clinical diagnostic guidance while ensuring privacy and security, especially when collecting and analyzing personal health information across multiple medical institutions to protect personal privacy from being leaked?

Method used

Data is identified by anxieties-generated x-IDs. Encrypted x-ID information is generated and transmitted through the interactive connection between personal identification data collection terminals and institutional data collection terminals. The identification data management party performs anonymized data processing and aggregation to ensure that the health information data of the same person in different institutions can be aggregated and analyzed without disclosing personal identity information.

Benefits of technology

This technology enables the effective collection and analysis of multiple medical visits by the same individual while protecting personal privacy. This data is then used for scientific research and diagnostic guidance, reducing the risk of personal information leakage and ensuring data security.

✦ Generated by Eureka AI based on patent content.
Patent Text Reader

Abstract

The present invention relates to the field of medical information technology, and in particular to a medical data collection and analysis system. A medical data aggregation statistical analysis system comprises: a personal identification data collection terminal, an institutional data collection terminal, and a data application request terminal. The personal identification data collection terminal generates an encrypted x-ID using personal information, and is interactively connected with the institutional data collection terminal. The institutional data collection terminal aggregates x-ID and the health information data attached to the x-ID. The data application request terminal is used to provide an anonymous data computing environment. The present invention provides a data analysis system and a data processing method, which anonymously analyze and process the health data of the same person who has visited a medical institution multiple times from beginning to end, and aggregate and collect the health data to form a health data set for one person, which is conducive to the rational application of medical data and at the same time achieves the purpose of strictly protecting personal privacy.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the field of medical information technology, and in particular to a medical data collection and analysis system. Background Art

[0002] The development and changes of emerging information and communication technologies and information perception methods such as mobile Internet, Internet of Things, and cloud computing have profoundly changed the traditional medical and health service model. In this process, medical data has been gradually liberalized, and the intelligent medical care and precision medicine brought by big data have begun to cover more directions, playing a more important role in comparative effect research of clinical operations, clinical decision support systems, transparency of medical data, remote patient monitoring, and advanced analysis of patient files. At the same time, with the application and development of emerging technologies such as regional medical care, mobile medical care, and translational medicine, data such as electronic medical records, electronic health records, translational genes, clinical test data in intensive care units, and even personal health status records perceived by wearable sensors have shown explosive growth. Accurately using these data and conducting data analysis and research on medical data, so that billions of accumulated medical data can become standardized medical decision-making basis that doctors can call at any time during diagnosis and treatment, is an effective way to improve diagnosis and treatment efficiency, reduce avoidable human errors, and alleviate the problem of uneven distribution of medical resources. However, due to the sensitivity of health and medical data, the personal information it contains is very sensitive. The leakage of personal information will bring immeasurable troubles to individuals or hospitals. Therefore, when using medical data, we should also pay great attention to protecting data security and personal privacy. How to use medical data for scientific research and clinical diagnosis guidance while ensuring privacy security is a problem that needs to be solved. Summary of the invention

[0003] The present invention provides a medical data aggregation statistical analysis system, which aims to collect and analyze the collected medical data while ensuring that the patient's personal information is not leaked, and to classify and organize the data through anonymous operation analysis, so as to obtain the health information data of the same person who visits medical institutions at different times and aggregate them for scientific research.

[0004] To achieve the above object, the present invention adopts the following technical solutions:

[0005] A medical data aggregation statistical analysis system includes: a personal identification data collection terminal, an institutional data collection terminal, and a data application request terminal.

[0006] Furthermore, the data application request end includes an identification data manager, which is a legal manager of a personal identification information database, and can submit different anonymization codes, namely, the x-ID of the present invention, to determine whether the authentication is for the same person.

[0007] The personal identification data collection terminal generates an encrypted x-ID from the personal information, interacts with the institutional data collection terminal, and transmits the x-ID information to the institutional data collection terminal. Further, the personal information includes the ID number and name.

[0008] Furthermore, the generation rule of the x-ID is an institution code or a personal in-hospital identification code. The institution code is generated by the medical institution according to the patient's identity information according to its generation rule, and the personal in-hospital identification code is generated by the identification data management party according to the patient's identity information according to its generation rule. Therefore, the x-ID obtained by each person each time he visits the hospital can uniquely correspond to his identity information.

[0009] Furthermore, the generation rule of the x-ID is the institution code + the personal hospital identification code, and the x-ID representing the same person can be generated by combining the institution code + the personal hospital identification code according to a certain generation rule.

[0010] The x-ID generated each time a person goes to a different medical institution for treatment is different, but they are all encrypted and generated according to certain generation rules. Therefore, the personal information contained in the x-ID is actually the same. Furthermore, the identification data manager is the same, and the identification data manager's personal hospital identification code generation rules are also the same. In this case, it is possible to determine which of the multiple x-IDs belong to the same person based on the personal hospital identification code generation rules and the personal hospital identification code information.

[0011] Furthermore, the medical institution is the same, and the x-ID generated by a medical institution each time a person goes for treatment is different, but they are all encrypted and generated according to the institution code generation rules of the medical institution. Therefore, the personal information contained in the x-ID is actually the same. In this case, it is possible to determine which ones in the x-ID data set are the same person based on the institution code generation rules and the institution code information.

[0012] The x-ID dataset is a collection of several x-IDs. Special note: the a-ID and b-ID are the x-IDs obtained when a person visits a certain institution for medical treatment.

[0013] Furthermore, there are multiple personal identification data collection terminals. The personal identification data collection terminal a accepts the request from person A to institution No. 1, generates a-ID and sends it to the institution data collection terminal. The personal identification data collection terminal b accepts the request from person A to institution No. 2, generates b-ID and sends it to the institution data collection terminal.

[0014] The institutional data collection terminal aggregates x-ID and the health information data attached to x-ID, wherein the health information data includes the patient's age, gender, and disease, but does not include contact information, home address, work unit, etc.

[0015] Furthermore, institution No. 1 accepts a-ID and collects a health information data associated with a-ID, and institution No. 2 accepts b-ID and receives b health information data associated with b-ID.

[0016] The data application request end is used to provide an anonymous database collision and computing environment.

[0017] Furthermore, the data application request end accepts the x-ID and the health information data attached thereto sent by the institutional data collection end, performs anonymized data operations on the x-ID data set, determines the identity information of the patient represented in the x-ID data set and groups the x-IDs belonging to the same person together; if they are the same person, the x-ID and the health data attached thereto are accepted and summarized in the information of person A.

[0018] Furthermore, the data application request end combines the data provided by institution 1 and institution 2 according to the identity information contained in x-ID. The entire data set can be used by the research project team including institution 1 and institution 2. During the entire process, the patient's personal information only reflects health information data, and other personal information is completely confidential.

[0019] Furthermore, after the data of x-ID is submitted, x-ID can be removed from the submitted table and then provided to the project team including institution 1 and institution 2 for scientific research, further reducing the risk of personal information leakage and protecting personal privacy.

[0020] Furthermore, after obtaining the x-ID data set, the identification data manager identifies the parts belonging to the same person, collects and organizes them, and feeds them back to the institutional data collection end.

[0021] A medical data aggregation statistical analysis method comprises the following steps:

[0022] 1) Data collection: The personal identification data collection terminal generates an encrypted x-ID for the personal information and interacts with the institutional data collection terminal.

[0023] 2) Data collection: Associate the individual’s health information data with the corresponding x-ID. If the individual has visited a doctor multiple times, the health data of the medical institutions corresponding to different x-IDs will be associated separately.

[0024] 3) Data processing: Anonymize multiple x-IDs, analyze and obtain x-IDs with the same identity information, and aggregate the health information data under the same identity information.

[0025] The x-ID includes but is not limited to an institution code, a personal hospital identification code or a combination of the two. The institution code is a code generated by the medical institution according to the patient's identity information according to its generation rules, and the personal hospital identification code is a code generated by the identification data management party according to the patient's identity information according to its generation rules.

[0026] Furthermore, the data processing described in step 3) is as follows: the personal hospital identification code generation rules of the identification data management party are the same, and the parts of multiple x-IDs belonging to the same person can be determined based on the personal hospital identification code generation rules and personal hospital identification code information.

[0027] Furthermore, if a person goes to the same medical institution multiple times, his / her x-ID at the medical institution will be different each time he / she goes there for treatment, but they are all encrypted and generated according to the institution code generation rules of the medical institution. Therefore, the personal information contained in the x-ID is actually the same. In this case, it can be determined which of the multiple x-IDs belong to the same person based on the institution code generation rules and the institution code information.

[0028] The above data collection and processing process only involves x-ID related operations and the collection of health information data. In addition, the decryption of x-ID is done by identifying the data manager or the database collision operation inside the computer, and is not public or completely decrypted. Therefore, there is no need to worry about the leakage of personal privacy.

[0029] In summary, case information is personal privacy. If it is leaked, it will have a very serious adverse impact on the individual. However, in medical scientific research or diagnosis, it is a very effective diagnostic basis and scientific research data. How to effectively use this data and strictly protect personal privacy is very important. The present invention provides a data analysis system and a data processing method, which anonymously analyzes and processes the health data of the same person who has been treated in the hospital for multiple times, and aggregates them to form a health data set for one person, which is conducive to the rational application of medical data and at the same time achieves the purpose of strictly protecting personal privacy. DETAILED DESCRIPTION

[0030] The technical solution of the present invention is further explained below in conjunction with specific embodiments.

[0031] Embodiment 1:

[0032] A medical data aggregation statistical analysis system includes: a personal identification data collection terminal, an institutional data collection terminal, an identification data management party, and a data application request terminal.

[0033] The personal identification data collection terminal generates an encrypted x-ID from the personal information, and the personal identification data collection terminal is interactively connected with the institutional data collection terminal. The institutional data collection terminal transmits multiple x-IDs to the identification data management party, and the identification data management party determines that the identity information in the multiple x-IDs is part of the same person.

[0034] There are multiple personal identification data collection terminals, for example: the personal identification data collection terminal a accepts the request from person A to institution No. 1, generates a-ID and sends it to the institution data collection terminal, and the personal identification data collection terminal b accepts the request from person A to institution No. 2, generates b-ID and sends it to the institution data collection terminal.

[0035] The institutional data collection terminal aggregates the individual's health information data and associates the collected aggregated data with the individual's x-ID. Institution No. 1 receives a-ID and collects a health information data associated with a-ID, and institution No. 2 receives b-ID and receives b health information data associated with b-ID.

[0036] After receiving the x-ID data set, the identification data manager determines and analyzes the information in the x-ID data set and groups the x-IDs belonging to the same person together.

[0037] After obtaining the x-IDs provided by different parties, the data application request end sends a request to the identification data management party, requesting the identification data management party to feedback whether multiple x-IDs belong to the same person; after the identification data management party provides feedback, the data application request end aggregates the health information data corresponding to each x-ID in a data package belonging to the same person, and can also conduct scientific research analysis.

[0038] During the entire process, the patient's personal information is kept completely confidential and only health information data is reflected.

[0039] After completing the data submission of x-ID, x-ID can be removed from the submitted table, further reducing the risk of personal information leakage and protecting personal privacy.

[0040] During the above-mentioned aggregation and analysis process of medical data, the data information analysis of x-ID is judged and processed by the data identification management party, and other non-designated units cannot obtain specific information. The final information received by the data application request end is only the collection result of each x-ID in the x-ID data set, and does not involve personal information. Therefore, the data security of personal information can be effectively guaranteed.

[0041] Embodiment 2:

[0042] A medical data aggregation statistical analysis system includes: a personal identification data collection terminal, an institutional data collection terminal, a data application request terminal, and an identification data management party.

[0043] The personal identification data collection terminal generates an encrypted x-ID from the personal information. The generation rule of the x-ID includes an institution code + a personal in-hospital identification code. The institution code is a code formed by a medical institution, and the personal in-hospital identification code is a code formed according to the patient's identity information according to its generation rule.

[0044] There are multiple personal identification data collection terminals. The personal identification data collection terminal a accepts the request from person A to institution No. 1, generates a-ID and sends it to the institution data collection terminal. The personal identification data collection terminal b accepts the request from person A to institution No. 2, generates b-ID and sends it to the institution data collection terminal.

[0045] The institutional data collection terminal aggregates the individual's health information data and associates the collected health information data with the individual's x-ID. Institution No. 1 receives a-ID and collects a health information data associated with a-ID, and institution No. 2 receives b-ID and receives b health information data associated with b-ID.

[0046] The data application request end is used to provide an anonymous database collision and computing environment. The data application request end receives the a-ID and its attached health information data and the b-ID and its attached health information data sent by the institutional data collection end.

[0047] The data application request end sends a request to the identification data management party, requesting the identification data management party to determine whether the patients represented by a-ID and b-ID are the same person.

[0048] The identification data manager feedbacks that the data application requester a-ID and b-ID are the same person.

[0049] The data application requester aggregates a-ID, b-ID and the health data contained therein in person A's profile.

[0050] The data application request end combines the data provided by institution 1 and institution 2 according to the mutual correspondence between a-ID and b-ID. In the whole process, the personal information of patient A is kept completely confidential, and only health information is reflected.

[0051] After completing the data submission of a-ID and b-ID, a-ID and b-ID can be removed from the submitted table. Then they can be used for scientific research, further reducing the risk of leaking personal A's information and protecting personal privacy.

[0052] Embodiment 3:

[0053] A medical data aggregation statistical analysis method comprises the following steps:

[0054] 1) Data collection: The personal identification data collection terminal generates an encrypted x-ID from the personal information and interacts with the institutional data collection terminal. That is, when person A visits institution No. 1 for treatment, a-ID is generated; when person A visits institution No. 2 for treatment, b-ID is generated. The generation rule of the x-ID is institution code + personal in-hospital identification code, that is, an institution code is generated by the medical institution, and the personal in-hospital identification code is generated according to the patient's identity information according to its generation rule.

[0055] 2) Data collection: Associate the health information data belonging to an individual with the corresponding x-ID. If the individual receives medical treatment at multiple medical institutions, the health data of the medical institutions corresponding to different x-IDs are associated respectively. That is, institution No. 1 receives a-ID and collects a health information data associated with a-ID, and institution No. 2 receives b-ID and receives b health information data associated with b-ID.

[0056] 3) Data request: The data application request end receives health information data containing x-ID from different parties, outputs the obtained x-ID to the identification data manager, and sends a request to the identification data manager to feedback whether a-ID and b-ID are the same person.

[0057] 4) Data aggregation: The identification data management party accepts the request from the data application request end, that is, performs anonymized data operations on a-ID and b-ID to determine whether the patients represented by a-ID and b-ID are the same person. If they are the same person, the result is fed back to the data application request end.

[0058] 5) Data analysis: The data application request end receives the feedback from the identification data manager and summarizes the health data attached to the x-ID belonging to the same person in the person's profile for corresponding data calculation.

[0059] Embodiment 4:

[0060] The data application request end accepts the commission to conduct research and analysis on whether pneumonia patients belong to the high-risk group for contracting the new crown. And obtain multiple pneumonia medical data from institution No. 1, including a-ID-pneumonia medical data, b-ID-pneumonia medical data, c-ID-pneumonia medical data; multiple new crown medical data from institution No. 2, including d-ID-new crown medical data, e-ID-new crown medical data, f-ID-new crown medical data, g-ID-new crown medical data, and multiple new crown medical data from institution No. 3, including h-ID-new crown medical data, i-ID-new crown medical data, j-ID-new crown medical data.

[0061] The data application request end sends a~j-ID to the identification data management party, requesting the identification data management party to determine which IDs in a~j-ID are the same person. The identification data management party obtains that a-ID, d-ID, h-ID are the same person, b-ID, e-ID are the same person, c-ID and g-ID are the same person according to the encoding rules when a~j-ID is produced by the personal identification data collection terminal, and feeds back to the data application request end.

[0062] The data application request end aggregates the medical data of a-ID, d-ID, and h-ID into the information of person A, aggregates the medical data of b-ID and e-ID into the information of person B, and aggregates the medical data of c-ID and g-ID into the information of person C, and performs analysis to generate a scientific research report.

[0063] The data processing system of the present invention is described in detail above, but the present invention is not limited to the specific details in the above-mentioned implementation mode. Within the technical concept of the present invention, the technical solution of the present invention can be subjected to various changes, and these simple variations all belong to the protection scope of the present invention.

Claims

1. A medical data aggregation statistical analysis system, characterized by: include: A personal identification data collection terminal, an institutional data collection terminal, and a data application request terminal; the personal identification data collection terminal generates an encrypted x ID from personal information, interacts with the institutional data collection terminal, and transmits the x ID information to the institutional data collection terminal; the institutional data collection terminal aggregates personal health information data and associates the collected health information data with the personal x-ID; the data application request terminal includes an identification data manager, which is a legal manager with a personal identification information database, and submits different anonymization codes, namely the x ID, to determine whether it is the authentication of the same person; when the data application request terminal receives the X-IDs of different institutions sent by the institutional data collection terminal, the data application request terminal sends a request to the identification data manager, requesting the identification data manager to determine whether the patients represented by the X-IDs from different institutions are the same person; when the identification data manager determines that two or more different X-IDs are the same person, the identification data manager feeds back that the X-ID sent by the data application request terminal is the same person; then the data application request terminal aggregates the health data attached to different X-IDs of the same person in the A person information.

2. The medical data aggregation statistical analysis system as described in claim 1, wherein there are multiple personal identification data collection terminals, the personal identification data collection terminal a accepts the request from person A to institution No. 1, generates an a ID and sends it to the institution data collection terminal, and the personal identification data collection terminal b accepts the request from person A to institution No. 2, generates a b ID and sends it to the institution data collection terminal.

3. The medical data aggregation statistical analysis system according to claim 1, characterized in that: The institutional data collection end aggregates personal health information data, wherein institution No. 1 accepts a-ID and collects a health information data associated with a-ID, and institution No. 2 accepts b-ID and receives b health information data associated with b-ID.

4. The medical data aggregation statistical analysis system according to claim 1, wherein: The data application request end merges the data provided by institution No. 1 and institution No. 2 according to the mutual correspondence given by a-ID and b-ID.

5. The medical data aggregation statistical analysis system according to claim 4, characterized in that: After the data merger is completed, a-ID and b-ID are removed from the merged table and then provided to the project team including institution 1 and institution 2 for scientific research use, thereby reducing the risk of personal information leakage and protecting personal privacy.

Citation Information

Cited By

  • An identity-based verifiable data aggregation and analysis system assisted by SGX

    CN117675200B