KR20230039178A - Medical data sharing method based on block-chain without private information leakage and service providing apparatus - Google Patents

Abstract

A blockchain-based medical data sharing method without exposing personal information includes the steps of: receiving medical data from a plurality of users, respectively, by a service device; extracting, by the service device, data items composed of 'key and value' from the medical data; filtering, by the service device, by removing items related to personal information from the data items; and distributing, by the service device, block data including the identification key of the service device and the filtered data items to a blockchain.

Description

Blockchain-based medical data sharing method and service device without personal information exposure

A technique described below relates to a technique for sharing medical data without exposing personal information.

Medical data can be used in various fields such as drug development, disease diagnosis, and insurance design. Medical data may include personal identifiers, personal health information, and the like. That is, medical data basically corresponds to personal information. Therefore, medical data has properties that are difficult to use as public data.

Korean Patent Publication No. 10-2021-0039190

The technology described below aims to provide a technique capable of sharing necessary information while de-identifying medical data with personal information properties. Furthermore, the technology described below aims to provide a system capable of compensating data providers according to the use of medical data provided by individuals.

A blockchain-based medical data sharing method without personal information exposure includes the steps of receiving medical data from a plurality of users by a service device, extracting data items composed of 'keys and values' from the medical data by the service device, The service device removing and filtering items related to personal information from among the data items and distributing block data including the identification key of the service device and the filtered data items to a blockchain by the service device. include

A service device providing a medical data sharing service extracts data items composed of 'keys and values' from an input device that receives medical data from a plurality of users, respectively, from the medical data, and among the data items related to personal information. It includes an arithmetic unit that removes items to extract filtered data items and generates block data including an identification key of a service device and the filtered data items, and a communication unit that transmits the block data to a blockchain.

The technology described below de-identifies personal medical data and creates ownership information in the medical data based on NFT (Non Fungible Token), so that data providers can be compensated without exposing personal information.

1 is an example of a blockchain-based medical data sharing system.
2 is an example of a process of processing medical data by a service device.
3 is an example of a service device.

Since the technology to be described below can have various changes and various embodiments, specific embodiments will be illustrated in the drawings and described in detail. However, this is not intended to limit the technology described below to specific embodiments, and it should be understood to include all modifications, equivalents, or substitutes included in the spirit and scope of the technology described below.

Terms such as first, second, A, B, etc. may be used to describe various elements, but the elements are not limited by the above terms, and are merely used to distinguish one element from another. used only as For example, without departing from the scope of the technology described below, a first element may be referred to as a second element, and similarly, the second element may be referred to as a first element. The terms and/or include any combination of a plurality of related recited items or any of a plurality of related recited items.

In terms used in this specification, singular expressions should be understood to include plural expressions unless clearly interpreted differently in context, and terms such as “comprising” refer to the described features, numbers, steps, operations, and components. , parts or combinations thereof, but it should be understood that it does not exclude the possibility of the presence or addition of one or more other features or numbers, step-action components, parts or combinations thereof.

Prior to a detailed description of the drawings, it is to be clarified that the classification of components in the present specification is merely a classification for each main function in charge of each component. That is, two or more components to be described below may be combined into one component, or one component may be divided into two or more for each more subdivided function. In addition, each component to be described below may additionally perform some or all of the functions of other components in addition to its main function, and some of the main functions of each component may be performed by other components. Of course, it may be dedicated and performed by .

In addition, in performing a method or method of operation, each process constituting the method may occur in a different order from the specified order unless a specific order is clearly described in context. That is, each process may occur in the same order as specified, may be performed substantially simultaneously, or may be performed in the reverse order.

The technology to be described below is a medical data sharing method and sharing system.

Medical data may be composed of various items of information. Medical data may include health examination results, diagnosis results, and biometric information. For example, medical data includes image data (CT, MRI, X-ray), biopsy results, blood analysis results, body information (height, weight, etc.), bio-signal data (electrocardiogram results, blood pressure, etc.), and data measured by IoT devices. It may include lifestyle data (exercise amount, activity pattern, etc.), genetic data, and the like.

Genomic data may include a nucleotide sequence obtained from a sample (cell or tissue) of a specific user, gene expression data, genetic variation with standard genome data, DNA methylation, and the like.

The service device is a device that removes personal information from medical data and shares the medical data. The service device may be implemented as various devices capable of processing data. For example, the analysis device may be implemented as a PC, a server on a network, a chipset in which a dedicated program is embedded, and the like.

1 is an example of a blockchain-based medical data sharing system 100.

Medical data can be generated by various entities. Medical data can be generated by hospitals, genome analysis institutions, health examination centers, and wearable devices. The medical data generating device 50 generates medical data of a corresponding individual. The medical data generating device 50 may be various, such as a diagnosis device, a genome analysis device, a wearable device, a medical institution server, and the like. Medical data may be provided to a corresponding user in the form of digital data. A user may check medical data through the user terminal 110 . Furthermore, medical data may be stored in a database such as an electronic medical record (EMR) 120.

The user A may transmit his or her medical data to the service server 130 through the user terminal 110 . The service server 130 is a service device that provides a medical data sharing service. Meanwhile, the service server 130 may receive medical data from a database storing medical data, such as the EMR 120 .

The service server 130 regularly processes medical data and deletes personal information. The service server 130 de-identifies the medical data and stores it in the internal database 135 along with identification information of a provider (individual) of the medical data. In addition, the service server distributes block data including medical data to the blockchain 140 using the key of the service server 130 .

The medical data user (B) can obtain desired data from the blockchain 140 using the user terminal 150 . The service server 130 may compensate the user A for the medical data used by the user B of the medical data.

2 is an example of a process 200 of processing medical data by a service device.

The service device receives medical data of each user from a plurality of users (user 1 to user n) (210). Of course, the service device may receive medical data held by other institutions (hospitals, health examination centers, genome analysis companies, etc.) with the user's consent.

Medical data can be of various types. For convenience of explanation, it is assumed that the medical data is a health checkup result. Health examination results are generally in the form of digital files (PDF, JPG, etc.) that can be viewed on a computer device.

If an individual user uploads his or her health checkup results to a service device, they can generally be uploaded in the form of a digital file. In this case, the individual may transmit his or her medical data to the service device in the form of a file such as PDF. Meanwhile, an individual user may transmit certain information in the form of text to a service device using his/her own terminal.

Alternatively, the service device may receive a health checkup result for a specific individual from a separate database having health checkup results. In this case, the service device may directly receive medical data in the form of text as well as the aforementioned digital files (PDF, JPG, etc.).

The service device extracts medical data items and values for the items in the form of (key, value) from the image file or text file (220). The service device may extract the text using image processing technology in the case of a file from which text cannot be directly extracted. The service device may extract (key, value) from the image file using a machine learning model such as an artificial neural network model. Data extracted by the service device may vary as shown in Table 1 below. Table 1 below is an example of some of the medical data.

number Key Value One personal name text 2 personally identifiable information text 3 Disease information text 4 height value 5 age value 6 weight value 7 Blood pressure value 8 Blood tests (platelets) value 9 Blood test (HDL) value 10 blood test (blood sugar) value 11 Blood tests (total markers) value 12 Urine test (urea nitrogen) value 13 Urinalysis (creatinine) value 14 gastroscopy text, video 15 genomic data sequence file

The service device may filter information sensitive to exposure from the extracted data (key, value) (230). For example, the service device may remove items such as name, address, social security number, and the like so as not to be exposed. In FIG. 2, shaded (key, value) correspond to objects to be removed.

The service device is removed and the remaining data is stored in the database (240). At this time, the service device stores data together with information identifying a user who provided the corresponding medical data. For example, the service device may store data in a database in the form of (user identification key, (key, value)). In this case, the user identification key refers to information for identifying a user within a platform providing a medical data sharing service.

The service device creates block data for the extracted medical data (250) and distributes it to the blockchain. The service device will distribute the medical data along with key information that uniquely identifies the block data. The service device generates block data using the identification key of the platform. In other words, the block data stored in the blockchain indicates that the platform (service provider) is the source of the data.

In the case of a typical blockchain, the blockchain stores data along with identifiers that identify individual nodes distributing that data. In this case, a third party who has access to the blockchain can know that specific data has been delivered (generated) from a specific node. In the case of medical data, it is necessary to prevent exposure of personal information, but if a personal node is identified, there is a risk that the subject of the medical data will be known. To prevent such a problem, service devices share medical data using a key identifying the platform. In this case, a third party can know that a specific platform has shared medical data, but cannot know which subject the data was extracted from.

A service device can distribute block data to a non-fungible token (NTF) blockchain. NTF is generally used to issue unique ownership of digital data and is used for transactions on that data.

3 is an example of a service device 300 . The service device 300 corresponds to the aforementioned service device ( 130 in FIG. 1 ). The service device 300 may be physically implemented in various forms. For example, the service device 300 may have a form of a computer device such as a PC, a network server, and a data processing dedicated chipset.

The service device 300 may include a storage device 310, a memory 320, an arithmetic device 330, an interface device 340, a communication device 350, and an output device 360.

The storage device 310 may store personal medical data.

The storage device 310 may store programs or codes for processing medical data. The storage device 310 may store a machine learning model for extracting (key, value) from a medical data source file. Machine learning models must be trained to extract (key, value) from digital files (videos, etc.) in advance. The storage device 310 may store an algorithm for extracting (key, value) by mining text in a medical data source file.

The storage device 310 may store unidentified medical data, block data, and the like.

The memory 320 may store data and information generated in the process of processing and sharing medical data by the service device 300 .

The interface device 340 is a device that receives certain commands and data from the outside. The interface device 340 may receive personal medical data from a physically connected input device or external storage device. The interface device 340 may receive information (identification information) of an individual providing medical data.

The communication device 350 refers to a component that receives and transmits certain information through a wired or wireless network. The communication device 350 may receive personal medical data from an external object. The communication device 350 may receive personal information (identification information) providing medical data.

Alternatively, the communication device 350 may transmit block data including de-identified medical data to the blockchain.

Since the interface device 340 and the communication device 350 are configured to send and receive certain data from a user or other physical object, they can also be collectively referred to as input/output devices. If the function of receiving medical data is limited, the interface device 340 and the communication device 350 may also be referred to as input devices.

The output device 360 is a device that outputs certain information. The output device 360 may output interfaces and data processing results required for data processing.

The arithmetic device 330 may detect measurement points in the head measurement radiographic image using instructions or program codes stored in the storage device 310 .

The computing device 330 may extract a data set consisting of (key, value) from medical data. The computing device 330 may extract a data set by inputting medical data to a machine learning model. Computing device 330 may extract a data set from text data. Through this process, the computing device 330 performs de-identification of medical data.

The computing device 330 filters data corresponding to personal information from the extracted data set. As described above, the arithmetic device 330 may delete data corresponding to personal information such as a name, address, social security number, and the like as a key.

The arithmetic device 330 may finally generate block data using the remaining data set. At this time, the computing device 330 may configure the identification key of the service device (platform) and the data of the data set as block data. The computing device 330 may configure one (key, value) as one block data or may configure the entire medical data set provided by the same individual as one block data.

The arithmetic device 330 may be a device such as a processor, an AP, or a chip in which a program is embedded that processes data and performs certain arithmetic operations.

4 is an example of a process 400 for providing a medical data sharing service.

First, users involved in sharing medical data may sign up for service. A user providing medical data requests membership registration to the service server 130 through the user terminal 110 (401). Meanwhile, a user who wants to use medical data may also request membership registration to the service server 130 through the user terminal 150 (402). The service server 130 proceeds with a certain membership registration process (403). The service server 130 may generate an individual private key for the authenticated user.

The user terminal 110 transmits certain medical data to the service server 130 (411). The service server 130 may process the received medical data regularly. The service server 130 may extract a medical data set having items (key, value) from a digital file using a machine learning model (421). The service server 130 may filter items related to personal information from the data set extracted through the de-identification process (421).

The service server 130 transfers the private key of the user who provided the medical data and the finally filtered data medical data to the internal DB 135 (422), and the internal DB 135 stores the private key and medical data in the form of a table. Save the set (423).

The service server 130 distributes the final filtered medical data set to the blockchain 140 (431). At this time, the service server 130 distributes the medical data to the blockchain 140 using the unique key of the platform. Blockchain 140 stores (432) a de-identified data set (medical data).

The user terminal 150 requests specific medical data from the service server 130 (441). The service server 130 transmits the requested specific medical data to the user terminal 150 (442). This process can be implemented in various ways. The service server 130 may transmit information about a block in which corresponding medical data is stored to the user terminal 150 so that the user terminal 150 can access the medical data. Alternatively, upon receiving a request for specific medical data, the service server 130 may transmit the request to the block chain 140 and transmit the specific medical data to the user terminal 150 using a smart contract.

The user terminal 150 may request medical data corresponding to specific request information. In this case, the service server 130 may control the requested medical data to be transmitted to the mobile terminal 150 . The specific request information may include at least one of age group, gender, race, disease type, and specific phenotype.

Meanwhile, unlike FIG. 4 , the user terminal 150 may directly acquire desired medical data from the blockchain 140 . In this case, the block chain 140 may execute a smart contract to inform the service server 130 that specific medical data has been used.

The service server 130 queries the internal DB 135 for the owner of the medical data used (requested) by the user terminal 150 (451), and extracts the owner's private key (451).

Thereafter, the service server 130 may reward the corresponding user with respect to the use of the medical data (461). Compensation can be carried out through coin transfers on the blockchain or online financial transactions in the real world.

In addition, the medical data processing method or medical data sharing method as described above may be implemented as a program (or application) including an executable algorithm that may be executed on a computer. The program may be stored and provided in a temporary or non-transitory computer readable medium.

A non-transitory readable medium is not a medium that stores data for a short moment, such as a register, cache, or memory, but a medium that stores data semi-permanently and can be read by a device. Specifically, the various applications or programs described above are CD, DVD, hard disk, Blu-ray disk, USB, memory card, ROM (read-only memory), PROM (programmable read only memory), EPROM (Erasable PROM, EPROM) Alternatively, it may be stored and provided in a non-transitory readable medium such as EEPROM (Electrically EPROM) or flash memory.

Temporary readable media include static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDR SDRAM), and enhanced SDRAM (Enhanced SDRAM). SDRAM, ESDRAM), Synchronous DRAM (Synclink DRAM, SLDRAM) and Direct Rambus RAM (DRRAM).

This embodiment and the drawings accompanying this specification clearly represent only a part of the technical idea included in the foregoing technology, and those skilled in the art can easily understand it within the scope of the technical idea included in the specification and drawings of the above technology. It will be obvious that all variations and specific examples that can be inferred are included in the scope of the above-described technology.

Claims (8)

receiving medical data from a plurality of users by a service device;
extracting, by the service device, data items composed of 'key and value' from the medical data;
filtering by the service device by removing items related to personal information from among the data items; and
Distributing, by the service device, block data including the identification key of the service device and the filtered data items to a blockchain. According to claim 1,
The method of sharing blockchain-based medical data without exposing personal information, wherein the service device extracts the data item from medical data that is an image using a learned machine learning model. According to claim 1,
The service device further comprises storing an identification key of each of the plurality of users and data items provided by the user in a database,
extracting, by the service device, an identification key for the provided data item and the corresponding item from the database, when there is a data item provided at the user's request among the data items distributed in the blockchain; and
A blockchain-based medical data sharing method without exposing personal information comprising the step of the service device performing a compensation operation for the user of the extracted identification key. According to claim 1,
The blockchain is a non-fungible token (NTF) based blockchain, a blockchain-based medical data sharing method without exposing personal information. an input device that receives medical data from a plurality of users;
Data items composed of 'key and value' are extracted from the medical data, and filtered data items are extracted by removing items related to personal information among the data items, and the identification key of the service device and the filtered data items are extracted. an arithmetic unit for generating block data including; and
A service device providing a medical data sharing service including a communication device transmitting the block data to a blockchain. According to claim 5,
The service device providing a medical data sharing service in which the computing device extracts the data item from medical data, which is an image, using a learned machine learning model. According to claim 5,
Further comprising a storage device for storing a user's identification key and the filtered data items provided by the user for each of the plurality of users,
Wherein the computing device extracts the user's identification key for the provided item when there is a data item provided at the user's request among the data items distributed on the blockchain. According to claim 5,
The block chain is a non-fungible token (NTF) based block chain, a service device providing a medical data sharing service.

Images