JP6544697B2 - Biological information evaluation system - Google Patents

Description

  The present invention relates to a biological information evaluation system that calculates a disease risk from changes in biological information.

  Conventionally, as this type of biological information evaluation system, as shown in Patent Document 1 below, RNA transcripts of one or more selected gene markers or their expression products in a gastrointestinal sample obtained from a patient A device is known that determines the signs of cell proliferation by determining the expression level of

JP, 2015-165811, A

  Here, in the conventional biological information evaluation system, the expression level is determined from a specific gene marker, but in the first place, attention is paid to any index included in the biological information from biological information such as huge gene information. Whether it should be or not requires a large number of trials.

  Then, an object of the present invention is to provide a living body information evaluation system which can find out the specificity of the index contained in living body information simply and surely.

The biological information evaluation system of the first invention is a biological information evaluation system for calculating a disease risk from a change in biological information, and
A disease for which a disease risk evaluation model is created and stored for calculating a disease risk when a plurality of biological information having a plurality of indices are input and the same type of biological information is input from the plurality of input biological information Risk assessment model creation department,
When the biological information for which the disease risk is to be calculated is designated, the disease risk of the biological information is evaluated by the disease risk evaluation model stored by the disease risk evaluation model creating unit based on the plurality of indices of the biological information. And a disease risk calculation unit that calculates and outputs
The disease risk assessment model creating unit is based on time series data by inputting time series data of a part or all of the plurality of indices of the biological information as a feature amount into a hierarchical time memory algorithm which is a learning device. The hierarchical time memory algorithm generates an evaluation model in which state transition diagrams of appearance patterns and appearance probabilities are grouped into biological information combinations having high transition probabilities as groups of biological information to be included in the state transition diagrams, The created evaluation model is characterized as the disease risk evaluation model.

  According to the living body information evaluation system of the first invention, evaluation is performed in which a part or all of a plurality of indices of living body information is input as a feature amount to a hierarchical time memory algorithm which is a learning device, and the hierarchical time memory algorithm generates Make the model a disease risk assessment model. Here, since the temporal change is reflected, the hierarchical time memory algorithm can easily and surely find out a specific appearance pattern and appearance establishment, taking into consideration the temporal change from the huge amount of biological information.

  Thus, according to the living body information evaluation system of the first aspect of the invention, the specificity of the index included in the living body information can be found easily and surely.

  The disease risk includes, in addition to the risk of developing a specific disease, constitution (hormone balance), stress, personality, and life span.

The biometric information evaluation system according to a second aspect of the present invention is the system according to the first aspect, wherein
The biological information is a cytokine level of saliva, and the plurality of indicators are a plurality of cytokine markers of the saliva,
The disease risk assessment model creation unit is characterized in that a plurality of cytokine values of saliva having a plurality of cytokine markers are input, and a cancer risk assessment model for calculating cancer risk is created and stored from the input cytokine markers. I assume.

  According to the biological condition evaluation system of the second invention, the cytokine value of saliva is taken as biological information, and the plurality of cytokine markers of the saliva are used as a plurality of indicators, thereby providing saliva having a plurality of cytokine markers in the hierarchical time memory algorithm. A plurality of cytokine values are input, and a cancer risk assessment model for calculating cancer risk can be created from the input cytokine markers.

  Thus, according to the biological information evaluation system of the second aspect of the present invention, the specificity of a particular cytokine marker can be found simply and surely for the cytokine level of saliva.

The biometric information evaluation system according to a third aspect of the present invention is the first or second aspect, wherein
The disease risk assessment model creation unit inputs a part or all of the plurality of indices of the biological information as feature quantities to a learning device other than the hierarchical time memory algorithm, and the hierarchical time memory algorithm and the other The disease risk assessment model is created by integrating the primary assessment model created by each of the learners.

  According to the biometric information evaluation system of the third aspect, part or all of a plurality of indicators of biometric information are also input as feature amounts to a learning device other than the hierarchical time memory algorithm, and the hierarchical time memory algorithm and the other By integrating the primary evaluation models created by the learning devices, it is possible to create a disease risk evaluation model that exceeds the generalization ability of each learning device.

  Thus, according to the living body information evaluation system of the third aspect of the invention, the specificity of the index included in the living body information can be found easily and more reliably.

BRIEF DESCRIPTION OF THE DRAWINGS The system configuration | structure figure which shows the outline | summary of the biometric information evaluation system of this embodiment. The flowchart which shows the processing content of the biometric information evaluation system of FIG. Explanatory drawing which shows the processing content of the biometric information evaluation system of FIG. FIG. 2 is a system configuration diagram showing an overview of a biological information management system in which the biological information evaluation system of FIG. 1 is incorporated. FIG. 5 is a flowchart showing processing contents in the biological information management system of FIG. 4; FIG. FIG. 5 is a flowchart showing processing contents in the biological information management system of FIG. 4; FIG. FIG. 5 is a flowchart showing processing contents in the biological information management system of FIG. 4; FIG. FIG. 5 is a flowchart showing processing contents in the biological information management system of FIG. 4; FIG.

  As shown in FIG. 1, the biological information evaluation system 1 of the present embodiment is a system for calculating a disease risk from a change in biological information, and is configured by a computer system.

  Although detailed illustration is omitted, the computer system is, for example, a system including one computer or a plurality of computers which can communicate with each other. An arithmetic processing unit including a CPU, a RAM, a ROM, an interface circuit and the like is mounted on a computer constituting the computer system.

  In addition, the computer system includes, as a component or additional element of a computer constituting the computer system, an input operation unit constituted by a keyboard, a mouse, a touch panel etc., an information output unit constituted by a display, a printer etc. A wireless communication device and a storage device configured by a hard disk or the like are included.

  In addition, when biometric information price evaluation system 1 is constituted by a plurality of computers, those computers may be distributed and arranged at a plurality of distant places.

  In addition, the input operation unit or the information output unit may include a personal computer used by the administrator or user of the biometric information price evaluation system 1 as needed, or a portable terminal (smartphone, tablet terminal, etc.).

  In the present embodiment, biological information to be evaluated by the biological information price evaluation system 1 is, for example, a cytokine value of saliva obtained by collecting saliva. Then, the biometric information price evaluation system 1 has a biometric information storage unit 11 and personal data as functions realized by the hardware configuration (the arithmetic processing unit) of the computer that constitutes it and the software installed in the computer. A storage unit 12, a disease risk assessment model creation unit 13, and a disease risk calculation unit 14 are provided.

  The biological information storage unit 11 is a means for storing and holding biological information, and stores and holds, for example, time-series data of values of salivary cytokines linked to an ID for which an individual is not identified.

  The personal data storage unit 12 is means for storing and holding the information of the subject related to the biological information, and for example, data such as gender information, age information, smoking information, etc. linked to an ID for which an individual is not identified It is kept in memory.

  The disease risk assessment model creation unit 13 creates a disease risk assessment model for calculating the disease risk from the input biological information.

  Specifically, the disease risk assessment model creating unit 13 inputs a part or all of a plurality of indices of biological information as feature amounts into a hierarchical time memory algorithm as a learning device, and the hierarchical time memory algorithm is generated. The evaluated model is taken as a disease risk evaluation model.

  For example, assuming that the cytokine level of saliva is biological information and the plurality of cytokine markers of saliva is a plurality of indexes, a plurality of cytokine values of saliva having a plurality of cytokine markers are input and input to the hierarchical time memory algorithm. From the cytokine markers, a cancer risk assessment model can be created to calculate cancer risk.

  When the biological information for which the disease risk is to be calculated is designated, the disease risk calculation unit 14 uses the disease risk evaluation model stored by the disease risk evaluation model generation unit 13 based on a plurality of indices of the biological information. The disease risk of the biological information is calculated and output.

  Next, with reference to FIG. 2 and FIG. 3, the contents of processing for creating a disease risk assessment model by the disease risk assessment model creation unit 13 will be described.

  As shown in FIG. 2, the disease risk assessment model creating unit 13 first acquires biological information (STEP 11 / FIG. 2).

  For example, when using a cytokine level of saliva as biological information, temporal change data of 30 types of cytokine levels measured from saliva are acquired.

  Next, the disease risk assessment model creating unit 13 identifies, from the plurality of indices possessed by the biological information, some or all of the biological information acquired in STEP 11 that can be a feature (STEP 12 / FIG. 2).

  For example, when the cytokine level of saliva is used as biological information, of the 30 types of cytokine levels obtained as measurement values, 18 characteristic types as shown on the lower side of FIG. 3 are specified as cytokine markers.

  Next, the disease risk assessment model creating unit 13 creates a state transition diagram of a pattern based on time series data of the index specified in STEP 12 (STEP 13 / FIG. 2).

  For example, in the case where salivary cytokine levels are used as biological information, as shown on the upper side of FIG. 3, four cytokine data are grouped into one group as a first layer (first layer), and appearance patterns of these four groups A second layer is formed based on the appearance probability. Then, a third layer is formed based on the appearance pattern of the second layer and the probability thereof. Create only such transition patterns.

  Next, the disease risk assessment model creating unit 13 groups the combinations of indicators of biological information included in the state transition diagram created in STEP 13 so that those with high transition probability become groups (STEP 14 / FIG. 2).

  For example, in the case where salivary cytokine levels are used as biological information, combinations in which transition probability is high are set as grouping based on time series data of 18 types of cytokine markers.

  Next, the disease risk evaluation model creating unit 13 assigns the grouping determined in STEP 14 to the state transition diagram of STEP 13 and calculates conditional probability (STEP 15 / FIG. 2).

  For example, in the case where salivary cytokine levels are used as biological information, it is preferable to group the cytokine markers determined in STEP 14 (combination of the transition probabilities of the 18 kinds of cytokine markers with high transition probability). Assign to one hierarchy. Then, for the first hierarchy, the appearance pattern and the appearance probability of the grouping (combination) are calculated.

  Next, the disease risk assessment model creating unit 13 determines whether the conditional probability calculation process of STEP 15 has been completed for all nodes and layers (STEP 16 / FIG. 2).

  Then, if the process has not been completed for all nodes and hierarchies (NO in STEP 16 / FIG. 2), the series of processes from STEP 13 are repeatedly executed until all the nodes and hierarchies are completed, and the appearance pattern calculated And remember the probability of appearance.

  On the other hand, if all the nodes and hierarchies have been completed (YES in STEP 16 / FIG. 2), the disease risk assessment model creating unit 13 ends the series of processes.

  The above is the contents of processing to create a disease risk assessment model by the disease risk assessment model creation unit 13, and such a disease risk assessment model is based on a vast amount of biological information by using a hierarchical time memory algorithm in which changes over time are reflected. The appearance pattern and the appearance establishment of a specific index can be found simply and surely in consideration of the time change. That is, the specificity of the index included in the biological information can be found simply and reliably, and a disease risk assessment model based on this can be created.

  In the present embodiment, the hierarchical time memory algorithm is used as the learning device. However, the present invention is not limited to this, and may be combined with a learning device other than the hierarchical time memory algorithm. For example, by integrating a primary evaluation model created by the hierarchical time memory algorithm and deep learning as another learning device, a disease risk evaluation model exceeding the generalization ability of each learning device may be generated. Good.

  Furthermore, other learners to be combined may combine random forests and elastic nets in addition to deep learning.

  Further, in the present embodiment, the case of creating a disease risk evaluation model using the biological information stored in the biological information storage unit 11 has been described, but the present invention is not limited to this. The appearance pattern and the appearance probability may be calculated by combining data such as gender information, age information and smoking information stored in 12.

  The disease risk assessment model created in this manner is used, for example, in the creation of cancer risk assessment results (STEP 232 / FIG. 7) in the biological information management system shown in FIG.

  The biological information management system shown in FIG. 4 is a system for storing and holding the biological information of the user, and includes a user terminal 100 provided on the user side, a management system main body 200 connected to the user terminal 100 via a network, And a distributed ledger system 300 connected to the management system main body 200 via a network and storing and holding biometric information of the user.

  Here, the biological information is various information such as various physiological and anatomical information related to the living body, and besides the information specifying the individual like DNA information, the individual is not specified like the heart rate It is a concept that includes both of information.

  The user terminal 100 is, for example, an information terminal such as a smartphone or a tablet of the user of the saliva cancer marker test kit, which is a measurement kit of biological information, and includes the network communication unit 110, the work memory 111, and the program memory 112. , A display input unit 13, a photographing unit 114, and a key data storage unit 115.

  The network communication unit 110 is a communication processing unit that performs connection with a wide area communication network such as the Internet.

  The work memory 111 temporarily stores data for various processes in the user terminal 100.

  The program memory 112 stores the program itself in various processes in the user terminal 100, and in the present embodiment, has a web application unit 112a that stores a program of a web application, and an API (Application Program Interface) server unit 112b. .

  The display / input unit 113 is a display unit as an interface capable of display and touch input.

  The imaging unit 114 is an imaging unit including a CCD camera, a CMOS sensor, and the like.

  The key data storage unit 115 is a storage holding unit in which a decryption key described later is stored.

  The management system body 200 includes a network communication unit 220, a work memory 221, a program memory 222, and a storage unit 225.

  The network communication unit 220 functions as a communication processing unit that performs connection with the user terminal 100 to a wide area communication network such as the Internet, and also performs communication control unit that performs local network connection with the distributed ledger system 300. Act as.

  The work memory 221 temporarily stores data for various processes in the management system main body 200.

  The program memory 222 stores the program itself in various processes in the management system main body 200, and in the present embodiment, has a Web server unit 223 and an API (Application Program Interface) server unit 224.

  The web server unit 223 is an application server that performs processing according to the web application unit 112a of the user terminal 100, and in the present embodiment, the saliva returning unit 223a, the evaluation result viewing unit 223b, and the analysis result input unit 223c. , A saliva ID generation unit 223d, and a manager function unit 223e.

  The API server unit 224 includes a saliva collating unit 224a, a biometric information writing unit 224b, and an evaluation result acquiring unit 224c.

  The storage unit 225 is configured as a saliva metadata storage unit that stores and holds overall data related to saliva data, which is biological information in the present embodiment.

  The distributed ledger system 300 is, for example, a block chain database, and in the present embodiment, it comprises two databases DB1 and DB2 in which the same saliva data is stored, and these are encrypted with different keys.

  The above is the configuration of the living body information management system of the present embodiment. In the above configuration, the user terminal 100 of the biometric information management system, the management system main body 200, and the distributed ledger system 300 are, for example, a central processing unit (CPU), a read only memory (ROM), and a random access memory (RAM). Memory, etc., and a program for executing processing by each processing unit 110 to 113, 115, 220 to 225, DB1, DB2 is stored and held in the memory, and the program is executed to execute the control process. Functions as an arithmetic unit (sequencer) for executing

  Next, with reference to FIGS. 5-8, the processing content of the biometric information management system comprised as mentioned above is demonstrated.

  First, key pair generation processing will be described with reference to FIG.

  In FIG. 8, the user terminal 100 accesses the management system main body 200 by reading in advance a QR code (registered trademark) having a function as a unique identification ID attached to a saliva cancer marker test kit and a serial number. When the user terminal 100 can use the Web application with the management system 200, a key pair of the encryption key and the decryption key is generated by the user's access to the top screen (STEP 111 / FIG. 8). (STEP 112 / FIG. 8).

  Here, the key pair of the encryption key and the decryption key is linked to the unique identification ID attached to the saliva cancer marker test kit.

  Then, it is judged whether or not the key pair has been created (STEP 113 / FIG. 8), and when the key pair can not be generated (STEP 113 / NO in FIG. 8), an error is output.

  On the other hand, when the key pair can be generated (YES in STEP 113 / FIG. 8), the encryption key is transmitted to the management system body 200 and stored in the management system body 200 (STEP 211 / FIG. 8). Are stored in the user terminal 100 (STEP 115).

  Next, with reference to FIG. 6, registration processing of metadata of saliva ID will be described.

  First, when the user collects saliva with the saliva cancer marker test kit and reads, for example, the QR code (registered trademark) of the saliva ID attached to the collection tube through the user terminal 100 (STEP 121 / FIG. 6) It is determined whether the QR code (registered trademark) has been read correctly (STEP 122 / FIG. 6).

  Then, if the QR code (registered trademark) is not read correctly (NO in STEP 122 / FIG. 6), an error is output (STEP 123 / FIG. 6).

  On the other hand, when the QR code (registered trademark) is correctly read (YES in STEP 122 / FIG. 6), the input screen of the inquiry item is displayed (STEP 124 / FIG. 6), and the inquiry item answered is the management system body It transmits to 200 and registration of metadata of object saliva ID is made (STEP221 / FIG. 6).

  Here, the QR code (registered trademark) of the saliva ID attached to the collection tube is basically the same as the QR code (registered trademark) having a function as a unique identification ID attached to the saliva cancer marker test kit or a serial number. However, for example, in the case where there are a plurality of collection tubes for one salivary cancer marker test kit, they may be different.

  When the unique identification ID and the saliva ID are the same, the association between the above-mentioned encryption key and decryption key is maintained as it is. On the other hand, when there is a plurality of saliva IDs for the unique identification ID, the unique identification ID and the plurality of saliva IDs are linked in advance, and the association between the above-mentioned encryption key and decryption key is via the unique identification ID. It is also linked to the saliva ID. In this case, preferably, the unique identification ID is appropriately replaced with the identification ID of the user terminal 100. This is because when the user purchases the saliva cancer marker test kit multiple times, it is necessary to associate the user with the saliva ID of the collection tube bundled with each.

  Next, with reference to FIG. 7, registration of cytokine data of saliva ID and processing for creating a cancer risk evaluation result will be described.

  When the user mails in advance the collection tube from which saliva has been collected using the saliva cancer marker test kit to a testing organization, the testing organization analyzes cytokines in the saliva.

  Here, the analysis result of the cytokine is provided to the management system body 200, and the management system body 200 acquires the analysis result of the cytokine identified by the saliva ID (STEP 231 / FIG. 7).

  Then, the management system body 200 identifies the encryption key of the acquired cytokine data of the target saliva ID based on the unique identification ID, encrypts the cytokine data with the encryption key, and then registers the cytokine data in the distributed ledger system 300. , Store the data in the distributed ledger system 300 (STEP 331 / FIG. 7).

  Furthermore, the management system body 200 creates a cancer risk evaluation result based on the cytokine data of the acquired target saliva ID (and time series data including the already acquired cytokine data if there is any). The obtained cancer risk evaluation result is encrypted with the encryption key and stored in the management system 200 (STEP 232 / FIG. 7).

  The creation of the cancer risk evaluation result is executed by the disease risk calculation unit 14 of the biological information evaluation system 1 of the present embodiment.

  Next, with reference to FIG. 8, the process of providing the cancer risk evaluation result to the user will be described.

  First, when the user operates the user terminal 100 to access the evaluation result display screen (STEP 141 / FIG. 8), the management system body 200 uses the cytokine data of the target saliva ID based on the saliva ID (unique identification ID) And from the distributed ledger system 300 (STEP 241 / FIG. 8).

  Next, the management system body 200 acquires the cancer risk evaluation result of the target saliva ID from the inside of the management system body 200 based on the saliva ID (unique identification ID) (STEP 242 / FIG. 8).

  Here, the cytokine data and cancer risk evaluation result of the target saliva ID acquired in STEP 241 and STEP 242 are in a state of being encrypted by the encryption key.

  Therefore, it is determined whether a decryption key forming a key pair with the encryption key can be acquired by transmission from the user terminal 100 (STEP 142 / FIG. 8) (STEP 243 / FIG. 8).

  Then, if the decryption key can not be acquired (NO in STEP 243 / FIG. 8), an error is output to the user terminal 100 (STEP 143 / FIG. 8), and if the decryption key can be acquired (YES in STEP 243) (FIG. 8) After the cytokine data and the cancer risk evaluation result are decrypted by the decryption key, they are transmitted to the user terminal 100 and displayed (STEP 144 / FIG. 8).

  The above is the configuration and processing contents of the living body information management system of the present embodiment, and according to the living body information management system, when storing and storing cytokine data which is living body information, the user terminal 100 to the management system main body 200 in advance. By access, an encryption key and a decryption key are generated, the encryption key is stored in the management system body 200, and the decryption key is stored in the user terminal 100.

  Therefore, the decryption key is only present in the user terminal 100, and the user who is the subject is not directly identified by the decryption key.

  In addition, cytokine data which is biological information of the user is encrypted based on the encryption key of the management system main body 200, and the encrypted cytokine data is stored and held in the distributed ledger system 300. Furthermore, since the encoded cytokine data read from the distributed ledger system 300 is decrypted by the decryption key acquired from the user terminal 100, access to the biological information is restricted by the encryption key and the decryption key.

  Furthermore, by linking the encryption key and the decryption key with the unique identification ID (saliva ID) of the saliva cancer marker test kit that is the measurement kit, the cytokine data that is the measurement result is based on the unique identification ID by the encryption key While being able to be encrypted, access to biometric information can be made possible only to user terminals having a decryption key linked to a unique identification ID.

  As described above, according to the biometric information management system of the present embodiment, access to biometric information can be restricted while preventing a user from being identified.

  In addition, although this embodiment demonstrated the case where the saliva cancer marker test kit which is a measurement kit of biological information was used as a living body information management system, it is not limited to this, and other test kits (colon cancer test It may be a kit) or a biological information measuring device (a sphygmomanometer, an activity meter, etc.) other than a test kit.

  In this case, the biometric information (data value or measurement value used as an index in the examination) and the evaluation result based on these (if necessary) are encrypted with the encryption key and then the distributed ledger system from the management system body 200 The biometric information and the evaluation result read from the distributed ledger system 300 are decrypted by the decryption key of the user terminal 100 and provided to the user terminal 100 from the management system main body 200 while being stored and stored at 300.

DESCRIPTION OF SYMBOLS 1 ... biometric information price evaluation system, 11 ... biometric information storage part, 12 ... personal data storage part, 13 ... disease risk evaluation model preparation part, 14 ... disease risk calculation part, 100 ... user terminal, 200 ... management system main body, 300 ... distributed ledger system.

Claims (3)

A biological information evaluation system for calculating a disease risk from changes in biological information, comprising:
A disease for which a disease risk evaluation model is created and stored for calculating a disease risk when a plurality of biological information having a plurality of indices are input and the same type of biological information is input from the plurality of input biological information Risk assessment model creation department,
When the biological information for which the disease risk is to be calculated is designated, the disease risk of the biological information is evaluated by the disease risk evaluation model stored by the disease risk evaluation model creating unit based on the plurality of indices of the biological information. And a disease risk calculation unit that calculates and outputs
The disease risk assessment model creating unit is based on time series data by inputting time series data of a part or all of the plurality of indices of the biological information as a feature amount into a hierarchical time memory algorithm which is a learning device. The hierarchical time memory algorithm generates an evaluation model in which state transition diagrams of appearance patterns and appearance probabilities are grouped into biological information combinations having high transition probabilities as groups of biological information to be included in the state transition diagrams, A biological information evaluation system , wherein the evaluation model created is used as the disease risk evaluation model. In the biometric information evaluation system according to claim 1,
The biological information is a cytokine level of saliva, and the plurality of indicators are a plurality of cytokine markers of the saliva,
The disease risk assessment model creation unit is characterized in that a plurality of cytokine values of saliva having a plurality of cytokine markers are input, and a cancer risk assessment model for calculating cancer risk is created and stored from the input cytokine markers. Biological information evaluation system to be. In the biometric information evaluation system according to claim 1 or 2,
The disease risk assessment model creation unit inputs a part or all of the plurality of indices of the biological information as feature quantities to a learning device other than the hierarchical time memory algorithm, and the hierarchical time memory algorithm and the other A biological information evaluation system, characterized in that the disease risk evaluation model is created by integrating the primary evaluation model created by each of the learning devices.