JP2019030275A - Foul breath determination apparatus and program - Google Patents

Abstract

To determine presence/absence of foul breath of a subject based on a saliva of the subject.SOLUTION: A foul breath determination device comprises: a storage part for storing a learned model learned by machine learning, for, based on teacher strain information indicating kinds of bacteria which exist in a bacterial flora in an oral cavity, and teacher ratio information for indicating for every kind, a ratio of each bacterium indicated by the teacher strain information in the bacterial flora, outputting foul breath information indicating whether or not, there is foul breath in the oral cavity; an acquisition part for acquiring strain information indicating kinds of bacteria which exist in the bacterial flora in the oral cavity of the subject, and ratio information indicating the ratio of each bacteria indicated by the strain information for every kind of each bacteria; and an output part for, inputting the strain information acquired by the acquisition part and ratio information acquired by the acquisition part in the learned model, and outputting foul breath information being calculated and indicating whether or not, there is foul breath in the oral cavity of the subject.SELECTED DRAWING: Figure 1

Description

  The present invention relates to a bad breath determination apparatus and a program.

2. Description of the Related Art Conventionally, a technique for detecting the concentration of a specific gas contained in a subject's breath and determining whether or not a bad breath has occurred in the subject's mouth (for example, Patent Document 1) is known.
Further, a technique for cultivating bacteria in the oral cavity based on the saliva of the subject and analyzing the cultured bacteria to determine whether or not bad breath has occurred in the oral cavity of the subject is known (for example, Patent Document 2).

JP 2003-329630 A JP 2002-236124 A

However, in the technique described in Patent Literature 1, when determining whether or not bad breath has occurred, the subject moves to a place where a device capable of detecting exhalation is installed, or a device capable of detecting exhalation. May be required to be moved to the place where the subject undergoes the examination. In the technique described in Patent Document 2, it is required to culture bacteria in the oral cavity of a subject when determining whether or not bad breath has occurred, and it is difficult to shorten the time required for determination. There was a case.
The present invention has been made in view of the above problems, and an object thereof is to provide a bad breath determination apparatus and a program capable of determining the presence or absence of bad breath of a subject based on the saliva of the subject.

  One aspect of the present invention is a teacher bacterial species information indicating the type of bacteria present in the bacterial flora in the oral cavity, and teacher ratio information indicating the proportion of the bacteria indicated by the teacher bacterial species information in the bacterial flora for each type. And a storage unit for storing a learned model learned by machine learning so as to output bad breath information indicating whether or not there is bad breath in the oral cavity, and the bacteria present in the bacterial flora in the oral cavity of the subject The acquisition part which acquires the bacterial species information which shows a type, the ratio information which shows the ratio in the said microflora of the microbe which the said bacterial species information shows for every said type, The said bacterial species information which the said acquisition part acquired, An output unit that inputs the ratio information acquired by the acquisition unit to the learned model and outputs bad breath information indicating whether or not the calculated subject has bad breath.

  In the bad breath odor determination apparatus of one embodiment of the present invention, the machine learning is deep learning.

  In the bad breath odor determination apparatus according to one aspect of the present invention, the teacher bacterial species information and the teacher ratio information are information based on a result of analyzing saliva of a plurality of subjects.

  In addition, the bad breath odor determination apparatus according to an aspect of the present invention includes a detection unit that detects the type of a short base sequence having 5 bases, which is a DNA base sequence present in the saliva bacterial flora, and the detection unit For each type of the short base sequence detected by the method, a rate acquisition unit that acquires a rate at which the base sequence of the type is present in the bacterial flora, a type of bacteria present in the bacterial flora in the oral cavity of the subject, Criteria information indicating the correspondence with the ratio of the bacteria in the bacterial flora for each combination of the type and the ratio, the type of the short base sequence detected by the detection unit, and the short base sequence acquired by the ratio acquisition unit Based on the ratio for each type of, the determination of the type of bacteria present in the bacterial flora in the oral cavity of the subject and the ratio of the bacteria in the bacterial flora, the acquisition unit, Bacterial species indicating the type determined by the determination unit Obtaining a distribution, and a ratio information indicating a ratio in the flora of bacteria indicating the species information for each of the types.

  In addition, the bad breath odor determination apparatus according to an aspect of the present invention includes a detection unit that detects a known base sequence that matches a base sequence of a known 16S rRNA gene, which is a base sequence of DNA present in the bacterial flora of saliva, For each type of the known base sequence detected by the detection unit, a rate acquisition unit that acquires a rate at which the type of base sequence is present in the bacterial flora, and a type of bacteria present in the bacterial flora in the oral cavity of the subject , Reference information indicating the correspondence of the proportion of the bacterium in the bacterial flora for each combination of the type and the proportion, the type of the known base sequence detected by the detection unit, and the known acquired by the proportion acquisition unit A determination unit that determines the type of bacteria present in the bacterial flora in the oral cavity of the subject based on the ratio of each type of base sequence, and the ratio of the bacteria in the bacterial flora, and the acquisition unit Said It acquires the species information indicating the type of part is determined, and the ratio information indicating a ratio in the flora of bacteria the species information indicates for each of the types.

  Further, according to one aspect of the present invention, there is provided a base sequence of DNA existing in a bacterial flora in the oral cavity, the teacher short base information indicating the type of the short base sequence having five bases, and the teacher short base information. A learned model learned by machine learning is stored so as to output bad breath information indicating whether or not there is bad breath in the oral cavity based on the short base ratio information indicating the short base ratio for each type. A short base sequence information indicating the type of short base sequence having five bases, and a short base sequence information indicating the short base sequence information. An acquisition unit that acquires, for each type, a ratio of the base sequence in the bacterial flora, the short base sequence information acquired by the acquisition unit, and the short base ratio information acquired by the acquisition unit. Into the trained model An output unit for outputting bad breath information indicating whether there is bad breath computed the subject, a bad breath determination device comprising a.

  Further, according to one aspect of the present invention, teacher bacterial information indicating the type of bacteria present in the bacterial flora in the oral cavity, and the teacher ratio indicating the ratio of the bacteria indicated by the teacher bacterial species information in the bacterial flora for each type Based on the information, the computer includes a storage unit that stores a learned model learned by machine learning so as to output bad breath information indicating whether or not there is bad breath in the oral cavity. The acquisition step which acquires the bacterial species information which shows the kind of microbe which exists in the said microbe, and the ratio information which shows the ratio in the said microflora of the microbe which the said bacterial species information shows for every said type, The said microbe acquired in the said acquisition step Execute seed information and the ratio information acquired in the acquisition step to the learned model, and output the oral odor information indicating whether or not the calculated subject has bad breath It is a program program to.

  According to the present invention, the presence or absence of bad breath of the subject can be determined based on the saliva of the subject.

It is a figure which shows the outline | summary of the bad breath determination system of this embodiment. It is a functional lineblock diagram showing an example of composition of a microbial species ratio detection device which detects microbial species information and ratio information based on the existence rate of a short base sequence of this embodiment. It is a 1st figure which shows an example of the corresponding information of this embodiment. It is a functional block diagram which shows an example of a structure of the bacterial species ratio detection apparatus which detects bacterial species information and ratio information based on the presence ratio of 16S rRNA gene of this embodiment. It is a 2nd figure which shows an example of the correspondence information of this embodiment. It is a functional block diagram which shows an example of a structure of the halitosis determination apparatus of this embodiment. It is a flowchart which shows an example of operation | movement of the halitosis determination system of this embodiment.

[Embodiment]
Hereinafter, embodiments of the present invention will be described with reference to the drawings.
FIG. 1 is a diagram showing an overview of a bad breath determination system 1 of the present embodiment.
As shown in FIG. 1, the bad breath determination system 1 includes a bad breath determination device 10 and a fungus species ratio detection device 20.
The bad breath determination device 10 is a device that determines the presence or absence of bad breath of a person to be determined (hereinafter, subject ET). The fungus species ratio detection device 20 acquires a collection of bacteria (bacteria flora) in the oral cavity of the subject ET, and determines the type of bacteria present in the oral cavity of the subject ET and the ratio of the bacteria present in the oral cavity. It is a device that detects each type. The bacterial flora can be obtained from, for example, the tongue coating of the subject ET or the saliva of the subject ET (hereinafter referred to as saliva SV). In an example of the present embodiment, the bacterial species ratio detection device 20 detects the type of bacteria and the ratio of the bacteria present in the oral cavity based on the saliva SV of the subject ET. In the following description, information indicating the type of bacteria present in the oral cavity of the subject ET, which is information detected by the bacterial species ratio detection device 20, will be referred to as bacterial species information KB. Moreover, it is the information which the microbe ratio detection apparatus 20 detected, Comprising: The information which shows the ratio for which the microbe which microbe species information KB exists in the test subject's ET oral cavity for every kind of microbe is described as ratio information RB. The bad breath determination apparatus 10 determines the presence or absence of bad breath of the subject ET based on the bacterial species information KB detected by the bacterial species ratio detection device 20 and the ratio information RB.

  Here, the method of detecting the bacterial species information KB and the proportion information RB by the bacterial species ratio detection device 20 includes a method based on the presence ratio of a short base sequence (hereinafter referred to as a short base sequence) and a method based on the presence ratio of a 16S rRNA gene. There is. First, the bacterial species ratio detection device 20 (hereinafter referred to as the bacterial species ratio detection device 20a) that detects the bacterial species information KB and the percentage information RB based on the presence ratio of the short base sequence will be described, and then the existing ratio of the 16S rRNA gene. The bacterial species ratio detection device 20 (hereinafter referred to as the bacterial species ratio detection device 20b) that detects the bacterial species information KB and the percentage information RB will be described. In the following description, in the bacterial species ratio detection device 20, the configuration of the bacterial species ratio detection device 20a is provided with “a” at the end of the reference numeral. In addition, the configuration of the bacterial species ratio detection device 20b is provided with “b” at the end of the reference numeral. In addition, in the case where it is not distinguished which of the bacterial species ratio detection device 20 is configured, “a” or “b” is omitted.

<About the bacterial species ratio detection apparatus 20a>
Hereinafter, the details of the bacterial species ratio detection apparatus 20a that detects the bacterial species information KB and the percentage information RB based on the presence ratio of the short base sequence will be described with reference to the drawings.
FIG. 2 is a functional configuration diagram illustrating an example of the configuration of the bacterial species ratio detection apparatus 20a that detects the bacterial species information KB and the ratio information RB based on the presence ratio of the short base sequences of the present embodiment.
The bacterial species ratio detection device 20a includes a sequencer 21a, a control unit 22a, and a storage unit 23a. The storage unit 23a is realized by, for example, a ROM (Read Only Memory), a flash memory, an SD card, a RAM (Random Access Memory), a register, and the like. For example, short base information 231a and correspondence information 232a are stored in the storage unit 23a in advance.

The short base information 231a is information indicating a deoxyribonucleic acid (hereinafter referred to as DNA) base sequence to be analyzed by the sequencer 21a, and is information indicating a short base sequence indicated by a combination of five nucleotides. In an example of the present embodiment, the analysis target of the sequencer 21a is a bacterium that exists in the saliva SV (in the oral cavity of the subject ET).
The sequencer 21a analyzes the base sequence to be analyzed indicated by the short base information 231a among the DNA base sequences of the bacteria present in the saliva SV (in the oral cavity of the subject ET). Such a sequence comparison is called an alignment. The sequencer 21a aligns and supplies information indicating the type of the obtained short base sequence (hereinafter, short base sequence information SB) to the control unit 22a. In addition, the sequencer 21a performs alignment, and information (hereinafter, short base ratio information RSB) indicating the amount (ratio) of the obtained short base sequence in the saliva SV for each type of the short base sequence (hereinafter, short base ratio information RSB) is sent to the control unit 22a. Supply.

  The control unit 22a implements each functional unit when a processor such as a CPU (Central Processing Unit) executes a program stored in the storage unit 23a. The control unit 22a implements, for example, the determination unit 221a and the output unit 222a as functional units. The control unit 22a may be realized by hardware such as LSI (Large Scale Integration), ASIC (Application Specific Integrated Circuit), or FPGA (Field-Programmable Gate Array), or may be realized by cooperation of software and hardware. May be.

  The determination unit 221a acquires the short base sequence information SB and the short base ratio information RSB from the sequencer 21a. Based on the short base sequence information SB, the short base ratio information RSB, and the correspondence information 232a, the determination unit 221a includes the bacteria (bacteria species information KB) present in the oral cavity of the subject ET, and the bacteria are present in the oral cavity. An existing ratio (ratio information RB) is determined. The correspondence information 232a is information indicating correspondence between the short base sequence information SB and the short base ratio information RSB, the bacterial species information KB, and the ratio information RB.

Hereinafter, details of the correspondence information 232a will be described with reference to the drawings. FIG. 3 is a first diagram illustrating an example of the correspondence information 232a according to the present embodiment.
As shown in FIG. 3, the correspondence information 232a is associated with the short base sequence information SB, the short base ratio information RSB, the fungus species information KB, and the ratio information RB.
Here, when the short base sequence information SB and the short base ratio information RSB of a subject ET are known, the type of bacteria (bacterial species information KB) present in the oral cavity of the subject ET and the bacteria are present in the oral cavity The ratio to be performed (ratio information RB) is uniquely determined. The association between the short base sequence information SB and the short base ratio information RSB, the bacterial species information KB and the ratio information RB is based on the short base sequence indicated by the short base information 231a and the bacteria in the saliva SV in which the base sequence exists. This is performed based on the analysis result.

In the example shown in FIG. 3, n types of short base sequence information SB and the number (n) of short base sequence information RSB corresponding to the short base sequence information SB are associated as the short base information 231a. . n is a natural number. Specifically, FIG. 3 shows that “GGACC (short base sequence information SB1)” is present in the saliva SV at a rate of 0.25% (short base ratio information RSB1), and “CCCCC (short base sequence information SB2) is present. ) "Is present at a rate of 0.5% (short base ratio information RSB2), ..." CCTAG (short base sequence information SBn) "is present at a ratio of 0.25% (short base ratio information RSBn) Indicates.
In the example shown in FIG. 3, the short base sequence information SB1 to the short base sequence information SBn and the short base ratio information RSB1 to the short base ratio information RSBn described above include the bacterial species information KB1 to the bacterial species information KB4 and the ratio information. RB1 to ratio information RB4 are associated as the short base information 231a. Specifically, in the short base information 231a shown in FIG. 3, the short base sequences of the short base sequence information SB1 to the short base sequence information SBn are present in the saliva SV at a ratio of the short base ratio information RSB1 to the short base ratio information RSBn. In this case, in the oral cavity of the subject ET, Actinomycetemcomitans (bacteria species information KB1) is present at a rate of 19% (ratio information RB1), and Nucleatum (bacteria species information KB2) is 29% (ratio information RB2). Gingivalis (bacterial species information KB3) is present at a rate of 21% (ratio information RB3) and mutans (bacterial species information KB4) is present at a rate of 31% (ratio information RB4). Show. In the correspondence information 232a, the bacterial species information KB and the ratio information RB are associated with each combination of the short base sequence information SB and the short base ratio information RSB. The correspondence information 232a is an example of reference information.

Returning to FIG. 2, the determination unit 221a searches the correspondence information 232a using the acquired short base sequence information SB and the short base ratio information RSB as search keys. The determination unit 221a determines (extracts) the bacterial species information KB and the ratio information RB associated with the short base sequence information SB and the short base ratio information RSB that match the search key in the correspondence information 232a. The determination unit 221a supplies the determined bacterial species information KB and the ratio information RB to the output unit 222a.
The output unit 222a supplies the bacterial species information KB and the ratio information RB acquired from the determination unit 221a to the bad breath determination apparatus 10.

In addition, although the case where the short base information 231a is information indicating a combination of five nucleotides has been described above, the present invention is not limited to this. The short base information 231a may be information indicating a base sequence of any length as long as it is information indicating a combination of at least five or more nucleotides.
Further, the sequencer 21a may be configured to supply base sequence information indicating the DNA base sequence of the bacteria present in the saliva SV to the control unit 22a. In this case, the control unit 22a may include a function unit (for example, a detection unit) that detects the type of the short base sequence based on the base sequence information acquired from the sequencer 21a and the short base information 231a. Moreover, the control part 22a may be provided with the function part (for example, ratio acquisition part) which acquires the quantity (ratio) in a short base sequence in saliva SV for every kind of detected short base sequence.

<About the bacterial species ratio detection apparatus 20b>
Hereinafter, the details of the bacterial species ratio detection apparatus 20b that detects the bacterial species information KB and the percentage information RB based on the presence ratio of the 16S rRNA gene will be described with reference to the drawings.
FIG. 4 is a functional configuration diagram illustrating an example of the configuration of the bacterial species ratio detection apparatus 20b that detects the bacterial species information KB and the ratio information RB based on the presence ratio of the 16S rRNA gene of the present embodiment.
The bacterial species ratio detection device 20b includes a sequencer 21b, a control unit 22b, and a storage unit 23b. For example, known base information 231b and correspondence information 232b are stored in the storage unit 23b in advance.

The known base information 231b is information indicating a DNA base sequence to be analyzed by the sequencer 21b, and is information indicating a known 16S rRNA gene base sequence. In the following description, a known 16S rRNA gene base sequence is referred to as a known base sequence.
The sequencer 21b analyzes the base sequence of the analysis target indicated by the known base information 231b among the DNA base sequences of the bacteria present in the saliva SV (in the oral cavity of the subject ET). The sequencer 21b aligns and supplies information indicating the type of the obtained known base sequence (hereinafter, known base sequence information EB) to the control unit 22b. In addition, the sequencer 21b aligns the information (hereinafter, known base ratio information REB) indicating the amount (ratio) of the obtained known base sequence in the saliva SV for each type of the known base sequence to the control unit 22b. Supply.

  The control unit 22b implements each functional unit when a processor such as a CPU executes a program stored in the storage unit 23b. The control unit 22b implements, for example, the determination unit 221b and the output unit 222b as functional units.

  The determination unit 221b acquires the known base sequence information EB and the known base ratio information REB from the sequencer 21b. Based on the known base sequence information EB, the known base ratio information REB, and the correspondence information 232b, the determination unit 221b determines the bacteria (bacteria species information KB) present in the oral cavity of the subject ET and the bacteria in the oral cavity. An existing ratio (ratio information RB) is determined. The correspondence information 232b is information indicating correspondence between the known base sequence information EB and the known base ratio information REB, the bacterial species information KB, and the ratio information RB.

Hereinafter, details of the correspondence information 232b will be described with reference to the drawings.
FIG. 5 is a second diagram illustrating an example of the correspondence information 232b according to the present embodiment.
As shown in FIG. 5, the correspondence information 232b is associated with the known base sequence information EB, the known base ratio information REB, the bacterial species information KB, and the ratio information RB.
Here, when the known base sequence information EB and the known base ratio information REB of a subject ET are known, the type of bacteria (bacteria species information KB) present in the oral cavity of the subject ET and the bacteria are present in the oral cavity The ratio to be performed (ratio information RB) is uniquely determined. The association of the known base sequence information EB and the known base ratio information REB with the bacterial species information KB and the ratio information RB is based on the known base sequence indicated by the known base information 231b and the bacteria in the saliva SV in which the known base sequence exists. It is performed based on the analysis result.

In the example shown in FIG. 5, m pieces of known base sequence information EB and (m pieces) of known base ratio information REB corresponding to the known base sequence information EB are associated as known base information 231b. m is a natural number. Specifically, FIG. 5 shows that “GGACC (known base sequence information EB1)” is present in saliva SV at a rate of 0.25% (known base sequence information REB1), and “CCCCC (known base sequence information EB2). ) "Is present at a rate of 0.5% (known base ratio information REB2), ...," CCTAG (known base sequence information EBm) "is present at a rate of 0.25% (known base ratio information REBm) Indicates.
Further, in the example shown in FIG. 5, the above-described known base sequence information EB1 to known base sequence information EBm and known base sequence information EB1 to known base sequence information EBm include bacterial species information KB1 to bacterial species information KB4 and known bases. The ratio information REB1 to the known base ratio information REB4 are associated as the known base information 231b. Specifically, the known base information 231b shown in FIG. 5 includes the known base sequence information EB1 to the known base sequence information EBm in the saliva SV at the ratio of the known base ratio information REB1 to the known base ratio information REBm. In this case, in the oral cavity of the subject ET, Actinomycetemcomitans (bacteria species information KB1) is present at a rate of 19% (ratio information RB1), and Nucleatum (bacteria species information KB2) is 29% (ratio information RB2). Gingivalis (bacterial species information KB3) is present at a rate of 21% (ratio information RB3) and mutans (bacterial species information KB4) is present at a rate of 31% (ratio information RB4). Show. In the correspondence information 232b, the bacterial species information KB and the ratio information RB are associated with each combination of the known base sequence information EB and the known base ratio information REB. The correspondence information 232b is an example of reference information.

Returning to FIG. 4, the determination unit 221b searches the correspondence information 232b using the acquired known base sequence information EB and the known base ratio information REB as search keys. The determination unit 221b determines (extracts) the bacterial species information KB and the ratio information RB associated with the known base sequence information EB and the known base ratio information REB that match the search key in the correspondence information 232b. The determination unit 221b supplies the determined bacterial species information KB and ratio information RB to the output unit 222b.
The output unit 222 b supplies the bacterial species information KB and the ratio information RB acquired from the determination unit 221 b to the bad breath determination apparatus 10.

The sequencer 21b may be configured to supply base sequence information indicating the DNA base sequence of the bacteria present in the saliva SV to the control unit 22b. In this case, the control unit 22b may include a function unit (for example, a detection unit) that detects the type of the known base sequence based on the base sequence information acquired from the sequencer 21b and the known base information 231b. Moreover, the control part 22b may be provided with the function part (for example, ratio acquisition part) which acquires the quantity (ratio) in a known base sequence in saliva SV for every kind of the detected known base sequence.
In addition, the fungus species ratio detection device 20 may have a configuration including both the functions of the fungus species ratio detection device 20a and the fungus species ratio detection device 20b.

Hereinafter, the bad breath determination apparatus 10 will be described in detail with reference to the drawings.
FIG. 6 is a functional configuration diagram illustrating an example of the configuration of the bad breath determination apparatus 10 of the present embodiment.
As shown in FIG. 6, the bad breath determination apparatus 10 includes a control unit 11 and a storage unit 12.
The storage unit 12 stores a learned model 121 in advance. The learned model 121 includes teacher bacterial species information (hereinafter referred to as teacher bacterial species information TKB) indicating the types of bacteria present in the oral bacterial flora, and the teacher bacterial species information TKB among the bacteria present in the bacterial flora. This is a model in which the parameters of the activation function of the hidden layer are machine-learned so as to output the result information RT based on the teacher ratio information TRB indicating the ratio of bacteria to be displayed for each type of bacteria. The result information RT is information indicating whether or not there is a bad breath in the oral cavity. The result information RT indicates, for example, “1” when there is bad breath in the oral cavity and “0” when there is no bad breath in the oral cavity. The case where the oral cavity has bad breath is, for example, a case where the concentration of gas (for example, methyl mercaptan) that causes bad breath in the exhaled breath is equal to or higher than a predetermined threshold. Accordingly, the result information RT is based on the bacterial species information KB and the ratio information RB, when it is estimated that the concentration of the gas (hereinafter referred to as a specific gas) that causes bad breath contained in the exhalation is equal to or higher than a predetermined threshold value. When “1” is indicated and it is estimated that the value is lower than the predetermined threshold, “0” is indicated. The machine learning is, for example, SVM (Support Vector Machine) or deep learning. In an example of the present embodiment, a case where the learned model 121 is learned by deep learning will be described.

The learned model 121 is learned based on saliva SV of a plurality of subjects ET whose result information RT has been acquired in advance by detecting the concentration of a specific gas contained in exhaled breath, for example. Specifically, the learned model 121 uses the bacterial species information KB and the proportion information RB acquired by the bacterial species proportion detection apparatus 20 having the above-described configuration based on the saliva SV, respectively, as the teacher bacterial species information TKB and the teacher proportion information. Learned as TRB.
The learned model 121 calculates the result information RT based on, for example, the teacher bacterial species information TKB and the teacher ratio information TRB and the parameters of the hidden layer activation function. In the learned model 121, when the result information RT calculated based on the teacher fungus species information TKB and the teacher ratio information TRB is incorrect, the parameter of the hidden layer activation function is adjusted by the error back propagation method.

  Note that the result information RT may be information indicating the value of the concentration of a specific gas included in exhaled breath. In this case, the learned model 121 is learned based on saliva SV of a plurality of subjects ET from which result information RT indicating the concentration of a specific gas contained in exhalation has been acquired in advance.

  The control unit 11 realizes each functional unit when a processor such as a CPU executes a program stored in the storage unit 12. The control part 11 implement | achieves the acquisition part 111, the calculating part 112, and the output part 113 as the function part, for example.

The acquisition unit 111 acquires the bacterial species information KB and the proportion information RB from the bacterial species ratio detection device 20. The acquisition unit 111 supplies the acquired bacterial species information KB and ratio information RB to the calculation unit 112.
The calculation unit 112 calculates the result information RT based on the acquired bacterial species information KB and ratio information RB and the learned model 121. The calculation unit 112 supplies the calculated result information RT to the output unit 113.
The output unit 113 acquires the result information RT from the calculation unit 112. The output unit 113 outputs the acquired result information RT. For example, the output unit 113 outputs an image indicating the result information RT to a display device such as a display panel, and displays the image. Moreover, the output part 113 transmits result information RT to the server apparatus which memorize | stores the test result of the test subject ET, for example.

Hereinafter, the operation of the bad breath determination system 1 will be described with reference to the drawings.
FIG. 7 is a flowchart showing an example of the operation of the bad breath determination system 1 of the present embodiment.
The sequencer 21 provided in the fungus species ratio detection device 20 determines, based on the saliva SV of the subject ET, the types of DNA base sequences present in the saliva SV and the ratios of the base sequences of that type in the saliva SV for each type. Analysis is performed (step S110). Specifically, the sequencer 21a analyzes the short base sequence information SB and the short base ratio information RSB based on the saliva SV of the subject ET and the short base information 231a. The sequencer 21b analyzes the known base sequence information EB and the known base ratio information REB based on the saliva SV of the subject ET and the known base information 231b. The determination unit 221 determines the bacterial species information KB and the ratio information RB based on the information analyzed by the sequencer 21 and the correspondence information 232 (step S120). Specifically, the determination unit 221a determines, among the correspondence information 232a, the bacterial species information KB and the ratio information RB associated with the acquired short base sequence information SB and the short base ratio information RSB. Further, the determination unit 221 determines the bacterial species information KB and the ratio information RB in which the acquired known base sequence information EB and the known base ratio information REB are associated with each other in the correspondence information 232b. The output unit 222 outputs the bacterial species information KB and the ratio information RB determined by the determination unit 221 to the halitosis determination device 10 (step S130).

  The acquisition unit 111 included in the bad breath determination device 10 acquires the bacterial species information KB and the proportion information RB from the bacterial species ratio detection device 20 (step S140). The calculation unit 112 calculates the result information RT based on the bacterial species information KB and the ratio information RB acquired by the acquisition unit 111 and the learned model 121 (step S150). The output unit 113 outputs the result information RT calculated by the calculation unit 112 (step S160).

  As described above, the bad breath determination system 1 of the present embodiment includes the bad breath determination device 10 and the fungus species ratio detection device 20. The bad breath determination apparatus 10 includes a control unit 11 and realizes an acquisition unit 111, a calculation unit 112, and an output unit 113 as functional units. The acquisition unit 111 is information detected by the bacterial species ratio detection device 20, and includes bacterial species information KB indicating the type of bacteria present in the oral flora (in this example, saliva SV) of the subject ET, The ratio information RB indicating the ratio of the bacteria in the saliva SV indicated by the species information KB for each type is acquired. The calculation unit 112 calculates based on the bacterial species information KB acquired by the acquisition unit 111, the ratio information RB acquired by the acquisition unit 111, and the learned model 121. The output unit 113 is information indicating the calculation result of the calculation unit 112 and outputs bad breath information (in this example, result information RT) indicating whether or not the subject ET has bad breath. Here, the learned model 121 includes teacher bacterial species information TKB indicating the type of bacteria present in the saliva SV, and teacher ratio information TRB indicating, for each type, the proportion of the bacteria indicated by the teacher bacterial species information TKB in the saliva SV. Is a learned model learned by machine learning so as to output the result information RT.

  Thereby, the bad breath determination apparatus 10 of this embodiment determines whether there exists a bad breath in the test subject ET based on saliva SV. Therefore, the breath odor determination apparatus 10 of the present embodiment can determine whether or not the subject ET has a bad breath without using a device that detects a gas contained in exhaled breath. In addition, the bad breath determination apparatus 10 of the present embodiment cultivates the bacteria present in the oral cavity and has bad breath in order to determine whether there is bad breath based on the bacteria present in the saliva SV and the proportion of the bacteria. It is possible to determine whether or not the subject ET has bad breath in a short time compared to the method of determining whether or not.

In addition, the learned model 121 of the present embodiment is a model learned by deep learning. Here, even when bacteria that generate gas causing halitosis are present in the oral cavity, there is not always halitosis (the concentration of gas causing halitosis contained in exhaled breath increases). Specifically, the condition for generating bad breath is related to the type of bacteria present in the oral cavity and the ratio of each type of bacteria present in the oral cavity. However, it is difficult to analyze all combinations of the types of bacteria and the ratios for each type as reference information (short base information 231a and known base information 231b).
The bad breath determination apparatus 10 of this embodiment can calculate the result information RT by the learned model 121, and can determine whether the subject ET has bad breath by a simple process.

  In addition, the teacher bacterial species information TKB and the teacher ratio information TRB of the present embodiment are information based on the result of analyzing saliva SV of a plurality of subjects ET. Specifically, the teacher species information TKB is a plurality of species information KB detected by the species ratio detector 20 based on a plurality of saliva SVs. The teacher ratio information TRB is a plurality of ratio information RB detected by the fungus species ratio detection apparatus 20 based on a plurality of saliva SVs. When the bacterial flora used when acquiring the teacher bacterial species information TKB and the teacher ratio information TRB is saliva SV, the presence or absence of bad breath can be determined in a shorter period of time compared to the case where the bacterial flora is exhaled. .

  Moreover, the bacterial species ratio detection apparatus 20a of the present embodiment includes a sequencer 21a, a control unit 22a, and a storage unit 23a. The control unit 22a implements a determination unit 221a and an output unit 222a as functional units. The sequencer 21a detects the type of short base sequence present in the saliva SV. Moreover, the sequencer 21a acquires the ratio that the kind of short base sequence exists in saliva SV for every kind of detected short base sequence. Based on the short base information 231a, the short base sequence information SB, and the short base ratio information RSB for each short base sequence indicated by the short base sequence information SB, the determination unit 221a includes the bacterial species information KB and the ratio information RB. Determine.

  Here, the DNA base sequence contained in the saliva SV is influenced by copy number fluctuation, chimera formation, error by polymerase chain reaction, horizontal gene transfer between bacteria, etc., and the bacterial species information KB and the ratio information RB are determined. It may be difficult to specify the base sequence used when The bacterial species ratio detection apparatus 20a of the present embodiment determines the bacterial species information KB and the percentage information RB based on the short base sequence included in the saliva SV. The short base sequence has a small number of nucleotides to be judged (in this example, 5 bases), so it is affected by copy number fluctuation, chimera formation, errors due to polymerase chain reaction, horizontal gene transfer between bacteria, etc. Can be reduced. Therefore, the bacterial species ratio detection apparatus 20 of the present embodiment accurately determines the bacterial species information KB and the ratio information RB, and the halitosis determination apparatus 10 determines the bad breath of the subject ET based on the determined bacterial species information KB and the ratio information RB. The presence or absence can be determined.

  Moreover, the bacterial species ratio detection apparatus 20b of the present embodiment includes a sequencer 21b, a control unit 22b, and a storage unit 23b. The control unit 22b implements a determination unit 221b and an output unit 222b as functional units. The sequencer 21b detects the types of known base sequences present in the saliva SV. Moreover, the sequencer 21b acquires the ratio that the kind of known base sequence exists in the saliva SV for each kind of the detected known base sequence. Based on the known base information 231b, the known base sequence information EB, and the known base ratio information REB for each known base sequence indicated by the known base sequence information EB, the determination unit 221b includes the bacterial species information KB and the ratio information RB. Determine.

  Here, when the types of base sequences used when determining the bacterial species information KB and the ratio information RB are enormous, it is difficult to reduce the time required for the process of determining the bacterial species information KB and the ratio information RB. There is a possibility. The bacterial species ratio detection apparatus 20b of the present embodiment uses a known base sequence (for example, 16SrRNA gene) of bacteria that exist in the oral cavity and may generate a specific gas among the DNA base sequences contained in saliva SV. Based on this, the bacterial species information KB and the ratio information RB are determined. Therefore, the bacterial species ratio detection apparatus 20 of the present embodiment determines the bacterial species information KB and the ratio information RB by a simple process, and uses the determined bacterial species information KB and the ratio information RB to inform the breath odor determination apparatus 10 of the subject ET. The presence or absence of bad breath can be determined.

The bad breath determination apparatus 10 may have a configuration for re-learning the learned model 121. In this case, the control unit 11 of the bad breath determination apparatus 10 includes an input unit, a determination unit, and an update unit as functional units. The input unit acquires examination information indicating whether or not bad breath has occurred in the subject ET.
The input unit is, for example, a device for inputting character information such as a keyboard, a pointing device such as a mouse or a touch panel, and the like. The determination unit determines whether the result information RT matches the inspection information.
When the determination unit determines that the result information RT and the inspection information do not match, the update unit re-learns (updates) the learned model 121. The re-learning of the learned model 121 is to update the teacher data (teacher fungus species information TKB and teacher ratio information TRB) to the latest one and newly learn the model again. Specifically, the updating unit sets the bacterial species information KB and the rate information RB of the subject ET of the test for which the result information RT and the test information do not match as the teacher bacterial type information TKB and the teacher rate information TRB. Further, the update unit adjusts the parameter of the activation function of the hidden layer of the learned model 121 by the error back propagation method so that the result information RT based on the teacher fungus species information TKB and the teacher ratio information TRB matches the inspection information. To do. Here, the update of the update unit may be performed each time the determination unit determines that the result information RT does not match the test information, and the bacteria determined that the result information RT and the test information do not match This may be performed when the seed information KB and the ratio information RB are acquired by the number that can update the parameters of the activation function of the hidden layer. In addition, for updating by the update unit, the bacterial species information KB and the rate information RB of the test subject ET whose result information RT and the test information match may be used as the teacher bacterial species information TKB and the teacher rate information TRB. .
The bad breath determination apparatus 10 may be configured to include a functional unit (importance adding unit) that weights the bacterial species information KB and the known base ratio information REB. In this case, the importance level adding unit performs high weighting on the bacterial species information KB and the known base proportion information REB that are important in determining the presence or absence of bad breath among the bacterial species information KB and the known base proportion information REB, Low weighting is performed on the unimportant bacteria species information KB and the known base ratio information REB.

<Modification>
In addition, although the case where the bad breath determination apparatus 10 outputs the result information RT based on the bacterial species information KB and the ratio information RB has been described above, the present invention is not limited thereto. The bad breath determination apparatus 10 may be configured to output the result information RT based on the known base sequence information EB and the known base ratio information REB.
In this case, the learned model 121 is learned based on the saliva SV of a plurality of subjects ET for which the result information RT has been acquired in advance. More specifically, the learned model 121 uses each of the known base sequence information EB and the known base ratio information REB acquired by the bacterial species ratio detection device 20b having the above-described configuration based on the saliva SV as teacher data (hereinafter referred to as teacher data). It is learned as known base sequence information TEB and teacher known base ratio information TREB). The learned model 121 calculates result information RT based on the teacher known base sequence information TEB, the teacher known base ratio information TREB, and the parameters of the hidden layer activation function. In the learned model 121, when the result information RT calculated based on the teacher known base sequence information TEB and the teacher known base ratio information TREB is incorrect, the parameters of the hidden layer activation function are adjusted by the error back propagation method. The
In this case, the bacterial species ratio detection apparatus 20b supplies the known base sequence information EB and the known base ratio information REB to the halitosis determination apparatus 10 instead of the bacterial species information KB and the ratio information RB. The bad breath determination apparatus 10 outputs the result information RT based on the acquired known base sequence information EB and known base ratio information REB, and the learned model 121.
Thereby, the bad breath smell determination system 1 can omit the process of detecting the bacterial species information KB and the ratio information RB by the bacterial species ratio detection device 20b, so that the process related to the output of the result information RT can be performed at a higher speed. Can be done.

  In addition, each part with which the bad breath determination apparatus 10 and the bacteria species ratio detection apparatus 20 in each said embodiment are provided may be implement | achieved by dedicated hardware, and is implement | achieved by memory and a microprocessor. There may be.

  Each unit included in the bad breath determination apparatus 10 and the fungus species ratio detection device 20 is configured by a memory and a CPU (central processing unit), in order to realize the function of each part included in the bad breath determination device 10 and the fungus species ratio detection device 20. This function may be realized by loading the program into a memory and executing it.

  Further, a program for realizing the function of each unit included in the bad breath determination apparatus 10 and the fungus species ratio detection apparatus 20 is recorded on a computer-readable recording medium, and the program recorded on the recording medium is read into a computer system. The processing may be performed by executing. Here, the “computer system” includes an OS and hardware such as peripheral devices.

Further, the “computer system” includes a homepage providing environment (or display environment) if a WWW system is used.
The “computer-readable recording medium” refers to a storage device such as a flexible medium, a magneto-optical disk, a portable medium such as a ROM and a CD-ROM, and a hard disk incorporated in a computer system. Furthermore, the “computer-readable recording medium” dynamically holds a program for a short time like a communication line when transmitting a program via a network such as the Internet or a communication line such as a telephone line. In this case, a volatile memory in a computer system serving as a server or a client in that case, and a program that holds a program for a certain period of time are also included. The program may be a program for realizing a part of the functions described above, and may be a program capable of realizing the functions described above in combination with a program already recorded in a computer system.

  The embodiment of the present invention has been described in detail with reference to the drawings. However, the specific configuration is not limited to this embodiment, and appropriate modifications may be made without departing from the spirit of the present invention. it can. You may combine the structure as described in each embodiment mentioned above.

DESCRIPTION OF SYMBOLS 1 ... Bad breath determination system, 10 ... Bad breath determination apparatus, 20, 20a, 20b ... Bacterial species ratio detection apparatus, 21, 21a, 21b ... Sequencer, 11, 22a, 22b ... Control part, 12, 23a, 23b ... Storage part, DESCRIPTION OF SYMBOLS 111 ... Acquisition part, 112 ... Operation part, 113, 222, 222a, 222b ... Output part, 221, 221a, 221b ... Determination part, 121 ... Learned model, 231a ... Short base information, 231b ... Known base information, 232, 232a, 232b ... correspondence information, KB, KB1, KB2, KB3, KB4 ... fungus species information, RB, RB1, RB2, RB3, RB4 ... ratio information, EB, EB1, EB2, EB3 ... known base sequence information, REB, REB1 , REB2, REB3 ... known base ratio information, SB, SB1, SB2, SB3 ... short base sequence information, RSB, RSB1, RS 2, RSB3 ... short base ratio information, RT ... result information, TKB ... teacher species information, TRB ... teacher ratio information, ET ... subject, SV ... saliva

Claims (7)

Based on teacher bacterial species information indicating the type of bacteria present in the bacterial flora in the oral cavity, and teacher ratio information indicating the proportion of bacteria in the bacterial flora indicated by the teacher bacterial species information for each type, bad breath in the oral cavity A storage unit that stores a learned model learned by machine learning so as to output bad breath information indicating whether or not there is,
An acquisition unit for acquiring the bacterial species information indicating the type of bacteria present in the bacterial flora in the oral cavity of the subject, and the ratio information indicating the ratio in the bacterial flora of the bacteria indicated by the bacterial species information, for each type,
The bacterial species information acquired by the acquisition unit and the ratio information acquired by the acquisition unit are input to the learned model, and the calculated bad breath information indicating whether the subject has bad breath is output. An output section;
A bad breath determination apparatus. The machine learning is
Deep learning,
The bad breath determination apparatus according to claim 1. The teacher bacterial species information and the teacher ratio information are
Information based on the results of analyzing the saliva of multiple subjects.
The bad breath determination apparatus according to claim 1 or 2. A detection unit for detecting the type of a short base sequence having 5 bases, the base sequence of DNA existing in the saliva bacterial flora;
For each type of the short base sequence detected by the detection unit, a ratio acquisition unit that acquires a ratio of the type of base sequence present in the bacterial flora,
Reference information indicating the correspondence between the type of bacteria present in the bacterial flora in the oral cavity of the subject and the ratio of the bacteria in the bacterial flora for each combination of the type and the ratio, and the short detected by the detection unit Based on the type of base sequence and the ratio of each type of short base sequence acquired by the ratio acquisition unit, the type of bacteria present in the oral flora of the subject and the bacterial flora of the bacteria A determination unit for determining a ratio;
With
The acquisition unit
Obtaining the species information indicating the type determined by the determination unit, and the rate information indicating the proportion of the bacteria indicated by the species information in the bacterial flora for each type.
The bad breath determination apparatus according to claim 3. A detection unit for detecting a known base sequence that matches the base sequence of a known 16S rRNA gene, which is a base sequence of DNA present in the bacterial flora of saliva;
For each type of the known base sequence detected by the detection unit, a ratio acquisition unit that acquires a ratio of the type of base sequence present in the bacterial flora,
Reference information indicating the correspondence between the type of bacteria present in the bacterial flora in the oral cavity of the subject and the ratio of the bacteria in the bacterial flora for each combination of the type and the ratio, and the known detected by the detection unit Based on the type of base sequence and the ratio of each type of the known base sequence acquired by the ratio acquisition unit, the type of bacteria present in the oral flora of the subject, and the bacterial flora of the bacteria A determination unit for determining a ratio;
With
The acquisition unit
Obtaining the species information indicating the type determined by the determination unit, and the rate information indicating the proportion of the bacteria indicated by the species information in the bacterial flora for each type.
The bad breath determination apparatus according to claim 3 or 4. The base sequence of DNA existing in the bacterial flora in the oral cavity, and the ratio of the short base information indicating the type of the short base sequence having five bases and the short base indicated by the teacher short base information for each type A storage unit that stores a learned model learned by machine learning so as to output bad breath information indicating whether there is bad breath in the oral cavity based on the teacher short base ratio information shown in FIG.
The base sequence of DNA present in the bacterial flora in the oral cavity of the subject, the short base sequence information indicating the type of the short base sequence having five bases, and the short base sequence indicated by the short base sequence information An acquisition unit for acquiring short base ratio information indicating the ratio in the plexus for each type;
Bad breath information indicating whether or not the subject has a bad breath by inputting the short base sequence information acquired by the acquisition unit and the short base ratio information acquired by the acquisition unit into the learned model. An output unit for outputting
A bad breath determination apparatus. Based on teacher bacterial species information indicating the type of bacteria present in the bacterial flora in the oral cavity, and teacher ratio information indicating the proportion of bacteria in the bacterial flora indicated by the teacher bacterial species information for each type, bad breath in the oral cavity A computer having a storage unit for storing a learned model learned by machine learning so as to output bad breath information indicating whether or not there is,
An acquisition step of acquiring bacterial species information indicating the type of bacteria present in the bacterial flora in the oral cavity of the subject, and ratio information indicating the ratio in the bacterial flora of the bacteria indicated by the bacterial species information for each type,
The fungus species information acquired in the acquisition step and the ratio information acquired in the acquisition step are input to the learned model, and output of the mouth odor information indicating whether or not the calculated subject has bad breath Steps,
A program that executes

Images