# US 12,014,822 B2 · Machine learning device, trained model, data structure, periodontal disease detection method, periodontal disease detection system, and periodontal disease detection kit

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 12,014,822 B2
- Document ID: US12014822B2
- Status: Granted
- Kind: B2
- Application number: 16/488,661
- Filed: 2018-02-28
- Published: 2020-07-23
- Granted: 2024-06-18
- Earliest claimed: 2017-03-01
- Assignees: Mitsui Chemicals, Inc.
- Applicants: Mitsui Chemicals, Inc.
- Inventors: Makoto Taniguchi
- Web page: https://patentgrep.com/patent/US12014822B2

## CPC

- G16H 50/20: for computer-aided diagnosis, e.g. based on medical expert systems
- A61B 5/0088: {for oral or dental tissue}
- A61B 5/4842: {Monitoring progression or stage of a disease}
- A61B 5/7264: {Classification of physiological signals or data, e.g. using neural networks, statistical classifiers, expert systems or fuzzy systems}
- A61C 19/04: Measuring instruments specially adapted for dentistry ({A61C5/44 takes precedence; testing vitality of teeth A61B5/0534;} radiation diagnosis specially adapted for dentistry A61B6/51)
- C12M 1/00: Apparatus for enzymology or microbiology
- C12Q 1/02: involving viable microorganisms
- C12Q 1/6893: for protozoa
- G06F 18/214: Generating training patterns; Bootstrap methods, e.g. bagging or boosting
- G06F 18/217: {Validation; Performance evaluation; Active pattern learning techniques}
- G06N 3/044: Recurrent networks, e.g. Hopfield networks
- G06N 3/045: Combinations of networks
- G06N 3/0455: Auto-encoder networks; Encoder-decoder networks
- G06N 3/0499: Feedforward networks
- G06N 3/063: using electronic means
- G06N 3/08: Learning methods
- G06N 3/09: Supervised learning
- G06N 20/00: Machine learning
- G16H 10/40: for data related to laboratory analysis, e.g. patient specimen analysis
- G16H 50/70: for mining of medical data, e.g. analysing previous cases of other patients
- C12N 15/09: Recombinant DNA-technology
- G16H: HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- A61B: DIAGNOSIS; SURGERY; IDENTIFICATION (usefulness limited to only animals A61D)
- A61C: DENTISTRY; APPARATUS OR METHODS FOR ORAL OR DENTAL HYGIENE (non-driven toothbrushes A46B; {tongue scrapers A61B17/24;} preparations for dentistry A61K6/00; preparations for cleaning the teeth or mouth A61K8/00, A61Q11/00)
- C12M: APPARATUS FOR ENZYMOLOGY OR MICROBIOLOGY; {APPARATUS FOR CULTURING MICROORGANISMS FOR PRODUCING BIOMASS, FOR GROWING CELLS OR FOR OBTAINING FERMENTATION OR METABOLIC PRODUCTS, i.e. BIOREACTORS OR FERMENTERS}
- C12Q: MEASURING OR TESTING PROCESSES INVOLVING ENZYMES, NUCLEIC ACIDS OR MICROORGANISMS (immunoassay G01N33/53); COMPOSITIONS OR TEST PAPERS THEREFOR; PROCESSES OF PREPARING SUCH COMPOSITIONS; CONDITION-RESPONSIVE CONTROL IN MICROBIOLOGICAL OR ENZYMOLOGICAL PROCESSES
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- C12N: MICROORGANISMS OR ENZYMES; COMPOSITIONS THEREOF; PROPAGATING, PRESERVING, OR MAINTAINING MICROORGANISMS; MUTATION OR GENETIC ENGINEERING; CULTURE MEDIA (microbiological testing media C12Q1/00)

## Abstract

A machine learning device that includes a training section configured perform training based on plural training data each configured from oral cavity information detected from a specimen and at least one determination value selected from the group consisting of a probability of periodontal disease contraction of a provider of the specimen or a state of periodontal disease, so as to train the function to decide the determination value. The training section includes a reward calculation section, a function updating section, and a convergence determination section. The reward calculation section calculates a reward for a defined result of the probability of periodontal disease contraction or the state of periodontal disease based on the training data. The function updating section updates the function so as to increase the reward calculated by the reward calculation section. The convergence determination section causes repeated calculations and updates until a predetermined convergence condition is satisfied.

## Claims

### Claim 1

A periodontal disease detection method comprising: (i) a detection process to detect in a specimen at least two bacterial strains selected from the group consisting of Anaeroglobus, Cryptobacterium, Desulfobulbus, Desulfomicrobium, Desulfovibrio, Erysipelotrichaceae, Fretibacterium, Johnsonella, Mitsuokella, Mollicutes, Parascardovia, Pseudoramibacter, Pyramidobacter, Scardovia, Shuttleworthia, and Mycoplasma, and (ii) an evaluation process after the detection process to evaluate a possibility that a specimen provider has contracted periodontal disease as high in cases in which a sum total of a number of sequence reads of the at least two bacterial strains included in the group is 0.02% or more with respect to a sum total of a number of sequence reads obtained in the detection process of 100%.

### Claim 2 (depends on 1)

The periodontal disease detection method of claim 1, wherein the at least two bacterial strains included in the group are at least two bacterial strains selected from the group consisting of Anaeroglobus, Fretibacterium, and Mycoplasma.

### Claim 3 (depends on 1)

The periodontal disease detection method of claim 1, wherein the detection is performed by metagenomic analysis.

### Claim 4 (depends on 1)

The periodontal disease detection method of claim 1, wherein the specimen is saliva.

### Claim 5

A periodontal disease detection system comprising: (i) a detection section to detect in a specimen at least two bacterial strains selected from the group consisting of Anaeroglobus, Cryptobacterium, Desulfobulbus, Desulfomicrobium, Desulfovibrio, Erysipelotrichaceae, Fretibacterium, Johnsonella, Mitsuokella, Mollicutes, Parascardovia, Pseudoramibacter, Pyramidobacter, Scardovia, Shuttleworthia, and Mycoplasma, and (ii) an evaluation section to evaluate a possibility that a specimen provider has contracted periodontal disease as high in cases in which a sum total of a number of sequence reads of the at least two bacterial strains included in the group is 0.02% or more with respect to a sum total of a number of sequence reads obtained by the detection section of 100%.

### Claim 6

A periodontal disease detection kit comprising: (i) a detection device to detect in a specimen at least two bacterial strains selected from the group consisting of Anaeroglobus, Cryptobacterium, Desulfobulbus, Desulfomicrobium, Desulfovibrio, Erysipelotrichaceae, Fretibacterium, Johnsonella, Mitsuokella, Mollicutes, Parascardovia, Pseudoramibacter, Pyramidobacter, Scardovia, Shuttleworthia, and Mycoplasma, and (ii) an evaluation device to evaluate a possibility that a specimen provider has contracted periodontal disease as high in cases in which a sum total of a number of sequence reads of the at least two bacterial strains included in the group is 0.02% or more with respect to a sum total of a number of sequence reads obtained by the detection section of 100%.

### Claim 7

A periodontal disease detection method including: (i) a detection process to detect in a specimen at least one bacterial strain selected from the group consisting of GN02, Ottowia, Sneathia, and Lautropia, and (ii) an evaluation process after the detection process to evaluate a possibility that a specimen provider has contracted periodontal disease as high in cases in which a sum total of a number of sequence reads of the at least one bacterial strain included in the group is 0.01% or less with respect to a sum total of a number of sequence reads obtained in the detection process of 100%.

### Claim 8 (depends on 7)

The periodontal disease detection method of claim 7, wherein the detection is performed by metagenomic analysis.

### Claim 9 (depends on 7)

The periodontal disease detection method of claim 7, wherein the specimen is saliva.

### Claim 10 (depends on 7)

The periodontal disease detection method of claim 7, wherein the at least one bacterial strain included in the group includes Lautropia.

### Claim 11 (depends on 7)

The periodontal disease detection method of claim 7, wherein the at least one bacterial strain included in the group is a combination of Lautropia combined with at least one bacterial strain selected from the group consisting of GN02, Ottowia, and Sneathia.

### Claim 12

A periodontal disease detection system comprising: (i) a detection section to detect in a specimen at least one bacterial strain selected from the group consisting of GN02, Ottowia, Sneathia, and Lautropia, and (ii) an evaluation section to evaluate a possibility that a specimen provider has contracted periodontal disease as high in cases in which a sum total of a number of sequence reads of the at least two bacterial strains included in the group is 0.01% or more with respect to a sum total of a number of sequence reads obtained by the detection section of 100%.

### Claim 13

A periodontal disease detection kit comprising: (i) a detection device to detect in a specimen at least one bacterial strain selected from the group consisting of GN02, Ottowia, Sneathia, and Lautropia, and (ii) an evaluation device to evaluate a possibility that a specimen provider has contracted periodontal disease as high in cases in which a sum total of a number of sequence reads of the at least two bacterial strains included in the group is 0.01% or more with respect to a sum total of a number of sequence reads obtained by the detection section of 100%.