JP7324390B2 - Information processing device, information processing method and program - Google Patents

Description

The present invention relates to an information processing device, an information processing method, and a program.

In order for the pharmacist to provide appropriate services to the patient, there are cases where it is desired to grasp the type of disease that the patient is suffering from. Various techniques have been proposed for estimating the type of patient's disease. Patent Literature 1 describes a technique for estimating the type of disease from a patient's symptoms.

Japanese Patent Application Laid-Open No. 2004-160082

A pharmacist's understanding of a patient's symptoms is less accurate than a doctor's. Therefore, even if the technique described in Patent Document 1 is used, it is difficult for the pharmacist to appropriately estimate the patient's disease. An object of the present invention is to provide a new technique for estimating the type of patient's disease.

In view of the above problems, in some embodiments, for each of a plurality of patients, prescription information about the type of drug prescribed for the individual patient, disease information about the type of disease of the individual patient , By performing statistical analysis using the acquisition means for acquiring the combination with the age category of the individual patient and the combination for the plurality of patients, the type of disease of the patient prescribed one or more drugs is determined. and determining means for determining an estimation function for estimating.

By means of the above, new techniques can be used to estimate patient disease.

1 is a block diagram illustrating a configuration example of an information processing apparatus according to some embodiments of the present invention; FIG. 2 is a flowchart for explaining an operation example of the information processing apparatus in FIG. 1; FIG. 2 is a diagram for explaining an example of complaint data used by the information processing apparatus in FIG. 1; The figure explaining the example of the indication information which the information processing apparatus of FIG. 1 uses. FIG. 2 is a diagram for explaining an example of an estimation function used by the information processing apparatus in FIG. 1;

Embodiments of the invention are described below with reference to the accompanying drawings. The same reference numerals are given to the same elements throughout the various embodiments, and duplicate descriptions are omitted. Further, each embodiment can be modified and combined as appropriate.

A configuration of an information processing apparatus 100 according to some embodiments of the present invention will be described with reference to the block diagram of FIG. The information processing apparatus 100 performs operations for estimating the type of patient's disease. Details of the processing will be described later. The information processing apparatus 100 is implemented by, for example, an information processing apparatus such as a personal computer, workstation, smart phone, or tablet device. The information processing apparatus 100 may be implemented as a single device, or may be implemented as a plurality of devices interconnected via a network. The information processing apparatus 100 has each component shown in FIG.

The processor 101 controls the operation of the information processing apparatus 100 as a whole. The processor 101 functions, for example, as a CPU. The memory 102 stores programs and temporary data used for the operation of the information processing apparatus 100 . The memory 102 is implemented by, for example, ROM or RAM. The input unit 103 is used by the user of the information processing apparatus 100 to input to the information processing apparatus 100, and is realized by an input device such as a mouse or a keyboard. The output unit 104 is used to output information from the information processing apparatus 100 to the user, and is realized by, for example, a display device (display) or an audio device (speaker). The communication unit 105 provides a function for the information processing apparatus 100 to communicate with other apparatuses, and is realized by a network card, for example. Communication with other devices may be wired or wireless.

The storage unit 106 stores data used for the operation of the information processing apparatus 100 , such as indication information 107 , claim data 108 and estimation function 109 . Details of the indication information 107, the claim data 108, and the estimation function 109 will be described later. The storage unit 106 is realized by a storage device such as a disk drive (for example, HDD or SDD). In this embodiment, indication information 107 , complaint data 108 and estimation function 109 are stored in information processing device 100 . Alternatively, part or all of these contents may be stored in a device (external storage device) different from the information processing device 100 . In this case, the information processing apparatus 100 uses the communication unit 105 to receive the indication information 107, the complaint data 108, and the estimation function 109 from the other apparatus. Indication information 107 and claim data 108 may be stored in file format, or may be stored in a database or other format. The estimation function 109 may be stored separately in the function formula and the parameter values included in this formula.

An example of the operation of the information processing apparatus 100 for estimating the type of patient's disease will be described with reference to FIG. 2 . Each step of the method illustrated in FIG. 2 is performed, for example, by processor 101 executing a program stored in memory 102 . Alternatively, some or all steps of the method may be implemented in hardware such as an ASIC (Application Specific Integrated Circuit).

At step S201, the processor 101 obtains prescription information and disease information. Prescription information includes, for example, a receipt identifier (receipt ID) and the type of drug prescribed to the patient. Types of drugs include, for example, Feburic, Aimix, and Tragenta. The number of drug types may be, for example, about 9000 types. The types of drugs may be subdivided according to usage and quantity. The processor 101 acquires prescription information for each of multiple prescriptions identified by the receipt identifier. Prescription information is read, for example, from a prescription receipt input to the information processing apparatus 100 .

The disease information includes, for example, a receipt identifier and the type of patient's disease. Furthermore, the disease information may include the patient's age category, gender, and patient identifier (patient ID). Types of diseases include, for example, allergic rhinitis, hypertension, and bronchial asthma. The types of diseases may be, for example, about 600 types. The patient's age is divided into three categories, for example, under 15 years old, 15-65 years old, and over 65 years old. The number of age categories is not limited to this. Processor 101 acquires disease information for each of a plurality of diagnoses identified by the receipt identifier. The disease information is read, for example, from a medical receipt input to the information processing apparatus 100 .

At step S202, the processor 101 generates complaint data 108 based on the obtained prescription information and disease information. An example of complaint data 108 is shown in FIG. The complaint data 108 is data relating to a combination of prescription information regarding the type of drug prescribed to the patient and disease information regarding the type of disease of this patient.

One or more columns 301 indicate disease types. A column is generated for each disease type. A value of "0" in the field indicates that the patient does not have the disease of interest (eg, disease A), and a value of "1" indicates that the patient has the disease of interest. Column 302 shows the receipt identifier. A claim identifier is information for uniquely identifying a claim. Column 303 shows patient identifiers. A patient identifier is information for uniquely identifying a patient. Column 304 indicates the age category of the patient. Column 305 indicates the gender of the patient. One or more columns 306 indicate drug types. A column is generated for each drug type. A value of '0' in the field indicates that the patient was not prescribed the drug of interest (eg, drug A), and a value of '1' indicates that the patient was prescribed the drug of interest.

The processor 101 stores the combination obtained by associating the prescription information and the disease information using the receipt identifier as a key in the storage unit 106 as a record of the complaint data 108 . That is, each record in claims data 108 represents a combination of information regarding the type of medication prescribed for a particular patient and information regarding the type of disease for that particular patient. In addition, each record represents other attributes of this particular patient, such as age bracket and gender.

At step S203, the processor 101 cleanses the complaint data 108 with reference to the indication information 107. FIG. The disease information acquired in step S201 may contain past disease information. For example, assume that a patient has had bronchial asthma in the past and has since recovered completely. Bronchial asthma should not be included in the disease information about this patient after complete recovery, but bronchial asthma may be included in the disease information due to omission of updating. Therefore, the processor 101 refers to the indication information 107 and deletes inappropriate records from the complaint data 108 .

The indication information 107 is information in which the type of drug is associated with the type of disease for which the type of drug can be used. An example of indication information 107 is shown in FIG. One or more rows 401 indicate drug types. A wax is prescribed for each type of drug. One or more columns 402 indicate disease types. A column is defined for each disease type. If the value of the field is "0", it indicates that the target drug (eg, drug A) is not available for the target disease (eg, disease B), and if it is "1", the target drug (eg, , indicates that drug A) can be used for the disease of interest (eg, disease A). This indication information 107 is stored in advance in the storage unit 106 of the information processing apparatus 100 . For example, if the claim data 108 contains a record in which the disease A field is 1 and the drug B field is "1", the record does not match the indication information 107, so the claim Delete from data 108 . Records deleted from claim data 108 are not used for the statistical analysis described below.

At step S204, the processor 101 consolidates the records of the complaint data 108 for the same patient. For example, in the complaint data 108 of FIG. 3, three records with the patient identifier "P001" are integrated. In integration, the processor 101 takes the logical sum of each field in the column 301 as the field value of the record after integration. Also, the processor 101 sets the logical sum of each field in the column 306 as the field value of the record after integration. By integrating records in this way, estimation accuracy can be improved even for cases with a small number of patients. The above steps S203 and S204 are optional to improve the accuracy of the estimation function and may be omitted.

At step S<b>205 , the processor 101 determines the estimation function 109 by performing statistical analysis using multiple records of the claim data 108 . The estimation function 109 is a function for estimating diseases of patients prescribed one or more drugs. A patient's disease estimation result is given by the probability that the patient has each disease (hereinafter referred to as morbidity probability). The morbidity probability P (disease j) of disease j (j=A, B, .

P(disease j)=1/{1+exp(-α-Σβ _i x _i ) Equation (1)
Here, _xi is a variable representing whether or not a drug i (i=A, B, . . . ) is prescribed, and is "1" if prescribed and "0" if not prescribed. Furthermore, x _i may represent attributes other than drug prescription, such as age group and gender. β _i is a parameter of x _i and α is a parameter representing the intercept. α and β _i are determined by performing statistical analysis using claim data 108 .

For example, processor 101 determines the above parameters α and β _i by performing logistic regression analysis, which is a kind of statistical analysis. Furthermore, the processor 101 may determine the parameters α, _βi by machine learning. In these statistical analyses, parameters α, β _i are determined based on the frequency of occurrence of combinations.

FIG. 5 shows an example of the estimation function parameters 109a forming part of the estimation function 109. As shown in FIG. Column 501 indicates the type of disease. Column 502 shows the value of parameter α. Column 503 shows the value of parameter β for gender. Column 504 shows the values of parameter β for age categories. One or more columns 505 show the value of the parameter β for drug type. In this way, since the parameter values of the estimation function are different for each disease type, the morbidity probability is calculated for each disease type. The processor 101 stores the determined estimation function 109 , more specifically, the estimation function parameters 109 a in the storage unit 106 . Equation (1) of estimation function 109 is stored in storage unit 106 in advance.

At step S206, the processor 101 obtains input information including the type of drug. The input information may include patient attributes, such as age range and gender. This input information may be input using the input unit 103 of the information processing device 100 or may be received from an external device by the communication unit 105 . For example, the information processing apparatus 100 may function as a web server, and an external client terminal may transmit input information to the information processing apparatus 100 via a browser. In one scenario, a pharmacist at a pharmacy inputs into the information processing device 100 the type of drug stated in the patient's prescription.

At step S207, the processor 101 applies the estimation function 109 to the input information. Specifically, the processor 101 substitutes the values of the parameters α and β _i determined in step 205 and the value of x _i determined by the input information into the above equation (1), thereby obtaining each disease Calculate the morbidity probability for

At step S208, the processor 101 outputs the morbidity probability for each disease as an estimation result. The processor 101 may output the estimation result to the output unit 104 of the information processing device 100, or may transmit the estimation result to an external device. In the above scenario, a pharmacist at a pharmacy can obtain the prevalence probability for each disease.

As can be seen, according to embodiments of the present invention, an estimation function 109 can be determined for estimating disease in patients prescribed one or more medications. By inputting the type of drug prescribed to the patient to this estimation function 109, the disease that the patient is suffering from can be estimated.

100 Information Processing Device, 107 Indication Information, 108 Complaint Data, 109 Estimation Function

Claims (10)

For each of a plurality of patients, a combination of prescription information regarding the type of drug prescribed for the individual patient, disease information regarding the type of disease of the individual patient, and age category of the individual patient is obtained. acquisition means;
determining means for determining an estimating function for estimating disease type for a patient prescribed one or more drugs by performing a statistical analysis using the combination for the plurality of patients;
Information processing device. Obtaining, for each of a plurality of patients, a combination of prescription information regarding the type of drug prescribed for the individual patient, disease information regarding the type of disease of the individual patient, and the sex of the individual patient means and
determining means for determining an estimating function for estimating disease type for a patient prescribed one or more drugs by performing a statistical analysis using the combination for the plurality of patients;
Information processing device. For each of a plurality of patients, prescription information on the type of drug prescribed for the individual patient, disease information on the type of disease of the individual patient, age category of the individual patient, and the individual patient an obtaining means for obtaining a combination of gender and
determining means for determining an estimating function for estimating disease type for a patient prescribed one or more drugs by performing a statistical analysis using the combination for the plurality of patients;
Information processing device. The acquisition means further acquires indication information in which the type of drug and the type of disease for which the type of drug can be used are associated,
The information processing apparatus according to any one of claims 1 to 3 , wherein said determining means does not use said combination that does not match said indication information for said statistical analysis. input means for acquiring input information including the type of drug;
estimation means for estimating the type of disease by applying the estimation function to the input information;
an output means for outputting an estimation result by the estimation means;
The information processing apparatus according to any one of claims 1 to 4 , further comprising: 6. The information processing apparatus according to claim 5 , wherein said estimation result includes a morbidity probability for each of a plurality of types of diseases. A program for causing a computer to function as each means of the information processing apparatus according to any one of claims 1 to 6 . A computer-implemented information processing method comprising:
For each of a plurality of patients, a combination of prescription information regarding the type of drug prescribed for the individual patient, disease information regarding the type of disease of the individual patient , and age category of the individual patient is obtained. an acquisition step;
a determining step of determining an estimation function for estimating a disease type for a patient prescribed one or more drugs by performing a statistical analysis using the combination for the plurality of patients;
An information processing method comprising: A computer-implemented information processing method comprising:
Obtaining, for each of a plurality of patients, a combination of prescription information regarding the type of drug prescribed for the individual patient, disease information regarding the type of disease of the individual patient, and the sex of the individual patient process and
a determining step of determining an estimation function for estimating a disease type for a patient prescribed one or more drugs by performing a statistical analysis using the combination for the plurality of patients;
An information processing method comprising: A computer-implemented information processing method comprising:
For each of a plurality of patients, prescription information on the type of drug prescribed for the individual patient, disease information on the type of disease of the individual patient, age category of the individual patient, and the individual patient an obtaining step of obtaining a combination of gender and
a determining step of determining an estimation function for estimating a disease type for a patient prescribed one or more drugs by performing a statistical analysis using the combination for the plurality of patients;
An information processing method comprising: