Information processing system, information processing method, and prediction method

Abstract

An objective of the present invention is to analyze drugs used for each disease. An information processing system (3) comprises: an acquisition unit (11) that acquires information related to diseases each user is suffering from and drugs being used for the diseases by the users from a plurality of user terminals (2) via a network; and an analysis unit (13) that analyzes the drugs used for each of the diseases on the basis of used drug information related to the diseases and the drugs and based on the information acquired by the acquisition unit (11). The analysis unit (13) may also perform the analysis even more on the basis of drug-related information acquired from a database of drug-related information, which is information related to drugs.

Description

Information Processing System, Information Processing Method, and Prediction Method

[0001] One aspect of the present disclosure relates to an information processing system, an information processing method, and a prediction method for analyzing drugs used by a user for each disease the user suffers from.

[0002] In Patent Document 1 below, a computer-implemented method for measuring the therapeutic effect of a medical drug against a disease is disclosed.

[0003] Japanese Patent Application Laid-Open No. 2022-506976

[0004] However, with the above computer-implemented method, for example, it is not possible to analyze the drugs used for each disease.

[0005] An information processing system according to one aspect of the present disclosure includes an acquisition unit that acquires information regarding a disease that each user suffers from and a drug that the user uses for the disease from a plurality of user terminals via a network, and an analysis unit that analyzes the drugs used for each disease based on the drug usage information regarding the disease and the drug based on the information acquired by the acquisition unit. In such an aspect, it is possible to analyze the drugs used for each disease.

[0006] An information processing method according to one aspect of the present disclosure is an information processing method executed by a computer, including an acquisition step of acquiring information regarding a disease that each user suffers from and a drug that the user uses for the disease from a plurality of user terminals via a network, and an analysis step of analyzing the drugs used for each disease based on the drug usage information regarding the disease and the drug based on the information acquired in the acquisition step. In such an aspect, it is possible to analyze the drugs used for each disease.

[0007] Furthermore, a prediction method relating to one aspect of this disclosure is a computer-based prediction method that includes a prediction step of predicting drug inventory status, the timing of the next drug production, the timing of drug production orders, or drug demand, based on pharmaceutical information relating to manufactured drugs and medication information relating to the use of drugs by patients. In this aspect, it is possible to predict drug inventory status, the timing of the next drug production, the timing of drug production orders, or drug demand.

[0008] Information processing systems, information processing methods, information processing programs, prediction methods, prediction devices, prediction programs, and methods relating to one aspect of this disclosure may also be described as follows: [1] An information processing system comprising: an acquisition unit that acquires information from multiple user terminals via a network regarding the diseases each user suffers from and the drugs the user is using for those diseases; and an analysis unit that performs an analysis of drugs used for each disease based on drug usage information relating to diseases and drugs based on the information acquired by the acquisition unit. [2] The information processing system according to [1], wherein the analysis unit further performs the analysis based on drug-related information acquired from a database of drug-related information, which is information related to pharmaceuticals. [3] The information processing system according to [1] or [2], wherein the drug usage information includes information on at least one of the following: disease name, drug usage status, drug manufacturer / distributor, and user's residential area. [4] The information processing system according to [1] to [3], wherein the analysis relates to at least one of the following: area-specific prescription trends, disease-specific prescription patterns, drug use compliance status, and co-occurring disease trends. [5] The information processing system according to any one of [1] to [4], wherein the acquisition unit acquires information obtained by mechanically reading information written on the drug packaging, or information provided from equipment used when using the drug. [6] The information processing system according to any one of [1] to [5], wherein the drug usage information further includes information about the user's residential area, and the analysis unit performs an analysis of the drugs used for each disease and area. [7] The information processing system according to any one of [1] to [6], wherein the drug usage information further includes information about the manufacturer / distributor of the drug used by the user, and the analysis unit performs an analysis of the proportion of manufacturers / distributors of drugs used for each disease. [8] The information processing system according to [7], wherein the drug usage information further includes information about the user's residential area, and the analysis unit performs an analysis of the proportion of manufacturers / distributors of drugs used for each disease and area.[9] The information processing system according to any one of [1] to [8], wherein the drug usage information further includes information about the manufacturer of the drug being used by the user, and the analysis unit performs an analysis of the drug being used for each disease and manufacturer.

[10] The information processing system according to any one of [1] to [9], wherein the drug usage information further includes information about the timing of drug use by the user, and the analysis unit performs an analysis of the timing of drug use for each disease.

[11] The information processing system according to

[10] , wherein the drug usage information further includes information about the manufacturer of the drug being used by the user, and the analysis unit performs an analysis of the timing of drug use for each disease and manufacturer.

[12] The information processing system according to

[10] or

[11] , wherein the analysis is an analysis of compliance with drug use based on the timing of drug use by the user and predetermined usage intervals for the drug.

[13] The information processing system according to any one of [1] to

[12] , wherein the analysis unit performs an analysis of drugs used for other diseases co-occurring with the disease suffered by the user.

[14] The information processing system according to

[13] , wherein the drug usage information further includes information about the manufacturer of the drugs used by the user, and the analysis unit performs an analysis of drugs used for other diseases co-occurring with the disease suffered by the user, for each disease and manufacturer.

[15] An information processing method performed by a computer, comprising: an acquisition step of acquiring information from multiple user terminals via a network about the disease each user suffers from and the drugs the user uses for that disease; and an analysis step of performing an analysis of drugs used for each disease based on the drug usage information regarding the disease and drugs based on the information acquired in the acquisition step.

[16] An information processing program for causing a computer to function as: an acquisition unit that acquires information from multiple user terminals via a network regarding diseases suffered by each user and the drugs that the user is using for those diseases; and an analysis unit that performs an analysis of drugs used for each disease based on drug usage information regarding diseases and drugs based on the information acquired by the acquisition unit.

[17] A computer-based prediction method, comprising a prediction step of predicting the inventory status of a drug, the timing of the next production of a drug, the timing of ordering the production of a drug, or the demand for a drug, based on pharmaceutical information regarding manufactured drugs and medication information regarding the use of drugs by patients.

[18] The prediction method according to

[17] , wherein the prediction step predicts based on at least one of the following included in the pharmaceutical information: identification information of a manufactured drug, information regarding the timing of the production of the drug, information regarding the quantity of the drug, and information regarding the expiration date of the drug; and at least one of the following included in the medication information: identification information of a drug administered to a patient, and information regarding the timing of the drug's use.

[19] A forecasting device comprising at least one processor, wherein the at least one processor forecasts the inventory status of a drug, the timing of the next production of a drug, the timing of ordering the production of a drug, or the demand for a drug, based on pharmaceutical information relating to a manufactured drug and medication information relating to the use of a drug to a patient.

[20] A forecasting program for causing a computer to function as a forecasting unit that forecasts the inventory status of a drug, the timing of the next production of a drug, the timing of ordering the production of a drug, or the demand for a drug, based on pharmaceutical information relating to a manufactured drug and medication information relating to the use of a drug to a patient.

[21] An information processing system comprising: an acquisition unit that acquires information on drugs used by each user from a plurality of user terminals; an analysis unit that analyzes the market inventory of a drug based on medication information relating to the use of a drug based on the information acquired by the acquisition unit and pharmaceutical information relating to a manufactured drug acquired from a pharmaceutical device; and an output unit that outputs the analysis results from the analysis unit.

[22] The information processing system according to

[21] , further comprising a forecasting unit that forecasts the demand for a drug based on the history of the market inventory.

[23] The information processing system according to

[22] , further comprising a proposal generation unit that proposes the next manufacturing timing of a drug and the timing of ordering raw materials based on the prediction results of the prediction unit.

[24] A computing device implementation method for automatic tracking and optimization of manufacturing and supply, wherein the computing device includes one or more processors, the processors comprising: receiving information (drug information) from reading barcodes of pharmaceuticals by patients for a plurality of patients, and acquiring data on the patients' drug use (date and time of use (the date and time of use can be obtained from the date and time of patient information transmission or information on the date and time of use entered by the patient), user ID, drug information, and location information); acquiring data on the market inventory of drugs from a data source including at least an inventory database; comparing and analyzing the data on the patients' drug use with the acquired data; and outputting information on the market inventory as a result of the analysis.

[25] The method according to

[24] , wherein the inventory database is a database that holds lot information related to at least one of pharmaceuticals and APIs (Active Pharmaceutical Ingredients).

[26] A method for implementing a computing device for optimizing the manufacture and supply of pharmaceuticals, wherein the computing device includes one or more processors, and comprises: acquiring data on the lot-by-lot manufacturing quantity and inventory quantity of the pharmaceutical from a pharmaceutical data source; acquiring data on the lot-by-lot usage quantity from user pharmaceutical usage data; analyzing the acquired usage quantity, manufacturing quantity and inventory quantity using a predefined set of rules to estimate the amount of unused pharmaceutical; and outputting information regarding future manufacturing based on the estimation results. (The estimation based on the set of rules is as follows. The information regarding future manufacturing is as follows: (1) Calculate the quantity shipped from the manufacturing quantity and inventory quantity. (2) Calculate the pharmaceutical wholesaler inventory using the quantity shipped from pharmaceutical wholesalers to medical institutions in each area.(3) Subtract the usage quantity obtained from user data from the shipment quantity from pharmaceutical wholesalers to medical institutions in each area to estimate the amount of unused drug in medical institutions. (4) Combine the pharmaceutical wholesaler inventory and the amount of unused drug in medical institutions to estimate the amount of unused drug in circulation. (5) Furthermore, predict future usage based on past usage trends and patient number data, and consider whether supply can keep up based on current inventory and manufacturing plans. (6) If a supply shortage is expected, propose increasing the production line or bringing forward the timing of raw material orders.

[0009] According to one aspect of this disclosure, it is possible to perform analyses of the drugs used for each disease.

[0010] This figure shows an example of the system configuration of an analysis system including an analysis device according to the embodiment. This figure shows an example of the functional configuration of the analysis device according to the embodiment. This figure shows an example of the hardware configuration of the computer used in the analysis device according to the embodiment. This figure shows the configuration of the analysis program according to the embodiment together with an auxiliary storage device. This is a sequence diagram showing an example of the processing performed by the analysis system. This figure shows an example of a table of all user information. This figure shows an example of a table of user information. This figure shows an example of a table of drug information. This is a sequence diagram showing an example of the processing performed by the analysis system. This figure shows an example of a table of updated user information. This figure shows an example of a table of added drug information. This is a sequence diagram showing an example of the processing performed by the analysis system. This figure shows an example of the drug usage screen of the application. This figure shows an example of a table of updated user information. This figure shows an example of a table of updated drug information. This is a sequence diagram showing an example of the analysis processing (1) performed by the analysis system. This figure shows an example of a table of disease-specific manufacturer information (1). This figure shows an example of a table of disease-specific manufacturer information (2). This is a sequence diagram showing an example of the analysis processing (2) performed by the analysis system. This figure shows an example of a table of disease-specific manufacturer information (3). This figure shows an example of a table of disease-specific manufacturer information (4). This figure shows an example table of disease-specific manufacturer information (part 5). This figure shows an example table of disease-specific manufacturer information (part 6). This is a sequence diagram showing an example of the analysis process (part 3) performed by the analysis system. This figure shows an example table of compliance status information (part 1). This figure shows an example table of compliance status information (part 2). This figure shows an example table of compliance status information (part 3). This figure shows an example table of compliance status information (part 4). This figure shows an example table of compliance status information (part 5). This is a sequence diagram showing an example of the analysis process (part 4) performed by the analysis system. This figure shows an example table of compliance status information (part 6). This is a sequence diagram showing an example of the analysis process (part 5) performed by the analysis system. This figure shows an example table of disease-related co-occurring disease information. This figure shows an example system configuration of a prediction system including a prediction device according to the embodiment. This figure shows an example of the functional configuration of a prediction device according to the embodiment.This figure shows an example of the hardware configuration of a computer used in a prediction device according to the embodiment. This figure shows the configuration of the prediction program according to the embodiment together with an auxiliary storage device. This is a sequence diagram showing an example of the processing performed by the prediction system. This figure shows an example of a table of all pharmaceutical information. This figure shows an example of a table of pharmaceutical information. This is a sequence diagram showing an example of the prediction processing performed by the prediction system. This figure shows an example of a table of updated pharmaceutical information (part 1). This figure shows an example of a table of updated pharmaceutical information (part 2). This figure shows an example of a table of updated pharmaceutical information (part 3). This figure shows an example of a table of inventory prediction information (part 1). This figure shows an example of a table of inventory prediction information (part 2). This is a sequence diagram showing an example of the prediction processing (part 3) performed by the prediction system.

[0011] The embodiments of this disclosure will be described in detail below with reference to the drawings. In the description of the drawings, the same elements will be denoted by the same reference numerals, and redundant descriptions will be omitted. Furthermore, the embodiments of this disclosure described below are specific examples of the present invention and are not limited to these embodiments unless otherwise stated to limit the present invention.

[0012] Figure 1 is a diagram showing an example of the system configuration of an analysis system 3, which includes an analysis device 1 (information processing system) according to an embodiment. As shown in Figure 1, the analysis system 3 is composed of an analysis device 1 and one or more user terminals 2. The analysis device 1 and each user terminal 2 are connected to each other by a network such as a mobile communication network, and can send and receive information from each other.

[0013] The analyzer 1 is a computer device that performs analysis on the medications used by a user (patient) for each disease the user is suffering from. The analyzer 1 may also be a system (information processing system) consisting of one or more computer devices. Details of the analyzer 1 will be described later.

[0014] User terminal 2 is a mobile communication terminal or a computer device such as a laptop computer that performs mobile communication. In this embodiment, a smartphone is assumed to be user terminal 2, but it is not limited to this. User terminal 2 is carried as appropriate by the user of user terminal 2. User terminal 2 is equipped with GPS (Global Positioning System) and uses GPS to acquire the current location information (latitude, longitude, etc.) of user terminal 2. User terminal 2 may also be equipped with other sensors or functions that are typical of a smartphone.

[0015] Figure 2 shows an example of the functional configuration of the analysis device 1 (analytical device) according to the embodiment. As shown in Figure 2, the analysis device 1 is composed of a storage unit 10, an acquisition unit 11, a registration unit 12, and an analysis unit 13. Details of each functional block will be described later.

[0016] Each functional block of the analysis device 1 is intended to function within the analysis device 1, but is not limited to this. For example, some of the functional blocks of the analysis device 1 may function within a computer device separate from the analysis device 1, connected to the analysis device 1 via a network, while appropriately sending and receiving information with the analysis device 1. Furthermore, some functional blocks of the analysis device 1 may be omitted, multiple functional blocks may be integrated into a single functional block, or a single functional block may be broken down into multiple functional blocks.

[0017] Figure 3 shows an example of the hardware configuration of the computer used in the analysis device 1. Physically, as shown in Figure 3, the analysis device 1 is configured as a computer system including a central processing unit (CPU) 100 (at least one), main memory (RAM) 101 and ROM (Read Only Memory) 102, input / output devices 103 such as a keyboard, microphone, and display, a data transmission and reception device (communication module) 104, and auxiliary storage devices 105 such as a hard disk and SSD (Solid State Drive). The CPU 100, RAM 101 and ROM 102, input / output devices 103, communication module 104, and auxiliary storage devices 105 may each be configured in multiple units. The functions of each functional block shown in Figure 2 are realized by loading predetermined computer software onto the hardware such as the CPU 100 and RAM 101 shown in Figure 3, thereby operating the input / output devices 103 and communication module 104 under the control of the CPU 100, and reading and writing data to the RAM 101 and auxiliary storage devices 105.

[0018] Next, we will explain the analysis program P1 (information processing program) that causes a computer to execute a series of processes performed by the analysis device 1. As shown in Figure 4, the analysis program P1 is inserted into the computer and accessed, or stored in a program storage area formed in the auxiliary storage device 105 provided by the computer. More specifically, the analysis program P1 is stored in a program storage area formed in the auxiliary storage device 105 provided by the analysis device 1.

[0019] The analysis program P1 comprises a storage module P10, an acquisition module P11, a registration module P12, and an analysis module P13. The functions realized by executing the storage module P10, acquisition module P11, registration module P12, and analysis module P13 are the same as the functions of the storage unit 10, acquisition unit 11, registration unit 12, and analysis unit 13 of the analysis device 1 described above.

[0020] Analysis program P1 is a program that causes the analysis device 1 (one or more CPUs), which is a computer, to function as a storage unit 10, an acquisition unit 11, a registration unit 12, and an analysis unit 13.

[0021] Furthermore, the analysis program P1 may be configured such that part or all of it is transmitted via a transmission medium such as a communication line, received by other devices, and stored (including installed). Also, each module of the analysis program P1 may be installed on any of several computers, not just one. In that case, the series of processes of the analysis program P1 described above will be performed by a computer system consisting of these multiple computers.

[0022] The following describes the functions of the analyzer 1 shown in Figure 2.

[0023] The storage unit 10 stores any information used or output by the analysis device 1 in a database (DB in the diagram). The database may be provided on the analysis device 1 or on another device via a network. The storage unit 10 may also store information calculated by each functional block of the analysis device 1. The information stored by the storage unit 10 may be referenced as appropriate by each functional block of the analysis device 1.

[0024] The acquisition unit 11 acquires arbitrary information. The acquisition unit 11 may acquire information from other devices such as the user terminal 2 via a network, or it may acquire information via the input / output device 103.

[0025] The acquisition unit 11 acquires at least information about the medications the user uses from the user. More specifically, the acquisition unit 11 acquires at least information about the medications the user uses from the user's user terminal 2 via the network. Furthermore, the acquisition unit 11 may acquire information about the user's illness from the user. More specifically, the acquisition unit 11 acquires at least information about the user's illness from the user's user terminal 2 via the network.

[0026] Information about a disease may be any information related to the disease. Similarly, information about a drug may be any information related to the drug. Information about a drug may include, for example, information about the type and name of the drug used by the user, the amount used, the time of use, the method of use, the duration of use, and whether or not there were side effects. Information about a disease may be any information related to the disease, for example, the name of the disease, the definition and symptoms of the disease, diagnostic methods, treatment methods, statistical information about the disease such as the incidence rate by age / sex / region, and research results on the cause and mechanism of the disease.

[0027] The acquisition unit 11 may acquire symptom information regarding the user's symptoms from the user. More specifically, the acquisition unit 11 may acquire symptom information from the user's user terminal 2 via the network.

[0028] The acquisition unit 11 may acquire information obtained by mechanically reading information written on the drug packaging, or information provided by equipment used when using the drug.

[0029] For example, the acquisition unit 11 may acquire information obtained by scanning a code, identification code, barcode, two-dimensional code, or QR code (registered trademark) (hereinafter collectively referred to as "code") written on the drug packaging with the camera provided by the user terminal 2. The code may be a code defined by GS1, an organization promoting standardization in distribution (for example, a GS1 barcode). The code may include any information related to the drug, such as the manufacturer / distributor (manufacturing company, business code), product name, drug code (product code), usage interval (recommended usage interval), lot number (manufacturing number), manufacturing date, and expiration date (expiration date), and this information can be obtained by mechanically reading the code. The code may be written (printed) on the drug packaging when the drug is dispensed, or it may be written on the packaging in advance.

[0030] Alternatively, for example, the acquisition unit 11 may acquire information obtained by scanning the text (string of characters) written on the drug packaging with the camera provided by the user terminal 2 and performing OCR (Optical Character Recognition). The text may include any information about the drug in the packaging on which the text is written (similar to the information included in the code described above), and this information can be obtained by mechanically reading the text. The text may be written (printed) on the drug packaging when the drug is dispensed, or it may be written on the packaging in advance.

[0031] Alternatively, for example, the acquisition unit 11 may acquire information provided by an auto-injector (automatic syringe) used when administering the drug. The auto-injector is equipped with a wireless communication function such as Bluetooth® and provides arbitrary information (similar to the information included in the code described above) regarding the drug used by the auto-injector to the user terminal 2 via wireless communication.

[0032] The acquisition unit 11 may store the acquired information in the storage unit 10, or it may output it to another functional block.

[0033] The registration unit 12 causes the storage unit 10 to store (register) the information. More specifically, the registration unit 12 generates information and registers the generated information. For example, the registration unit 12 may generate user information, as described below, based on information about the user, and register the generated user information. Alternatively, for example, the registration unit 12 may generate drug information, as described below, based on information about the drug, and register the generated drug information.

[0034] The registration unit 12 stores (updates) information by updating it using the storage unit 10. More specifically, the registration unit 12 updates (the information previously stored by the storage unit 10) based on update information. For example, the registration unit 12 may update the user information or drug information previously stored by the storage unit 10, as described below, based on update information at any update timing. An example of an update timing is when update information is received from the user terminal 2.

[0035] The analysis unit 13 performs an analysis of the medications used for each disease, based on the disease each user suffers from and the medication information the user is using for that disease.

[0036] The drug usage information is based on information acquired by the acquisition unit 11. For example, it is based on information acquired from the user regarding the disease each user is suffering from and the medications the user is using for that disease. The acquisition unit 11, registration unit 12, or analysis unit 13 may generate the drug usage information based on the information acquired by the acquisition unit 11. The drug usage information may also include information about the disease and the medication. The drug usage information may further include information about the user's residential area and the area where the user is located. The drug usage information may further include information about the manufacturer and distributor of the medication the user is using. The drug usage information may further include information about when the user used the medication. The drug usage information may include at least one of the following: disease name, medication usage status, manufactured medication, manufacturer and distributor of the medication, and information about the user's residential area.

[0037] The analysis unit 13 can access the pharmaceutical-related information database, which is a database of pharmaceutical-related information, via a network. The pharmaceutical-related information database may be stored by the storage unit 10. Information based on the pharmaceutical-related information database may be acquired by the acquisition unit 11.

[0038] A pharmaceutical-related information database includes, for example, data on pharmaceutical companies, demand data from medical institutions, delivery data (shipping data) from wholesalers to medical institutions, and claims data showing how many patients a medical institution has treated / prescribed in a given period. Pharmaceutical company data includes, for example, manufacturing data (raw materials, processes, quality, etc.), sales data (sales volume, revenue, etc.), and promotional activity data.

[0039] The analysis unit 13 may perform an analysis of the drugs used for each disease based on information obtained from a pharmaceutical-related information database and drug usage information based on information about the disease each user suffers from and the drugs that the user is using for that disease.

[0040] The analysis performed by the analysis unit 13 may include at least one of the following: prescription trends by area, prescription patterns by disease, information on market inventory, compliance with drug use, and trends in co-occurring diseases.

[0041] The analysis unit 13 may perform an analysis of the drugs used for each disease and area. The analysis unit 13 may perform an analysis of the proportion of manufacturers and distributors of the drugs used for each disease. The analysis unit 13 may perform an analysis of the proportion of manufacturers and distributors of the drugs used for each disease and area.

[0042] The analysis unit 13 may perform an analysis of the drugs used for each disease and manufacturer. The analysis unit 13 may perform an analysis of the timing of drug use for each disease (first timing analysis). The analysis unit 13 may perform an analysis of the timing of drug use for each disease and manufacturer (second timing analysis). The first timing analysis and the second timing analysis may be analyses of compliance with drug use based on the timing at which the user used the drug and the predetermined usage interval for that drug.

[0043] The analysis unit 13 may perform an analysis of medications used by users suffering from a specific disease for other diseases. The analysis unit 13 may perform an analysis of medications used by users suffering from a particular disease for other diseases that are co-occurring with that disease. The analysis unit 13 may perform an analysis of medications used by users suffering from a particular disease for other diseases that are co-occurring with that disease, categorized by disease and manufacturer / distributor.

[0044] The analysis unit 13 outputs the analysis result. More specifically, the analysis unit 13 may output (display) the analysis result via the input / output device 103, may output (transmit) it to another device via the network, may cause it to be stored by the storage unit 10, or may output it to another functional block.

[0045] Hereinafter, referring to FIGS. 5 to 31, details of the processing (analysis method, information processing method) by the analysis system 3, including details of the analysis by the analysis unit 13, will be described. Hereinafter, it is assumed that the user is a patient with an arbitrary disease. Even when the owner of the user terminal 2 and the operator of the user terminal 2 are acting on behalf of the patient, since information regarding the patient's disease and medicine is registered, the user is assumed to be a patient with an arbitrary disease.

[0046] FIG. 5 is a sequence diagram showing an example of the processing executed by the analysis system 3. The processing shown in FIG. 5 shows a scene of newly registering user information and medicine information. The processing shown in FIG. 5 may be referred to as new registration processing. The processing shown in FIG. 5 is assumed to be executed at the timing when the user goes to the hospital, the disease is diagnosed, and the medicine for the disease is prescribed (and dispensed), but it is not limited to this.

[0047] First, the user starts a dedicated application (hereinafter referred to as "app") on the user terminal 2 of the user (step S1). Next, the user inputs information regarding the user within the app and makes a new registration request for the user, such as by pressing a registration button (step S1). Information regarding the user includes, for example, basic attribute information such as the user's name, gender, birthday, place of residence, etc., medical information such as the name of the disease the user is suffering from, symptoms, onset time, severity, presence or absence of complications, examination data, treatment history, current treatment status, etc., and information such as past treatment history and transfer history, but is not limited to these.

[0048] Next, the user terminal 2 transmits information about the user input in step S1 to the analysis device 1 in order to perform a new registration of the user according to the instructions of the application (step S2). At this time, the position of the user at the time of data input may be automatically acquired from the user terminal 2 and transmitted as information about the user. In this case, as information about the user, instead of inputting the residence of the user, the position of the user automatically acquired may be used as the residence of the user and registered in subsequent processing. Next, the analysis device 1 receives (acquires) the information about the user transmitted in step S2 (the acquisition unit 11). The registration unit 12 issues a user ID for identifying the user upon receiving a new registration request for the user (step S3, acquisition step). The user ID may be a number with an arbitrary number of digits, and in this case, a number with an appropriate number of digits is issued. The registration unit 12 generates user information based on the issued user ID and the received information about the user (step S3, acquisition step). The registration unit 12 registers the generated user information in the database (step S3, acquisition step).

[0049] The analysis device 1 may manage the issued user ID in all user information. FIG. 6 is a diagram showing an example of a table of all user information. In the example of the table of all user information shown in FIG. 6, the data item "user ID" includes the user IDs issued so far (that is, the user IDs of all users at the current time).

[0050] User information is information including any information about the user. The user information includes the issued user ID and the above-described information about the user, and may further include other information. FIG. 7 is a diagram showing an example of a table of user information. FIG. 7 is an example including a user ID, a residence, and a disease as user information. In the example of the table of user information shown in FIG. 7, the data item "user ID" indicating the user ID of the user is "000003", the data item "residence" indicating the area where the user lives is "Tokyo", and the data item "disease (multiple possible)" indicating the disease that the user has is "disease A". Here, the residence is the name of a prefecture, but it is not limited to this, and the classification may be arbitrary, such as a country name, a regional name, a city name, etc.

[0051] Returning to Figure 5, following step S3, the analysis device 1 (the registration unit 12) transmits the user ID issued in step S3 to the user terminal 2 (step S4). Upon receiving the user ID transmitted in step S4, the user terminal 2 stores the received user ID within the application. Subsequent processing within the application uses this user ID as appropriate to identify that it is a user's processing.

[0052] Next, the user requests the registration of a new medication (step S5). Specifically, if the app is not running, the user first launches the app on user terminal 2 (step S5). Then the user enters information about the medication on the app (step S5). Information about the medication can be entered, for example, by mechanically reading the information written on the medication packaging, or by receiving it from the equipment used when the medication is administered. As an example, information about the medication can be obtained by reading the description / barcode of the prescribed medication using the camera or other equipment on user terminal 2. After entering the information about the medication, the user requests the registration of a new medication by pressing the registration button (step S5). The reading of the description / barcode of the medication is the same as described in the acquisition unit 11 above. Information about the medication includes, for example, the information contained in the code mentioned above, but is not limited to this.

[0053] Next, the user terminal 2 transmits the user ID stored in the app and the drug information entered in step S5 to the analyzer 1 in order to register a new drug according to the app's instructions (step S6). Next, the acquisition unit 11 of the analyzer 1 receives (acquires) the user ID and drug information transmitted in step S6.

[0054] The registration unit 12 generates drug information based on the received user ID and drug information, and registers the generated drug information in the database (step S7, acquisition step). After executing step S5 or step S7, the drug information entered in step S5 may also be managed in the application.

[0055] Drug information is optional information about a drug product and includes information that identifies the drug product.

[0056] As mentioned above, the information used to identify the drug product may be information obtained by the user reading the code displayed on the container. Specifically, the GS1 barcode is read using the camera of the user terminal 2, and the product code, manufacturing date and expiration date, manufacturing number or manufacturing code (lot number) displayed together with the GTIN are obtained as information about the drug. Based on this obtained information about the drug and the user ID, drug information about the drug used by the user is generated.

[0057] In addition, drug information may also include generally known drug characteristics, appropriate usage methods, and precautions. For example, this could include the drug name, generic name / ingredient name, route of use (oral, topical, subcutaneous injection, intravenous injection, etc.), recommended dosage and administration interval / timing as stated in the package insert, duration of use, efficacy / effects, side effects, contraindications, precautions when used in combination with other drugs, and storage methods, but other information may also be included. Information that identifies the drug product used by the user and any other information related to the drug product may be obtained from a drug-related information database. For example, product information registered with the PMDA (Pharmaceuticals and Medical Devices Agency) may be referenced based on the GS1 barcode. Specifically, since each business operator links the GTIN on the GS1 barcode displayed on the product with the electronic supplement when registering with the PMDA, it is possible to access the latest electronic supplement based on the GTIN on the barcode by reading the GS1 barcode displayed on the product container or packaging using an app or similar device. In addition to electronic attachments, it will also be possible to access related documents such as review reports using GS1 barcodes.

[0058] Figure 8 shows an example of a drug information table. In the example drug information table shown in Figure 8, the data item "Manufacturer / Distributor" indicating the manufacturer / distributor of the drug is "M Pharmaceutical," the data item "Product Name" indicating the product name of the drug is "Drug X," the data item "Usage Interval" indicating the recommended usage interval of the drug (by the manufacturer / distributor, etc.) is "1 day," the data item "Lot Number" indicating the lot number of the drug is "21AA520Z," the data item "Manufacturing Date" indicating the manufacturing date of the drug is "2024 / 01 / 18," and the data item "Expiration Date" indicating the expiration date of the drug is "2028 / 01 / 18."

[0059] In Figure 5, user registration and drug registration are shown consecutively, but these can be performed at different times or on different devices. After the user ID has been issued, drug registration can be performed at any time by launching the application on user device 2.

[0060] The example drug information table shown in Figure 8 is the drug information associated with "Disease A" in the data item "Disease (multiple allowed)" in the example user information table shown in Figure 7. In other words, the drugs shown in the example drug information table in Figure 8 are the drugs used by the user with user ID "000003" for disease A. In this embodiment, the registration unit 12 associates drug information with diseases included in the user information. In this embodiment, the combination of user information and drug information that are linked to each other is appropriately referred to as "used drug information".

[0061] Figure 9 is a sequence diagram showing an example of a process performed by the analysis system 3. The process shown in Figure 9 represents the updating and registration of user information or drug information. The process shown in Figure 9 can also be called the update and registration process.

[0062] The process shown in Figure 9 is performed when any event occurs. This includes, but is not limited to, situations such as when some user information is updated, when a new treatment plan is decided for an existing disease, or when a new disease is discovered and a new medication is prescribed. Examples of situations where a new treatment plan is decided include when a new medication is prescribed, when the medication content or dosage is changed, when side effects occur, when an existing medication is discontinued, or when the database or medical guidelines are updated.

[0063] First, the user submits an update registration request (step S10). First, if the app is not running on the user terminal 2, the user launches the app (step S10). The user submits an update registration request by entering update information on the app and pressing the registration button, etc. (step S10). As an example of entering update information, the user may appropriately write down the drug information or read the barcode. The explanation for writing down the drug information or reading the barcode is the same as described above for the acquisition unit 11. The update information may be, for example, updated information for some or all of the user information or drug information, but is not limited to this. Next, the user terminal 2 sends the user ID stored in the app and the update information entered in step S10 to the analyzer 1 in order to perform update registration according to the app's instructions (step S11). Next, in the analyzer 1, the acquisition unit 11 receives (acquires) the user ID and update information sent in step S11, and the registration unit 12 updates the user information or drug information registered in the database based on the received user ID and update information (step S12, acquisition step).

[0064] Figure 10 shows an example of a user information table updated (in step S12). More specifically, the user information table example shown in Figure 10 is the same as the user information table example shown in Figure 7, but the data item "Place of Residence" has been updated from "Tokyo" to "Osaka" (by the registration unit 12), and "Disease B" has been added to the data item "Disease (multiple allowed)" ("Disease A" has been updated to "Disease A, Disease B"). These updates indicate, for example, that a user with user ID "000003" has moved from Tokyo to Osaka and has newly contracted (comorbidly contracted) disease B.

[0065] Figure 11 shows an example of a drug information table added (in step S12). More specifically, the drug information table example shown in Figure 11 is the drug information associated with "Disease B" in the data item "Disease (multiple allowed)" in the user information table example shown in Figure 10. In the drug information table example shown in Figure 11, the data item "Manufacturer / Distributor" is "N Pharmaceutical," the data item "Product Name" is "Drug Y," the data item "Usage Interval" is "2 days," and the data item "Lot Number" is "42ZZB40" (explanation of other data items is omitted).

[0066] While this example assumes a scenario where users voluntarily request update registration, another possible implementation is where information is updated in conjunction with drug usage records.

[0067] The following is an example of how information is updated in accordance with the recording of drug use. As described below, in order for the user to record drug use, the user inputs information about the drug each time they use the drug on the app, such as by writing down the drug or scanning its barcode. The user then inputs the information to be registered and requests to record drug use by pressing the registration button. Next, the user terminal 2 sends the user ID stored in the app and the drug use information to the analyzer 1 in order to register drug use according to the app's instructions. In this embodiment, the acquisition unit 11 in the analyzer 1 receives (acquires) the user ID and drug use information transmitted in step S11. Past user information and drug information are acquired in light of the received user ID, and the differences between the acquired drug use information and past user information or drug information are identified. For example, when the number of drugs used has increased compared to past drug information, the addition of diseases to the user information data item "Disease (multiple possible)" or the addition of drug information is identified. The analyzer 1 transmits the identified differences to the user terminal 2. A message will appear on user terminal 2 asking whether registration of the differences is necessary. If the user approves the registration, information regarding the update will be generated.

[0068] Furthermore, even if the user does not voluntarily request an update registration on the app, if the GS1 code of the medication being used is read using the camera on user terminal 2, the update may be performed based on the difference from the previous version, as described above.

[0069] Figure 12 is a sequence diagram showing an example of a process performed by the analysis system 3. The analysis process shown in Figure 12 represents a scenario in which drug use is recorded. The process shown in Figure 12 can also be called drug use recording processing. The analysis process shown in Figure 12 is assumed to be performed at the time the user uses the drug, but it is not limited to this.

[0070] First, if the user has not launched the app, the app is launched on user terminal 2 (step S20). The user requests a record of drug use on the app's drug use screen (step S20). The request to record drug use may be made, for example, by pressing the drug use button, by reading the drug's label / barcode, or by activating the auto-injector.

[0071] Figure 13 shows an example of the app's medication usage screen. As shown in the example screen in Figure 13, there is a usage button for each medication managed by the app, and the user presses the usage button for the medication when they want to use it.

[0072] Returning to Figure 12, following step S20, the user terminal 2 acquires GPS location information, the lot number of the drug used, and the date and time of use (step S21). The lot number of the drug used is acquired, for example, by reading the drug's label / barcode or by operating the auto-injector.

[0073] Next, the user terminal 2 transmits the user ID stored in the app, the GPS location information acquired in step S21, the lot number, and the date and time of use to the analyzer 1 in order to record drug use according to the app's instructions (step S22). Next, the analyzer 1 receives (acquires) the user ID, GPS location information, lot number, and date and time of use transmitted in step S22 (acquisition unit 11), and the registration unit 12 updates the user information or drug information registered in the database based on the received user ID, GPS location information, lot number, and date and time of use (step S23, acquisition step).

[0074] Figure 14 shows an example of a user information table updated (in step S23). More specifically, the user information table example shown in Figure 14 is the same as the user information table example shown in Figure 10, but with the data item "Latest Location Information" (the area where the user is located) having the latitude and longitude "35.68, 139.77" added (by the registration unit 12). This update indicates, for example, that a user with user ID "000003" used (the most recent) medication at the location (area) indicated by "35.68, 139.77". Note that the latest location information may be estimated to be the user's residential area.

[0075] Figure 15 shows an example of a drug information table updated (in step S23). More specifically, the drug information table example shown in Figure 15 is the same as the drug information table example shown in Figure 8, but with "2024 / 07 / 07 12:00", which indicates the date and time the drug was used, added (by the registration unit 12) to the data item "Date and Time of Use (multiple entries allowed)". This update indicates, for example, that a user with user ID "000003" used "drug X" for "disease A" on "2024 / 07 / 07 12:00".

[0076] Furthermore, while the above assumes that the user obtains the lot number each time the medication is used, this is not the only case. For example, the user may input multiple prescriptions of medication at once, or record / scan the barcodes of multiple medications at once. In such cases, a medication usage screen may be displayed showing multiple medication names and lot numbers. In this case, the medications may be arranged in order of their expiration date.

[0077] Furthermore, the analyzer 1 may analyze whether a drug for which the user has requested a record of drug use is a safe drug. Specifically, before using a drug, the user sends information including the drug's lot number and the date and time of use to the analyzer 1. Based on the received drug's lot number, the analyzer 1 obtains information identifying the drug product the user intends to use and any other information about the drug product from a pharmaceutical-related information database. Then, based on the information identifying the drug product the user intends to use and the information regarding the date and time of use, it compares this information with the information provided by the manufacturer and determines whether or not the drug is safe.

[0078] For example, based on lot information provided by the manufacturer, the system obtains information about the expiration date and determines that the drug is safe if the user's usage date is before the expiration date (within the expiration date). If the expiration date is before the user's usage date (expired), the system determines that the drug is not safe. The system also determines whether the product is a counterfeit (not part of the official supply chain) based on lot information provided by the manufacturer. Furthermore, the system determines whether the product is subject to a recall based on lot information provided by the manufacturer. If the analysis determines that the drug is not safe, the analyzer 1 generates a warning message and sends it to the user terminal 2. The warning is then displayed on the user terminal 2.

[0079] Figure 16 is a sequence diagram showing an example of the analysis process (part 1) performed by the analysis system 3. The analysis process shown in Figure 16 illustrates the analysis of prescription trends for each disease. The process shown in Figure 16 can also be called disease-specific prescription trend analysis. The analysis process shown in Figure 16 is performed based on disease-specific manufacturer information.

[0080] The analysis process shown in Figure 16 can be performed at any time. While it is assumed that the analysis will be performed at the time the analyst performs the analysis, this is not the only option. The analysis may also be performed regularly, such as monthly, quarterly, or yearly.

[0081] First, the analysis unit 13 of the analysis device 1 extracts information about the manufacturers and distributors of drug information associated with a disease from the information stored in the database by the storage unit 10, for each disease (step S30). The extracted information about manufacturers and distributors is included in the disease-specific manufacturer and distributor information. Figure 17 shows an example table of disease-specific manufacturer and distributor information (part 1). More specifically, the example table of disease-specific manufacturer and distributor information shown in Figure 17 is an example of the information extracted in step S30. As shown in the example table of disease-specific manufacturer and distributor information in Figure 17, for each disease (for example, "Disease A", "Disease B", etc.), the manufacturers and distributors of drug information associated with that disease in the user information containing that disease (for example, "M Pharmaceutical", "N Pharmaceutical", etc.) are extracted.

[0082] Returning to Figure 16, following step S30, the analysis unit 13 of the analyzer 1 calculates the percentage of manufacturers and distributors of the drugs used for each disease (step S31, analysis step). The calculated information on the percentage of manufacturers and distributors is included in the disease manufacturer and distributor information. Figure 18 shows an example table of disease manufacturer and distributor percentage information (part 2). More specifically, the example table of disease-specific manufacturer and distributor information shown in Figure 18 is an example of the result of performing the calculation in step S31 on the example table of disease-specific manufacturer and distributor information shown in Figure 17. As shown in the example table of disease-specific manufacturer and distributor information shown in Figure 18, for each disease (for example, "Disease A", "Disease B", etc.), the percentage of manufacturers and distributors of the drugs used (for example, "M Pharmaceutical 70%, N Pharmaceutical 20%,...", "M Pharmaceutical 20%, N Pharmaceutical 50%,...", etc.) is calculated.

[0083] As described above, the analysis unit 13 may perform an analysis on the proportion of manufacturers and distributors of drugs used for each disease as a trend in prescriptions by disease. Alternatively, instead of analyzing by disease name, it may perform an analysis on the proportion of manufacturers and distributors of drugs used for each disease area as a trend in prescriptions by disease area.

[0084] Figure 19 is a sequence diagram showing an example of the analysis process (part 2) performed by the analysis system 3. The analysis process shown in Figure 19 shows a scenario in which the analysis is performed for each disease, similar to the analysis process shown in Figure 18, and further analyzes the prescribing trends by prefecture. The analysis process shown in Figure 19 can be performed at any time, similar to the analysis process shown in Figure 18. For example, it is assumed that it will be performed when the analyst performs the analysis, but this is not the only option. The analysis process may be performed regularly, such as monthly, quarterly, or yearly. The process shown in Figure 19 can also be called disease-specific prescribing trend analysis. The analysis process shown in Figure 19 is performed based on disease-specific manufacturer information.

[0085] First, the analysis unit 13 of the analysis device 1 extracts the residential location (or residential location based on the latest location information) of user information containing the disease for each disease, and the manufacturer / distributor of drug information associated with that disease in the user information, from the information stored in the database by the storage unit 10 (step S40). The extracted information is called disease-specific manufacturer / distributor information. Figure 20 is a diagram showing an example table of disease-specific manufacturer / distributor information (part 3). More specifically, the example table of disease-specific manufacturer / distributor information shown in Figure 20 is an example of the information extracted in step S40. As shown in the example table of disease-specific manufacturer / distributor information in Figure 20, for each disease (for example, "Disease A", "Disease B", etc.), the residential location (for example, "Tokyo", "Saitama", etc.) of user information containing the disease and the manufacturer / distributor of drug information associated with that disease in the user information (for example, "M Pharmaceutical", "N Pharmaceutical", etc.) are extracted.

[0086] Returning to Figure 19, following step S40, the analysis unit 13 of the analyzer 1 calculates the percentage of manufacturers and distributors of the drugs used by each user with the same disease and place of residence (step S41, analysis step). The calculated information is included in the disease-specific manufacturer information. Figure 21 is a diagram showing an example table of disease-specific manufacturer information (part 4). More specifically, the example table of disease-specific manufacturer information shown in Figure 21 is an example of the result of performing the calculation in step S41 on the example table of disease-specific manufacturer information shown in Figure 20. As shown in the example table of disease-specific manufacturer information in Figure 21, for each disease (for example, "Disease A", "Disease B", etc.), the percentage of manufacturers and distributors of the drugs used by the user (for example, "M Pharmaceutical 70%, N Pharmaceutical 20%,...", "M Pharmaceutical 20%, N Pharmaceutical 50%,...", etc.) is calculated for each user with the same place of residence (for example, "Tokyo", "Saitama", etc.).

[0087] As described above, the analysis unit 13 may perform an analysis of the drugs used for each disease and place of residence. The analysis unit 13 may also perform an analysis of the proportion of manufacturers and distributors of the drugs used for each disease and place of residence. Here, an analysis is performed by prefecture as an example of place of residence, but the area setting is arbitrary, and for example, the analysis may be performed by country, by regional division, or by city, town, or village.

[0088] Furthermore, the influence of each pharmaceutical company on each disease can be estimated by aggregating how many times each company's drugs are prescribed for each disease. By comparing the frequency of drug use for each disease, it is possible to rank which drugs are frequently prescribed for each disease, or conversely, which drugs are rarely prescribed. In addition, trends can be analyzed over time to determine how many times each company's drugs are prescribed for each disease. The analysis results can then be output (by the analysis unit 13) as changes in drug prescription trends for each disease.

[0089] The disease-specific prescription trend analysis shown in Figures 16 and 19 is performed for each disease based on information about the manufacturer of the drug linked to the user information containing that disease, but it may also be performed based on information obtained from a pharmaceutical-related information database.

[0090] Examples of pharmaceutical-related information databases include prescription databases containing prescription data from wholesalers to medical institutions, and claims databases containing claims data showing how many patients a medical institution has treated / prescribed for over a certain period.

[0091] For example, a comparative analysis may be performed between the shipment status of each drug based on information obtained from a prescription database and the actual usage status based on information about the manufacturer of the drug linked to the user information for that disease.

[0092] Figure 22 shows an example table of disease-specific manufacturer information (part 5). Figure 23 shows an example table of disease-specific manufacturer information (part 6). As shown in the example tables in Figures 22 and 23, compared to the example table in Figure 20, "Prescription DB" shows the quantity of prescribed drugs in the prescription DB, "App" shows the quantity of drugs reported to be used in the app, and "App Unused" shows the quantity of drugs whose use has not been reported because the app is not being used, obtained by subtracting the number of drugs reported to be used from the prescription DB (number of prescribed drugs). In the example tables in Figures 22 and 23, the percentage value in parentheses after the numerical value showing the quantity indicates the proportion of each pharmaceutical company's products in the total.

[0093] Focusing on the prescription DB and app columns in the example table shown in Figure 22, it can be confirmed that the prescription trends of app users are the same as those of the prescription DB. On the other hand, focusing on the prescription DB and app columns in the example table shown in Figure 23, the prescription trends of app users differ from those of the prescription DB, suggesting that there may be bias in app users or other factors at play. Furthermore, considering the data in the non-app users column in the example tables shown in Figures 22 and 23, the disease-specific prescription trend analysis by the analysis unit 13 makes it possible to formulate measures such as conducting awareness campaigns to encourage app use even among non-app users, particularly those residing in Saitama.

[0094] By using shipment data of pharmaceuticals from medical device wholesalers to medical institutions, the distribution volume of each pharmaceutical can be grasped. Here, the drug usage information obtained from users does not include information on all drugs used, but rather information on some of the drugs used by the app's users. However, the drug shipment data indicates the market size of the drug, and the drug usage records obtained from users indicate actual drug use. Therefore, it becomes possible to compare the shipment volume by disease / area with the amount of drug used by users. Identifying the gap between shipment volume and usage volume allows for more accurate analysis when performing analysis based on drug usage information obtained from users, as described below. The difference between the drug shipment volume and the amount of drug used as determined from user information may be calculated for each disease, area, and manufacturer. In this case, diseases, areas, and manufacturers where the difference between drug shipment volume and drug usage volume is significantly large or small may be extracted.

[0095] Based on the disease-specific prescription trend analysis performed by the analysis unit 13 described above, it becomes possible to formulate market strategies for each prefecture, identify the prefecture in which users reside using at least one of user ID and GPS information, analyze prescription trends for each disease by prefecture, and develop countermeasures against competitors.

[0096] The analysis unit 13 can execute policy proposals and formulations on the system based on the analysis results regarding drugs used for each disease and residential area. Specifically, it calculates the drug usage trends of each company's products for each disease and region, performs comparative analysis, and generates hypotheses to explore the background of the analysis. Furthermore, it outputs countermeasures and proposed solutions based on the results.

[0097] The analysis unit 13 can automatically generate and output analysis results such as whether the usage rate of M Pharmaceutical product in a specific area is low or high for disease A.

[0098] Furthermore, based on the above analysis results, AI (Artificial Intelligence) can automatically generate the following hypotheses: 1) The possibility that there are doctors in a specific hospital who prefer to prescribe products from a specific pharmaceutical company for a particular disease (e.g., the possibility that there are doctors in Hospital F who prefer to prescribe products from Pharmaceutical Company M for disease A). 2) The possibility that there are fan doctors of a specific pharmaceutical company in a specific area (e.g., the possibility that there are many fan doctors of Pharmaceutical Company N, mainly in private university hospitals in Saitama Prefecture). 3) The possibility that, due to the geographical situation of a specific area, there are prominent doctors specializing in the disease in question in a specific hospital, and that patients are concentrated there (e.g., due to the car-centric geographical situation in Ibaraki Prefecture, there is a possibility that prominent doctors specializing in disease A are located in hospitals that are easily accessible by car, and that patients are concentrated there). 4) The priority of each pharmaceutical company's products in a specific area (e.g., the possibility that Pharmaceutical Company M's products have a low priority in the formularies of hospitals in Saitama Prefecture).

[0099] Based on the above analysis results and generated hypotheses, this system can automatically propose the following countermeasures: 1) Investigating the delivery status and formulary listing status of hospitals in a specific area; 2) Increasing opportunities for visits to physicians and pharmacy departments; 3) Developing visit strategies when the usage rate of our products is significantly lower than that of competitors' products for specific diseases or regions.

[0100] These analysis results, hypothesis generation, and proposed countermeasures may all be performed on the system and output through a user interface. One aspect of this disclosure enables pharmaceutical companies to quickly and efficiently analyze drug use and formulate strategies, which can then be used to develop appropriate strategies and countermeasures. This will enable efficient and precise analysis of drug use and strategic planning, creating new value in the pharmaceutical industry.

[0101] Figure 24 is a sequence diagram showing an example of an analysis process (part 3) performed by the analysis system 3. The analysis process shown in Figure 24 illustrates a scenario in which medication adherence is analyzed. The process shown in Figure 24 can also be called medication adherence analysis. The analysis process shown in Figure 24 is assumed to be performed at the time the analyst performs the analysis, but is not limited to this. Figure 24 relates to a process in which the analysis unit 13 acquires medication information, including information about when the user used the medication, and performs an analysis (first timing analysis) regarding the timing of medication use for each disease.

[0102] First, the analysis unit 13 of the analysis device 1 extracts the manufacturer, usage interval, and usage date and time for each drug information associated with the disease in the user information containing that disease from the information stored in the database by the storage unit 10 (step S50). The extracted information is used as compliance status information. Figure 25 is a diagram showing an example of a compliance status information table (part 1). More specifically, the compliance status information table example shown in Figure 25 is an example of the information extracted in step S50. As shown in the compliance status information table example in Figure 25, for each disease (for example, "Disease A", "Disease B", etc.), the manufacturer (for example, "M Pharmaceutical", "N Pharmaceutical", etc.), usage interval (for example, "1 day", "2 days", "3 days", etc.) and usage date and time (for example, "2024 / 01 / 03 9:13, 2024 / 01 / 04 8:30, 2024 / 01 / 06 9:01, ...") are extracted for each drug information associated with the disease in the user information containing that disease.

[0103] Returning to Figure 24, following step S50, the analysis unit 13 of the analyzer 1 calculates the compliance rate using the usage interval and usage date and time (step S51). Specifically, if the difference between the actual usage interval calculated from an arbitrary usage date and time and the next usage date and time, and the set usage interval, is within a certain time, it is determined that the user is complying with the medication. If the difference between the actual usage interval calculated from an arbitrary usage date and time and the next usage date and time, and the set usage interval, is significant, it is determined that the user is not complying. For all user IDs, compliance is determined for each drug use using the accumulated drug use records for each user ID. By aggregating the results of the compliance determination, compliance status information can be obtained. Figure 26 is a diagram showing an example of a compliance status information (part 2) table. More specifically, the example compliance status information table shown in Figure 26 is an example of the result of performing the calculation in step S51 on the example compliance status information table shown in Figure 25. As shown in the example compliance status information table in Figure 26, for each disease, the compliance rate (e.g., "94%", "90%", "55%", etc.) is calculated for each manufacturer and distributor of the drug used. The example table may be output sorted in descending order of compliance rate, and values ​​below a certain threshold may be highlighted.

[0104] Returning to Figure 24, following step S51, the analysis unit 13 of the analyzer 1 calculates the average compliance rate for each manufacturer and distributor of each drug (step S52, analysis step). The calculated information is used as compliance status information. Figure 27 shows an example of a compliance status information table (part 3). More specifically, the compliance status information table example shown in Figure 27 is an example of the result of performing the calculation in step S52 on the compliance status information table example shown in Figure 26. As shown in the compliance status information table example in Figure 27, the compliance rate (for example, "92%", "60%", etc.) is calculated for each disease for each manufacturer and distributor of the drug used.

[0105] The analysis unit 13 may calculate the average compliance rate for each user. Figure 28 shows an example table of compliance status information (part 4). In the example table shown in Figure 28, the average compliance rate is calculated for each user ID. This makes it possible to see the relationship between treatment effectiveness and compliance. Furthermore, the analysis unit 13 may calculate the average compliance rate for each disease, for each region, or for each pharmaceutical company (for each product) based on the average compliance rate for each user.

[0106] The analysis unit 13 may also perform an analysis on medication compliance rates for concomitant diseases. Figure 29 shows an example table of compliance status information (part 5). The example table shown in Figure 29 is similar to the example table shown in Figure 28, but for diseases, it targets disease B, which is often co-occurring with disease A, the target of the example table shown in Figure 28. This makes it possible to analyze, for example, whether neglecting treatment for disease B leads to further neglect of treatment for disease A (for example, if a user is being treated with anticancer drugs and experiences nausea as a side effect, and has a low adherence rate to medication for nausea, the nausea may not subside, making it impossible to continue anticancer drug treatment).

[0107] Figure 30 is a sequence diagram showing an example of an analysis process (part 4) performed by the analysis system 3. The analysis process shown in Figure 30 illustrates a scenario in which medication adherence is analyzed. The analysis process shown in Figure 30 is assumed to be performed at the time the analyst performs the analysis, but is not limited to this. Figure 30 relates to a process in which the analysis unit 13 acquires drug usage information, including information on when the user used the drug and information on the manufacturer and distributor of the drug the user is using, and performs an analysis on the timing of drug use for each disease (second timing analysis).

[0108] Steps S50 and S51 in Figure 30 are the same as steps S50 and S51 in Figure 24, so their explanation is omitted. Following step S51 in Figure 30, the analysis unit 13 of the analyzer 1 calculates the average compliance rate for each disease (step S53, analysis step). The calculated average compliance rate is used as compliance status information. Figure 31 is a diagram showing an example of a compliance status information table (part 6). More specifically, the example compliance status information table shown in Figure 31 is an example of the result of performing the calculation in step S53 on the example compliance status information table shown in Figure 26. As shown in the example compliance status information table in Figure 31, a compliance rate (for example, "85%", "77%", etc.) is calculated for each disease.

[0109] As described above, the analysis unit 13 may perform an analysis of the drugs used for each disease and manufacturer. The analysis unit 13 may also perform an analysis of the timing of drug use for each disease (first timing analysis). The analysis unit 13 may also perform an analysis of the timing of drug use for each disease and manufacturer (second timing analysis). Here, the first timing analysis and the second timing analysis may be analyses of compliance with drug use based on the timing at which the user used the drug and the predetermined usage interval for that drug.

[0110] The analysis unit 13 can analyze compliance with the prescribed dosage and administration of medications. This analysis may be performed using artificial intelligence (AI) technology. Because AI has the ability to process large amounts of data at high speed and detect complex patterns, it can perform detailed analyses of drug use trends by disease and region.

[0111] Specifically, the analysis unit 13 may automatically perform an analysis of medication compliance status for each disease, such as calculating the medication compliance rate of patients using products from each pharmaceutical company, and output the results.

[0112] Furthermore, the analysis unit 13 may automatically generate the following hypotheses based on the above analysis results: 1) Factors that may cause differences in medication adherence rates among patients using products from M Pharmaceutical and N Pharmaceutical in disease A include: a) Insufficient understanding of dosage and administration by patients b) Insufficient information provided to patients by physicians c) Insufficient information provided to physicians by medical representatives (MRs)

[0113] Based on the analysis results and generated hypotheses, this analytical device 1 may also be capable of automatically suggesting the following countermeasures: 1) Introducing a smartphone application for patient medication management; 2) Improving M Pharmaceutical's promotional materials; 3) Improving pharmaceuticals that are difficult to use at home.

[0114] These analysis results, hypothesis generation, and proposed countermeasures can all be performed on the analyzer 1 and output through a user interface. This analyzer 1 enables pharmaceutical companies to develop and implement effective strategies to improve patient medication adherence.

[0115] Figure 32 is a sequence diagram showing an example of an analysis process (part 5) performed by the analysis system 3. The analysis process shown in Figure 32 illustrates the analysis of co-occurring diseases and therapeutic drugs. The analysis process shown in Figure 32 may also be called co-occurring disease analysis or concomitant drug analysis. The analysis process shown in Figure 32 is assumed to be performed at the time the analyst performs the analysis, but is not limited to this.

[0116] First, the analysis unit 13 of the analysis device 1 extracts, for each disease, the manufacturer and distributor of the drug information associated with the disease from the information stored in the database by the storage unit 10, the co-occurring diseases (comorbid diseases) from the user information, and the product names of the drug information associated with those co-occurring diseases (only extracting if there are co-occurring diseases) (step S60, analysis step). The extracted information is called disease-comorbid disease information. Figure 33 is a diagram showing an example of a table of disease-comorbid disease information. More specifically, the example table of disease-comorbid disease information shown in Figure 33 is an example of the information extracted in step S60. As shown in the example table of disease-related co-occurring disease information in Figure 33, for each disease (e.g., "Disease A", "Disease B", etc.), the manufacturer of the drug information associated with that disease in the user information containing that disease (e.g., "M Pharmaceutical", "N Pharmaceutical", etc.), the co-occurring diseases in the user information (e.g., "Disease B", "Disease C", "Disease D", etc.), and the product names of the drug information associated with those co-occurring diseases (e.g., "Drug X", "Drug Y", "Drug Z", etc.) are extracted.

[0117] As described above, the analysis unit 13 may perform an analysis of drugs used for other diseases suffered by users who have the disease in question, disease by disease. Furthermore, the analysis unit 13 may perform an analysis of drugs used for other diseases suffered by users who have the disease in question, disease by disease and by manufacturer / distributor.

[0118] The analysis performed by the analysis unit 13 described above makes it possible to identify co-occurring diseases and concomitant medications in a specific disease. For example, in a specific disease, analysis such as identifying the usage status of drugs for diseases other than the disease in question is automatically performed and the results are output. In addition, for a specific disease, it becomes possible to calculate the incidence rate of other diseases in patients using products from each pharmaceutical company (for example, the incidence rate of hypertension or diabetes).

[0119] Based on the above analysis results, this analytical device 1 can automatically generate the following hypotheses: 1) Whether disease A has a high proportion of patients who also have lifestyle-related diseases; 2) Whether there is a possibility of interaction problems with diabetes medications in patients using M Pharmaceutical's products; 3) Whether patients using N Pharmaceutical's products are also using diabetes medications from M Pharmaceutical.

[0120] Based on the analysis results and generated hypotheses, this analytical device 1 can automatically propose the following countermeasures: 1) Investigate the status of product delivery to each medical institution and its inclusion in formularies; 2) Increase opportunities for visits to physicians and pharmacy departments.

[0121] In particular, this analyzer 1 analyzes drug usage for each disease and area, and if the usage rate is significantly lower compared to other companies' products, it automatically outputs a suggestion to increase opportunities for visits to doctors and pharmacy departments. All of these analysis results, hypothesis generation, and suggested countermeasures are performed on the system and output through the user interface.

[0122] Next, we will explain the operation and effects of the analysis device 1 (information processing system).

[0123] The analysis device 1 includes an acquisition unit 11 that acquires information from multiple user terminals via a network regarding the diseases each user suffers from and the medications that the user is using for those diseases, and an analysis unit 13 that performs an analysis of the medications used for each disease based on the drug usage information related to the diseases and medications acquired by the acquisition unit 11. In this respect, it is possible to perform an analysis of the medications used for each disease.

[0124] The analyzer 1 includes at least an acquisition unit 11 that obtains information about the medications used by the user from the user. The information about the medications used is based on the information obtained by the acquisition unit 11. In this respect, an analysis of the medications used for each disease is performed based on the information about the medications used obtained from the user. This makes it possible to perform an analysis that reflects the actual circumstances of the user, for example.

[0125] The analysis unit 13 may perform further analysis based on pharmaceutical-related information obtained from a database of pharmaceutical-related information, which is information related to pharmaceuticals. In this respect, for example, a more accurate and detailed analysis can be performed based on further pharmaceutical-related information.

[0126] The drug information may include information on the disease name, drug usage, manufactured drug, drug manufacturer, and user's residential area, and the analysis may focus on at least one of the following: area-specific prescribing trends, disease-specific prescribing patterns, information on market inventory, drug use compliance, and trends in co-occurring diseases. In this regard, an analysis can be conducted on at least one of the following: area-specific prescribing trends, disease-specific prescribing patterns, information on market inventory, drug use compliance, and trends in co-occurring diseases.

[0127] The acquisition unit 11 may acquire information obtained by mechanically reading information written on the drug packaging, or information provided by the equipment used when the drug was administered. In this respect, for example, more accurate information about the drug can be obtained, thereby enabling analysis based on more accurate information.

[0128] The above drug usage information may further include information about the area where the user is located, and the analysis unit 13 may perform an analysis of the drugs used for each disease and area. In this respect, an analysis of the drugs used for each disease and area can be performed.

[0129] The above drug usage information may further include information about the manufacturer or distributor of the drug used by the user, and the analysis unit 13 may perform an analysis on the proportion of manufacturers or distributors of the drug used for each disease. In this respect, an analysis on the proportion of manufacturers or distributors of the drug used for each disease can be performed.

[0130] The above drug usage information may further include information about the area where the user is located, and the analysis unit 13 may perform an analysis on the proportion of manufacturers and distributors of the drugs used for each disease and area. In this respect, an analysis can be performed on the proportion of manufacturers and distributors of the drugs used for each disease and area.

[0131] The above drug usage information may further include information about the manufacturer and distributor of the drugs used by the user, and the analysis unit 13 may perform an analysis of the drugs used for each disease and manufacturer. In this respect, an analysis of the drugs used for each disease and manufacturer can be performed.

[0132] The above drug usage information may further include information about when the user used the drug, and the analysis unit 13 may perform an analysis of the timing of drug use for each disease (first timing analysis). In this respect, an analysis of the timing of drug use for each disease can be performed.

[0133] The above drug usage information may further include information about the manufacturer of the drug being used by the user, and the analysis unit 13 may perform an analysis (second timing analysis) regarding the timing of drug use for each disease and manufacturer. In this respect, an analysis regarding the timing of drug use for each disease and manufacturer can be performed.

[0134] The first and second timing analyses may also be analyses of compliance with drug use based on the timing at which the user used the drug and the predetermined dosing interval for that drug. In this respect, an analysis of compliance with drug use can be performed.

[0135] The analysis unit 13 may also perform an analysis of medications used for other co-occurring diseases in users suffering from each disease. In this respect, it is possible to perform an analysis of medications used for other diseases in each disease.

[0136] The above drug usage information may further include information about the manufacturer of the drug being used by the user, and the analysis unit 13 may perform an analysis of drugs used for other diseases that users suffering from the disease have co-occurring with that disease, for each disease and manufacturer. In this respect, it is possible to perform an analysis of drugs used for other diseases, for each disease and manufacturer.

[0137] As mentioned above, Patent Document 1 discloses a computer implementation method for measuring the therapeutic effect of a medical drug on a disease. However, this computer implementation method cannot predict, for example, the inventory status of a drug, the timing of the next manufacturing of a drug, the timing of ordering the manufacture of a drug, or the demand for a drug; in other words, it cannot make predictions related to drugs.

[0138] Figure 34 shows an example of the system configuration of a prediction system 6 including a prediction device 4 according to an embodiment. As shown in Figure 34, the prediction system 6 is composed of an analyzer 1, a prediction device 4, and a pharmaceutical device 5. The analyzer 1 and the prediction device 4 are connected to each other via a network such as the Internet, and can send and receive information from each other. Similarly, the prediction device 4 and the pharmaceutical device 5 are connected to each other via a network such as the Internet, and can send and receive information from each other. Note that the analyzer 1 and the prediction device 4 may not be separate devices but a single device. That is, the analyzer 1 may have the functions of the prediction device 4.

[0139] Prediction device 4 is a computer device that predicts drug inventory status, the timing of the next drug production, the timing of drug production orders, or drug demand based on pharmaceutical information regarding manufactured drugs and medication information regarding patients' drug use. Details of prediction device 4 will be described later.

[0140] The pharmaceutical device 5 is a computer device managed by the pharmaceutical manufacturer and distributor. The pharmaceutical device 5 is a manufacturing execution system, commonly known as an MES (Manufacturing Execution System), and is a computer system that manages the pharmaceutical manufacturing process. The pharmaceutical device 5 works in conjunction with an ERP (Enterprise Resource Planning) system and other systems to centrally manage manufacturing information. The pharmaceutical device 5 can generate information related to pharmaceuticals, such as the type and quantity of manufactured drugs, the date and time of manufacture, and the manufacturing lot number, and transmit it to the prediction device 4. The information obtainable from the pharmaceutical device 5 includes, but is not limited to, the type and quantity of manufactured drugs, the amount of raw materials used and inventory status, the time required at each stage of the manufacturing process, the operating status and maintenance information of the manufacturing equipment, and quality control data. The pharmaceutical device 5 is not essential for the prediction system 6. For example, the latest pharmaceutical information managed by the pharmaceutical device 5 may be pre-stored in at least one of the storage unit 10 of the analyzer 1 or the storage unit 40 of the prediction device 4, and instead of obtaining pharmaceutical information from the pharmaceutical device 5, the system may obtain and use that pre-stored pharmaceutical information.

[0141] Figure 35 shows an example of the functional configuration of the prediction device 4 (prediction device) according to the embodiment. As shown in Figure 35, the prediction device 4 is composed of a storage unit 40, an acquisition unit 41, a registration unit 42, and a prediction unit 43. Details of each functional block will be described later.

[0142] Each functional block of the prediction device 4 is intended to function within the prediction device 4, but is not limited to this. For example, some of the functional blocks of the prediction device 4 may function within a computer device separate from the prediction device 4, connected to the prediction device 4 via a network, while appropriately sending and receiving information with the prediction device 4. Furthermore, some functional blocks of the prediction device 4 may be omitted, multiple functional blocks may be integrated into a single functional block, or a single functional block may be decomposed into multiple functional blocks.

[0143] Figure 36 shows an example of the hardware configuration of the computer used in the prediction device 4. Physically, the prediction device 4 is configured as a computer system including a central processing unit (at least one) CPU 400, main memory modules RAM 401 and ROM 402, input / output devices 403 such as a keyboard, microphone, and display, a data transmission and reception device communication module 404, and auxiliary storage devices 405 such as a hard disk and SSD, as shown in Figure 36. The CPU 400, RAM 401 and ROM 402, input / output devices 403, communication module 404, and auxiliary storage devices 405 may each be configured in multiple units. The functions of each functional block shown in Figure 35 are realized by loading predetermined computer software onto the hardware such as the CPU 400 and RAM 401 shown in Figure 36, thereby operating the input / output devices 403 and communication module 404 under the control of the CPU 400, and reading and writing data to the RAM 401 and auxiliary storage devices 405.

[0144] Next, we will describe the prediction program P4 that causes the computer to execute a series of processes performed by the prediction device 4. As shown in Figure 37, the prediction program P4 is inserted into the computer and accessed, or stored in a program storage area formed in the auxiliary storage device 405 provided by the computer. More specifically, the prediction program P4 is stored in a program storage area formed in the auxiliary storage device 405 provided by the prediction device 4.

[0145] The prediction program P4 comprises a storage module P40, an acquisition module P41, a registration module P42, and a prediction module P43. The functions realized by executing the storage module P40, acquisition module P41, registration module P42, and prediction module P43 are the same as the functions of the storage unit 40, acquisition unit 41, registration unit 42, and prediction unit 43 of the prediction device 4 described above.

[0146] The prediction program P4 is a program that causes the prediction device 4 (one or more CPUs), which is a computer, to function as a storage unit 40, an acquisition unit 41, a registration unit 42, and a prediction unit 43.

[0147] Furthermore, the prediction program P4 may be configured such that part or all of it is transmitted via a transmission medium such as a communication line, received by other devices, and stored (including installed). Also, each module of the prediction program P4 may be installed on any of several computers, not just one. In that case, the series of processes of the prediction program P4 described above are performed by a computer system consisting of these multiple computers.

[0148] The following describes the functions of the prediction device 4 shown in Figure 35.

[0149] The storage unit 40 stores any information used or output by the processing of the prediction device 4 in a database. The database may be provided on the prediction device 4 or on another device via a network. The storage unit 40 may also store information calculated by each functional block of the prediction device 4. The information stored by the storage unit 40 may be referenced as appropriate by each functional block of the prediction device 4.

[0150] The acquisition unit 41 acquires arbitrary information. The acquisition unit 41 may acquire information from other systems or devices such as the analyzer 1 and the pharmaceutical device 5 via a network, or it may acquire information via the input / output device 403.

[0151] The acquisition unit 41 acquires information on drug use by a user from multiple user terminals 2 via the network. The acquisition unit 41 also acquires information on pharmaceuticals from the pharmaceutical device 5 via the network. The information on pharmaceuticals may be any information related to pharmaceuticals. Examples of information on pharmaceuticals include lot information related to pharmaceuticals, lot information related to APIs (Active Pharmaceutical Ingredients), manufacturing process control methods, and material supply control information. Examples of lot information related to pharmaceuticals include manufacturing number (lot number, batch number), manufacturing quantity per lot, manufacturing date, expiration date, manufacturing line or manufacturing facility, raw material receiving lot number, details of the manufacturing process (temperature, pressure, time, etc.), quality inspection results, manufacturing worker identification information, packaging work details, shipping destination and shipping quantity. Furthermore, lot information related to the API may include, for example, the name and specifications of the raw material, the name of the raw material manufacturer, the raw material manufacturing number (lot number, batch number), the date of manufacture of the raw material, the expiration date of the raw material, the date the raw material was received, the quantity of the raw material, the storage conditions of the raw material (temperature, humidity, etc.), the test results of the raw material, the raw material supplier, the source of shipment of the raw material, the method and conditions of transportation of the raw material, and whether or not the raw material is out of specification and the details thereof.

[0152] The acquisition unit 41 may store the acquired information in the storage unit 40, or it may output it to another functional block.

[0153] The registration unit 42 causes the storage unit 40 to store (register) the information. More specifically, the registration unit 42 generates information and registers the generated information. For example, the registration unit 42 may generate pharmaceutical information, as described below, based on information about pharmaceuticals, and register the generated pharmaceutical information.

[0154] For example, the registration unit 42 may generate medication information based on the user's drug use information acquired by the acquisition unit 41, and register the generated medication information.

[0155] The registration unit 42 stores (updates) information by updating it using the storage unit 40. More specifically, the registration unit 42 updates (the information previously stored by the storage unit 40) based on the update information. For example, the registration unit 42 may update the drug depletion count based on the update information.

[0156] The prediction unit 43 predicts the inventory status of a drug, the timing of the next drug production, the timing of ordering the drug production, or the demand for the drug, based on pharmaceutical information regarding the manufactured drug and medication information regarding the patient's use of the drug. The prediction unit 43 may also make predictions based on at least one of the following included in the pharmaceutical information: identification information of the manufactured drug, information regarding the timing of the drug production, information regarding the quantity of the drug, and information regarding the expiration date of the drug, and at least one of the following included in the medication information: identification information of the drug used by the patient, and information regarding the timing of the drug use.

[0157] The prediction unit 43 may further perform predictions using drug shipment data from medical device wholesalers to medical institutions (prescription data categorized by HP / GP, therapeutic effect, company, product, and dosage form).

[0158] The prediction unit 43 outputs the prediction result. More specifically, the prediction unit 43 may output (display) the prediction result via the input / output device 403, output (transmit) it to another device via a network, store it in the storage unit 40, or output it to another functional block.

[0159] In the following sections, we will explain the details of the processing (prediction method) by the prediction system 6, including the details of the predictions made by the prediction unit 43, with reference to Figures 38 to 47.

[0160] Figure 38 is a sequence diagram showing an example of a process performed by the prediction system 6. The process shown in Figure 38 represents the registration of new pharmaceutical information. The process shown in Figure 38 may also be called the pharmaceutical information registration process. The process shown in Figure 38 is assumed to be performed when the manufacturing of the drug is completed, but is not limited to this.

[0161] First, the pharmaceutical manufacturer / distributor requests new registration of pharmaceutical information by inputting information about the pharmaceutical on the pharmaceutical device 5 and pressing the registration button (step S70). Pharmaceutical information includes, but is not limited to, the lot number of the manufactured drug, the date and time of manufacture, the quantity of the drug, and the expiration date of the drug. Next, the pharmaceutical device 5 transmits the pharmaceutical information entered in step S70 to the prediction device 4 in order to register the new pharmaceutical (step S71). Next, the prediction device 4 receives (acquires) the pharmaceutical information transmitted in step S71 (acquisition unit 41), generates pharmaceutical information (registration unit 42) based on the received pharmaceutical information, and registers the generated pharmaceutical information (registration unit 42) in the database (step S72).

[0162] The prediction device 4 may manage the lot numbers included in the pharmaceutical information received in step S72 across all pharmaceutical information. Figure 39 shows an example of a table of all pharmaceutical information. In the example table of all pharmaceutical information shown in Figure 39, the data item "Lot Number (multiple possible)" includes the lot numbers received so far (i.e., the lot number of each drug at the present time).

[0163] Pharmaceutical information is information that includes any information related to pharmaceuticals, and may also include other information. Figure 40 is a diagram showing an example of a pharmaceutical information table. In the example pharmaceutical information table shown in Figure 40, the data item "Lot Number" which indicates the lot number of the manufactured drug is "21AA520Z", the data item "Manufacturing Date and Time" which indicates the manufacturing date and time the drug was manufactured is "2024 / 01 / 18 10:25", the data item "Quantity" which indicates the quantity of the manufactured drug is "30", and the data item "Expiration Date" which indicates the expiration date of the manufactured drug is "2028 / 01 / 18".

[0164] Figure 41 is a sequence diagram showing an example of a prediction process performed by the prediction system 6. The prediction process shown in Figure 41 illustrates a scenario in which predictions are made to avoid excess inventory and stockouts. The prediction process shown in Figure 41 is assumed to be performed (in the prediction device 4) at the time when the usage date and time of drug information is added (i.e., at the time when the user uses the drug), but is not limited to this.

[0165] First, the prediction device 4 acquires the lot number and usage date of the drug information to which the usage date and time have been added (step S80). Next, the prediction device 4 transmits the lot number and usage date and time acquired in step S80 to the prediction device 4 (step S81). Next, the prediction device 4 receives (acquires) the lot number and usage date and time transmitted in step S81 (acquisition unit 41), and based on the received lot number and usage date and time, the registration unit 42 updates the pharmaceutical information (registered in the database) which includes information on exhausted drugs (step S82). Information on exhausted drugs refers to information on exhaustion for each lot number of drugs, such as the number of drugs exhausted per lot or the drug exhaustion rate.

[0166] Figure 42 shows an example of a pharmaceutical information table (part 1) updated (in step S82). More specifically, the example pharmaceutical information table shown in Figure 42 is the same as the example pharmaceutical information table shown in Figure 40, but with the data item "Quantity" updated from "30" to "28" (by the registration unit 12), and "2024 / 07 / 08 8:01, 2024 / 07 / 10 10:34" (drug usage information) added to the data item "Date and Time of Use (multiple allowed)". These updates indicate, for example, that the user used the drug on July 8th and again on July 10th, i.e., used the drug twice. As described above, drug usage information may include drug usage information. Alternatively, drug usage information may include the data items "Lot Number" and "Date and Time of Use (multiple allowed)" and be managed independently of pharmaceutical information (in which case, the pharmaceutical information and drug usage information are linked by "Lot Number").

[0167] Figure 43 shows an example table of updated pharmaceutical information (part 2). The example table shown in Figure 43 pertains to drug A and includes multiple pieces of pharmaceutical information as well as the estimated exhaustion rate. Figure 44 shows an example table of updated pharmaceutical information (part 3). The example table shown in Figure 44 pertains to drug B and, similar to the example table shown in Figure 43, includes multiple pieces of pharmaceutical information as well as the estimated exhaustion rate.

[0168] The forecasting unit 43 may generate and output the forecast results as inventory forecast information when it forecasts the inventory status of a drug, the next manufacturing timing of a drug, the timing of ordering the manufacture of a drug, or the demand for a drug. Figure 45 shows an example table of inventory forecast information (part 1). The example table shown in Figure 45 includes the inventory forecast for drug A, the recommended manufacturing start date and recommended manufacturing quantity on the forecasted day. Specifically, it includes the inventory forecast date, which is the date on which the inventory was forecasted; the forecasted inventory quantity, which is the forecasted quantity of inventory; the forecasted exhaustion date, which is the forecasted exhaustion date; the recommended manufacturing start date, which is the recommended manufacturing start date; the manufacturing quantity, which is the quantity to be manufactured; and the required APIs. Figure 46 shows an example table of inventory forecast information (part 2). The example table shown in Figure 46 includes the inventory forecast for drug B, the recommended manufacturing start date and recommended manufacturing quantity on the forecasted day. Specifically, it includes the inventory forecast date, the forecasted inventory quantity, the forecast exhaustion date, the recommended manufacturing start date, and the manufacturing quantity.

[0169] Returning to Figure 41, following step S82, the prediction device 4 makes predictions about the drug based on the pharmaceutical information and the drug usage information (step S83, prediction step). The prediction unit 43 predicts the drug's inventory status, the next manufacturing timing of the drug, the timing of ordering the drug's manufacture, or the demand for the drug, based on the pharmaceutical information (including the drug usage information) stored by the storage unit 40. The prediction unit 43 may also make predictions based on at least one of the lot number, manufacturing date and time, quantity, and expiration date included in the pharmaceutical information, and at least one of the lot number and usage date and time included in the drug usage information.

[0170] The prediction device 4 uses the transmitted drug usage information and the pharmaceutical information obtained from the pharmaceutical device 5 to predict the market inventory of drugs. Specifically, the prediction device 4 performs the following processes: (a) Aggregates the amount of drug used (drug exhaustion) and the timing of drug use for each lot number from the drug usage information. (b) Obtains the production volume, production date, and shipment volume for each lot number from the pharmaceutical information. (c) For each lot number, calculates the drug exhaustion rate and estimates the current market inventory using the production volume, shipment volume, and drug usage amount.

[0171] Possible methods for estimating market inventory include the following: First, calculate the initial untracked inventory by subtracting the registered usage from the shipment volume. Then, calculate the ratio of registered users to the total number of patients and use this as a usage expansion factor. Multiply the registered usage by the expansion factor to calculate the estimated total usage. Subtract the estimated total usage from the shipment volume to calculate the estimated market inventory. Analyze seasonal and day-of-the-week variations in usage using time-series data to derive correction factors. Apply the correction factors to the estimated market inventory to calculate a more precise market inventory estimate. By adding these calculation processes, it becomes possible to estimate market inventory more accurately, taking into account the usage status of unregistered patients. Furthermore, by considering temporal variations, it becomes possible to grasp the inventory situation in a more realistic way.

[0172] The prediction device 4 may predict drug demand based on market inventory history. The prediction device 4 may perform more accurate drug demand predictions by combining market inventory history data and patient number information. In particular, for rare diseases, since the number of patients in Japan is publicly available, future drug demand may be predicted based on fluctuations in the number of patients, future patient number predictions, and market inventory and shipment history data.

[0173] The prediction device 4 may further include a suggestion generation unit (not shown) that suggests the next manufacturing timing for the drug and the timing for ordering raw materials based on the prediction results of the prediction unit 43.

[0174] As described above, the prediction unit 43 may predict the inventory status of a drug, the timing of the next drug production, the timing of ordering the drug production, or the demand for the drug based on pharmaceutical information regarding the manufactured drug and medication information regarding the patient's use of the drug. The prediction unit 43 may also make predictions based on at least one of the following included in the pharmaceutical information: identification information of the manufactured drug, information regarding the timing of the drug production, information regarding the quantity of the drug, and information regarding the expiration date of the drug, and at least one of the following included in the medication information: identification information of the drug administered to the patient, and information regarding the timing of the drug's use.

[0175] The forecasts made by the forecasting unit 43 allow for the optimization of the manufacturing schedule and the avoidance of excess inventory and stockouts. Furthermore, the inventory quantity of each lot circulating in the market can be statistically estimated. In addition, it enables the understanding of remaining inventory periods, the start date of the next production cycle, and the timing of raw material procurement, as well as more accurate demand forecasting when combined with market analysis.

[0176] Figure 47 is a sequence diagram showing an example of the prediction process (part 2) performed by the prediction system 6. First, the pharmaceutical device 5 sends a viewing instruction to the prediction device 4 (step S90). Next, the prediction device 4 sends information about the pharmaceutical product in response to the viewing instruction sent in step S90 (step S91). Next, the pharmaceutical device 5 displays the information about the pharmaceutical product sent in step S91 (step S92). For example, since the number of days from the start of manufacturing to formulation is fixed for API manufacturing, the pharmaceutical device 5 calculates the number of days including a buffer and automatically displays the order deadline. Based on the information displayed in step S92, the drug manufacturer / distributor issues an order instruction as appropriate (step S93).

[0177] The predictions made by the prediction unit 43 allow for optimization of the manufacturing schedule, for example. Here, we will explain the procurement of raw materials with long shelf lives. Not only the APIs for pharmaceuticals, but also the raw materials and intermediates of the APIs have expiration dates. As time passes, some raw materials and intermediates may decompose, and in some cases, the intermediates may need to be re-purified (this not only adds to the manufacturing cost but may also affect other manufacturing schedules). The predictions made by the prediction unit 43 have the effect of reducing labor costs. For example, the period and quantity of unnecessary inventory held in the factory will decrease, so management costs related to storage (utilities and rent for storage locations, etc.) and labor costs can be reduced. In addition, it becomes possible to reduce pharmaceutical waste. Pharmaceutical waste is estimated to be more than 100 billion yen per year (2018 data: National Cancer Center), and the predictions made by the prediction unit 43 can reduce the amount of waste by reducing excess inventory and improving adherence to medication.

[0178] Furthermore, the above prediction method may be used to implement a computing device for optimizing manufacturing and supply. The computing device includes one or more processors, and the processors include the steps of: receiving information (drug information) from reading barcodes of pharmaceuticals by patients for multiple patients and obtaining data on the patients' drug use (date and time of use (the date and time of use can be obtained from the date and time of patient information transmission or information on the date and time of use entered by the patient), user ID, drug information, and location information); obtaining data on the market inventory of pharmaceuticals from a data source including at least an inventory database; comparing and analyzing the data on the patients' drug use with the obtained data; and outputting information analyzing the market inventory as a result of the analysis. The inventory database may be a database that holds lot information related to pharmaceuticals and at least one API (Active Pharmaceutical Ingredient).

[0179] Furthermore, the method for implementing a computing device for optimizing the manufacturing and supply of pharmaceuticals includes: obtaining data on the lot-by-lot manufacturing quantity and inventory quantity of the above-mentioned pharmaceuticals from a pharmaceutical data source; obtaining data on the lot-by-lot usage quantity from user drug usage data; analyzing the obtained usage quantity, manufacturing quantity, and inventory quantity using a predefined set of rules to estimate the amount of unused pharmaceuticals; and outputting information regarding future manufacturing based on the estimation results.

[0180] In this process, estimating the amount of unused drug using a predefined set of rules includes: (1) calculating the quantity shipped from the quantity manufactured and the quantity in stock; (2) calculating the inventory of pharmaceutical wholesalers using the quantity shipped from pharmaceutical wholesalers to medical institutions in each area; and (3) estimating the amount of unused drug in medical institutions by subtracting the quantity used, obtained from user data, from the quantity shipped from pharmaceutical wholesalers to medical institutions in each area.

[0181] Furthermore, (4) it may also include estimating the amount of unused drugs in circulation by combining the inventory of pharmaceutical wholesalers and the amount of unused drugs in medical institutions.

[0182] Furthermore, outputting information regarding future manufacturing may include the following: (5) Predicting future usage based on past usage trends and patient numbers, and examining whether supply can keep up based on current inventory and manufacturing plans. (6) If a supply shortage is anticipated, proposing to increase production lines or bring forward the timing of raw material orders.

[0183] Next, we will explain the effects of the prediction device 4.

[0184] The prediction device 4 includes a prediction unit 43 that predicts the inventory status of a drug, the timing of the next drug production, the timing of ordering drug production, or the demand for a drug, based on pharmaceutical information regarding the manufactured drug and medication information regarding the use of the drug by patients. In this respect, it is possible to predict the inventory status of a drug, the timing of the next drug production, the timing of ordering drug production, or the demand for a drug.

[0185] The prediction unit 43 may make predictions based on at least one of the following included in the pharmaceutical information: identification information of the manufactured drug, information about the timing of the drug's manufacture, information about the quantity of the drug, and information about the drug's expiration date, and at least one of the following included in the medication information: identification information of the drug administered to the patient, and information about the timing of the drug's use. In this respect, predictions can be made more reliably and accurately.

[0186] According to the analysis system 3 and prediction system 6 described above, a medication information collection platform is provided, and by integrating it into a patient support app (app), it becomes possible to obtain highly reliable tracking data and achieve appropriate medication management in home treatment. This not only creates an environment in which patients can continue self-administering medication at home safely and securely, but also contributes to maximizing the value of pharmaceuticals by ensuring adherence to dosage and administration instructions.

[0187] 1...Analysis device, 2...User terminal, 3...Analysis system, 4...Prediction device, 5...Pharmaceutical device, 6...Prediction system, 10...Storage unit, 11...Acquisition unit, 12...Registration unit, 13...Analysis unit, 40...Storage unit, 41...Acquisition unit, 42...Registration unit, 43...Prediction unit, 100...CPU, 101...RAM, 102...ROM, 103...Input / output device, 104...Communication module, 105...Auxiliary storage device, 400...CPU, 401...RAM, 402...ROM, 403...Input / output device, 404...Communication module, 405...Auxiliary storage device, P1...Analysis program, P10...Storage module, P11...Acquisition module, P12...Registration module, P13...Analysis module, P4...Prediction program, P40...Storage module, P41...Acquisition module, P42...Registration module, P43...Prediction module.

Claims

An acquisition unit that acquires information from multiple user terminals via a network regarding the diseases each user is suffering from and the medications that the user is using for those diseases, Based on the drug usage information regarding diseases and drugs acquired by the acquisition unit, an analysis unit performs an analysis of drugs used for each disease. An information processing system equipped with the following features. 　 The analysis unit performs the analysis based on the drug-related information obtained from the drug-related information database, which is information related to pharmaceuticals. The information processing system according to claim 1. 　 The aforementioned drug usage information includes at least one of the following: disease name, drug usage status, drug manufacturer / distributor, and user's residential area. The aforementioned analysis relates to at least one of the following: prescribing trends by area, prescribing patterns by disease, adherence to medication use, and trends in co-occurring diseases. The information processing system according to claim 1 or 2. 　 The acquisition unit acquires information obtained by mechanically reading information written on the drug packaging, or information provided by equipment used when using the drug. An information processing system according to any one of claims 1 to 3. 　 The aforementioned drug usage information further includes information regarding the user's residential area. The aforementioned analysis unit performs analysis on drugs used for each disease and area. An information processing system according to any one of claims 1 to 4. 　 The aforementioned drug usage information further includes information about the manufacturer and distributor of the drug being used by the user. The aforementioned analysis unit performs an analysis on the proportion of manufacturers and distributors of drugs used for each disease. An information processing system according to any one of claims 1 to 5. 　 The aforementioned drug usage information further includes information regarding the user's residential area. The aforementioned analysis unit performs an analysis on the proportion of manufacturers and distributors of drugs used for each disease and area. The information processing system according to claim 6. 　 The aforementioned drug usage information further includes information about the manufacturer and distributor of the drug being used by the user. The aforementioned analysis unit performs analysis on drugs used for each disease and manufacturer / distributor. An information processing system according to any one of claims 1 to 7. 　 The aforementioned drug usage information further includes information regarding the timing of when the user used the drug, The aforementioned analysis unit performs an analysis regarding the timing of drug use for each disease. An information processing system according to any one of claims 1 to 8. 　 The aforementioned drug usage information further includes information about the manufacturer and distributor of the drug being used by the user. The aforementioned analysis unit performs analysis on the timing of drug use for each disease and manufacturer. The information processing system according to claim 9. 　 The aforementioned analysis concerns compliance with drug use, based on the timing of drug use by the user and the predetermined dosing interval for that drug. The information processing system according to claim 9 or 10. 　 The aforementioned analysis unit performs an analysis of medications used by users suffering from each disease for other co-occurring diseases. An information processing system according to any one of claims 1 to 11. 　 The aforementioned drug usage information further includes information about the manufacturer and distributor of the drug being used by the user. The aforementioned analysis unit performs analysis on drugs used for other diseases that are co-occurring with the disease in the user(s) suffering from that disease, for each disease and manufacturer / distributor. The information processing system according to claim 12. 　 A data acquisition step involves obtaining information from multiple user terminals via a network regarding the diseases each user is suffering from and the medications they are using for those diseases. Based on the drug usage information regarding diseases and drugs obtained in the acquisition step, an analysis step is performed to analyze the drugs used for each disease. A computer-based information processing method, including [a specific example]. A computer-based forecasting method, including a forecasting step, that predicts drug inventory status, the timing of the next drug production, the timing of ordering drug production, or drug demand, based on pharmaceutical information regarding manufactured drugs and medication information regarding patient use of drugs.

Images