Medication guidance support device, medication guidance support system, medication guidance support method, and program

Abstract

Medication guidance support will be provided by considering information such as the current prescription, the dispensing date of the current prescription, metadata characterizing the current prescription and at least one of the patient, past prescriptions, the dispensing dates of past prescriptions, and the patient's medication history. [Solution] The medication guidance support device includes a request data acquisition unit that acquires request data including the current prescription, the dispensing date of the current prescription, metadata characterizing at least one of the current prescription and the patient, past prescriptions, the dispensing date of past prescriptions, and the medication history of past prescriptions; and a medication guidance data output request unit that requests a medication guidance data output device, which outputs medication guidance data indicating medication guidance based on a trained model that has been trained to output output data corresponding to the input data, to output medication guidance data from the request data.

Description

Technical Field

[0001] The present disclosure relates to a medication guidance support device, a medication guidance support system, a medication guidance support method, and a program.

Background Art

[0002] The quality of medication guidance depends on the skills of individual pharmacists. Specifically, depending on the number of years of experience as a pharmacist and the characteristics of the pharmacy where they work (such as a general pharmacy or in front of a specialized hospital), there are pharmacists who can provide comprehensive medication guidance to a wide range of patients, and there are also pharmacists who can only provide appropriate medication guidance to patients with specific diseases. Also, for patients with chronic diseases who continue the same prescription over a long period, the medication guidance may be simplified.

[0003] Applications with functions for assisting medication guidance are being utilized. In such applications, by presenting options in advance from the perspective of medication guidance, it is ensured that there are no omissions in the essential content of the medication guidance, and the quality of the medication guidance content is standardized. Also, Patent Document 1 discloses a support device for assisting a pharmacist in providing medication guidance to patients (see Patent Document 1).

Prior Art Documents

Patent Documents

[0004]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0005] In the prior art as described above, there are cases where not all necessary information is necessarily considered in providing support for medication guidance, and there is room for improvement.

[0006] This disclosure is made in view of the above points, and provides a medication guidance support device, a medication guidance support system, a medication guidance support method, and a program that can support medication guidance by taking into account information such as the current prescription, the dispensing date of the current prescription, metadata characterizing the current prescription and at least one of the patient, past prescriptions, the dispensing date of past prescriptions, and the patient's medication history. [Means for solving the problem]

[0007] This disclosure is made to solve the above problems, and one aspect of this disclosure is a medication guidance support device comprising: a request data acquisition unit that acquires request data including the current prescription, the dispensing date of the current prescription, metadata characterizing at least one of the current prescription and the patient, past prescriptions, the dispensing date of the past prescriptions, and the medication history of the past prescriptions; and a medication guidance data output request unit that requests a medication guidance data output device, which outputs medication guidance data based on a trained model that has been trained to output output data corresponding to the input data, to output medication guidance data indicating medication guidance from the request data.

[0008] Furthermore, one aspect of this disclosure is a medication guidance support system comprising the above-mentioned medication guidance support device, a terminal device that presents the medication guidance data output by the medication guidance data output device to a user, and a database in which data used to acquire part or all of the requested data is stored.

[0009] Furthermore, one aspect of this disclosure is a medication guidance support method comprising: a request data acquisition step of acquiring request data including the current prescription, the dispensing date of the current prescription, metadata characterizing at least one of the current prescription and the patient, past prescriptions, the dispensing date of the past prescriptions, and the medication history of the past prescriptions; and a medication guidance data output request step of requesting a medication guidance data output device, which outputs medication guidance data indicating medication guidance based on a trained model trained to output output data corresponding to input data, to output the medication guidance data from the request data.

[0010] Furthermore, one aspect of this disclosure is a program for causing a computer to perform a request data acquisition step of acquiring request data including the current prescription, the dispensing date of the current prescription, metadata characterizing at least one of the current prescription and the patient, past prescriptions, the dispensing date of the past prescriptions, and the patient's medication history; and a medication guidance data output request step of requesting a medication guidance data output device, which outputs medication guidance data indicating medication guidance based on a trained model trained to output output data corresponding to input data, to output the medication guidance data from the request data. [Effects of the Invention]

[0011] According to the medication guidance support device, medication guidance support system, medication guidance support method, and program related to this disclosure, medication guidance support can be provided by taking into account information such as the current prescription, the dispensing date of the current prescription, metadata characterizing the current prescription and at least one of the patient, past prescriptions, the dispensing dates of past prescriptions, and the patient's medication history. [Brief explanation of the drawing]

[0012] [Figure 1] This figure shows an example of the configuration of the medication guidance support system 1 according to the embodiment of this disclosure. [Figure 2] This figure shows an example of the functional configuration of the medication guidance support system 1 according to the present disclosure. [Figure 3] This figure shows an example of the flow of medication guidance support processing according to the embodiment of this disclosure. [Figure 4] This figure shows an example of text data generated as request data C1 in the process of identifying guidance perspectives according to the embodiment of this disclosure. [Figure 5] This figure shows an example of text data generated as request data C1 in the process of identifying guidance perspectives according to the embodiment of this disclosure. [Figure 6] This figure shows an example of text data generated as request data C1 in the process of identifying guidance perspectives according to the embodiment of this disclosure. [Figure 7]It is a diagram showing an example of text data generated as medication guidance data D1 in the process of specifying guidance viewpoints according to an embodiment of the present disclosure. [Figure 8] It is a diagram showing an example of text data generated as request data C1 in the process of classifying guidance viewpoints according to an embodiment of the present disclosure. [Figure 9] It is a diagram showing an example of text data generated as request data C1 in the process of classifying guidance viewpoints according to an embodiment of the present disclosure. [Figure 10] It is a diagram showing an example of text data generated as request data C1 in the process of classifying guidance viewpoints according to an embodiment of the present disclosure. [Figure 11] It is a diagram showing an example of text data generated as medication guidance data D1 in the process of classifying guidance viewpoints according to an embodiment of the present disclosure. [Figure 12] It is a diagram showing an example of text data generated as medication guidance data D1 in the process of classifying guidance viewpoints according to an embodiment of the present disclosure. [Figure 13] It is a diagram showing an example of the functional configuration of a medication guidance support system 1a according to a modification of an embodiment of the present disclosure.

Mode for Carrying Out the Invention

[0013] (Embodiment) Hereinafter, embodiments of the present disclosure will be described in detail with reference to the drawings. FIG. 1 is a diagram showing an example of the configuration of a medication guidance support system 1 according to the present embodiment. The medication guidance support system 1 is a system that supports a pharmacist in providing medication guidance to a patient. In the following description, the medication guidance support system 1 includes a user terminal device 2, a medication guidance support device 3, and a database server 4. Also shown in FIG. 1 are a user U1 of the user terminal device 2 and a generation AI server 5. In the present embodiment, the user U1 is a pharmacist, but as another example, it may be a person who operates the user terminal device 2 on behalf of the pharmacist.

[0014] The user terminal device 2 is a terminal device used by the user U1. The user terminal device 2 is a computer device such as a personal computer, a tablet, or a smartphone. The user terminal device 2 includes a display unit 21 and an operation unit 22. The display unit 21 includes, for example, a liquid crystal display and displays various screens. In the following description, the display unit 21 displaying a screen is also referred to as presenting a screen to the user U1. The operation unit 22 includes, for example, a touch panel and detects operations of the user U1.

[0015] The user terminal device 2 includes an arithmetic unit 200 and a storage unit 250. The arithmetic unit 200 includes, for example, a Central Processing Unit (CPU), operates based on programs and data stored in the storage unit 250, and provides various functions. The storage unit 250 is composed of, for example, one or both of a hard disk drive and a semiconductor memory (flash memory), a RAM (Random Access Memory), a ROM (Read Only Memory), etc., and stores various information such as programs and data read by the arithmetic unit 200. Note that the storage unit 250 may be realized by a storage device such as a cloud server outside the user terminal device 2. The storage device may be, for example, a virtual storage device.

[0016] The medication guidance support device 3, the database server 4, and the generation AI server 5 are each, as an example, cloud servers. Note that the medication guidance support device 3, the database server 4, and the generation AI server 5 may each be realized as one computer or as a virtual server.

[0017] The medication guidance support device 3 includes an arithmetic unit 300 and a storage unit 350. The arithmetic unit 300, for example, includes a CPU and operates based on programs and data stored in the storage unit 350, providing various functions. The storage unit 350 is composed of, for example, one or both of a hard disk drive and semiconductor memory (flash memory), RAM, ROM, etc., and stores various types of information, such as programs and data read by the arithmetic unit 300. The storage unit 350 may also be implemented by a storage device such as a cloud server located outside the medication guidance support device 3. This storage device may be, for example, a virtual storage device.

[0018] The user terminal device 2, the medication guidance support device 3, the database server 4, and the generation AI server 5 can communicate with each other via a network. This network may include, for example, the internet, a WAN (Wide Area Network), a LAN (Local Area Network), a public network, provider equipment, a dedicated line, or a wireless base station.

[0019] User U1 operates the control unit 22 of the user terminal device 2 to send presentation request A1 to the medication guidance support device 3. Presentation request A1 is information requesting that medication guidance be presented. Medication guidance includes the perspective of medication guidance and the content of medication guidance.

[0020] When the medication guidance support device 3 receives a presentation request A1 from the user terminal device 2, it sends request data C1 to the generation AI server 5. Request data C1 is information requesting the generation AI server 5 to generate and output medication guidance data D1, and is used as input for the generation AI server 5 to generate and output medication guidance data D1. Here, the medication guidance support device 3 obtains patient data B1 from the database server 4 and generates request data C1 based on the obtained patient data B1.

[0021] The medication guidance support device 3 acquires the medication guidance data D1 output by the generating AI server 5. The medication guidance data D1 is data that indicates medication guidance. In this example, the medication guidance data D1 is text data. The medication guidance support device 3 generates presented medication guidance data E1, which is data processed from the medication guidance data D1 into a format to be presented to the user terminal device 2. The medication guidance support device 3 transmits the presented medication guidance data E1 to the user terminal device 2. The user terminal device 2 receives the medication guidance data E1 and displays the medication guidance data E1 on the display unit 21.

[0022] Figure 2 shows an example of the functional configuration of the medication guidance support system 1 according to this embodiment. The user terminal device 2 comprises a presentation request unit 201 and a presentation unit 202. Each of these functional units is realized, for example, by the CPU in the arithmetic unit 200 loading a program read from the ROM in the storage unit 250 into the RAM in the storage unit 250, and then executing processing according to that program. The presentation request unit 201 transmits presentation request A1 to the medication guidance support device 3. The display unit 202 displays the medication guidance data E1.

[0023] The medication guidance support device 3 comprises a presentation request reception unit 30, a request data acquisition unit 31, a guidance perspective determination unit 32, a medication guidance data output request unit 33, a medication guidance data acquisition unit 34, a medication guidance data output unit 35, and a patient data management unit 36. Each of these functional units is implemented, for example, by the CPU loading a program read from ROM into RAM and executing processing according to that program. These functional units may be distributed across multiple servers. In other words, the medication guidance support device 3 may be configured across multiple devices.

[0024] The information request receiving unit 30 receives information request A1.

[0025] The request data acquisition unit 31 acquires request data C1. Request data C1 includes the current prescription, the dispensing date of the current prescription, metadata characterizing at least one of the current prescription and the patient, past prescriptions, the dispensing date of past prescriptions, and the patient's medication history. In this embodiment, request data C1 further includes at least one of the following: guidance perspectives corresponding to the metadata, the calculation points for the current prescription, the calculation points for past prescriptions, classification information, seasonal information, patient summary information from a pharmaceutical management perspective, and the cover information of the medication history. Past prescriptions may be a part of multiple past prescriptions or all of multiple past prescriptions. Preferably, past prescriptions are all of multiple past prescriptions.

[0026] Metadata indicates characteristics such as new patient, new prescription, and Do prescription. If the metadata indicates a new patient, the corresponding guidance perspective is specific to new patients. If the metadata indicates a new prescription, the corresponding guidance perspective is specific to new prescriptions. If the metadata indicates a Do prescription, the corresponding guidance perspective is specific to cases where the same prescription continues. A Do prescription is a prescription in which there is no change in the prescription content between the previous and current prescriptions for the same patient.

[0027] Classification information indicates predetermined categories based on the perspective of medication guidance. For example, classification information indicates seven categories: confirmation of laboratory values, confirmation and guidance on the presence or absence of side effects, confirmation and guidance on difficulties related to taking medication, confirmation and guidance on lifestyle habits, points to be aware of considering seasonality, confirmation of medication record books, and guidance on improving and maintaining medication adherence. If medication guidance data D1 does not fall into any of these seven categories, it will be classified into the "other" category.

[0028] The perspectives and content of medication guidance included in the medication guidance data D1 generated by the generation AI server 5 may be difficult for user U1 to understand as they are, regarding which perspective of medication guidance is being used. Therefore, in this embodiment, by indicating which perspective of medication guidance the generated medication guidance data D1 is based on using a predetermined category, it is possible to make it easier for user U1 to understand the perspective of medication guidance.

[0029] The categories indicated by the classification information described above are merely examples and are not limited to them. The classification information may include fewer than seven categories or eight or more categories. If the classification information indicates fewer than seven categories, some of the seven categories described above may be combined into one category. If the classification information indicates eight or more categories, the seven categories described above may be further subdivided into categories.

[0030] In one example of this embodiment, the request data acquisition unit 31 acquires patient data B1 stored in the database server 4 as request data C1. Patient data B1 includes the current prescription, the dispensing date of the current prescription, metadata characterizing at least one of the current prescription and the patient, past prescriptions, the dispensing date of past prescriptions, the medication history of past prescriptions, guidance perspectives corresponding to the metadata, the calculation points for the current prescription, the calculation points for past prescriptions, classification information indicating predetermined categories based on the perspective of medication guidance, seasonal information, patient summary information from a pharmaceutical management perspective, and cover sheet information of the medication history.

[0031] Here, the patient data B1 and the request data C1 stored in the database server 4 do not necessarily have to match; for example, it is sufficient if the patient data B1 contains information that identifies the request data C1. In this case, the request data acquisition unit 31 acquires the request data C1 by generating the request data C1 based on the patient data B1 stored in the database server 4.

[0032] The instructional perspective determination unit 32 determines the instructional perspective from the metadata. In another example of this embodiment, the request data acquisition unit 31 acquires request data C1 by generating request data C1 based on patient data B1 stored in the database server 4 and the instruction perspective determination unit 32. In this case, for example, the request data acquisition unit 31 may generate request data C1 that includes information based on patient data B1 stored in the database server 4 and the instruction perspective determination unit 32.

[0033] The medication guidance data output request unit 33 requests the generating AI server 5 to output medication guidance data D1 from the request data C1.

[0034] The medication guidance data acquisition unit 34 acquires the medication guidance data D1 output by the generating AI server 5.

[0035] The medication guidance data output unit 35 outputs medication guidance data D1, or data generated based on medication guidance data D1. In one example of this embodiment, the medication guidance data output unit 35 converts the medication guidance data D1 into presented medication guidance data E1 and outputs it to the user terminal device 2.

[0036] The patient data management unit 36 ​​manages patient data B1. For example, the patient data management unit 36 ​​adds new patient data B1 to the database server 4. The patient data management unit 36 ​​also updates patient data B1 stored in the database server 4.

[0037] The database server 4 stores patient data B1. In other words, the database server 4 stores data used to retrieve some or all of the requested data C1. The patient data B1 stored in the database server 4 is added to or updated sequentially by the patient data management unit 36.

[0038] The patient data management unit 36 ​​may be provided as a separate server for managing patient data, distinct from the medication guidance support device 3. In that case, the patient data management unit 36 ​​may be omitted from the configuration of the medication guidance support device 3.

[0039] The generation AI server 5 outputs medication guidance data D1 from the request data C1, based on a generation AI (Artificial Intelligence) that has been trained to output medication guidance data D1 indicating medication guidance when request data C1 is input. The generation AI is a text generation AI based on a large language model (LLM), such as a transformer including GPT (Generative Pretrained Transformer). In addition, various generally available generation AI services may be used as the generation AI server 5.

[0040] Note that the request data C1 used during training is different from the request data C1 used during inference processing (i.e., the process in which the generating AI server 5 outputs the medication guidance data D1 for the current prescription).

[0041] Furthermore, in the training of the generative AI, supervised learning is performed using, for example, a vast amount of text from the internet as training data. Reinforcement learning may also be combined with supervised learning in the training of the generative AI. The vast amount of text used in training the generative AI includes text about prescriptions, dispensing dates, medication history, and medication guidance. The generative AI is an example of a trained model that has been trained to output output data according to the input data. The generative AI server 5 is an example of a medication guidance data output device.

[0042] Next, we will explain the medication guidance support process, which is a process that supports medication guidance by the medication guidance support system 1. Figure 3 shows an example of the flow of medication guidance support processing according to this embodiment.

[0043] Step S10: The presentation request receiving unit 30 receives presentation request A1 from the user terminal device 2. Here, user U1 operates the operation unit 22 of the user terminal device 2 to transmit presentation request A1 to the medication guidance support device 3. The operation by the operation unit 22 is a predetermined operation (such as tapping or clicking) performed on a button that instructs the presentation of medication guidance displayed on the display unit 21. Presentation request A1 includes information requesting the presentation of medication guidance, as well as information identifying the patient to whom medication guidance will be provided (patient identification information).

[0044] Step S20: The request data acquisition unit 31 acquires the request data C1. Here, the request data acquisition unit 31 acquires patient data B1 from the database server 4. The request data acquisition unit 31 acquires the request data C1 by generating the request data C1 from the acquired patient data B1. Here, the request data acquisition unit 31 acquires request data C1 relating to a patient identified by the patient identification information included in the presented request A1. In this case, the request data acquisition unit 31 only needs to acquire, for example, at least patient data B1 relating to the patient from the database server 4.

[0045] In one example of this embodiment, the request data acquisition unit 31 generates text data as request data C1. This text data is a prompt for giving instructions (or commands) to the text generation AI.

[0046] Step S30: The instruction perspective determination unit 32 determines the instruction perspective from the metadata. The instruction perspective determination unit 32 determines the instruction perspective that should be emphasized in medication guidance for the current prescription from the metadata included in the patient data B1 acquired by the request data acquisition unit 31. For example, the instruction perspective determination unit 32 determines the instruction perspective from the metadata based on a table in which metadata and instruction perspectives are associated. As another example, the instruction perspective determination unit 32 may determine the instruction perspective from the metadata based on a trained model that has been trained to output an instruction perspective when metadata is input.

[0047] The request data acquisition unit 31 acquires request data C1 which includes the instructional perspective determined by the instructional perspective determination unit 32. Here, the request data acquisition unit 31 includes the instructional perspective determined by the instructional perspective determination unit 32 in the text data generated as request data C1.

[0048] Furthermore, the key points to be emphasized in the medication guidance for this prescription may be specified by user U1. In that case, user U1 inputs the guidance points from the operation unit 22 of the user terminal device 2. The guidance points may be entered as text or selected from a list of options. If user U1 specifies the key points to emphasize in the medication guidance for the current prescription, the guidance point determination unit 32 may be omitted from the configuration of the medication guidance support device 3. In this case, the key points to emphasize in the medication guidance for the current prescription, as specified by user U1, will be used instead of the determination result from the guidance point determination unit 32. Furthermore, the guidance points to be emphasized in the medication guidance for this prescription may be a combination of guidance points specified by user U1 and guidance points determined by the guidance point determination unit 32.

[0049] In this embodiment, the process of inputting request data C1 into a generation AI and having the generation AI generate medication guidance data D1 (referred to as the medication guidance data generation process) is performed in two stages, as an example. The two stages consist of a process for identifying guidance perspectives and a process for classifying guidance perspectives. The reason for dividing the process into two stages is that the accuracy of the output text tends to be higher when the text is divided into two parts and input sequentially into the generation AI, rather than inputting a long text all at once.

[0050] The data that the medication guidance support device 3 sends to the generation AI server 5 the first time out of the request data C1 is referred to as the first request data C1A. The data that the medication guidance support device 3 sends to the generation AI server 5 the second time out of the request data C1 is referred to as the second request data C2A. The first response data is obtained from the generation AI server 5 when the medication guidance support device 3 outputs the first request data C1A to the generation AI server 5 the first time out of the request data C1A. The second response data is obtained from the generation AI server 5 when the medication guidance support device 3 outputs the second request data C2A to the generation AI server 5 the second time out of the request data C1A. In this example, the second response data corresponds to the medication guidance data D1.

[0051] Figures 4, 5, and 6 show examples of text data generated as the first request data C1A in the process of identifying instructional perspectives. Note that the input texts P1, P2, and P3 shown in Figures 4 through 6, respectively, are presented in multiple diagrams but are actually a single, unified text data.

[0052] Input text P1 contains instructions, context, and constraints for carrying out the instructions. The text "You are a pharmacist at a dispensing pharmacy." is an example of context. The text "Below are the prescriptions and medication history for the past three prescriptions, including this one." and the text "Please identify the content of medication guidance, the content to confirm with the patient, and any advice to give regarding this prescription." are examples of instructions.

[0053] The text, "However, please limit the total number of items you identify to seven or fewer," is an example of a constraint. This constraint indicates that the number of instructional perspectives is limited to a predetermined number.

[0054] The texts, "When identifying what needs to be addressed, please prioritize the content that has not been addressed in the past and should be addressed now," and "When identifying what needs to be addressed, the following points should be considered to determine appropriate guidance: • This patient has been on the same prescription for a long time, so it is difficult to decide what to advise them on. • This patient has been receiving treatment for a total of more than 5 years, so long-term treatment is required. • It is currently summer and very hot, so that should also be taken into consideration," indicate the guidance perspectives determined from the meta-information by the guidance perspective determination unit 32.

[0055] Input text P2 includes the current dispensing date, current prescription, previous dispensing date, previous prescription, and previous medication history. Input text P3 includes the dispensing date two prescriptions ago, the prescription two prescriptions ago, and the patient's medical history two prescriptions ago.

[0056] Step S40: The medication guidance data output request unit 33 requests the generating AI server 5 to output medication guidance data D1 from the request data C1. Here, the medication guidance data output request unit 33 sends the request data C1 generated by the request data acquisition unit 31 to the generating AI server 5. The generation AI server 5 generates medication guidance data D1 from the request data C1 based on the generation AI.

[0057] Figure 7 shows an example of text data generated as medication guidance data D1 in the process of identifying guidance perspectives. Output text P4 contains seven guidance perspectives. In accordance with the restriction condition specified in input text P1 to limit the number of guidance perspectives to a predetermined number, the number of guidance perspectives in output text P4 is limited to that predetermined number (7).

[0058] Figures 8, 9, and 10 show examples of text data generated as the second request data C2A in the process of classifying instructional perspectives. Input texts P5, P6, and P7 shown in Figures 8 to 10 are text data input to the generating AI in the process of classifying instructional perspectives. Although input texts P5, P6, and P7 shown in Figures 8 to 10 are shown in separate diagrams, they are a single, combined text data.

[0059] The input text P5 contains instructions, context, and constraints for performing the instructions. The text "You are a pharmacist at a dispensing pharmacy," and the text "The following are your thoughts on medication guidance and points to confirm with patients," are examples of context. The text "Could you convert this to JSON format based on the following example for system processing?" is an example of an instruction. Therefore, the input text P5 contains text instructing the system to convert the output text to a predetermined format (for example, JSON format).

[0060] Text: "Please note that the JSON category property should be one of the following seven types." • Checking test results • Checking for and providing guidance on the presence or absence of side effects. • Confirmation and guidance regarding any problems related to taking the medication. • Confirmation and guidance regarding lifestyle habits Points to be aware of, taking seasonality into consideration. • Confirmation regarding your medication record book • Guidance on improving and maintaining medication adherence • Others are examples of constraints. These constraints instruct the identified instructional perspectives to be classified into pre-specified categories. These constraints prevent the identified instructional perspectives from becoming haphazardly broad and ensure ease of processing in subsequent applications.

[0061] Input text P6 is the example text described above. Input text P6 is an example of a constraint. Input text P6 is used for the generating AI to mimic when generating the output text. Input text P7 contains text data output during the process of identifying guidance perspectives. In input text P7, the text "#Medication guidance, and points to confirm with the patient" indicates that the text following this text is the text that will be processed in the process of classifying guidance perspectives.

[0062] Figures 11 and 12 show examples of text data generated as medication guidance data D1 in the process of classifying guidance perspectives. Output texts P8 and P9 shown in Figures 11 and 12 contain the category to which the guidance perspectives are classified, the title of the guidance perspective, and the content of the guidance perspectives for each guidance perspective, up to a predetermined number (7). Furthermore, in output texts P8 and P9, these categories, titles, and content are included in a predetermined format (for example, JSON format). This corresponds to the fact that input text P7 included text instructing the conversion of the output text to a predetermined format. Note that output texts P8 and P9 shown in Figures 11 and 12, respectively, are shown in multiple figures, but they are a single, combined text data.

[0063] As described above, medication guidance data D1 includes the results of classifying the perspectives of medication guidance shown in medication guidance data D1 into predetermined categories. These categories are indicated by the classification information described above. However, medication guidance data D1 does not necessarily have to include the results of classifying the perspectives of medication guidance into predetermined categories. In that case, the classification information may be omitted from the requested data C1.

[0064] Step S50: The medication guidance data acquisition unit 34 acquires the medication guidance data D1 output by the generating AI server 5.

[0065] Step S60: The medication guidance data output unit 35 converts the medication guidance data D1 into presented medication guidance data E1. The presented medication guidance data E1 is data in a format suitable for display on the display unit 21 of the user terminal device 2. The process of converting the medication guidance data D1 into presented medication guidance data E1 includes processing, editing, or formatting.

[0066] Step S70: The medication guidance data output unit 35 outputs the presented medication guidance data E1 to the user terminal device 2.

[0067] Step S80: The presentation unit 202 presents the medication guidance data E1. The presentation unit 202 presents the medication guidance data E1 by displaying it on the display unit 21. User U1, for example, before giving medication guidance, refers to the medication guidance data E1 displayed on the display unit 21 as a reference for giving medication guidance. With this, the medication guidance support system 1 terminates the medication guidance support process.

[0068] In this embodiment, an example of a case where the medication guidance data generation process is performed in two stages has been described, but it is not limited to this. The medication guidance data generation process may be performed in one stage without being divided into two stages. When the medication guidance data generation process is performed in one stage, the above-mentioned input texts P1, P2, P3, P5, and P6 are used as input texts. In this case, the text "The following are your thoughts on medication guidance and points to confirm with the patient. Could you convert this into JSON format based on the following example for system processing?" in input text P6 is changed to text such as "Could you convert the identified points to JSON format based on the following example for system processing?". Furthermore, the medication guidance data generation process may be divided into three or more stages. Whether the medication guidance data generation process is performed in one step or in several stages should be appropriately selected depending on the required accuracy of the medication guidance data and the processing time.

[0069] In this embodiment, an example has been described in which medication guidance data D1 is converted into presented medication guidance data E1 by the medication guidance support device 3 and presented to the user terminal device 2, but this is not the only example. Medication guidance data D1 may be transmitted from the medication guidance support device 3 to the user terminal device 2, and the medication guidance data D1 may be converted into presented medication guidance data E1 by the user terminal device 2.

[0070] In this embodiment, an example of how the request data C1 is generated by the medication guidance support device 3 has been described, but it is not limited to this. The request data C1 may also be generated based on the operation of user U1. For example, user U1 operates the operation unit 22 of the user terminal device 2 to select which information from patient data B1 to include in the request data C1. Even when the request data C1 is generated based on the operation of user U1, the current prescription, the dispensing date of the current prescription, metadata characterizing at least one of the current prescription and the patient, past prescriptions, the dispensing date of past prescriptions, and the medication history of past prescriptions are included in the request data C1. Therefore, by the operation of user U1, at least one of the following can be selected to be included in the request data C1: guidance perspective corresponding to the metadata, calculation points for the current prescription, calculation points for past prescriptions, classification information, seasonality information, patient summary information from a pharmaceutical management perspective, and cover information of the medication history.

[0071] In this embodiment, an example has been described in which the medication guidance support device 3 receives a presentation request A1 from the user terminal device 2 and sends the request data C1 to the generation AI server 5, but it is not limited to this example. The medication guidance support device 3 may automatically send the request data C1 to the generation AI server 5 when the data indicating the current prescription is stored in the database server 4. In that case, the medication guidance support device 3 stores the medication guidance data D1 generated by the generation AI server 5 in the database server 4. When the medication guidance support device 3 receives a presentation request A1 from the user terminal device 2, it retrieves the previously stored medication guidance data D1 from the database server 4. The medication guidance support device 3 converts the retrieved medication guidance data D1 into presented medication guidance data E1 and presents it to the user terminal device 2. For example, when the medication guidance support device 3 reads a specific system file provided by the claims processing computer, the medication guidance support device 3 may automatically start the process of generating medication guidance data. This system file contains patient information and information about the current prescription (i.e., patient data B1).

[0072] In this embodiment, an example has been described in which the medication guidance data D1 generated by the generation AI server 5 is output to the medication guidance support device 3, but this is not the only example. The generation AI server 5 may also output the generated medication guidance data D1 directly to the user terminal device 2 without going through the medication guidance support device 3.

[0073] In this embodiment, an example has been described in which the trained model is a generative AI and the medication guidance data output device is the generative AI server 5, but it is not limited to this. The trained model may be a trained model based on a machine learning model other than a generative AI, as long as it is trained to output medication guidance data D1 indicating medication guidance when request data C1 is input.

[0074] In this embodiment, an example has been described in which the user terminal device 2 and the medication guidance support device 3 are provided as separate devices in the medication guidance support system 1, but the system is not limited to this. The user terminal device 2 and the medication guidance support device 3 may be a single integrated device. In other words, the functional units provided in the user terminal device 2 may also be provided in the medication guidance support device 3.

[0075] Figure 13 shows an example of the functional configuration of the medication guidance support system 1a according to a modified example of this embodiment. When the functional unit of the user terminal device 2 is provided in the medication guidance support device 3, the medication guidance support system 1 is referred to as medication guidance support system 1a. Medication guidance support system 1a comprises a medication guidance support device 3a and a database server 4.

[0076] The medication guidance support device 3a is, for example, a computer. The medication guidance support device 3a comprises a display unit and an operation unit. The display unit comprises, for example, a liquid crystal display and displays various screens. The operation unit comprises, for example, a mouse, keyboard, or touch panel and detects the operation of user U1.

[0077] The medication guidance support device 3a comprises a presentation request unit 201, a presentation unit 202, a presentation request reception unit 30, a request data acquisition unit 31, a guidance perspective determination unit 32, a medication guidance data output request unit 33, a medication guidance data acquisition unit 34, a medication guidance data output unit 35, and a patient data management unit 36.

[0078] The functions of the presentation request unit 201 and the presentation unit 202 are the same as those of the presentation request unit 201 and the presentation unit 202 provided in the user terminal device 2.

[0079] As described above, the medication guidance support device 3 according to this embodiment includes a request data acquisition unit 31 and a medication guidance data output request unit 33. The request data acquisition unit 31 acquires the request data C1. The request data C1 includes the current prescription, the dispensing date of the current prescription, metadata characterizing at least one of the current prescription and the patient, past prescriptions, the dispensing dates of past prescriptions, and the patient's medication history. The medication guidance data output request unit 33 requests the medication guidance data output device (in this embodiment, the generating AI server 5), which outputs medication guidance data D1 based on a trained model that has been trained to output output data corresponding to the input data, to output medication guidance data D1 indicating medication guidance from the request data C1.

[0080] With this configuration, the medication guidance support system 1 according to this embodiment can request the output of medication guidance data D1 from request data C1 which includes the current prescription, the dispensing date of the current prescription, metadata characterizing the current prescription and at least one of the patient, past prescriptions, the dispensing date of past prescriptions, and the patient's medication history. Therefore, it can provide support for medication guidance by considering information such as the current prescription, the dispensing date of the current prescription, metadata characterizing the current prescription and at least one of the patient, past prescriptions, the dispensing date of past prescriptions, and the patient's medication history.

[0081] In this context, for example, applications equipped with conventional medication guidance support functions sometimes presented options for guidance perspectives. However, the pharmacist themselves selected the guidance perspectives, and depending on the pharmacist's experience and skills, simply being presented with options may not allow them to identify important guidance perspectives. Furthermore, with conventional technology, guidance perspectives based on the ideal total dosage for prescribed drugs were always displayed, and because the guidance perspectives were diverse, it was difficult to select the appropriate guidance perspective for the current medication guidance session, taking into account the patient's past guidance history. For example, in the case of patients who were being prescribed drugs indiscriminately or who were continuously prescribed Do, there was a possibility that the pharmacist themselves might become complacent or overconfident and forget to provide appropriate guidance perspectives.

[0082] On the other hand, in the medication guidance support system 1 according to this embodiment, the medication guidance data output device can identify important guidance points for the current medication guidance from request data C1 which includes the current prescription, the dispensing date of the current prescription, metadata characterizing at least one of the current prescription and the patient, past prescriptions, the dispensing date of past prescriptions, and the medication history of past prescriptions. Before providing medication guidance, user U1 is helped to recall the specific content to be taught in this medication guidance session for the patient by referring to the presented medication guidance data E1 displayed on the display unit 21. This helps to prevent any omissions in important guidance points for that patient.

[0083] Furthermore, in the medication guidance support system 1 according to this embodiment, the guidance perspectives identified by the medication guidance data output device take into account the patient's medical history from past prescriptions. Therefore, even in cases where the pharmacist has little experience or where the patient has been previously handled by another pharmacist, medication guidance of a certain quality can be ensured.

[0084] For example, a computer program to implement the functions of each of the above-mentioned devices may be recorded on a computer-readable recording medium, and the program recorded on this recording medium may be loaded into a computer system and executed. The term "computer system" here may include hardware such as an operating system and peripheral devices. Furthermore, "computer-readable recording media" refers to writable non-volatile memory such as flexible disks, magneto-optical disks, ROMs, and flash memory, portable media such as DVDs (Digital Versatile Discs), and storage devices such as hard disks built into computer systems. Furthermore, "computer-readable recording media" also includes volatile memory (such as DRAM (Dynamic Random Access Memory)) within a computer system that acts as a server or client when a program is transmitted via a network such as the Internet or a communication line such as a telephone line, which retains the program for a certain period of time.

[0085] Furthermore, the above program may be transmitted from a computer system that stores the program in a memory device or the like to another computer system via a transmission medium or by transmission waves within the transmission medium. Here, the "transmission medium" for transmitting the program refers to a medium that has the function of transmitting information, such as a network (communication network) like the Internet or a communication line (communication line) like a telephone line. Furthermore, the above program may be intended to implement some of the functions described above. It may also be a so-called differential file (differential program) that can implement the aforementioned functions in combination with programs already recorded in the computer system.

[0086] While embodiments of this disclosure have been described in detail above with reference to the drawings, the specific configuration is not limited to these embodiments and may include design changes and the like that do not depart from the gist of this disclosure.

[0087] <Note> [Configuration Example 1] A medication guidance support device comprising: a request data acquisition unit that acquires request data including the current prescription, the dispensing date of the current prescription, metadata characterizing at least one of the current prescription and the patient, past prescriptions, the dispensing date of the past prescriptions, and the medication history of the past prescriptions; and a medication guidance data output request unit that requests a medication guidance data output device, which outputs medication guidance data indicating medication guidance based on a trained model trained to output output data corresponding to input data, to output the medication guidance data from the request data.

[0088] [Configuration Example 2] The medication guidance support device according to [Configuration Example 1] comprises a medication guidance data acquisition unit that acquires the medication guidance data output by the medication guidance data output device, and a medication guidance data output unit that outputs the medication guidance data.

[0089] [Configuration Example 3] The medication guidance support device described in [Configuration Example 1] or [Configuration Example 2] includes, for the above-mentioned request data, at least one of the following: guidance perspectives corresponding to the metadata, calculation points for the current prescription, calculation points for past prescriptions, classification information indicating a predetermined category based on the perspective of medication guidance, seasonal information, patient summary information from a pharmaceutical management perspective, and cover sheet information of the medication history.

[0090] [Configuration Example 4] The medication guidance data includes the results of classifying the perspectives of medication guidance indicated by the medication guidance data into predetermined categories, as described in any one of [Configuration Example 1] to [Configuration Example 3].

[0091] [Configuration Example 5] A medication guidance support device according to any one of [Configuration Example 1] to [Configuration Example 4], further comprising a guidance perspective determination unit that determines a guidance perspective from the metadata, wherein the request data acquisition unit acquires the request data including the guidance perspective determined by the guidance perspective determination unit.

[0092] [Configuration Example 6] A medication guidance support system comprising: a medication guidance support device described in any one of [Configuration Example 1] to [Configuration Example 5]; a terminal device that presents the medication guidance data output by the medication guidance data output device to user U1; and a database that stores data used to acquire part or all of the requested data.

[0093] [Configuration Example 7] A medication guidance support method comprising: a request data acquisition step of acquiring request data including the current prescription, the dispensing date of the current prescription, metadata characterizing at least one of the current prescription and the patient, past prescriptions, the dispensing date of the past prescriptions, and the medication history of the past prescriptions; and a medication guidance data output request step of requesting a medication guidance data output device, which outputs medication guidance data indicating medication guidance based on a trained model trained to output output data corresponding to input data, to output the medication guidance data from the request data.

[0094] [Configuration Example 8] A program for causing a computer to perform a request data acquisition step of acquiring request data including the current prescription, the dispensing date of the current prescription, metadata characterizing at least one of the current prescription and the patient, past prescriptions, the dispensing date of the past prescriptions, and the medication history of the past prescriptions; and a medication guidance data output request step of requesting a medication guidance data output device, which outputs medication guidance data indicating medication guidance based on a trained model that has been trained to output output data corresponding to the input data, to output the medication guidance data from the request data. [Explanation of symbols]

[0095] 1...Medication guidance support system, 2...User terminal device, 3...Medication guidance support device, 5...Generating AI server, 31...Request data acquisition unit, 33...Medication guidance data output request unit, C1...Request data, D1...Medication guidance data

Claims

1. A request data acquisition unit acquires request data including the current prescription, the dispensing date of the current prescription, metadata characterizing at least one of the current prescription and the patient, past prescriptions, the dispensing date of the past prescriptions, and the medication history of the past prescriptions. A medication guidance data output request unit requests a medication guidance data output device, which outputs medication guidance data indicating medication guidance based on a trained model trained to output output data corresponding to input data, to output the medication guidance data from the requested data. A medication guidance support device equipped with the following features.

2. A medication guidance data acquisition unit that acquires the medication guidance data output by the medication guidance data output device, A medication guidance data output unit outputs the aforementioned medication guidance data, A medication guidance support device according to claim 1, comprising:

3. The requested data includes at least one of the following: a guidance perspective corresponding to the metadata, the calculation points for the current prescription, the calculation points for past prescriptions, classification information indicating a predetermined category based on the perspective of medication guidance, seasonal information, patient summary information from a pharmaceutical management perspective, and information on the patient's medication history. The medication guidance support device according to claim 1.

4. The medication guidance data includes the results of classifying the perspectives of medication guidance indicated by the medication guidance data into predetermined categories. The medication guidance support device according to claim 1.

5. The system further includes a guidance perspective determination unit that determines the guidance perspective from the aforementioned metadata, The request data acquisition unit acquires the request data, including the instructional perspective determined by the instructional perspective determination unit. The medication guidance support device according to claim 1.

6. A medication guidance support device according to any one of claims 1 to 5, A terminal device that presents the medication guidance data output by the medication guidance data output device to the user, A database in which data used to obtain some or all of the aforementioned request data is stored, A medication guidance support system equipped with the following features.

7. A request data acquisition step that acquires request data including the current prescription, the dispensing date of the current prescription, metadata characterizing at least one of the current prescription and the patient, past prescriptions, the dispensing date of the past prescriptions, and the medication history of the past prescriptions. A medication guidance data output request step involves requesting a medication guidance data output device, which outputs medication guidance data indicating medication guidance based on a trained model that has been trained to output output data corresponding to input data, to output the medication guidance data from the requested data. A medication guidance support method that includes [specific features / features].

8. On the computer, A request data acquisition step that acquires request data including the current prescription, the dispensing date of the current prescription, metadata characterizing at least one of the current prescription and the patient, past prescriptions, the dispensing date of the past prescriptions, and the medication history of the past prescriptions. A medication guidance data output request step involves requesting a medication guidance data output device, which outputs output data corresponding to input data, to output medication guidance data indicating medication guidance from the requested data. A program to execute.

Images