Pharmacist work support system, pharmacist work support method, and pharmacist work support program

Abstract

This will enable high-quality medication instructions to be provided regardless of the pharmacist in charge. [Solution] A search unit (116) extracts guidance information about drugs prescribed to patients, which guidance information is related to patient personal information indicating patient attributes, from a database that stores guidance information generated using at least precautions and side effect information included in package inserts of multiple drugs. An input unit (111) inputs the extracted guidance information to a learning model (112). An output unit (113) outputs advice information for providing medication guidance to patients, which advice information is generated by the learning model (112) in response to the guidance information.

Description

[Technical Field]

[0001] The present disclosure relates to a technology for supporting pharmacists in their work, such as providing medication instructions. [Background technology]

[0002] Pharmacists not only perform the physical task of dispensing medicines according to prescriptions, but also the interpersonal task of providing medication instructions to patients. Differences in the experience and knowledge of pharmacists can easily result in differences in the quality of medication instructions. It is desirable to be able to provide high-quality medication instructions regardless of the pharmacist in charge.

[0003] Patent Document 1 describes extracting and displaying a list of medication instruction items according to the type of medication and the number of times the medication has been provided, thereby enabling pharmacists to provide medication instruction without omission. [Prior art documents] [Patent documents]

[0004] [Patent Document 1] Japanese Patent Application Laid-Open No. 2014-059675 Summary of the Invention [Problem to be solved by the invention]

[0005] The technology described in Patent Document 1 only indicates guidance items according to the type of medication and the number of times the medication has been provided, and there are cases where appropriate medication guidance items are not indicated. The present disclosure aims to enable high-quality medication instructions to be provided regardless of the pharmacist in charge. [Means for solving the problem]

[0006] The pharmacist work support system according to the present disclosure includes: a search unit that extracts, from a database that stores guidance information generated using at least information on precautions and side effects included in package inserts of a plurality of drugs, guidance information about drugs prescribed to a patient, the guidance information being related to attributes of the patient; an input unit that inputs the instruction information extracted by the search unit into a learning model; an output unit that outputs advice information generated by the learning model in response to the instruction information input by the input unit when providing medication instruction to the patient; Equipped with. [Effects of the Invention]

[0007] In this disclosure, guidance information obtained from information included in the package insert is used as input, and advice information generated by a learning model is output. By referring to the advice information, it becomes possible to understand what kind of medication instruction should be given to the patient, enabling high-quality medication instruction to be given regardless of the pharmacist in charge. [Brief explanation of the drawings]

[0008] [Figure 1] 1 is a configuration diagram of a pharmacist work support system 100 according to a first embodiment. [Figure 2] 1 is a configuration diagram of a pharmacist work support device 10 according to a first embodiment. [Figure 3] FIG. 2 is a configuration diagram of a pharmacy terminal 20 according to the first embodiment. [Figure 4] FIG. 3 is an explanatory diagram of patient data 131 according to the first embodiment. [Figure 5] 3 is a flowchart of the processing of the pharmacist work support system 100 according to the first embodiment. [Figure 6] FIG. 2 is an explanatory diagram of patient personal information according to the first embodiment. [Figure 7] FIG. 3 is an explanatory diagram of medical questionnaire information according to the first embodiment. [Figure 8] FIG. 2 is an explanatory diagram of prescription information according to the first embodiment. [Figure 9] 10 is a flowchart of a reception process according to the first embodiment. [Figure 10] 10 is a flowchart of a reception process according to the second embodiment. [Figure 11] 10 is a flowchart of a reception process according to the second embodiment. [Figure 12] FIG. 10 is an explanatory diagram of a prompt according to the first to eighth embodiments. [Figure 13] FIG. 10 is an explanatory diagram of a prompt according to the first to eighth embodiments. [Figure 14] FIG. 10 is an explanatory diagram of a prompt according to the first to eighth embodiments. [Figure 15] FIG. 10 is an explanatory diagram of a prompt according to the first to eighth embodiments. [Figure 16] FIG. 10 is an explanatory diagram of a prompt according to the first to eighth embodiments. [Figure 17] FIG. 10 is an explanatory diagram of a prompt according to the first to eighth embodiments. [Figure 18] FIG. 10 is an explanatory diagram of a prompt according to the first to eighth embodiments. [Figure 19] FIG. 10 is an explanatory diagram of a prompt according to the first to eighth embodiments. [Figure 20] FIG. 10 is an explanatory diagram of a prompt according to the first to eighth embodiments. [Figure 21] FIG. 10 is an explanatory diagram of a prompt according to the first to eighth embodiments. [Figure 22] FIG. 10 is an explanatory diagram of a prompt according to the first to eighth embodiments. [Figure 23] FIG. 13 is a configuration diagram of a pharmacist work support system 100 according to a ninth embodiment. [Figure 24] FIG. 13 is a configuration diagram of a pharmacist work support device 10 according to a ninth embodiment. [Figure 25] 13 is a flowchart of the processing of the pharmacist work support system 100 according to the ninth embodiment. [Figure 26] FIG. 23 is an explanatory diagram of input information according to the ninth embodiment. [Figure 27] FIG. 23 is an explanatory diagram of input information according to the ninth embodiment. [Figure 28] FIG. 23 is an explanatory diagram of guidance information according to the ninth embodiment. [Figure 29] FIG. 23 is an explanatory diagram of advice information according to the ninth embodiment. [Figure 30]FIG. 23 is an explanatory diagram of advice information according to the ninth embodiment. [Figure 31] FIG. 20 is an explanatory diagram of information of an attachment according to the ninth embodiment. DETAILED DESCRIPTION OF THE INVENTION

[0009] Embodiment 1 ***Configuration Description*** The configuration of a pharmacist work support system 100 according to the first embodiment will be described with reference to FIG. Pharmacist work support system 100 includes pharmacist work support device 10 and one or more pharmacy terminals 20. Pharmacist work support device 10 and each pharmacy terminal 20 are connected via network 90. The pharmacist work support device 10 is a computer such as a cloud server. The pharmacy terminal 20 is a computer such as a PC installed in a pharmacy 30 and operated by a pharmacist. PC stands for personal computer. The pharmacy 30 may be a chain store or an individual store that is not affiliated with a chain. A plurality of pharmacy terminals 20 may be installed in the same pharmacy 30. When a plurality of pharmacy terminals 20 are installed, different devices such as a PC and a tablet terminal may be installed in combination.

[0010] The configuration of the pharmacist work support device 10 according to the first embodiment will be described with reference to FIG. The pharmacist work support device 10 is a computer. The pharmacist work support device 10 includes hardware components including a processor 11, a memory 12, a storage 13, and a communication interface 14. The processor 11 is connected to other hardware components via signal lines and controls the other hardware components.

[0011] Pharmacist work support device 10 includes, as functional components, input unit 111, learning model 112, output unit 113, and recording unit 114. The functions of each functional component of pharmacist work support device 10 are realized by software. Storage 13 stores programs that realize the functions of each functional component of pharmacist work support device 10. These programs are loaded into memory 12 by processor 11 and executed by processor 11. As a result, the functions of each functional component of pharmacist work support device 10 are realized.

[0012] The storage 13 stores patient data 131.

[0013] The configuration of pharmacy terminal 20 according to the first embodiment will be described with reference to FIG. Pharmacy terminal 20 is a computer. Pharmacy terminal 20 includes the following hardware components: processor 21, memory 22, storage 23, and communication interface 24. Processor 21 is connected to other hardware components via signal lines and controls the other hardware components. If pharmacy terminal 20 is a PC, it may be connected to multiple monitors as hardware components.

[0014] Pharmacy terminal 20 includes, as functional components, reception unit 211, extraction unit 212, and display unit 213. The functions of each functional component of pharmacy terminal 20 are realized by software. Storage 23 stores a program that realizes the function of each functional component of pharmacy terminal 20. This program is loaded into memory 22 by processor 21 and executed by processor 21. In this way, the function of each functional component of pharmacy terminal 20 is realized.

[0015] The processors 11 and 21 are ICs that perform processing. IC stands for Integrated Circuit. Specific examples of the processors 11 and 21 are a CPU, a DSP, and a GPU. CPU stands for Central Processing Unit. DSP stands for Digital Signal Processor. GPU stands for Graphics Processing Unit.

[0016] The memories 12 and 22 are storage devices that temporarily store data. Specific examples of the memories 12 and 22 are SRAM and DRAM. SRAM stands for Static Random Access Memory. DRAM stands for Dynamic Random Access Memory.

[0017] The storages 13 and 23 are storage devices that store data. Specific examples of the storages 13 and 23 are HDDs. HDD stands for Hard Disk Drive. The storages 13 and 23 may also be portable recording media such as SD (registered trademark) memory cards, CompactFlash (registered trademark), NAND flash, flexible disks, optical disks, compact disks, Blu-ray (registered trademark) disks, and DVDs. SD stands for Secure Digital. DVD stands for Digital Versatile Disk.

[0018] The communication interfaces 14 and 24 are interfaces for communicating with external devices. Specific examples of the communication interfaces 14 and 24 are Ethernet (registered trademark), USB, and HDMI (registered trademark) ports. USB is an abbreviation for Universal Serial Bus. HDMI is an abbreviation for High-Definition Multimedia Interface.

[0019] 2 shows only one processor 11. However, there may be multiple processors 11, and the multiple processors 11 may cooperate to execute programs that realize each function. Similarly, in FIG. 3, there is only one processor 21 shown. However, there may be multiple processors 21, and the multiple processors 21 may cooperate to execute programs that realize each function.

[0020] 2, the pharmacist work support device 10 includes the learning model 112. However, the learning model 112 may be provided outside the pharmacist work support device 10.

[0021] ***Explanation of Operation*** The operation of the pharmacist work support system 100 according to the first embodiment will be described with reference to FIGS. The operation procedure of pharmacist work support system 100 according to embodiment 1 corresponds to the pharmacist work support method according to embodiment 1. Furthermore, the program that realizes the operation of pharmacist work support system 100 according to embodiment 1 corresponds to the pharmacist work support program according to embodiment 1.

[0022] The patient data 131 according to the first embodiment will be described with reference to FIG. The patient data 131 is information about each patient. The patient data 131 includes information about each patient, such as personal information, prescription drug information, contact information, basic confirmation information, medication instruction history, and SOAP medication history. Personal information is information about the patient, such as the insurer number, name, sex, date of birth, height, and weight. Prescription drug information is historical information about drugs prescribed to the patient. Contact information includes comments and previous instruction handovers. Comments are information that should be noted about the patient regarding dispensing or medication instructions, etc. Previous instruction handovers are items handed over from the pharmacist who provided the previous instruction. Basic confirmation information is information about items that need to be confirmed about the patient regarding dispensing or medication instructions, etc. Medication instruction history is historical information about medication instructions that have been given in the past. SOAP medication history is a medication history recorded divided into Subject, Object, Assessment, and Plan. Subject records subjective information about the patient. Object records objective information. Assessment records the pharmacist's analysis and opinion. Plan records the plan for the issue.

[0023] The flow of processing performed by the pharmacist work support system 100 according to the first embodiment will be described with reference to FIG. (Step S11: Reception process) Reception unit 211 of pharmacy terminal 20 receives reception information from a patient who is to receive a prescription for medicines. The reception information includes patient personal information, medical questionnaire information, and prescription information. The patient personal information is information that indicates the patient's attributes, etc. As shown in Fig. 6, the patient personal information includes information such as the patient's name, telephone number, address, sex, age, height, and weight. The medical questionnaire information is information indicating the patient's answers to the medical questionnaire. As shown in Fig. 7, the medical questionnaire information includes the patient's answers to questions about the name of the disease, medication status, and side effect occurrence status. Prescription information is information that indicates the contents of a prescription for a patient. As shown in Figure 8, prescription information includes the name, dosage, and usage of each prescribed drug. Prescription information also includes the name of the hospital that issued the prescription and the date of issuance.

[0024] The reception process (step S11 in FIG. 5) according to the first embodiment will be described with reference to FIG. When a patient visits the pharmacy 30, the pharmacist has the patient fill out personal patient information. The pharmacist inputs the filled-out patient personal information into the pharmacy terminal 20, and the reception unit 211 accepts the patient personal information (step S111). Next, the pharmacist has the patient fill out a medical questionnaire. The pharmacist inputs the answers to the medical questionnaire into the pharmacy terminal 20, and the reception unit 211 accepts the medical questionnaire information (step S112). Next, the pharmacist receives a prescription from the patient. The pharmacist inputs the prescription information into the pharmacy terminal 20, and the reception unit 211 accepts the prescription information (step S113). At least some of the processes from step S111 to step S113 may be performed in parallel.

[0025] (Step S12: Extraction process) The extraction unit 212 of the pharmacy terminal 20 extracts input information from the reception information received in step S11 and transmits the input information to the pharmacist work support device 10. Note that the extraction unit 212 may extract all of the reception information as input information. Specifically, the extraction unit 212 extracts at least a portion of information from the patient's personal information in the reception information and includes it in the input information. For example, the extraction unit 212 extracts information such as gender, age, height, and weight from the patient's personal information in the reception information and includes it in the input information. The extraction unit 212 also extracts at least a portion of information from the medical questionnaire information in the reception information and includes it in the input information. For example, the extraction unit 212 extracts pairs of questions and answers for each question item from the medical questionnaire information in the reception information and includes it in the input information. The extraction unit 212 also extracts at least a portion of information from the prescription information in the reception information and includes it in the input information. For example, the extraction unit 212 extracts the name, quantity, and usage of the prescribed drug from the prescription information in the reception information and includes it in the input information.

[0026] (Step S13: Input processing) The input unit 111 of the pharmacist work support device 10 receives the input information transmitted in step S12. The input unit 111 inputs the input information and information contained in the package insert of the drug included in the input information as prompts to the learning model 112. The package insert of the drug is the package insert of a medical drug. The package insert is stored in advance in the storage 13. Here, the input unit 111 inputs at least information on precautions and side effects as information contained in the package insert to the learning model 112. The input unit 111 may further input information on efficacy and effect as information contained in the package insert to the learning model 112. At this time, the input unit 111 adds to the prompt, in addition to the input information and the information contained in the attached document, an order indicating assumptions and instructions, and constraints. Here, the input unit 111 writes, in the order, the assumption that the person is a pharmacist and an instruction to generate advice information for providing medication instruction. The input unit 111 writes, in the constraints, how to write the advice information, the amount of information to be written, etc. The advice information for providing medication instruction is information indicating what kind of medication instruction should be given to the patient. The input unit 111 may describe, as the instruction content, advice information for providing medication instruction from information included in the package insert. This allows advice information for providing medication instruction to be extracted from information included in the package insert, rather than extracted from information on the Internet.

[0027] (Step S14: Generation process) The learning model 112 of the pharmacist work support device 10 generates advice information for providing medication instruction based on the prompt input in step S13. The learning model 112 is a so-called generative AI. AI stands for artificial intelligence. The learning model 112 may be configured using algorithms such as BERT and GPT, for example. BERT is a bidirectional It is an abbreviation for Encoder Representations from Transformers. GPT is an abbreviation for Generative Pretrained Transformer. The learning model 112 may be configured by combining multiple algorithms including these algorithms.

[0028] (Step S15: Output process) The output unit 113 of the pharmacist work support device 10 acquires the advice information for providing medication instruction generated in step S14. Then, the output unit 113 transmits the acquired advice information for providing medication instruction to the pharmacy terminal 20.

[0029] (Step S16: Display processing) Display unit 213 of pharmacy terminal 20 acquires the advice information for providing medication instruction transmitted in step S15. Display unit 213 displays the acquired advice information for providing medication instruction on a display device connected to pharmacy terminal 20 via communication interface 24.

[0030] ***Effects of the First Embodiment*** As described above, the pharmacist work support system 100 according to the first embodiment receives input information and information contained in the attached document as input, and outputs advice information generated by the learning model 112. By referring to the advice information, it becomes possible to know what kind of medication instruction should be given to the patient, and high-quality medication instruction can be given regardless of the pharmacist in charge. Furthermore, by outputting the questions as sample questions that can be asked directly to patients, the advice information becomes easy to use regardless of the pharmacist's experience.

[0031] In the pharmacist work support system 100 of the first embodiment, information contained in the package insert is provided as input to the learning model 112. This makes it possible to prevent hallucination and obtain appropriate advice information corresponding to the prescribed drug. In particular, by providing instructions to extract advice information for providing medication instructions from the information contained in the package insert, hallucination is appropriately prevented.

[0032] ***Other Configurations*** <Variation 1> In the first embodiment, the input information includes information extracted from the medical questionnaire information. However, the medical questionnaire information is not essential. If the input information includes information extracted from the medical questionnaire information, it is possible to obtain more appropriate advice information. However, even if the input information does not include information extracted from the medical questionnaire information, it is possible to obtain generally appropriate advice information.

[0033] Embodiment 2 The second embodiment differs from the first embodiment in that prescription difference information indicating the difference between the contents of the current prescription and the contents of the previous prescription is input. In the second embodiment, this difference will be explained, and explanations of the same points will be omitted.

[0034] There are cases where a patient revisits the pharmacy 30. In such cases, information about the patient from previous visits has been recorded. Therefore, the pharmacist work support system 100 generates a prompt using the information recorded about the patient.

[0035] ***Explanation of Operation*** The operation of the pharmacist work support system 100 according to the second embodiment will be described with reference to FIGS.

[0036] The processing of the pharmacist work support system 100 according to the second embodiment will be described with reference to Fig. 5. The processing from step S11 to step S13 differs from that of the first embodiment. (Step S11: Reception process) As in the first embodiment, reception unit 211 of pharmacy terminal 20 receives reception information from a patient who is prescribed medication. The reception information includes patient personal information, medical questionnaire information, and prescription information. In the case of a patient who is visiting the pharmacy again, the patient personal information and medical questionnaire information include information on changes since the patient's previous visit. Furthermore, the prescription information includes not only the most recent prescription information, which is information on the prescription at the current visit, but also past prescription information, which is information on the prescription at the previous visit.

[0037] The reception process (step S11 in FIG. 5) according to the second embodiment will be described with reference to FIG. The processing from step S111 to step S113 is the same as that in FIG.

[0038] The reception unit 211 determines whether the patient is a returning patient based on the patient's name, telephone number, address, etc. (step S110). Specifically, the reception unit 211 searches personal information in the patient data 131 of the pharmacist work support device 10 using the patient's name, telephone number, and address as keywords. If no information corresponding to the keywords is found, the reception unit 211 determines that the patient is a first-time patient. On the other hand, if information corresponding to the keywords is found, the reception unit 211 determines that the patient is a returning patient. If the patient is visiting the store for the first time, the reception unit 211 advances the process to step S111. On the other hand, if the patient is visiting the store for the second time, the reception unit 211 advances the process to step S114.

[0039] In the case of a returning patient, the reception unit 211 reads out the patient's personal information and medical questionnaire information from the patient data 131 in the pharmacist work support device 10. The pharmacist confirms with the patient any changes to the patient's personal information and medical questionnaire information. When the pharmacist inputs the changes into the pharmacy terminal 20, the reception unit 211 accepts the patient's personal information and medical questionnaire information with the identified changes (step S114). Note that the reception unit 211 may also include information before the changes. Next, the pharmacist receives the prescription from the patient. The pharmacist inputs the prescription information into the pharmacy terminal 20, and the reception unit 211 receives the most recent prescription information. Furthermore, the reception unit 211 reads out the patient's previous prescription information from the patient data 131 of the pharmacist work support device 10 as past prescription information. The reception unit 211 then sets the most recent prescription information and the past prescription information together as the prescription information (step S115).

[0040] (Step S12: Extraction process) As in the first embodiment, extraction unit 212 of pharmacy terminal 20 extracts input information from the reception information received in step S11 and transmits the input information to pharmacist work support device 10. However, the extraction unit 212 also includes information indicating changes to the patient personal information and medical questionnaire information in the input information. Furthermore, with regard to prescription information, the extraction unit 212 extracts at least a portion of information from each of the most recent prescription information and the past prescription information. For example, the extraction unit 212 extracts the drug name, quantity, and usage of the prescribed drug from each of the most recent prescription information and the past prescription information. Then, the extraction unit 212 extracts prescription difference information indicating the difference between the information extracted from the most recent prescription information and the information extracted from the past prescription information. In other words, the extraction unit 212 extracts prescription difference information indicating the difference between the contents of the current prescription and the contents of the previous prescription. Then, the extraction unit 212 includes the most recent prescription information and the prescription difference information in the input information. Note that the extraction unit 212 may also include past prescription information in the input information.

[0041] (Step S13: Input processing) As in the first embodiment, the input unit 111 of the pharmacist work support device 10 inputs input information as a prompt to the learning model 112. As a result, for the patient personal information and medical questionnaire information, information indicating changes is input as a prompt. For the prescription information, in addition to the most recent prescription information, prescription difference information is input as a prompt.

[0042] ***Effects of the Second Embodiment*** As described above, the pharmacist work support system 100 according to the second embodiment generates prompts by using previously recorded information about the patient, which enables the learning model 112 to generate more appropriate advice information.

[0043] Embodiment 3 The third embodiment differs from the second embodiment in that information indicating the content of medication instructions given to the patient in the past is input to the learning model 112. In the third embodiment, this difference will be explained, and explanation of the same points will be omitted.

[0044] The processing of the pharmacist work support system 100 according to the third embodiment will be described with reference to Fig. 5. The processing from step S11 to step S13 differs from that of the second embodiment. (Step S11: Reception process) In the case of a returning patient, reception unit 211 of pharmacy terminal 20 reads out information indicating the contents of medication instructions previously given to the patient.

[0045] The reception process (step S11 in FIG. 5) according to the third embodiment will be described with reference to FIG. The processing from step S110 to step S115 is the same as in Fig. 10. In the case of a returning patient, following the processing of step S115, reception unit 211 reads out information indicating the content of medication instructions given to the patient in the past and adds it to the reception information (step S116). Specifically, reception unit 211 reads out information registered in the patient's past SOAP medication history as information indicating the content of medication instructions given in the past. At this time, reception unit 211 may read out all of the patient's past SOAP medication history, or may read out only the SOAP medication history for a certain period of time in the past.

[0046] (Step S12: Extraction process) As in the second embodiment, extraction unit 212 of pharmacy terminal 20 extracts input information from the reception information received in step S11 and transmits the input information to pharmacist work support device 10. However, the extraction unit 212 includes at least a part of the information indicating the contents of medication instructions given in the past in the input information.

[0047] (Step S13: Input processing) As in the second embodiment, the input unit 111 of the pharmacist work support device 10 inputs input information as a prompt to the learning model 112. As a result, information indicating the content of medication instructions given to the patient in the past is input as a prompt.

[0048] ***Effects of the Third Embodiment*** As described above, the pharmacist work support system 100 according to the third embodiment inputs information indicating the content of medication instructions given to patients in the past into the learning model 112. This enables the learning model 112 to identify items that should have been instructed but have not been given. As a result, the learning model 112 can generate more appropriate advice information.

[0049] ***Other Configurations*** <Variation 2> In the third embodiment, a case where a function is added to the second embodiment has been described. That is, in the third embodiment, in addition to the prescription difference information etc. described in the second embodiment, information indicating the content of medication instructions given to the patient in the past is additionally input. However, it is also possible to additionally input only the information indicating the content of medication instructions given to the patient in the past without inputting the prescription difference information etc. described in the second embodiment. Even in this case, a certain degree of effect can be obtained.

[0050] Embodiment 4 The fourth embodiment differs from the first to third embodiments in that information indicating that a hearing has not been conducted is input to the learning model 112. In the fourth embodiment, this difference will be explained, and explanation of the same points will be omitted. In the fourth embodiment, a case where a modification is made to the first embodiment will be described. However, modifications can also be made to the second and third embodiments.

[0051] ***Explanation of Operation*** The processing of the pharmacist work support system 100 according to the fourth embodiment will be described with reference to Fig. 5. The processing of step S13 differs from that of the first embodiment.

[0052] (Step S13: Input processing) As in the first embodiment, the input unit 111 of the pharmacist work support device 10 inputs the input information as a prompt to the learning model 112. At this time, the input unit 111 adds information indicating that the pharmacist has not yet interviewed the patient to the prompt, and then inputs the information to the learning model 112. Here, it is assumed that medication instructions will be given to patients and that patient interviews will be conducted by referring to the advice information generated by the learning model 112. By inputting information indicating that no interviews have been conducted into the learning model 112, it becomes possible to properly convey this assumption to the learning model 112.

[0053] ***Effects of the Fourth Embodiment*** As described above, the pharmacist work support system 100 according to the fourth embodiment inputs information indicating that no interview has been conducted into the learning model 112. This allows the learning model 112 to be informed of the assumption that medication instructions will be provided to the patient and that an interview will be conducted with the patient, by referring to the advice information generated by the learning model 112. As a result, it becomes possible for the learning model 112 to generate more appropriate advice information.

[0054] Embodiment 5 The fifth embodiment differs from the first to fourth embodiments in that statistical information indicating the onset time of side effects of drugs is input to the learning model 112. In the fifth embodiment, this difference will be explained, and explanation of the same points will be omitted. In the fifth embodiment, a case where a modification is made to the first embodiment will be described. However, modifications can also be made to the second to fourth embodiments.

[0055] ***Explanation of Operation*** The processing of the pharmacist work support system 100 according to the fifth embodiment will be described with reference to Fig. 5. The processing of step S13 differs from that of the first to fourth embodiments.

[0056] (Step S13: Input processing) As in the first embodiment, the input unit 111 of the pharmacist work support device 10 inputs input information as a prompt to the learning model 112. At this time, the input unit 111 adds statistical information indicating the timing of the occurrence of side effects of the drug currently prescribed to the patient to the prompt, and then inputs the information to the learning model 112. Statistical information indicating the timing of side effects is information that indicates, for example, that there is an A% chance that side effect X will occur within x days of starting to take the drug, and that there is a B% chance that side effect Y will occur between x and x days.

[0057] ***Effects of the Fifth Embodiment*** As described above, the pharmacist work support system 100 according to the fifth embodiment inputs statistical information indicating the timing of the onset of side effects into the learning model 112. This enables the learning model 112 to identify what side effects are likely to occur in the current patient, and to generate advice information regarding the side effects that may occur. As a result, the learning model 112 can generate more appropriate advice information.

[0058] Embodiment 6 The sixth embodiment differs from the first to fifth embodiments in that advice information is output with a priority assigned to it. In the sixth embodiment, this difference will be explained, and explanation of the same points will be omitted. In the sixth embodiment, a case where a modification is made to the first embodiment will be described. However, modifications can also be made to the second to fifth embodiments.

[0059] ***Explanation of Operation*** The processing of the pharmacist work support system 100 according to the sixth embodiment will be described with reference to Fig. 5. The processing of step S13 differs from that of the first to fifth embodiments. (Step S13: Input processing) As in the first embodiment, the input unit 111 of the pharmacist work support device 10 inputs input information as a prompt to the learning model 112. At this time, the input unit 111 writes an instruction to prioritize advice information in the instruction form for generating the prompt. The input unit 111 writes the instruction so that advice information indicating content that should be given priority to the patient is given a higher priority.

[0060] ***Effects of the Sixth Embodiment*** As described above, the pharmacist work support system 100 according to the sixth embodiment prioritizes advice information. This allows the pharmacist to refer to the priority order when providing medication instruction and decide which advice information to refer to. As a result, medication instruction can be provided smoothly.

[0061] ***Other Configurations*** <Variation 3> The input unit 111 may write in the command or constraint conditions for generating a prompt that a specified number of pieces of advice information are to be output in descending order of priority. A plurality of modes may be prepared as operation modes of pharmacy terminal 20, and the designated number may be changed depending on the selected operation mode. For example, a normal mode and a simple mode may be prepared, and when the simple mode is selected, the designated number may be reduced compared to when the normal mode is selected, so that advice information is displayed in a simpler manner.

[0062] Embodiment 7 The seventh embodiment differs from the first to sixth embodiments in that in addition to generating advice information, generation of a reason for selecting the advice information is instructed. In the seventh embodiment, this difference will be explained, and explanation of the same points will be omitted. In the seventh embodiment, a case where a modification is made to the first embodiment will be described. However, modifications can also be made to the second to sixth embodiments.

[0063] ***Explanation of Operation*** The processing of the pharmacist work support system 100 according to the sixth embodiment will be described with reference to Fig. 5. The processing from step S13 to step S16 differs from that of the first embodiment. (Step S13: Input processing) As in the first embodiment, the input unit 111 of the pharmacist work support device 10 inputs the input information as a prompt to the learning model 112. At this time, the input unit 111 writes an instruction to generate a reason for selecting the advice information in the instruction for generating the prompt.

[0064] (Step S14: Generation process) The learning model 112 of the pharmacist work support device 10 generates advice information for providing medication instruction based on the prompt input in step S13, and also generates a reason for selecting the generated advice information. (Step S15: Output process) The output unit 113 of the pharmacist work support device 10 acquires the advice information and the selection reason for providing medication instruction generated in step S14. Then, the output unit 113 transmits the acquired advice information and the selection reason for providing medication instruction to the pharmacy terminal 20.

[0065] (Step S16: Display processing) Display unit 213 of pharmacy terminal 20 acquires the advice information and the selection reason for providing medication instruction transmitted in step S15. Display unit 213 displays the acquired advice information and the selection reason for providing medication instruction on a display device connected to pharmacy terminal 20 via communication interface 24.

[0066] ***Effects of the Seventh Embodiment*** As described above, the pharmacist work support system 100 according to the seventh embodiment instructs the generation of reasons for selecting the advice information in addition to generating advice information. As a result, the learning model 112 generates reasons for selecting the advice information when generating the advice information. When an experienced pharmacist provides medication instructions, the learning model 112 determines the content of the instructions after understanding the reasons for selecting the content of the instructions. By generating reasons for selecting the advice information when generating the advice information, the learning model 112 is able to think in a similar way to an experienced pharmacist when providing medication instructions, making it possible to generate more appropriate advice information.

[0067] The pharmacist work support system 100 according to the seventh embodiment displays the reason for selecting the advice information together with the advice information. By referring to the selection reason, the pharmacist can easily determine the advice information to refer to.

[0068] When prioritizing advice information, it is useful to refer to the reasons for selecting the advice information. Therefore, by adding the functions of embodiment 7 to embodiment 6 and generating the reasons for selecting the advice information while prioritizing the advice information, it becomes possible to appropriately prioritize the advice information.

[0069] Embodiment 8 The eighth embodiment differs from the first to seventh embodiments in that in addition to generating advice information, it instructs the generation of an OAP in the SOAP medication history. In the eighth embodiment, this difference will be explained, and explanation of the same points will be omitted. In the eighth embodiment, a case where a modification is made to the first embodiment will be described. However, modifications can also be made to the second to seventh embodiments.

[0070] ***Explanation of Operation*** The processing of the pharmacist work support system 100 according to the sixth embodiment will be described with reference to Fig. 5. The processing from step S13 to step S16 differs from that of the first embodiment. (Step S13: Input processing) As in the first embodiment, the input unit 111 of the pharmacist work support device 10 inputs the input information as a prompt to the learning model 112. At this time, the input unit 111 writes an instruction to generate an OAP for the SOAP medication history in the instruction form for generating the prompt.

[0071] (Step S14: Generation process) The learning model 112 of the pharmacist work support device 10 generates advice information for providing medication instruction based on the prompt input in step S13, and also generates an OAP for the SOAP medication history. (Step S15: Output process) The output unit 113 of the pharmacist work support device 10 acquires the advice information for providing medication instruction and the OAP of the SOAP medication history generated in step S14. Then, the output unit 113 transmits the acquired advice information for providing medication instruction and the OAP of the SOAP medication history to the pharmacy terminal 20.

[0072] (Step S16: Display processing) Display unit 213 of pharmacy terminal 20 acquires the advice information for providing medication instruction and the OAP of the SOAP medication history transmitted in step S15. Display unit 213 displays the acquired advice information for providing medication instruction and the OAP of the SOAP medication history on a display device connected to pharmacy terminal 20 via communication interface 24.

[0073] ***Effects of the eighth embodiment*** As described above, the pharmacist work support system 100 according to the seventh embodiment instructs the generation of an OAP of a SOAP medication history in addition to the generation of advice information. As a result, the learning model 112 generates an OAP of a SOAP medication history when generating advice information. When an experienced pharmacist provides medication instructions, the content of the instructions is determined after considering what the OAP of the SOAP medication history will be. By generating an OAP of a SOAP medication history when generating advice information, the learning model 112 is able to think in a similar way to an experienced pharmacist when providing medication instructions, making it possible to generate more appropriate advice information.

[0074] Here, when an experienced pharmacist provides medication instructions, he or she considers what the OAP of the SOAP medication history will be, imagines the reasons for selecting the instruction content, and then decides on the instruction content. Therefore, it is more desirable to add the functions of embodiment 8 to embodiment 7, so that in addition to generating advice information, the system instructs the reasons for selecting the advice information and the generation of the OAP of the SOAP medication history. This allows the system to think more similarly to how an experienced pharmacist would when providing medication instructions, making it possible to generate more appropriate advice information.

[0075] The pharmacist work support system 100 according to the eighth embodiment displays the OAP of the SOAP medication history together with advice information. By referring to the OAP, the pharmacist can provide medication instructions while imagining the items to be written in the OAP of the SOAP medication history.

[0076] When prioritizing advice information, it is useful to refer to the OAP of the SOAP medication history. Therefore, by adding the functions of the eighth embodiment to the sixth embodiment and generating the OAP of the SOAP medication history while prioritizing the advice information, it becomes possible to appropriately prioritize the advice information.

[0077] ***Other Configurations*** <Variation 4> When generating advice information, it is considered that pharmacists place importance on P in the OAP. Therefore, the input unit 111 may enter an instruction to generate only P in the SOAP medication history in the instruction for generating the prompt. It is also considered that pharmacists place importance on A after P. Therefore, the input unit 111 may enter an instruction to generate only AP from the SOAP medication history in the instruction form for generating the prompt.

[0078] The processor 11, memory 12, storage 13, and electronic circuit 15 are collectively referred to as a processing circuit. In other words, the functions of the respective functional components are realized by the processing circuit.

[0079] <Example prompt> Examples of prompts are described with reference to Figures 12 through 19. Figures 12 to 14 show the system prompt. The system prompt defines Role, Status, Goal, Variables, Constraints, OutputFormat, and keys. Role, Status, and Goal correspond to the above-mentioned instruction. Constraints correspond to the above-mentioned constraints. OutputFormat is information that determines the output format. Keys is a term definition. Here, the Goal is instructed to generate questions to be asked in medication guidance corresponding to the content described in embodiment 1, as well as the reason for generation (reason for selection) corresponding to the content described in embodiment 7, and a SOAP medication history corresponding to the content described in embodiment 8. Note that here, the generation of S in the SOAP medication history is also instructed, but since the hearing has not yet taken place, it is also possible to instruct the generation of only the OAP, excluding S.

[0080] 15 to 19 show user prompts. A user prompt is information that defines a patient and corresponds to the input in a system prompt. The user prompt defines the gender and age extracted from the patient's personal information, the symptoms (current illness name) extracted from the medical questionnaire information, and the name and amount of the drug extracted from the prescription information. The user prompt also defines information contained in the drug's package insert (such as precautions, side effect information, and efficacy).

[0081] An example of a response obtained from the learning model 112 will be described with reference to Figures 20 to 22. The response includes an example of a SOAP medication history entry, the reason for the generated information, and advice information (interview). Note that Figures 15 to 19 show only information about a newly prescribed atorvastatin tablet 5 mg among the prescribed medications, but in reality, it is assumed that the prescription of Zetia tablets 10 mg and Lotriga granular capsules 2 g has been continued and the prescription of Livalo tablets 2 mg has been discontinued. Normally, the fact that the prescription of Zetia tablets 10 mg and Lotriga granular capsules 2 g has been continued and the prescription of Livalo tablets 2 mg has been discontinued would also be stated in the user prompt.

[0082] Embodiment 9 The ninth embodiment differs from the first to eighth embodiments in that, instead of inputting the information contained in the package insert into the learning model 112, guidance information corresponding to the patient obtained from a database 40 that stores guidance information generated using the information contained in the package insert is input into the learning model 112. In other words, the ninth embodiment differs from the first to eighth embodiments in that RAG is used to generate input to the learning model 112 for the information contained in the package insert. RAG stands for Retrieval-Augmented Generation. In the ninth embodiment, this difference will be explained, and explanations of the same points will be omitted. In the ninth embodiment, a case where a modification is made to the first embodiment will be described. However, modifications can also be made to the second to eighth embodiments.

[0083] ***Configuration Description*** The configuration of a pharmacist work support system 100 according to the ninth embodiment will be described with reference to FIG. 1 in that it includes a database 40. The pharmacist work support device 10 is connected to the database 40 via a network 90. ​​The database 40 stores guidance information generated using at least the information on precautions and side effects contained in the package inserts of multiple drugs.

[0084] The configuration of a pharmacist work support device 10 according to the ninth embodiment will be described with reference to FIG. Pharmacist work support device 10 differs from pharmacist work support device 10 shown in FIG. 2 in that it includes search unit 116 as a functional component.

[0085] ***Explanation of Operation*** Referring to FIG. 25, the processing of the pharmacist work support system 100 according to the ninth embodiment will be described. The processes in steps S21 and S22 are the same as those in steps S11 and S12 in Fig. 5. The processes in steps S25 to S27 are the same as those in steps S14 to S16 in Fig. 5.

[0086] (Step S23: Search process) The search unit 116 of the pharmacist work support device 10 extracts guidance information corresponding to the patient from the database 40. Specifically, the search unit 116 extracts guidance information about drugs prescribed to patients and related to patient personal information indicating patient attributes from the database 40. That is, the search unit 116 extracts guidance information corresponding to the patient from the database 40 using information about the prescribed drugs, the patient personal information, and the medical questionnaire information included in the input information. Here, the search unit 116 may perform a keyword search using keywords included in the patient's personal information and search for related guidance information based on a match of character strings, etc. Alternatively, the search unit 116 may perform a vector search based on the patient's personal information to search for related guidance information. Alternatively, the search unit 116 may perform a hybrid search that combines a keyword search and a vector search to search for related guidance information. Alternatively, the search unit 116 may use other search methods to search for related guidance information. For example, the search unit 116 may identify guidance information about a drug prescribed to a patient by a drug-based keyword search, and then perform a vector search based on the patient's personal information to extract guidance information related to the patient's personal information from the guidance information about the identified drug. The search unit 116 may be configured by the RAG described above.

[0087] (Step S24: Input processing) The input unit 111 of the pharmacist work support device 10 inputs the input information transmitted in step S22 and the guidance information extracted in step S23 as prompts to the learning model 112. In the first embodiment, the information contained in the attached document was input as a prompt to the learning model 112. However, here, the information contained in the attached document is not input as a prompt, and instead the guidance information extracted from the database 40 is input as a prompt to the learning model 112. At this time, in addition to the input information and instruction information, the input unit 111 adds an order indicating assumptions and instructions and constraints to the prompt, similar to step S13 in Fig. 5. Here, the input unit 111 writes in the order the assumption that the person is a pharmacist and the instruction to generate advice information for providing medication instruction. The input unit 111 writes in the constraints how to write the advice information, the amount to write, etc. The advice information for providing medication instruction is information indicating what kind of medication instruction should be given to the patient.

[0088] As a result, advice information for providing medication instruction to a patient is generated by the learning model 112 in response to the input information and instruction information input by the input unit 111.

[0089] For example, assume that input information such as that shown in Figures 26 and 27 is obtained in the processing of step S22. The input information includes medical questionnaire information, patient personal information, information on prescribed medications, information on medication instructions given in the past, etc. Note that while Figures 26 and 27 only indicate that drug A has been newly prescribed, it is assumed that the input information also indicates that other prescribed medication information includes continued prescriptions of drugs B and C, and that the prescription of drug D has been discontinued. In the process of step S23, guidance information corresponding to the patient is extracted from the database 40 based on the information contained in this input information. As a result, guidance information such as that shown in FIG. 28 is obtained, for example. In the process of step S24, a prompt including the input information obtained in the process of step S22 and the guidance information obtained in the process of step S23 is input to the learning model 112 to generate advice information. As a result, advice information such as that shown in FIGS. 29 and 30 is obtained.

[0090] Here, in the pharmacist work support device 10 according to the first embodiment, it is necessary to input information from the package insert of the drug as shown in FIG. 31 as a prompt into the learning model 112. Note that FIG. 31 shows an excerpt of the information from the package insert for drug A. In reality, the information from the package insert for drug A alone contains more information than is shown in FIG. 31. Then, it is necessary to input information from the package inserts for not only drug A but also other drugs B, C, and D as prompts into the learning model 112. Therefore, in the pharmacist work support device 10 according to the first embodiment, it is necessary to input more information into the learning model 112 than in the pharmacist work support device 10 according to the second embodiment.

[0091] ***Effects of the 9th embodiment*** As described above, the pharmacist work support system 100 according to the ninth embodiment inputs guidance information corresponding to the patient extracted from the database 40 into the learning model 112, instead of package insert information. That is, in the first embodiment, the pharmacist work support system 100 inputs package insert information for each drug prescribed to the patient into the learning model 112. In contrast, the pharmacist work support system 100 according to the ninth embodiment identifies guidance information for the drug prescribed to the patient that is related to the patient's personal information indicating the patient's attributes, and inputs the guidance information into the learning model 112. This makes it possible to reduce the amount of information input to the learning model 112. By reducing the amount of information input to the learning model 112, it is possible to shorten the time it takes to obtain a response from the learning model 112. Furthermore, with the generation AI, costs may be incurred depending on the amount of information input. Therefore, by reducing the amount of information input to the learning model 112, it is possible to reduce the costs associated with operating the pharmacist work support system 100.

[0092] In addition, the pharmacist work support system 100 of embodiment 9 can improve the accuracy of the advice information generated by the learning model 112 by identifying guidance information related to patient personal information and inputting the guidance information into the learning model 112. The pharmacist work support system 100 according to the first embodiment inputs the patient's personal information into the learning model 112 along with information on the package insert of the prescribed drug. As a result, the learning model 112 has a high degree of freedom in generating advice information, and the generation of advice information is heavily dependent on the learning model 112. As a result, there is a risk that the advice information will not be generated accurately. In contrast, the pharmacist work support system 100 according to the ninth embodiment inputs guidance information related to the patient's personal information into the learning model 112, thereby reducing the dependency on the learning model 112. Therefore, compared to the pharmacist work support system 100 according to the first embodiment, the possibility of obtaining the intended advice information can be increased.

[0093] ***Other Configurations*** <Variation 5> In the ninth embodiment, the database 40 stores guidance information generated using at least the information on precautions and side effects included in the package inserts of a plurality of drugs. The database 40 may store the guidance information organized based on problems. A problem is an issue that a patient has. When searching the database 40, the search unit 116 searches for the patient's problem based on the patient's personal information, etc., making it possible to identify guidance information related to the patient's personal information. This makes it possible to identify appropriate guidance information and input the appropriate guidance information into the learning model 112. As a result, it becomes possible to obtain appropriate advice information.

[0094] <Variation 6> In the ninth embodiment, the guidance information is generated using at least the information on precautions and side effects included in the package inserts of the plurality of drugs. The guidance information may be generated using statistical information indicating the timing of onset of side effects for the drugs. In other words, the guidance information may include not only information generated using the information included in the package inserts of the plurality of drugs, but also information generated using statistical information indicating the timing of onset of side effects for the drugs.

[0095] <Variation 7> In the ninth embodiment, the input unit 111 inputs the input information transmitted in step S22 and the guidance information extracted in step S23 as prompts to the learning model 112. The input unit 111 may input information other than the guidance information regarding other patients described in the second and subsequent embodiments to the learning model 112. Specifically, the input unit 111 may input, as prompts, to the learning model 112, prescription difference information indicating the difference between the content of the current prescription and the content of the previous prescription described in the second embodiment, information indicating the content of medication guidance previously given to the patient described in the third embodiment, information indicating that a hearing has not been conducted described in the fourth embodiment, and the like.

[0096] At this time, the input unit 111 may instruct to generate predetermined advice information when it is identified from other information regardless of the content of the guidance information. The predetermined advice information is, for example, advice information regarding at least one of matters handed over at the time of the previous medication guidance, the results of an audit check of the prescription content, guidance regarding high-risk drugs, and point-addition recommendation information. The advice information regarding the results of the audit check of the prescription content is, for example, advice information regarding contraindications, triple whammy, etc. The advice information regarding point-addition recommendation information is advice information regarding a specific drug management guidance surcharge, an infant formulation surcharge, etc. If the decision on whether to generate advice information that you want to be sure to output is left to the learning model 112, it may happen that the instruction information takes priority and the information is not generated even when it should be generated. Therefore, for advice information that you want to be sure to output, it is effective to instruct that it be generated if it is identified from other information, even if it is not included in the instruction information. In this way, by having the learning model 112 generate advice information not only from the instruction information obtained from the database 40 but also from other information, it becomes possible to generate more appropriate advice information.

[0097] Here, it is important to distinguish which information to store as guidance information in database 40, and which information to input directly into learning model 112, guidance information related to patient personal information, etc. In other words, it is not appropriate to register guidance information based on all information in database 40. It is effective to register the information on the package insert described in embodiment 9 and the statistical information on the timing of side effect onset described in variant example 6 as guidance information in database 40, input the retrieved guidance information into learning model 112, and input the other information directly into learning model 112. This allows advice information to be generated appropriately.

[0098] <Variation 8> There may be cases where guidance information is not extracted in step S23. That is, depending on the settings of the database 40, guidance information may not be extracted appropriately. When guidance information is not extracted in this way, the input unit 111 may input a prompt including information contained in the package insert of the drug included in the input information to the learning model 112 in step S24, as in the first embodiment. This makes it possible to generate advice information using information contained in the package insert of the drug even in exceptional cases.

[0099] <Variation 9> In the first embodiment, each functional component is realized by software. However, as a modification 9, each functional component may be realized by hardware. The differences between this modification 9 and the above embodiments will be described below.

[0100] When each functional component is realized by hardware, the pharmacist work support device 10 includes an electronic circuit 15 instead of the processor 11, the memory 12, and the storage 13. The electronic circuit 15 is a dedicated circuit for realizing the functions of each functional component, the memory 12, and the storage 13.

[0101] The electronic circuit 15 may be a single circuit, a composite circuit, a programmed processor, a parallel programmed processor, a logic IC, a GA, an ASIC, or an FPGA. GA stands for Gate Array. ASIC stands for Application Specific Integrated Circuit. FPGA stands for Field-Programmable Gate Array. Each functional component may be realized by one electronic circuit 15, or each functional component may be realized by distributing it among a plurality of electronic circuits 15.

[0102] <Modification 10> As a tenth modification, some of the functional components may be realized by hardware, and other functional components may be realized by software.

[0103] Aspects of the present disclosure Various aspects of the present disclosure are summarized below as appendices. (Appendix 1) a search unit that extracts, from a database that stores guidance information generated using at least information on precautions and side effects included in package inserts of a plurality of drugs, guidance information about drugs prescribed to a patient, the guidance information being related to attributes of the patient; an input unit that inputs the instruction information extracted by the search unit into a learning model; an output unit that outputs advice information generated by the learning model in response to the instruction information input by the input unit when providing medication instruction to the patient; A pharmacist work support system equipped with the following. (Appendix 2) The database stores the instruction information organized based on problems. A pharmacist work support system as described in Appendix 1. (Appendix 3) The database also includes guidance information generated using statistical information indicating the timing of occurrence of side effects of the drug. A pharmacist work support system as described in Appendix 1 or 2. (Appendix 4) The input unit further inputs other information about the patient other than the instruction information into the learning model, and instructs the system to generate advice information about at least one of matters handed over at the time of the previous medication instruction, the results of an audit check of prescription contents, instructions about high-risk drugs, and information about recommended points for adding points if the advice information is specified from the other information, regardless of the content of the instruction information. A pharmacist work support system described in any one of appendices 1 to 3. (Appendix 5) The input unit further inputs patient personal information indicating attributes of a patient who will receive a prescription for a drug and prescription information indicating the contents of a prescription for the patient into the learning model. A pharmacist work support system described in any one of appendices 1 to 4. (Appendix 6) The input unit inputs, as the prescription information, current prescription information indicating the content of the current prescription and prescription difference information indicating the difference between the content of the current prescription and the content of the previous prescription. A pharmacist work support system as described in Appendix 5. (Appendix 7) The input unit further inputs medical questionnaire information indicating the patient's answers to a medical questionnaire. A pharmacist work support system described in any one of appendices 1 to 6. (Appendix 8) The input unit further inputs information indicating the content of medication instructions given to the patient in the past. A pharmacist work support system described in any one of appendices 1 to 7. (Appendix 9) The input unit further inputs information indicating that a hearing from the patient has not been conducted. A pharmacist work support system described in any one of appendices 1 to 8. (Appendix 10) the input unit instructs the learning model to generate the advice information and also to generate a reason for selecting the advice information; The output unit further outputs a reason for selecting the advice information generated by the learning model. A pharmacist work support system described in any one of appendices 1 to 9. (Appendix 11) The input unit instructs the learning model to generate at least a plan in a SOAP (Subject Object Assessment Plan) medication history in addition to generating the advice information, The output unit further outputs the plan generated by the learning model. A pharmacist work support system described in any one of appendices 1 to 10. (Appendix 12) the input unit instructs the learning model to generate a specified number of pieces of advice information having high priority from among the pieces of advice information; The output unit outputs the specified number of pieces of advice information generated by the learning model. A pharmacist work support system described in any one of Appendices 1 to 11. (Appendix 13) a computer extracts, from a database storing guidance information generated using at least information on precautions and side effects included in package inserts of a plurality of drugs, guidance information about drugs prescribed to a patient, the guidance information being related to attributes of the patient; The computer inputs the instruction information into a learning model; A pharmacist work support method in which a computer outputs advice information generated by the learning model in response to the instruction information when providing medication instructions to the patient. (Appendix 14) a search process for extracting guidance information about a drug prescribed to a patient, the guidance information being related to attributes of the patient, from a database that stores guidance information generated using at least information on precautions and side effects included in package inserts of a plurality of drugs; an input process of inputting the instruction information extracted by the search process into a learning model; an output process for outputting advice information generated by the learning model in response to the instruction information input by the input process when providing medication instruction to the patient; A pharmacist work support program that enables a computer to function as a pharmacist work support system.

[0104] The embodiments and modifications of the present disclosure have been described above. Some of these embodiments and modifications may be combined and implemented. Also, one or more of them may be implemented partially. Note that the present disclosure is not limited to the above embodiments and modifications, and various modifications are possible as needed. [Explanation of symbols]

[0105] 100 Pharmacist work support system, 10 Pharmacist work support device, 11 Processor, 12 Memory, 13 Storage, 14 Communication interface, 111 Input unit, 112 Learning model, 113 Output unit, 114 Recording unit, 115 Learning unit, 116 Search unit, 131 Patient data, 20 Pharmacy terminal, 21 Processor, 22 Memory, 23 Storage, 24 Communication interface, 211 Reception unit, 212 Extraction unit, 213 Display unit, 30 Pharmacy, 40 Database.

Claims

1. a search unit that extracts, from a database that stores guidance information generated using at least information on precautions and side effects included in package inserts of a plurality of drugs, guidance information about drugs prescribed to a patient, the guidance information being related to attributes of the patient; an input unit that inputs the guidance information extracted by the search unit and information indicating that no interview with the patient has been conducted into a learning model; an output unit that outputs advice information generated by the learning model in response to the instruction information input by the input unit when providing medication instruction to the patient; A pharmacist work support system equipped with the following.

2. The database stores the instruction information organized based on problems. The pharmacist work support system according to claim 1.

3. The database also includes guidance information generated using statistical information indicating the timing of occurrence of side effects of the drug. The pharmacist work support system according to claim 1.

4. The input unit further inputs patient personal information indicating attributes of a patient who will receive a prescription for a drug and prescription information indicating the contents of a prescription for the patient into the learning model. The pharmacist work support system according to claim 1.

5. The input unit inputs, as the prescription information, current prescription information indicating the content of the current prescription and prescription difference information indicating the difference between the content of the current prescription and the content of the previous prescription. The pharmacist work support system according to claim 4.

6. The pharmacist business support system according to claim 1 , wherein the input unit further inputs medical questionnaire information indicating the patient's answers to a medical questionnaire.

7. The input unit further inputs information indicating the content of medication instructions given to the patient in the past. The pharmacist work support system according to claim 1.

8. the input unit instructs the learning model to generate the advice information and also to generate a reason for selecting the advice information; The output unit further outputs a reason for selecting the advice information generated by the learning model. The pharmacist work support system according to claim 1.

9. The input unit instructs the learning model to generate at least a Plan in a SOAP (Subject Object Assessment Plan) medication history in addition to generating the advice information, The output unit further outputs the plan generated by the learning model. The pharmacist work support system according to claim 1.

10. the input unit instructs the learning model to generate a specified number of pieces of advice information having high priority from among the pieces of advice information; The output unit outputs the specified number of pieces of advice information generated by the learning model. The pharmacist work support system according to claim 1.

11. a computer extracts, from a database storing guidance information generated using at least information on precautions and side effects included in package inserts of a plurality of drugs, guidance information about drugs prescribed to a patient, the guidance information being related to attributes of the patient; The computer inputs the instruction information and information indicating that the patient has not been interviewed into a learning model; A pharmacist work support method in which a computer outputs advice information generated by the learning model in response to the instruction information when providing medication instructions to the patient.

12. a search process for extracting guidance information about a drug prescribed to a patient, the guidance information being related to attributes of the patient, from a database that stores guidance information generated using at least information on precautions and side effects included in package inserts of a plurality of drugs; an input process of inputting the guidance information extracted by the search process and information indicating that no interview with the patient has been conducted into a learning model; an output process for outputting advice information generated by the learning model in response to the instruction information input by the input process when providing medication instruction to the patient; A pharmacist work support program that enables a computer to function as a pharmacist work support system.

Images