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

Abstract

To ensure high-quality medication guidance is provided regardless of the pharmacist in charge. [Solution] The input unit 111 inputs patient personal information indicating the attributes of the patient receiving the prescription, prescription information indicating the contents of the prescription for the patient, and at least the information on precautions and side effects from the information contained in the drug's package insert into the learning model 112. The output unit 113 outputs advice information for providing medication guidance to the patient, which is generated by the learning model 112 in correspondence with the patient personal information, prescription information, and information contained in the package insert.

Description

Technical Field

[0001] This disclosure relates to a technology for assisting pharmacists in tasks such as medication guidance.

Background Art

[0002] Pharmacists perform not only object tasks such as dispensing according to prescriptions but also person-to-person tasks such as medication guidance for patients. Medication guidance is likely to show differences in quality due to differences in pharmacists' experience or knowledge. It is desired to enable high-quality medication guidance regardless of the pharmacist in charge.

[0003] Patent Document 1 describes extracting and displaying a list of guidance items for medication guidance according to the type of drug and the number of times the drug has been provided. Thus, in Patent Document 1, pharmacists are enabled to perform medication guidance without omission.

Prior Art Documents

Patent Documents

[0004]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0005] The technology described in Patent Document 1 only shows guidance items according to the type of drug and the number of times the drug has been provided, and there may be cases where appropriate medication guidance items are not shown. An object of this disclosure is to enable high-quality medication guidance regardless of the pharmacist in charge.

Means for Solving the Problems

[0006] The pharmacist task support system according to this disclosure is An input unit that inputs patient personal information indicating the attributes of the patient receiving the prescription, prescription information indicating the contents of the prescription for the said patient, and at least the information of precautions and side effects from the information contained in the package insert of the said drug into a learning model. An output unit that outputs advice information for providing medication guidance to the patient, which is generated by the learning model in correspondence with the patient's personal information, prescription information, and information contained in the attached document, input by the input unit. It is equipped with. [Effects of the Invention]

[0007] This disclosure uses patient personal information, prescription information, and information contained in package inserts as inputs to output advice information generated by a learning model. By referring to this advice information, it becomes possible to understand what kind of medication guidance should be provided to the patient, enabling high-quality medication guidance regardless of the pharmacist in charge. [Brief explanation of the drawing]

[0008] [Figure 1] Configuration diagram of the pharmacist work support system 100 according to Embodiment 1. [Figure 2] Configuration diagram of the pharmacist work support device 10 according to Embodiment 1. [Figure 3] Configuration diagram of the pharmacy terminal 20 according to Embodiment 1. [Figure 4] An explanatory diagram of patient data 131 according to Embodiment 1. [Figure 5] A flowchart of the processing of the pharmacist work support system 100 according to Embodiment 1. [Figure 6] Diagram illustrating patient personal information according to Embodiment 1. [Figure 7] Diagram illustrating the information on the medical questionnaire according to Embodiment 1. [Figure 8] Diagram illustrating prescription information according to Embodiment 1. [Figure 9] Flowchart of the reception process according to Embodiment 1. [Figure 10]Flowchart of the reception process according to Embodiment 2. [Figure 11] Flowchart of the reception process according to Embodiment 2. [Figure 12] Explanatory diagram of the prompt according to Embodiments 1 to 8. [Figure 13] Explanatory diagram of the prompt according to Embodiments 1 to 8. [Figure 14] Explanatory diagram of the prompt according to Embodiments 1 to 8. [Figure 15] Explanatory diagram of the prompt according to Embodiments 1 to 8. [Figure 16] Explanatory diagram of the prompt according to Embodiments 1 to 8. [Figure 17] Explanatory diagram of the prompt according to Embodiments 1 to 8. [Figure 18] Explanatory diagram of the prompt according to Embodiments 1 to 8. [Figure 19] Explanatory diagram of the prompt according to Embodiments 1 to 8. [Figure 20] Explanatory diagram of the prompt according to Embodiments 1 to 8. [Figure 21] Explanatory diagram of the prompt according to Embodiments 1 to 8. [Figure 22] Explanatory diagram of the prompt according to Embodiments 1 to 8.

Modes for Carrying Out the Invention

[0009] Embodiment 1. ***Description of Configuration*** Referring to FIG. 1, the configuration of the pharmacist work support system 100 according to Embodiment 1 will be described. The pharmacist work support system 100 includes a pharmacist work support device 10 and one or more pharmacy terminals 20. The pharmacist work support device 10 and each pharmacy terminal 20 are connected via a network 90. The pharmacist support device 10 is a computer such as a cloud server. The pharmacy terminal 20 is a computer such as a PC installed in the pharmacy 30 and operated by a pharmacist. PC stands for Personal Computer. The pharmacy 30 can be a chain store or an independent store not affiliated with a chain. Multiple pharmacy terminals 20 may be installed in the same pharmacy 30. Furthermore, when installing multiple pharmacy terminals 20, different devices such as PCs and tablet terminals may be combined.

[0010] Referring to Figure 2, the configuration of the pharmacist work support device 10 according to Embodiment 1 will be described. The pharmacist work support device 10 is a computer. The pharmacist work support device 10 comprises hardware including a processor 11, memory 12, storage 13, and a communication interface 14. The processor 11 is connected to the other hardware via signal lines and controls this other hardware.

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

[0012] The storage device 13 stores patient data 131.

[0013] Referring to Figure 3, the configuration of the pharmacy terminal 20 according to Embodiment 1 will be described. The pharmacy terminal 20 is a computer. The pharmacy terminal 20 comprises hardware including a processor 21, memory 22, storage 23, and a communication interface 24. The processor 21 is connected to and controls other hardware via signal lines. If the pharmacy terminal 20 is a PC, it may be connected to multiple monitors as hardware.

[0014] The pharmacy terminal 20 comprises a reception unit 211, a dispensing unit 212, and a display unit 213 as functional components. The functions of each functional component of the pharmacy terminal 20 are implemented by software. Storage 23 stores programs that implement the functions of each functional component of the pharmacy terminal 20. These programs are loaded into memory 22 by the processor 21 and executed by the processor 21. This enables the implementation of the functions of each functional component of the pharmacy terminal 20.

[0015] Processors 11 and 21 are integrated circuits (ICs) that perform processing. IC stands for Integrated Circuit. Specific examples of processors 11 and 21 include CPUs, DSPs, and GPUs. CPU stands for Central Processing Unit. DSP stands for Digital Signal Processor. GPU stands for Graphics Processing Unit.

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

[0017] Storage 13 and 23 are storage devices for storing data. A concrete example of storage 13 and 23 is an HDD. HDD stands for Hard Disk Drive. Alternatively, storage 13 and 23 may be portable recording media such as SD® memory cards, CompactFlash®, NAND flash, flexible disks, optical disks, compact disks, Blu-ray® discs, and DVDs. SD stands for Secure Digital. DVD stands for Digital Versatile Disk.

[0018] Communication interfaces 14 and 24 are interfaces for communicating with external devices. Specific examples of communication interfaces 14 and 24 include Ethernet®, USB, and HDMI® ports. USB stands for Universal Serial Bus. HDMI stands for High-Definition Multimedia Interface.

[0019] In Figure 2, only one processor 11 was shown. However, there may be multiple processors 11, and multiple processors 11 may work together to execute programs that implement each function. Similarly, in Figure 3, only one processor 21 was shown. However, there may be multiple processors 21, and multiple processors 21 may work together to execute programs that implement each function.

[0020] In Figure 2, the pharmacist support device 10 is equipped with a learning model 112. However, the learning model 112 may be located outside the pharmacist support device 10.

[0021] ***Explanation of operation*** Referring to Figures 4 to 10, the operation of the pharmacist work support system 100 according to Embodiment 1 will be explained. The operating procedure of the pharmacist support system 100 according to Embodiment 1 corresponds to the pharmacist support method according to Embodiment 1. Furthermore, the program that implements the operation of the pharmacist support system 100 according to Embodiment 1 corresponds to the pharmacist support program according to Embodiment 1.

[0022] Referring to Figure 4, the patient data 131 according to Embodiment 1 will be explained. Patient data 131 contains information about each patient. For each patient, patient data 131 includes personal information, prescribed medication information, contact information, basic confirmation information, medication guidance history, and SOAP medication history. Personal information includes the patient's personal information such as the insurer number, name, gender, date of birth, height, and weight. Prescription drug information is the history of medications prescribed to the patient. Contact information includes comments and previous guidance handover. Comments are information that should be noted regarding the patient in relation to dispensing or medication guidance. Previous guidance handover is information that was passed on from the pharmacist who provided the previous guidance. Basic confirmation information is information that needs to be confirmed regarding the patient in relation to dispensing or medication guidance. Medication guidance history is the history of medication guidance provided in the past. SOAP medication history is a medication history recorded in four parts: Subject, Object, Assessment, and Plan. Subject records subjective information of the patient. Object records objective information. Assessment records the pharmacist's analysis and opinion. Plan records the plan for addressing the issues.

[0023] Referring to Figure 5, the processing flow of the pharmacist work support system 100 according to Embodiment 1 will be explained. (Step S11: Reception Processing) The reception unit 211 of the pharmacy terminal 20 receives reception information from patients receiving prescriptions. This reception information includes patient personal information, medical questionnaire information, and prescription information. Patient personal information refers to information that indicates the patient's attributes, etc. As shown in Figure 6, patient personal information includes the patient's name, telephone number and address, gender, age, height, and weight. Questionnaire information is information that shows the patient's answers to the questionnaire. As shown in Figure 7, questionnaire information includes the patient's answers to questions about the name of the illness, medication status, and the occurrence of side effects. Prescription information is information that shows the contents of a prescription for a patient. As shown in Figure 8, prescription information includes the name of the drug, the quantity, and the instructions for use for each prescribed medication. In addition, prescription information includes the name of the hospital that issued the prescription and the date of issue.

[0024] Referring to Figure 9, the reception process according to Embodiment 1 (step S11 in Figure 5) will be explained. When a patient visits pharmacy 30, the pharmacist has the patient fill out their personal information. The reception desk 211 receives the patient's personal information by having the pharmacist input it into the pharmacy terminal 20 (step S111). Next, the pharmacist has the patient answer a medical questionnaire. The reception desk 211 receives the questionnaire information by having the pharmacist input the answers into the pharmacy terminal 20 (step S112). Next, the pharmacist receives a prescription from the patient. The reception desk 211 receives the prescription information by having the pharmacist input the prescription information into the pharmacy terminal 20 (step S113). Furthermore, at least a portion of the processing 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. The extraction unit 212 may also extract all of the reception information as input information. Specifically, the extraction unit 212 extracts at least some 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 some information from the medical questionnaire information in the reception information and includes it in the input information. For example, the extraction unit 212 extracts question and answer pairs for each question item from the medical questionnaire information in the reception information and includes them in the input information. The extraction unit 212 also extracts at least some information from the prescription information in the reception information and includes it in the input information. For example, the extraction unit 212 extracts the drug name, quantity, and usage instructions of the prescribed medication from the prescription information in the reception information and includes them 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 the information contained in the drug's package insert into the learning model 112 as prompts. The drug's package insert is the package insert for a prescription drug. The package insert is stored in storage 13 in advance. Here, the input unit 111 inputs at least the information of precautions and side effects into the learning model 112 as the information contained in the package insert. The input unit 111 may also input the information of efficacy and effects into the learning model 112 as the information contained in the package insert. In this case, the input unit 111 adds, in addition to the input information and the information contained in the attached document, an instruction document indicating assumptions and instructions, and constraints to the prompt. Here, the input unit 111 includes in the instruction document the assumption that the user is a pharmacist and the instruction to generate advice information for when providing medication guidance. The input unit 111 includes in the constraints the format and amount of advice information to be included. The advice information for when providing medication guidance is information that indicates what kind of medication guidance should be given to the patient. The input unit 111 may also be configured to extract advice information for medication guidance from the information contained in the package insert. This ensures that advice information for medication guidance is not extracted from information on the internet, but rather from the information contained in the package insert.

[0027] (Step S14: Generation process) The learning model 112 of the pharmacist support device 10 generates advice information for medication guidance based on the prompt entered in step S13. The learning model 112 is a so-called generative AI. AI stands for Artificial Intelligence. The learning model 112 may be constructed using algorithms such as BERT and GPT, as specific examples. BERT is a bidirectional AI. GPT stands for Encoder Representations from Transformers. The learning model 112 may be constructed by combining multiple algorithms, including these algorithms.

[0028] (Step S15: Output processing) The output unit 113 of the pharmacist support device 10 acquires the advice information for medication guidance generated in step S14. The output unit 113 then transmits the acquired advice information for medication guidance to the pharmacy terminal 20.

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

[0030] ***Effects of Embodiment 1*** As described above, the pharmacist support system 100 according to Embodiment 1 takes input information and information contained in the package insert as input and outputs advice information generated by the learning model 112. By referring to the advice information, it becomes possible to understand what kind of medication guidance should be given to the patient, enabling high-quality medication guidance to be provided regardless of the pharmacist in charge. Furthermore, by outputting example questions that can be directly asked to patients, the advice becomes easy to use regardless of the pharmacist's experience level.

[0031] In Embodiment 1, the pharmacist support system 100 provides information contained in the package insert as input to the learning model 112. This prevents hallucination and makes it possible to obtain appropriate advice information corresponding to the prescribed medication. In particular, by specifying in the instructions that advice information for medication guidance should be extracted from the information contained in the package insert, hallucination is effectively prevented.

[0032] ***Other configurations*** <Example 1> In Embodiment 1, the input information included information extracted from the medical questionnaire. However, the medical questionnaire information is not mandatory. Including information extracted from the medical questionnaire in the input information makes it possible to obtain more appropriate advice. However, even if the input information does not include information extracted from the medical questionnaire, it is still possible to obtain generally appropriate advice.

[0033] Embodiment 2. Embodiment 2 differs from Embodiment 1 in that it inputs prescription difference information showing the difference between the contents of the current prescription and the contents of the previous prescription. Embodiment 2 explains this difference, and omits the explanation of the same points.

[0034] Patients may return to pharmacy 30. In this case, information about the patient from their previous visit is recorded. The pharmacist support system 100 then uses the recorded information about the patient to generate prompts.

[0035] ***Explanation of operation*** The operation of the pharmacist work support system 100 according to Embodiment 2 will be explained with reference to Figures 5 and 10.

[0036] Referring to Figure 5, the processing of the pharmacist work support system 100 according to Embodiment 2 will be described. The processing from step S11 to step S13 differs from that of Embodiment 1. (Step S11: Reception Processing) The reception unit 211 of the pharmacy terminal 20 receives reception information from patients receiving prescriptions, similar to Embodiment 1. The reception information includes patient personal information, medical questionnaire information, and prescription information. In the case of returning patients, the patient personal information and medical questionnaire information include information on changes since their last visit. In addition, the prescription information includes not only the most recent prescription information, which is the prescription for the current visit, but also past prescription information, which is the prescription for the previous visit.

[0037] Referring to Figure 10, the reception process according to Embodiment 2 (step S11 in Figure 5) will be described. The process from step S111 to step S113 is the same as in Figure 9.

[0038] The reception unit 211 identifies whether the patient is a returning patient or not based on the patient's name, telephone number, and address (step S110). Specifically, the reception unit 211 searches the patient's 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 identifies the patient as a first-time visitor. On the other hand, if information corresponding to the keywords is found, the reception unit 211 identifies the patient as a returning visitor. The reception unit 211 proceeds to step S111 if the patient is visiting for the first time. On the other hand, the reception unit 211 proceeds to step S114 if the patient is visiting for the second time.

[0039] For returning patients, the reception unit 211 reads the patient's personal information and medical questionnaire information from the patient data 131 of the pharmacist support device 10. The pharmacist confirms with the patient any changes to the patient's personal information and medical questionnaire information. When the pharmacist enters 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). The reception unit 211 may also include the information before the changes when considering 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 the patient's previous prescription information from the patient data 131 of the pharmacist work support device 10 as past prescription information. Then, the reception unit 211 combines the most recent prescription information and the past prescription information and sets it as prescription information (step S115).

[0040] (Step S12: Extraction process) The extraction unit 212 of the pharmacy terminal 20 extracts input information from the reception information received in step S11, similar to the first embodiment, and transmits the input information to the pharmacist work support device 10. However, the extraction unit 212 also includes information indicating changes in patient personal information and medical questionnaire information as input information. Furthermore, the extraction unit 212 extracts at least some information from both 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 medication from both the most recent prescription information and the past prescription information. The extraction unit 212 then extracts prescription difference information, which shows 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, which shows the difference between the contents of the current prescription and the contents of the previous prescription. The extraction unit 212 then includes the most recent prescription information and the prescription difference information in the input information. The extraction unit 212 may also include past prescription information in the input information.

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

[0042] ***Effects of Embodiment 2*** As described above, the pharmacist support system 100 according to Embodiment 2 generates prompts using previously recorded information about patients. This makes it possible for the learning model 112 to generate more appropriate advice information.

[0043] Embodiment 3. Embodiment 3 differs from Embodiment 2 in that information indicating the content of medication guidance previously given to the patient is input into the learning model 112. Embodiment 3 explains this difference, while the same points are omitted from the explanation.

[0044] Referring to Figure 5, the processing of the pharmacist work support system 100 according to Embodiment 3 will be described. The processing from step S11 to step S13 differs from that of Embodiment 2. (Step S11: Reception Processing) The reception unit 211 of the pharmacy terminal 20 reads out information indicating the content of medication guidance previously given to the patient, in the case of a returning patient.

[0045] Referring to Figure 11, the reception process according to Embodiment 3 (step S11 in Figure 5) will be described. The processing from steps S110 to S115 is the same as in Figure 10. If the patient is a returning patient, the reception unit 211 reads information indicating the medication guidance given to the patient in the past, following the processing in step S115, and adds it to the reception information (step S116). Specifically, the reception unit 211 reads the information registered in the patient's past SOAP medication history as information indicating the medication guidance given in the past. In this case, the reception unit 211 may read all of the patient's past SOAP medication history, or it may read only SOAP medication history for a certain period of time in the past.

[0046] (Step S12: Extraction process) The extraction unit 212 of the pharmacy terminal 20 extracts input information from the reception information received in step S11, similar to the second embodiment, and transmits the input information to the pharmacist work support device 10. However, the extraction unit 212 includes at least some of the information indicating the content of medication guidance provided in the past as input information.

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

[0048] ***Effects of Embodiment 3*** As described above, the pharmacist support system 100 according to Embodiment 3 inputs information indicating the content of medication guidance previously given to patients into the learning model 112. This allows the learning model 112 to identify items where guidance should have been given but was not. As a result, the learning model 112 can generate more appropriate advice information.

[0049] ***Other configurations*** <Modification 2> Embodiment 3 describes a case where additional functions are added to Embodiment 2. In other words, Embodiment 3 describes the additional input of information indicating the content of medication guidance previously given to the patient, in addition to the prescription difference information etc. described in Embodiment 2. However, it is also possible to input only the information indicating the content of medication guidance previously given to the patient, without inputting the prescription difference information etc. described in Embodiment 2. Even in this case, a certain degree of effectiveness can be obtained.

[0050] Embodiment 4. Embodiment 4 differs from Embodiments 1 to 3 in that information indicating that no interviews were conducted is input to the learning model 112. Embodiment 4 explains this difference, while omitting explanations of the same points. Embodiment 4 describes a case in which a modification has been made to Embodiment 1. However, it is also possible to modify Embodiments 2 and 3.

[0051] ***Explanation of operation*** Referring to Figure 5, the processing of the pharmacist work support system 100 according to Embodiment 4 will be described. The processing in step S13 differs from that of Embodiment 1.

[0052] (Step S13: Input Processing) The input unit 111 of the pharmacist work support device 10 inputs the input information as a prompt to the learning model 112, similar to the first embodiment. At this time, the input unit 111 adds information indicating that the pharmacist has not yet conducted an interview with the patient to the prompt before inputting it to the learning model 112. Here, it is assumed that medication guidance will be provided to the patient and an interview will be conducted with the patient, based on the advice information generated by the learning model 112. By inputting information into the learning model 112 indicating that an interview has not been conducted, it becomes possible to appropriately communicate this assumption to the learning model 112.

[0053] ***Effects of Embodiment 4*** As described above, the pharmacist support system 100 according to Embodiment 4 inputs information indicating that no interview has been conducted into the learning model 112. This communicates to the learning model 112 the assumption that the pharmacist will provide medication guidance to the patient and conduct an interview with the patient, based on the advice information generated by the learning model 112. As a result, the learning model 112 becomes capable of generating more appropriate advice information.

[0054] Embodiment 5. Embodiment 5 differs from Embodiments 1 to 4 in that statistical information indicating the timing of the onset of side effects for the drug is input into the learning model 112. Embodiment 5 explains this difference, while omitting explanations of the same points. Embodiment 5 describes a case where a modification has been made to Embodiment 1. However, it is also possible to modify Embodiments 2 to 4.

[0055] ***Explanation of operation*** Referring to Figure 5, the processing of the pharmacist work support system 100 according to Embodiment 5 will be described. The processing in step S13 differs from that of Embodiments 1 to 4.

[0056] (Step S13: Input Processing) The input unit 111 of the pharmacist work support device 10 inputs the input information as a prompt to the learning model 112, similar to the first embodiment. At this time, the input unit 111 adds statistical information indicating the timing of the onset of side effects for the medication prescribed to the patient to the prompt before inputting it to the learning model 112. Statistical information indicating the timing of side effects includes information such as, for example, that side effect X occurs in A% of cases within X days of starting the medication, and side effect Y occurs in B% of cases between X and Y days.

[0057] ***Effects of Embodiment 5*** As described above, the pharmacist support system 100 according to Embodiment 5 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 possible side effects. As a result, the learning model 112 can generate more appropriate advice information.

[0058] Embodiment 6. Embodiment 6 differs from Embodiments 1 to 5 in that it prioritizes the output of advice information. Embodiment 6 explains this difference, while omitting explanations of the same points. Embodiment 6 describes a case where a modification has been made to Embodiment 1. However, it is also possible to modify Embodiments 2 to 5.

[0059] ***Explanation of operation*** Referring to Figure 5, the processing of the pharmacist work support system 100 according to Embodiment 6 will be described. The processing in step S13 differs from that of Embodiments 1 to 5. (Step S13: Input Processing) The input unit 111 of the pharmacist work support device 10 inputs the input information as a prompt to the learning model 112, similar to the first embodiment. At this time, the input unit 111 includes an instruction in the prompt generation command to prioritize the advice information. The input unit 111 includes an instruction so that advice information indicating content that should be given priority to the patient is given a higher priority.

[0060] ***Effects of Embodiment 6*** As described above, the pharmacist support system 100 according to Embodiment 6 prioritizes the advice information. This allows pharmacists to refer to the priority order and decide which advice information to refer to during medication guidance. As a result, medication guidance can be conducted smoothly.

[0061] ***Other configurations*** <Variation 3> The input unit 111 may also include instructions or constraints in prompt generation that output a specified number of advice pieces of information in order of priority. The pharmacy terminal 20 may have multiple operating modes, and the number of specified items may be changed depending on the selected operating mode. For example, a normal mode and a simplified mode may be provided, and when the simplified mode is selected, the number of specified items may be reduced compared to when the normal mode is selected, so that the advice information is displayed in a simpler manner.

[0062] Embodiment 7. Embodiment 7 differs from Embodiments 1 to 6 in that, in addition to generating advice information, it also instructs the generation of reasons for selecting the advice information. Embodiment 7 explains this difference, while omitting explanations of the same points. Embodiment 7 describes a case where a modification has been made to Embodiment 1. However, it is also possible to modify Embodiments 2 to 6.

[0063] ***Explanation of operation*** Referring to Figure 5, the processing of the pharmacist work support system 100 according to Embodiment 6 will be described. The processing from step S13 to step S16 differs from that of Embodiment 1. (Step S13: Input Processing) The input unit 111 of the pharmacist work support device 10 inputs the input information as a prompt to the learning model 112, similar to the first embodiment. At this time, the input unit 111 includes an instruction in the prompt generation command to generate the reason for selecting the advice information.

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

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

[0066] ***Effects of Embodiment 7*** As described above, the pharmacist work support system 100 according to Embodiment 7 instructs the system to generate reasons for selecting advice information, in addition to generating advice information. As a result, the learning model 112 generates reasons for selecting advice information when generating advice information. When an experienced pharmacist provides medication guidance, they decide on the content of the guidance after understanding the reasons for selecting the content. By generating reasons for selecting advice information when generating advice information, the learning model 112 will perform a similar thought process to that of an experienced pharmacist when providing medication guidance, making it possible to generate more appropriate advice information.

[0067] The pharmacist support system 100 according to Embodiment 7 displays the reasons for selecting the advice information along with the advice information itself. By referring to the reasons for selection, pharmacists can more easily decide which advice information to refer to.

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

[0069] Embodiment 8. Embodiment 8 differs from Embodiments 1 to 7 in that, in addition to generating advice information, it also instructs the generation of OAP in the SOAP medical history. Embodiment 8 explains this difference, while omitting explanations of the same points. Embodiment 8 describes a case where a modification has been made to Embodiment 1. However, it is also possible to modify Embodiments 2 to 7.

[0070] ***Explanation of operation*** Referring to Figure 5, the processing of the pharmacist work support system 100 according to Embodiment 6 will be described. The processing from step S13 to step S16 differs from that of Embodiment 1. (Step S13: Input Processing) The input unit 111 of the pharmacist work support device 10 inputs the input information as a prompt to the learning model 112, similar to the first embodiment. At this time, the input unit 111 includes an instruction to generate an OAP for SOAP medication history in the command document for prompt generation.

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

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

[0073] ***Effects of Embodiment 8*** As described above, the pharmacist support system 100 according to Embodiment 7 instructs the generation of an OAP (Outline Application Form) for SOAP medication history in addition to generating advice information. As a result, the learning model 112 generates an OAP for SOAP medication history when generating advice information. When an experienced pharmacist provides medication guidance, they consider what the OAP for SOAP medication history will contain before deciding on the content of the guidance. By generating an OAP for SOAP medication history when generating advice information, the learning model 112 will perform a similar thought process to that of an experienced pharmacist when providing medication guidance, making it possible to generate more appropriate advice information.

[0074] Here, when an experienced pharmacist provides medication guidance, they consider what the OAP (Output Application Plan) of the SOAP medication history will be, imagine the reasons for selecting the guidance content, and then decide on the guidance content. Therefore, it is more desirable to add the functions of Embodiment 8 to Embodiment 7, so that in addition to generating advice information, it also instructs the reasons for selecting the advice information and the generation of the OAP (Output Application Plan) of the SOAP medication history. This will allow the system to think in a way that is closer to that of an experienced pharmacist when providing medication guidance, and will enable the generation of more appropriate advice information.

[0075] The pharmacist support system 100 according to Embodiment 8 displays the SOAP medication history (OAP) along with advice information. By referring to the OAP, pharmacists can provide medication guidance while visualizing the information to be recorded in the SOAP medication history (OAP).

[0076] When prioritizing advice information, it is useful to refer to the OAP of the SOAP medication history. Therefore, by adding the functionality of Embodiment 8 to Embodiment 6, it becomes possible to generate the OAP of the SOAP medication history while simultaneously prioritizing the advice information, thereby enabling appropriate prioritization.

[0077] ***Other configurations*** <Modification 4> When generating advice information, pharmacists are likely to place importance on P in the SOAP medication history. Therefore, the input unit 111 may include an instruction in the prompt generation command to generate only P from the SOAP medication history. Furthermore, it is thought that pharmacists prioritize A after P. Therefore, the input unit 111 may include an instruction in the prompt generation command to generate only AP from the SOAP medication history.

[0078] <Modification 5> In Embodiment 1, each functional component was implemented in software. However, in Modification 5, each functional component may be implemented in hardware. The differences between this Modification 5 and Embodiment 1 will be explained below.

[0079] When each functional component is implemented in hardware, the pharmacist work support device 10 includes an electronic circuit 15 instead of a processor 11, memory 12, and storage 13. The electronic circuit 15 is a dedicated circuit that implements the functions of each functional component, as well as the functions of the memory 12 and storage 13.

[0080] Electronic circuits 15 can include single circuits, complex circuits, programmed processors, parallel programmed processors, logic ICs, GAs, ASICs, and FPGAs. GA stands for Gate Array. ASIC stands for Application Specific Integrated Circuit. FPGA stands for Field-Programmable Gate Array. Each functional component may be implemented in a single electronic circuit 15, or each functional component may be implemented by distributing them across multiple electronic circuits 15.

[0081] <Variation 6> As a sixth variation, some of the functional components may be implemented in hardware, while others may be implemented in software.

[0082] The processor 11, memory 12, storage 13, and electronic circuit 15 are collectively referred to as the processing circuit. In other words, the function of each functional component is realized by the processing circuit.

[0083] <Example of a prompt> Refer to Figures 12 to 19 to illustrate an example of a prompt. 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 instructions mentioned above. Constraints correspond to the constraints mentioned above. OutputFormat is information defining the output format. Keys are definitions of terms. Here, the Goal is to generate the questions to be asked during medication guidance, corresponding to the content described in Embodiment 1, as well as the reasons for generation (selection reasons), corresponding to the content described in Embodiment 7, and the SOAP medication history, corresponding to the content described in Embodiment 8. Although the generation of the SOAP medication history's S is also instructed here, since this is before the interview, it is also acceptable to omit S and instruct the generation of only the SOAP.

[0084] Figures 15 to 19 show user prompts. User prompts are patient-defining information and correspond to the Input in system prompts. User prompts define gender and age extracted from patient personal information, symptoms (current diagnosis) extracted from medical questionnaire information, and drug name and quantity extracted from prescription information. In addition, user prompts define information contained in the drug's package insert (precautions, side effect information, efficacy and effects, etc.).

[0085] Refer to Figures 20 to 22 to illustrate examples of responses obtained from the learning model 112. The responses include an example of a SOAP medication history entry, the reason for the generated information, and advice (interview). Note that Figures 15 to 19 only show information on the newly prescribed atorvastatin 5mg tablets among the prescribed medications, but in reality, it is assumed that Zetia 10mg tablets and Lotriga granular capsules 2g were continued prescriptions, and the prescription of Livalo 2mg tablets was discontinued. Ideally, the user prompt would also include information that Zetia 10mg tablets and Lotriga granular capsules 2g were continued prescriptions and the prescription of Livalo 2mg tablets was discontinued.

[0086] <Various aspects of this disclosure> The various aspects of this disclosure are summarized below as an appendix. (Note 1) An input unit that inputs patient personal information indicating the attributes of the patient receiving the prescription, prescription information indicating the contents of the prescription for the said patient, and at least the information of precautions and side effects from the information contained in the package insert of the said drug into a learning model. An output unit that outputs advice information for providing medication guidance to the patient, which is generated by the learning model in correspondence with the patient's personal information, prescription information, and information contained in the attached document, input by the input unit. A pharmacist work support system equipped with the following features. (Note 2) The input unit receives, as prescription information, current prescription information showing the contents of the current prescription and prescription difference information showing the difference between the contents of the current prescription and the contents of the previous prescription. The pharmacist work support system described in Appendix 1. (Note 3) The input unit further inputs questionnaire information showing the patient's answers to the questionnaire. The pharmacist work support system described in Appendix 1 or 2. (Note 4) The input unit further inputs information indicating the content of medication guidance previously given to the patient. A pharmacist work support system described in any one of the items 1 to 3 in the appendix. (Note 5) The input unit further inputs information indicating that an interview with the patient has not been conducted. A pharmacist work support system described in any one of the items 1 through 4 in the appendix. (Note 6) The input unit further inputs statistical information indicating the timing of the onset of side effects for the drug. A pharmacist work support system described in any one of the items 1 through 5 in the appendix. (Note 7) The input unit instructs the learning model to generate the reasons for selecting the advice information, in addition to generating the advice information. The output unit further outputs the reason for selecting the advice information generated by the learning model. A pharmacist work support system described in any one of the items 1 through 6 in the appendix. (Note 8) The input unit instructs the learning model to generate at least a Plan in the 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 the items 1 through 7 in the appendix. (Note 9) The input unit instructs the learning model to generate a specified number of high-priority pieces of advice information from among the 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 the items 1 through 8 in the appendix. (Note 10) The computer inputs patient personal information indicating the attributes of the patient receiving the prescription, prescription information indicating the contents of the prescription for the said patient, and at least the information on precautions and side effects from the information contained in the package insert of the said drug into a learning model. A method for supporting pharmacist work, wherein a computer outputs advice information for providing medication guidance to a patient, which is generated by the learning model in correspondence with the patient's personal information, prescription information, and information contained in the package insert. (Note 11) An input process that inputs patient personal information indicating the attributes of the patient receiving the prescription, prescription information indicating the contents of the prescription for the said patient, and at least the information of precautions and side effects from the information contained in the package insert of the said drug into a learning model. An output process that outputs advice information for providing medication guidance to the patient, which is generated by the learning model in correspondence with the patient's personal information, prescription information, and information contained in the attached document entered through the input process. A pharmacist work support program that enables a computer to function as a pharmacist work support system.

[0087] The embodiments and variations of this disclosure have been described above. Some of these embodiments and variations may be implemented in combination. Alternatively, some or all of them may be implemented in part. However, this disclosure is not limited to the embodiments and variations described above, and various modifications are possible as needed. [Explanation of Symbols]

[0088] 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, 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.

Claims

1. An input unit that inputs patient personal information indicating the attributes of the patient receiving the prescription, prescription information indicating the contents of the prescription for the said patient, and at least the information of precautions and side effects from the information contained in the package insert of the said drug into a learning model. An output unit that outputs advice information for providing medication guidance to the patient, which is generated by the learning model in correspondence with the patient's personal information, prescription information, and information contained in the attached document, input by the input unit. A pharmacist work support system equipped with the following features.

2. The input unit receives, as prescription information, current prescription information showing the contents of the current prescription and prescription difference information showing the difference between the contents of the current prescription and the contents of the previous prescription. The pharmacist work support system according to claim 1.

3. The input unit further inputs questionnaire information showing the patient's answers to the questionnaire. The pharmacist work support system according to claim 1.

4. The input unit further inputs information indicating the content of medication guidance previously given to the patient. The pharmacist work support system according to claim 1.

5. The input unit further inputs information indicating that an interview with the patient has not been conducted. The pharmacist work support system according to claim 1.

6. The input unit further inputs statistical information indicating the timing of the onset of side effects for the drug. The pharmacist work support system according to claim 1.

7. The input unit instructs the learning model to generate the reasons for selecting the advice information, in addition to generating the advice information. The output unit further outputs the reason for selecting the advice information generated by the learning model. The pharmacist work support system according to claim 1.

8. The input unit instructs the learning model to generate at least a Plan in the 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.

9. The input unit instructs the learning model to generate a specified number of high-priority pieces of advice information from among the 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.

10. The computer inputs patient personal information indicating the attributes of the patient receiving the prescription, prescription information indicating the contents of the prescription for the said patient, and at least the information on precautions and side effects from the information contained in the package insert of the said drug into a learning model. A method for supporting pharmacist work, wherein a computer outputs advice information for providing medication guidance to a patient, which is generated by the learning model in correspondence with the patient's personal information, prescription information, and information contained in the package insert.

11. An input process that inputs patient personal information indicating the attributes of the patient receiving the prescription, prescription information indicating the contents of the prescription for the said patient, and at least the information of precautions and side effects from the information contained in the package insert of the said drug into a learning model. An output process that outputs advice information for providing medication guidance to the patient, which is generated by the learning model in correspondence with the patient's personal information, prescription information, and information contained in the attached document entered through the input process. A pharmacist work support program that enables a computer to function as a pharmacist work support system.

Images