Medical record management system, information processing device, information processing method, and program

Abstract

This system provides a medication history management system that reduces the burden on pharmacists in providing medication guidance and creating patient medication records, thereby improving the efficiency of their work. [Solution] A system for managing a patient's medication history, which is a record of medications prescribed to a patient, comprising: a disease prediction module that predicts diseases based on prescription information and drug information; and a guidance plan generation module that generates guidance plans based on the prescription information and the prediction results.

Description

Technical Field

[0001] Embodiments of the present disclosure relate to a medication history management system, an information processing device, an information processing method, and a program.

Background Art

[0002] When a pharmacist provides medication guidance to a patient, a system has been developed that organizes the guidance content based on prescription drug information and creates a medication history.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] However, in conventional medication history management systems, there has been room for improvement in efficiently performing the guidance and medication history creation by pharmacists.

[0005] The problem to be solved by the present invention is to provide a medication history management system capable of reducing the burden on pharmacists in medication guidance and medication history creation and improving the efficiency of operations.

Means for Solving the Problems

[0006] As one aspect of the present disclosure, there is provided a system for managing a medication history, which is a history of medications described in a prescription prescribed to a patient, the system including a disease prediction module that predicts a disease based on prescription information and pharmaceutical information, and a guidance plan generation module that generates a guidance plan based on the prescription information and the prediction result.

Brief Description of the Drawings

[0007] [Figure 1]This is a schematic diagram showing the overall configuration of the medication history management system 1 according to the embodiment. [Figure 2] This is a block diagram showing the functional configuration of Server 200. [Figure 3] This is a flowchart showing the overall processing flow in the medication history management system 1. [Figure 4] This is a flowchart showing the processing flow of the disease prediction process (S100). [Figure 5] This is a flowchart showing the processing flow of the lesson plan generation process (S200). [Figure 6] This is a flowchart showing the processing flow of the medication history generation process (S300). [Figure 7] This figure shows an example of a screen displayed on user terminal 100. [Figure 8] This is a block diagram showing the hardware configuration of computer 90, which is an information processing device. [Modes for carrying out the invention]

[0008] <1. Embodiments> The following describes the medication history management system 1 as an embodiment of the present disclosure, with reference to the drawings. In this specification and in each drawing, elements similar to those already described are denoted by the same reference numerals, and detailed descriptions are not repeated. In this disclosure, the term "user" includes pharmacists who use the medication history management system 1. In this disclosure, "module" may include, for example, a configuration that combines hardware resources implemented by a circuit in a broad sense and software information processing that can be specifically realized by these hardware resources.

[0009] In this disclosure, "medication history" refers to a record of the process of prescription and medication guidance provided to a patient, and may include the name of the prescribed drug, dosage, usage, prescription date, medical department information, patient attribute information, guidance content, medication adherence, and even the presence or absence of side effects and lifestyle precautions. Medication history is a record for consistently understanding a patient's medication adherence and treatment progress, and is an indispensable source of information for ensuring medical safety and providing continuous pharmaceutical management.

[0010] (1.1. Overview of the medication history management system) Referring to Figure 1, an overview of the medication history management system according to this embodiment will be described. The medication history management system comprises a user terminal 100 operated by a user such as a pharmacist, a server 200 that processes prescription information and generates medication history, a claims computer 300 that manages prescription information, and an external AI server 400 that assists in disease prediction and guidance plan generation as needed. These components are connected to each other via a network N so that they can communicate with one another.

[0011] The user terminal 100 is an information processing device for pharmacists to refer to and input patient information, prescription details, and proposed guidance plans. For example, the user terminal 100 could be a tablet, smartphone, or pharmacy terminal. The user inputs prescription information and patient attribute information through the user terminal 100, and this data is transmitted to the server 200.

[0012] Server 200 is an information processing device that performs major processing related to medication history management based on prescription information and input information received from user terminal 100. Specifically, it performs disease prediction processing based on the current prescription information obtained from the claims computer 300 and information from the drug database 222, then generates a guidance plan using the prediction results, and finally generates a medication history reflecting the user's input. The details of the functional configuration of Server 200 are described in detail with reference to Figure 2.

[0013] The Receipt Computer 300 is an information processing device that creates and manages so-called receipts (statements of medical and dispensing fees). The Receipt Computer 300 accepts input of prescription information, information on medical and dispensing procedures, insurance information, etc., from medical institutions and pharmacies, and supports the process of generating statements for medical fee claims.

[0014] The external AI server 400 is an information processing device that functions as a server equipped with a Generative Artificial Intelligence (Generative AI) model, and performs auxiliary processing for disease prediction and guidance plan generation. For example, it performs processing to predict diseases based on prescription drug information and medical department information, or processing to generate appropriate guidance plans based on multiple drug information. Server 200 performs these processes in cooperation with the external AI server 400 as needed.

[0015] For example, the external AI server 400 may be an LLM (Large-Scale Language Model) including ChatGPT or Gemini, or it may be any other general-purpose generative AI model. The external AI server 400 has the function of generating appropriate output in response to input prompts. This configuration allows for the dynamic generation of guidance plans and medication history information based on the patient's attributes and prescriptions, based on generation parameters written in natural language, enabling flexible and highly accurate medication history management support.

[0016] (1.2. Functional configuration of Server 200) Referring to Figure 2, the functional configuration of the server 200 will be described. The server 200 comprises a control unit 210 and a storage unit 220. The control unit 210 includes a disease prediction module 211, a lesson plan generation module 212, and a medication history generation module 213. These modules function by the control unit 210 reading programs and data stored in the storage unit 220.

[0017] The disease prediction module 211 executes a process of predicting a disease corresponding to a prescribed medicine based on the prescription information acquired from the prescription computer 300 and the medicine information stored in the medicine database 222. Here, efficacy information of the medicine and information on the department of medicine are used for disease prediction, and the configuration is such that a disease can be specified in consideration of combinations of multiple medicines.

[0018] The guidance plan generation module 212 is responsible for a process of generating a guidance plan for the patient using the current prescription information, the prediction result by the disease prediction module 211, and past prescription information. Specifically, the previous prescription is identified by scoring based on the degree of match with past prescriptions, the prescription change points are extracted, and then guidance contents based on medicine information are combined to generate a guidance plan in the SOAP format (S / subjective: subjective information, O / objective: objective information, A / assessment: evaluation, P / plan: treatment plan).

[0019] The medication history generation module 213 accepts user input for the guidance plan output by the guidance plan generation module 212 and is responsible for a process of generating a medication history. The medication history is automatically generated before the guidance and can be modified after the guidance. It also has a correction function by voice input and can analyze the user's speech content and reflect it in the medication history.

[0020] The storage unit 220 is a storage device that accumulates various data in the server 200. As an example, the storage unit 220 includes a patient information database 221 and a medicine database 222.

[0021] The patient information database 221 stores the patient's identification information, age, gender, past history, allergy information, prescription history, guidance contents, etc. Thereby, the server 200 can execute processing while referring to the prescription status and guidance history for each patient.

[0022] The drug database 222 stores information such as the name of the drug, its efficacy, dosage, side effects, interactions, and precautions. This allows the server 200 to retrieve information about prescription drugs and use it for processing by the disease prediction module 211 and the guidance plan generation module 212. (1.3. Processing Procedure) Refer to Figures 3 to 6 to explain the processing flow in the medication history management system. First, refer to Figure 3 to explain the overall flow.

[0023] (1.3.1. Overall Flow) Refer to Figure 3 to explain the overall processing flow in the medication history management system. Figure 3 is a flowchart showing the processing flow of the three main processes performed in the system: the disease prediction process (step S100), the guidance plan generation process (step S200), and the medication history generation process (step S300). Each of these processes includes disease prediction processing based on the patient's prescription information, guidance plan generation processing based on the prediction results and prescription information, and medication history generation processing that reflects user input.

[0024] In the disease prediction process (step S100), a process is executed to predict the diseases that a patient may have, based on prescription information obtained from the claims computer and drug information stored in the drug database 222. For example, disease candidates are predicted by considering combinations of multiple drugs, medical department, patient attributes, etc. Through this process, pharmacists can understand the background of diseases that are difficult to grasp from prescription information alone. Details of this process will be described later with reference to Figure 4.

[0025] In the guidance plan generation process (step S200), a guidance plan to be presented to the patient is generated using the current prescription information, the prediction results from the disease prediction process (step S100), and the results of comparison with past prescription information. Specifically, the previous prescription is identified based on the degree of agreement with past prescriptions, and the differences (additions, deletions, changes, and continuations) between it and the current prescription are extracted. Furthermore, a guidance plan including lifestyle guidance and points to note is created based on drug information and patient attributes. Details of this process will be described later with reference to Figure 5.

[0026] In the medication history generation process (step S300), the medication history is automatically generated based on the guidance plan. Furthermore, input from the pharmacist after guidance and the results of voice data analysis are incorporated to finalize the medication history. The generated medication history is saved in a standard format such as SOAP and used for future prescriptions and medication guidance. This process reduces the burden on pharmacists in creating medication history and enables accurate and efficient medication history management. Details of this process will be described later with reference to Figure 6.

[0027] (1.3.2. Flow of the disease prediction process) Referring to Figure 4, the detailed processing flow of the disease prediction process (step S100) will be explained. The disease prediction process is executed by the disease prediction module 211 of the server 200. In this step, prescription data is acquired, drug information is referenced, and the process of predicting diseases related to the patient is carried out in stages. This makes it possible to predict disease backgrounds with greater accuracy than before, when pharmacists had empirically grasped them from prescription information.

[0028] In step S110, the disease prediction module 211 retrieves the prescription data from the claims computer 300. The prescription data includes patient identification information, medical department, YJ code of the prescribed drug (identification information for identifying the drug), usage, and dosage. For example, this process utilizes API processing based on NSIPS (National Standards for Prescription Information), and the server 200 receives the prescription data transmitted in NSIPS format and stores it in the storage unit 220. By using this standardized format, prescription data from different medical institutions and pharmacies can be handled uniformly.

[0029] In step S120, the disease prediction module 211 refers to the drug database 222 based on the YJ code of the acquired prescription drug. Here, information such as efficacy, indications, interactions, and precautions for each drug is obtained. For example, if an antibacterial drug is included, infectious diseases are listed as candidates, and if an antihypertensive drug or diuretic is included, hypertension and heart disease are listed as candidates. In this way, the relationship between the prescription and the disease is considered by referring to the drug information.

[0030] Furthermore, the disease prediction module 211 more accurately predicts the use of a drug by also referring to information about the medical department. For example, even if an antibiotic is prescribed, if the medical department is dentistry, dental diseases such as "prevention of infection after tooth extraction" or "prevention of suppuration after periodontal disease treatment" will be predicted. On the other hand, if the same antibiotic is prescribed in respiratory medicine, respiratory diseases such as "bronchitis" or "pneumonia" will be predicted. Also, if an antihistamine is prescribed, if the medical department is otolaryngology, "allergic rhinitis" will be predicted as a candidate disease; if it is dermatology, "urticaria" or "contact dermatitis" will be predicted; and if it is respiratory medicine, "bronchial asthma" will be predicted as a candidate disease. In this way, even with the same drug, the accuracy of disease prediction can be improved by associating it with the medical department.

[0031] In step S130, the disease prediction module 211 passes prescription drug combinations, medical departments, and patient attribute information (age, gender, etc.) to the external AI server 400, which then predicts the disease. For example, if an anti-asthma drug is prescribed to a child, "childhood asthma" is listed as a candidate, and if an anti-dementia drug is prescribed to an elderly person, "Alzheimer's disease" is among the candidates. Similarly, if an antibiotic is prescribed in an ENT clinic, "sinusitis" or "otitis media" is predicted, and if it is prescribed in a dermatology clinic, "superficial skin infection" (or "deep skin infection") is predicted. The prediction results output from the external AI server 400 are scored to rank multiple disease candidates based on their relevance, and the top candidates are passed to the guidance plan generation process (S200).

[0032] Thus, the disease prediction process (step S100) involves a series of processes, from acquiring prescription data to referencing drug information, to predicting potential diseases. This allows pharmacists to quickly understand the patient's disease background from the prescription content and obtain information that forms the basis for providing appropriate medication guidance in the subsequent guidance plan generation process.

[0033] (1.3.3. Flow of the Lesson Plan Generation Process) Referring to Figure 5, the detailed processing flow of the lesson plan generation process (step S200) will be explained. The lesson plan generation process is executed by the lesson plan generation module 212 of the server 200. In this process, past prescription information is referenced to identify the previous prescription, the differences with the current prescription are extracted, and then a lesson plan to be presented to the patient is generated. This allows pharmacists to quickly and easily grasp the key points of prescription changes and efficiently provide appropriate medication guidance to patients.

[0034] In step S210, the lesson plan generation module 212 retrieves past prescription data for the same patient from the patient information database 221. The past prescription data is extracted up to a predetermined number, such as a maximum of 5 records, in order of creation date and time, and is used for comparison with the current prescription. The retrieved data includes prescription date and time, medical department information, medical institution information, YJ code of the prescribed drug, and dosage and administration. For example, if a patient has had three most recent prescriptions issued by pediatrics, internal medicine, and otolaryngology, this prescription information is retrieved in chronological order and formatted in a way that allows for comparison with the current prescription.

[0035] In step S220, the lesson plan generation module 212 performs a scoring process on past prescriptions to identify the previous prescription. Specifically, it evaluates the match between past prescription data and the medical institution, the department, and the prescribed drug, and identifies prescription data whose total score exceeds a predetermined threshold as the previous prescription. For example, 2 points may be awarded if the medical institution matches, 2 points if the department matches, and 1 point if the YJ code matches. For example, if antihypertensive drug A and diuretic B, which were prescribed in the internal medicine department of a certain hospital, are also prescribed in the same hospital's internal medicine department in the current prescription, the score will exceed the threshold after adding points for each matching condition, and the prescription will be identified as the previous prescription. In this way, when the nature of the prescription content differs, such as between acute and chronic diseases, prescriptions that are closer in chronological order may not necessarily be the appropriate previous prescription, but by using this scoring method, it is possible to select a clinically appropriate previous prescription.

[0036] In step S230, the instruction plan generation module 212 compares the identified previous prescription with the current prescription and extracts the differences. The differences are categorized into additions, deletions, changes in dosage, or continuation of medications, and are organized as changes. For example, if an antibiotic included in the previous prescription is deleted and an anti-inflammatory drug is added instead, it will be recorded as "antibiotic deletion" and "anti-inflammatory drug addition." Also, if the dosage of an antihypertensive drug is changed from "1 tablet per day" to "2 tablets per day," it will be classified as "antihypertensive drug dosage change." By organizing the differences into specific categories in this way, pharmacists can easily grasp the key points to explain to patients, contributing to the efficiency and standardization of medication guidance.

[0037] In step S240, the guidance plan generation module 212 passes the current prescription, previous prescription, extracted changes, disease prediction information, patient attribute information, etc., to the external AI server 400, which then generates a guidance plan to present to the patient. The guidance plan is structured, for example, based on SOAP format. For example, if a patient complains of frequent dizziness (S), the high blood pressure readings and the inclusion of antihypertensive drugs in the prescription (O), the assessment of hypertension based on these (A), and advice on medication adherence and lifestyle improvements (P) are integrated and compiled into a guidance plan. Furthermore, information on precautions regarding side effects and drug interactions is also automatically generated, allowing pharmacists to obtain comprehensive medication guidance plans in a short amount of time.

[0038] Thus, the guidance plan generation process (step S200) is executed in a single, continuous flow, from obtaining past prescriptions to identifying the previous prescription, extracting differences, and generating the guidance plan. In particular, by using a scoring process to identify the previous prescription, it is possible to achieve a highly valid comparison based on the degree of agreement between medical institutions and departments, and the continuity of medications, rather than a simple time-series comparison of prescription information. As a result, it is possible to provide specific and patient-specific guidance based on prescription changes, thereby increasing the reliability of pharmacies using the medication history management system.

[0039] (1.3.4. Flow of the medication history generation process) Referring to Figure 6, the detailed processing flow of the medication history generation process (step S300) will be explained. The medication history generation process is executed by the medication history generation module 213 of the server 200. In this process, the guidance plan output from the guidance plan generation process (S200) is obtained, additional information input from the pharmacist is accepted, and then a medication history for each patient is generated. As a result, the medication history is finalized as a comprehensive record that reflects not only prescription information and disease prediction information, but also the actual content of medication guidance.

[0040] In step S310, the medication history generation module 213 retrieves the instruction plan output from the instruction plan generation process. The instruction plan includes the current prescription, the comparison results with the previous prescription, the extracted changes, and the disease prediction results. For example, if a change in the dosage of antihypertensive medication is detected, the instruction content "Increase the dosage of antihypertensive medication from once a day to twice a day" will be reflected in the instruction plan and will become the basic data for generating the medication history. This ensures that specific explanations related to prescription changes are reliably incorporated into the medication history.

[0041] In step S320, the medication history generation module 213 accepts additional information input from the pharmacist. This additional information may include "prescription type" (initial prescription, DO prescription (continuing prescription), acute phase, medication change, etc.), as well as medication adherence, changes in physical condition, presence or absence of side effects, and presence or absence of concomitant medications. For example, on the display screen 50 shown in Figure 7, the pharmacist can specify options such as "initial prescription" or "medication change," and can also select "yes" or "no" regarding side effects. In addition, comments regarding specific symptoms or lifestyle habits can be added to the special notes input field 55 as needed. This ensures that the actual medical situation of each patient is reflected in detail in the medication history.

[0042] In step S330, the medication history generation module 213 passes the acquired guidance plan and additional information from the pharmacist to the external AI server 400, which then generates the medication history. At this time, the medication history is constructed according to a standard record format such as SOAP format. For example, if a patient complains that "their nighttime cough has increased recently," this is recorded as S (subjective information), and the prescription details and the presence or absence of side effects are added as O (objective information). Furthermore, based on disease prediction, an A (assessment) is added stating "possibility of asthma relapse," and advice regarding medication adherence and lifestyle guidance is recorded as P (plan). The generated medication history can be modified or added to by the pharmacist as needed, and it is also possible to automatically reflect voice information by recording voice.

[0043] Thus, the medication history generation process (step S300) is based on the instruction plan, incorporates the pharmacist's specification of prescription type and input of additional information, and finally completes and saves the medication history. This allows the medication history to comprehensively record each patient's medical background and medication instruction content, thereby enhancing the effectiveness of the entire medication history management system.

[0044] (1.4. Screen example) Figure 7 shows an example of a display screen 50 displayed on the user terminal 100. The display screen 50 is configured to allow pharmacists to efficiently create patient medication histories after providing medication guidance to patients. As an example, the display screen 50 includes a prescription history display section 51, a current prescription display section 52, a guidance plan display section 53, a medication history input section 54, a special notes input field 55, a medication history input support section 56, a prescription type selection section 57, an AI support button 58, and a voice recording display field 59.

[0045] The prescription history display unit 51 is an area that displays a list of the patient's past prescription history. The pharmacist can compare the current prescription with a specific prescription by selecting it from the list of past prescriptions. In the illustrated example, "No previous prescription history" is displayed, but if a previous prescription exists, the drug name and prescription date will be displayed in chronological order.

[0046] The prescription display section 52 is the area that displays newly issued prescription information to the patient. For example, basic information such as the prescription date, clinic name, prescribing physician's name, prescribed drug name, dosage form, and dosage is displayed. For example, it is displayed specifically as "Prescribed drug: XXX syrup (100 mL)," so the pharmacist can immediately understand the details of the prescription.

[0047] The instruction plan display section 53 is an area that displays the instruction plan generated by the instruction plan generation process. For example, it may include lifestyle precautions and precautions regarding side effects, such as "Take with plenty of water in the morning" and "Avoid driving as it may cause drowsiness." The pharmacist can use this instruction plan to explain the medication to the patient and make revisions or additions as needed.

[0048] The medication history input section 54 is an area for inputting essential information for each patient's medication history, such as medication adherence, changes in physical condition, and the presence or absence of side effects. The display screen 50 has confirmation items such as "medication adherence," "changes in physical condition," and "occurrence of side effects," and pharmacists can input the relevant items in a checkbox format. In this way, the standardized input format ensures the standardization of records.

[0049] The special notes input field 55 is an area for recording patient-specific situations or free-form entries that do not fit into the standard items. For example, it can be used to record patient-specific notes such as "The patient has a strong bitter taste when taking medication and tends to refuse to take it." A function for inserting pre-written phrases is also provided to assist with input, allowing pharmacists to efficiently recall frequently used examples.

[0050] The medication history input support unit 56 is a UI (User Interface) area that supports medication history creation using an external AI server 400. When a pharmacist inputs general keywords and the patient's condition and then presses the AI ​​support button 58, a draft medication history document is generated and displayed based on the input. For example, if the input is "Medication status: Good, Special notes: Difficulty taking after meals," a sentence such as "Medication status is generally good, but additional guidance on medication timing was given because taking after meals is difficult" will be displayed. This significantly reduces the workload of creating medication history.

[0051] The prescription type selection section 57 is an area for selecting and inputting the type of prescription. Options such as "Initial Prescription," "Do Prescription," "Acute Care Prescription," and "Medication Change" are provided, and pharmacists can select the appropriate prescription type to reflect that information in the patient's medication history. This makes it possible to clearly record the background and context of the prescription.

[0052] Furthermore, the prescription type entered in the prescription type selection unit 57 may also be reflected in the disease prediction process and previous prescription scoring process described above. Specifically, the disease prediction module 211 performs score adjustments that take into account the treatment progress and the continuity of the prescription when scoring the previous prescription. For example, if the pharmacist selects "chronic prescription," the disease prediction module 211 highly values ​​the continued use of the drug and adjusts the score upward considering the persistence of the disease. On the other hand, if "acute prescription" is selected, the score is adjusted downward considering the possibility of recurrence or new onset. In this way, by utilizing prescription classifications based on medication history information in the scoring process, it becomes possible to perform disease predictions that are in line with the actual treatment progress and clinical judgments.

[0053] The voice recording display area 59 is an area for the pharmacist to assist with input operations, and voice recording starts when the recording start button 59a is pressed. The recorded content is automatically transcribed, and the text is displayed in the voice recording display area 59. This allows the pharmacist to record the content of patient instruction in a conversational format, and later revise and add supplementary information to the text.

[0054] Thus, the display screen 50 includes features such as comparing past and current prescriptions, referencing instruction plans, recording required input items, selecting prescription types, and AI-powered input assistance, as well as input support through voice recording. As a result, pharmacists can create comprehensive and standardized patient records in a short amount of time, improving the convenience and practicality of the patient record management system.

[0055] (1.5. Hardware configuration of information processing equipment) Referring to Figure 8, the hardware configuration of an information processing device used as a server 200, etc., will be described. As an example, the information processing device is implemented by the computer 90 shown in Figure 8. The computer 90 may include a CPU 91, ROM 92, RAM 93, storage 94, input interface 95, output interface 96, and communication interface 97.

[0056] The CPU 91 functions as a processor that executes processing. Specifically, the CPU 91 uses the RAM 93 as work memory and the ROM 92 executes programs stored in at least one of the storage 94. During program execution, the CPU 91 controls each component via the system bus 98 and performs various processes. As an example, the CPU 91 functions as a control unit 210.

[0057] ROM92 stores programs that control the operation of computer 90. ROM92 contains the programs necessary for computer 90 to perform each of the processes described above. RAM93 functions as a memory area where the programs stored in ROM92 are loaded.

[0058] The storage 94 stores data necessary for program execution and data obtained through program execution. The storage 94 includes one or more selected from Hard Disk Drives (HDDs) and Solid State Drives (SSDs). As an example, the storage 94 functions as a memory unit 220.

[0059] The input interface (I / F) 95 can connect the computer 90 and the input device 95a. The input interface 95 is, for example, a serial bus interface such as USB. The CPU 91 can read various data from the input device 95a via the input interface 95.

[0060] The output interface (I / F) 96 can connect the computer 90 to the output device 96a. The output interface 96 is a video output interface such as Digital Visual Interface (DVI) or High-Definition Multimedia Interface (HDMI®). The CPU 91 can transmit data to the output device 96a via the output interface 96 and cause the output device 96a to output data.

[0061] The input device 95a is an example of an input means and includes one or more selected from a mouse, keyboard, microphone (voice input), and touchpad. The output device 96a is an example of an output means and includes one or more selected from a display, projector, printer, and speaker. Devices that have the functions of both the input device 95a and the output device 96a, such as a touch panel, may also be used.

[0062] The communication interface (I / F) 97 allows the computer 90 to connect with an external server 97a located outside the computer 90. The communication interface 97 is, for example, a network card such as a LAN card. The CPU 91 can read various data from the external server 97a via the communication interface 97.

[0063] Each process performed by the user terminal 100 or the server 200 may be implemented by a single computer 90, or by the cooperation of multiple computers 90.

[0064] The processing of the various data described above may be recorded as a program that can be executed by a computer on a magnetic disk (flexible disk and hard disk, etc.), an optical disk (CD-ROM, CD-R, CD-RW, DVD-ROM, DVD±R, DVD±RW, etc.), a semiconductor memory, or another non-transitory computer-readable storage medium.

[0065] For example, information recorded on a recording medium can be read by a computer (or embedded system). The recording format (storage format) of the recording medium is arbitrary. For example, a computer reads a program from the recording medium and, based on this program, causes the processor to execute the instructions written in the program. In a computer, program acquisition (or reading) may be performed via a network.

[0066] (1.6.Summary) As described above, the medication history management system 1 includes a disease prediction module 211 that predicts diseases based on prescription information and drug information, a guidance plan generation module 212 that generates guidance plans based on the disease prediction results and comparison with past prescriptions, and a medication history generation module 213 that creates medication history based on the generated guidance plans and user input. This allows pharmacists to easily obtain guidance plans optimized for each patient and to create medication history efficiently, significantly improving the efficiency of medication guidance work.

[0067] Furthermore, the lesson plan generation module 212 compares the current prescription with past prescriptions and performs a scoring process to identify the previous prescription. This scoring process is based on whether at least one of the following matches: the medical institution, the clinical department, and the identification information (YJ code) used to identify the medication. For example, if a prescription is issued at the same clinic and clinical department, and the YJ codes of the main medications match, a high score will be assigned, making it easier to identify it as the previous prescription. This allows for accurate extraction of prescription continuations, discontinuations, and changes, and enables the presentation of a lesson plan tailored to the patient's treatment progress.

[0068] Furthermore, the medication history generation module 213 is configured to accept the type of prescription (initial prescription, Do prescription, acute care prescription, drug change, etc.) as input from the user. As a result, the background and context of the prescription are explicitly recorded in the medication history, making it easy for subsequent pharmacists or other personnel to understand the course of treatment when they refer to the medication history.

[0069] Furthermore, the medication history generation module 213 is configured to generate a draft of the medication history before the guidance session and to accept revisions afterward. This allows pharmacists to efficiently provide guidance based on pre-prepared medication histories and to immediately reflect revisions that reflect the actual guidance content, thereby increasing the accuracy and practicality of the medication history.

[0070] Furthermore, the medication history generation module 213 may also include a function to record the content of medication guidance given by the pharmacist as audio, convert that audio data into text, and reflect it in the medication history. This reduces the effort required for keyboard input for the pharmacist while faithfully reflecting the actual conversation in the medication history. In particular, it improves the comprehensiveness and reliability of the medication history because it can record without losing the nuances of explanations and lifestyle guidance given to the patient.

[0071] Thus, the medication history management system of the present invention includes disease prediction based on prescription information, identification of previous prescriptions and extraction of differences, automatic generation of guidance plans, and medication history creation that can be generated in advance or modified afterward. As a result, pharmacists can provide consistent and efficient medication guidance to patients, thereby improving the sophistication of medication history management and enhancing the quality of medical care.

[0072] <2. Other Embodiments> The medication history management system 1 according to this embodiment has been described above, but the application of the technical idea of ​​this disclosure is not limited to the above embodiment. For example, although the above embodiment was described using medication history management based on prescriptions in a pharmacy as an example, the technical idea of ​​the present invention is not limited to this and can be applied to a variety of other medical information management systems.

[0073] Specifically, the medication history management system described in this disclosure can be applied to the following cases, for example: • Support for creating patient education records in home healthcare and home visits. • Sharing of prescription and medication information and integrated medication history management among multiple medical departments within the hospital. • Purchase of over-the-counter medications and management of medication usage records to support self-medication. • Support for standardization of patient medication history data used in adverse event monitoring and post-marketing surveillance in pharmaceutical companies. • Long-term monitoring of patient treatment progress through integration with electronic medical record systems.

[0074] These applications all generate guidance content and records based on prescription information and medication adherence related to the patient, and can utilize the disease prediction module, guidance plan generation module, and medication history generation module disclosed herein. Furthermore, by adjusting the data input items (medication confirmation, changes in physical condition, occurrence of side effects, etc.) and record format according to the target medical setting and purpose of use, it is possible to support a wider range of medical services.

[0075] Furthermore, the technical concept of this disclosure can be applied in both the pre-instruction medication history generation stage and the post-instruction medication history revision stage. Specifically, a draft medication history may be automatically generated before patient instruction using instruction plans generated based on disease prediction results and prescription type information, or it may be applied to the process of revising and updating the medication history after instruction to reflect the actual instruction content and voice input data. This enables increased efficiency in both pre-instruction preparation and post-instruction recording in pharmacists' instruction work, while also allowing for use tailored to on-site operations.

[0076] Furthermore, while the above embodiment illustrates a configuration in which the server 200 comprises various components such as a disease prediction module 211, a lesson plan generation module 212, a medication history generation module 213, and a storage unit 220, and centrally executes each of these processes, the system is not limited to this configuration. For example, some or all of these processes may be distributed to the user terminal 100, and temporary storage of medication history and transcription processing using voice recordings may be performed locally. Alternatively, the system may be configured to enhance cooperation with an external AI server 400, and entrust the main parts of disease prediction and lesson plan generation to other external servers.

[0077] While several embodiments of this disclosure have been illustrated above, these embodiments are presented as examples only and are not intended to limit the scope of the invention. These novel embodiments can be implemented in various other forms, and various omissions, substitutions, and modifications can be made without departing from the spirit of the invention. These embodiments and their variations are included in the scope and spirit of the invention, as well as in the claims of the invention and its equivalents. Furthermore, the embodiments described above can be implemented in combination with each other. [Explanation of Symbols]

[0078] 1: Medication history management system, 50: Display screen, 51: Prescription history display unit, 52: Prescription display unit, 53: Guidance plan display unit, 54: Medication history input unit, 55: Special notes input field, 56: Medication history input support unit, 57: Prescription type selection unit, 58: AI support button, 59: Voice recording display field, 59a: Recording start button, 90: Computer, 91: CPU, 92: ROM, 93: RAM, 94: Storage, 95: Input interface, 95a: Input device, 96: Output interface, 96a: Output device, 97: Communication interface, 97a: External server, 98: System bus, 100: User terminal, 200: Server, 210: Control unit, 211: Disease prediction module, 212: Guidance plan generation module, 213: Medication history generation module, 220: Memory unit, 221: Patient information database, 222: Drug database, 300: Receipt computer, 400: External AI server

Claims

1. A system for managing a patient's medication history, which records the progress of prescriptions and medication guidance provided to the patient, A disease prediction module that predicts the disease associated with this prescription based on prescription information obtained from the prescription computer and information about the medication, A guidance plan generation module generates a guidance plan as a draft of medication guidance for the patient before the medication guidance, based on the prescription information and the predicted disease information. Equipped with, The aforementioned treatment plan generation module is a medication history management system that compares the current prescription information with a predetermined number of past prescription information entries in chronological order, and identifies previous prescription information related to a specific disease in accordance with the treatment progress, based on whether there is a match between the current and past prescription information for at least one of the identifying information for identifying the medical institution, department, and drug, and the prescription type in the said prescription information.

2. The medication history management system according to claim 1, further comprising a medication history generation module that receives user input for the aforementioned lesson plan and generates the aforementioned medication history.

3. The medication history management system according to claim 2, wherein the lesson plan generation module scores the past prescription information, and if the score calculated by the scoring exceeds a predetermined threshold, the prescription information corresponding to the score is identified as the previous prescription information.

4. The medication history management system according to claim 3, wherein the lesson plan generation module performs the scoring based on whether or not there is a match between the current and past prescription information and at least one of the identifying information for identifying the medical institution, the medical department, and the pharmaceutical product.

5. The medication history generation module receives input from the user regarding the type of prescription related to the current prescription information, as described in claim 2.

6. The aforementioned medication history generation module is: The patient's medical history is generated before the user provides instructions to the patient. The medication history management system according to claim 2, which accepts the modification of the medication history after the user has provided guidance to the patient.

7. The aforementioned medication history generation module provides the user with A medication history management system according to claim 2, which receives input of voice data relating to the content of the instructions given to the patient and modifies the generated medication history.

8. It comprises a control unit and a memory unit, The control unit, A disease prediction module that predicts the disease associated with this prescription based on prescription information obtained from the prescription computer and information about the medication, The system includes a guidance plan generation module that generates a guidance plan as a draft of medication guidance for the patient before the medication guidance is given, based on the prescription information and the predicted disease information. The aforementioned lesson plan generation module is an information processing device that compares the current prescription information with a predetermined number of past prescription information entries in chronological order of creation date, and identifies previous prescription information related to a specific disease in accordance with the course of treatment, based on whether there is a match between the current and past prescription information for at least one of the identifying information for identifying the medical institution, medical department, and drug, and the prescription type in the said prescription information.

9. A method for causing an information processing device, which comprises a control unit and a storage unit, to perform processing, The control unit, A disease prediction process is performed to predict the disease associated with this prescription, based on the prescription information obtained from the prescription computer and information about the medication. Based on the prescription information and the predicted disease information, a guidance plan generation process is performed to generate a guidance plan as a draft for medication guidance to the patient before the medication guidance is given. The aforementioned lesson plan generation process involves the control unit comparing the current prescription information with a predetermined number of past prescription information records in reverse chronological order of creation date, and identifying previous prescription information related to a specific disease in accordance with the treatment progress based on whether at least one of the identifying information records for identifying the medical institution, medical department, and pharmaceutical product matches between the current and past prescription information, and the prescription type in the prescription information.

10. A program that causes an information processing device, which comprises a control unit and a storage unit, to perform processing, The control unit, A disease prediction process is performed to predict the disease associated with this prescription, based on the prescription information obtained from the prescription computer and information about the medication. Based on the prescription information and the predicted disease information, a guidance plan generation process is executed to generate a guidance plan as a draft for medication guidance to the patient before the medication guidance is provided. The aforementioned lesson plan generation process includes a program that causes the control unit to compare the current prescription information with a predetermined number of past prescription information entries in reverse chronological order of creation date, and to identify the previous prescription information related to a specific disease in accordance with the treatment progress, based on whether there is a match between the current and past prescription information for at least one of the identifying information for identifying the medical institution, medical department, and pharmaceutical product, and based on the prescription type in the prescription information.

Images