Processing apparatus, processing program, and processing method

Abstract

The present invention provides a processing device, a processing program, and a processing method that enable the more efficient generation of medical documents. [Solution] The system determines the type of medical document to be created from among medical documents categorized based on multiple types, outputs a first screen containing first medical information which is medical information obtained based on the determined type from among multiple medical information associated with one or more subjects, receives editing instructions from the user for the medical information output on the first screen, and executes a process to output a second screen containing a medical document generated based on at least the determined type and second medical information which is medical information edited based on the instruction input.

Description

Technical Field

[0001] The present disclosure relates to a processing device, a processing program, and a processing method capable of generating medical documents.

Background Art

[0002] Conventionally, systems for improving the work efficiency of doctors have been considered. In Patent Document 1, a first processing unit that displays information on a plurality of items registered in advance in association with preventive vaccinations on an input support screen, and based on a user operation on the input support screen, records information on one or more of the items of the preventive vaccination displayed on the input support screen in an electronic medical record. An electronic medical record system is described that includes a second processing unit.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] Therefore, based on the above technologies, an object of the present disclosure is to provide a processing device, a processing program, and a processing method capable of more efficiently generating medical documents.

Means for Solving the Problems

[0005] According to one aspect of the present disclosure, a processing device is provided which comprises at least one processor, wherein the at least one processor is configured to determine a type to be created from among medical documents classified according to a plurality of types, output a first screen including first medical information which is medical information obtained from among a plurality of medical information associated with one or more subjects based on the determined type, receive an editing instruction input from a user for the medical information output on the first screen, and execute a process to output a second screen including a medical document generated based on at least the determined type and second medical information which is medical information edited based on the instruction input.

[0006] According to one aspect of this disclosure, a processing program is provided for a computer having at least one processor, which determines a type of medical document to be created from among medical documents classified according to a plurality of types, outputs a first screen containing first medical information which is medical information obtained from among a plurality of medical information associated with one or more subjects based on the determined type, receives editing instructions from a user for the medical information output on the first screen, and outputs a second screen containing a medical document generated based on at least the determined type and second medical information which is medical information edited based on the instruction input.

[0007] According to one aspect of this disclosure, a processing method is provided which is performed by at least one processor in a computer having at least one processor, and includes the steps of: determining a type of medical document to be created from among medical documents classified according to a plurality of types; outputting a first screen including first medical information which is medical information obtained from among a plurality of medical information associated with one or more subjects based on the determined type; receiving an editing instruction input from a user for the medical information output on the first screen; and outputting a second screen including a medical document generated based on at least the determined type and second medical information which is medical information edited based on the instruction input. [Effects of the Invention]

[0008] This disclosure provides a processing device, a processing program, and a processing method that can generate medical documents more efficiently.

[0009] The effects described above are merely illustrative for the sake of explanation and are not limiting. In addition to, or in lieu of, any other effects described herein or that would be obvious to those skilled in the art may be achieved. [Brief explanation of the drawing]

[0010] [Figure 1A] Figure 1A is a diagram showing an overview of the processing performed by processing system 1 according to one embodiment of the present disclosure. [Figure 1B] Figure 1B is a block diagram showing the configuration of a processing system 1 according to one embodiment of the present disclosure. [Figure 2] Figure 2 is a block diagram showing the configuration of a processing apparatus 100 according to one embodiment of the present disclosure. [Figure 3A] Figure 3A is a conceptual diagram showing a target management table stored in an information provision device 200 according to one embodiment of the present disclosure. [Figure 3B]Figure 3B is a conceptual diagram showing a template management table stored in a processing device 100 according to one embodiment of the present disclosure. [Figure 3C] Figure 3C shows an example of a user attribute management table stored in a processing device 100 according to one embodiment of the present disclosure. [Figure 4A] Figure 4A is a diagram showing the processing flow performed in the processing apparatus 100 according to one embodiment of the present disclosure. [Figure 4B] Figure 4B is a diagram showing the processing flow performed in the processing apparatus 100 according to one embodiment of the present disclosure. [Figure 4C] Figure 4C is a diagram showing the processing flow performed in the processing apparatus 100 according to one embodiment of the present disclosure. [Figure 5] Figure 5 shows an example of medical information according to one embodiment of the present disclosure. [Figure 6] Figure 6 shows an example of template information processed in the processing apparatus 100 according to one embodiment of the present disclosure. [Figure 7] Figure 7 shows an example of query information processed in the processing apparatus 100 according to one embodiment of the present disclosure. [Figure 8] Figure 8 shows an example of a medical document output by a processing device 100 according to one embodiment of the present disclosure. [Figure 9A] Figure 9A is a diagram showing an example of a screen output from a processing device 100 according to one embodiment of the present disclosure. [Figure 9B] Figure 9B shows an example of a screen output from a processing apparatus 100 according to one embodiment of the present disclosure. [Figure 9C] Figure 9C shows an example of a screen output from a processing device 100 according to one embodiment of the present disclosure. [Modes for carrying out the invention]

[0011] 1. Overview of Processing System 1 FIG. 1A is a diagram showing an outline of processing executed by a processing system 1 according to an embodiment of the present disclosure. According to FIG. 1A, the processing system 1 according to the present disclosure is used to generate a medical document based on medical information obtained from an information providing device such as a medical device, an interview device, an electronic medical record device, a PACS (Picture Archiving and Communication Systems), a medical staff terminal device that can be used by medical staff, a subject terminal device that can be used by a subject, or a database device in which information input to these devices is recorded.

[0012] The processing system 1 acquires various types of information such as subject attribute information, arrival information, interview information, findings information, diagnosis information, or discharge information from at least any one of a medical device, an interview device, an electronic medical record device, a PACS, a medical staff terminal device, a subject terminal device, and a database device that function as information providing devices. Then, medical information (first medical information) necessary for generating a desired medical document is extracted from the acquired information. The processing related to this extraction is performed using, for example, a first learned model. When the extraction of medical information is performed, a medical document is generated using the extracted medical information. The processing related to this generation is performed using, for example, a second learned model.

[0013] That is, the processing system 1 can perform processing related to the extraction of medical information required for the generation of a medical document and processing related to the generation of a medical document using the extracted medical information. For example, when medical staff, etc. need to input various types of information and create sentences when generating a medical document, it becomes possible to more efficiently generate a medical document by using the processing system 1.

[0014] The processing system 1 described herein is typically used in medical-related institutions. Such institutions include medical institutions, welfare facility operators, nursing care facility operators, various school operators, or public facility operators, with medical institutions being a preferred example. Such medical institutions are required to create various medical documents, such as referral letters to other medical institutions, permits to attend school or work, reports to designated bodies such as the national or local government reporting the occurrence of a specific disease, or reports to report the progress of medical treatment within the institution. Therefore, by using the processing system 1, it becomes possible to efficiently output such medical documents.

[0015] In this disclosure, "medical document" refers to any document generated using medical information. Therefore, a medical document is not limited to documents generated or used only in a medical institution. Furthermore, a medical document is not limited to those created by instructions entered by medical professionals, but may also be created by other persons, such as the subject or their relatives. Such medical documents include, but are not limited to, the referral letters to other medical institutions exemplified above, permission letters to attend school or work, reports to national or local governments reporting the occurrence of a specific disease or reports to institutions reporting the progress of medical treatment, as well as various other documents such as discharge summaries recording the progress during hospitalization, nursing summaries recording the patient's condition and nursing care at a medical institution, medical fee statements (so-called claims), detailed symptom descriptions related to medical fees, surgical records of procedures performed on the patient at a medical institution, opinion letters submitted to life insurance operators, attending physician's opinion letters, home nursing instruction forms, visit reports, special instruction forms, death certificates, or autopsy reports.

[0016] Furthermore, in this disclosure, "medical information" may be any information acquired or used by an institution related to medical care. Therefore, it is not limited to information acquired and used only by medical institutions. Examples of such medical information include attribute information indicating the attributes of the subject, interview information entered by the subject or medical professionals, findings information entered by medical professionals, diagnostic information indicating the results of a diagnosis by medical professionals, or treatment information indicating the details of treatment performed by medical professionals. More specifically, examples of medical information include: • Information indicating the subject's attributes, such as name, date of birth, age, gender, family structure, occupation, mode of transportation, address, and contact information. • Various information recorded in the medical record Information obtained from various medical devices such as CT scanners, MRI scanners, X-ray machines, electrocardiographs, ultrasound diagnostic devices, endoscopes, blood pressure monitors, or angiography equipment. • Historical information showing the history of medical treatment at a medical institution. * Diagnostic information including chief complaint, medical history, allergy history, medication history, disease name / location / severity, examination details and findings (examinations using the above medical devices, blood tests, physiological tests and the dates of these examinations), treatment details (surgical procedures, drug administration and the dates of these treatments), discharge prescription, patient condition (level of patient independence), degree of dementia, paralysis, limb loss, means of mobility, need for medical management (need for medical, care, and nursing-related services), discharge outcome, medical devices used, rehabilitation details, admission route (emergency transport or referral), attached documents (examination results, etc.), date of visit, date of discharge, and progress. These are some examples.

[0017] Furthermore, in this disclosure, "subject" can be any person who is the subject of a medical document generated using the processing system 1, and is not limited to persons with specific attributes. Such subject may include all persons, such as patients, test subjects, diagnostic subjects, and healthy individuals. Also, "user" can be any person who uses the processing unit 100 of the processing system 1, and is not limited to persons with specific attributes. Such users may include all persons, such as persons belonging to the above-mentioned institutions (medical professionals such as doctors, nurses, laboratory technicians, medical office staff, medical staff and administrators, paramedics, and personnel in charge of medical devices and equipment), as well as the subject themselves.

[0018] Figure 1B is a block diagram showing the configuration of a processing system 1 according to one embodiment of the present disclosure. According to Figure 1B, the processing system 1 includes at least a processing device 100 for outputting medical documents based on medical information, and an information providing device 200 for providing medical information to the processing device 100. The processing system 1 may also include, as necessary, a medical device for acquiring measurement data, a model generation device for generating various trained models used for generating medical documents, an output device to which medical documents are output (e.g., a display device, a printer device, or a terminal device of another institution), or an input device for receiving instructions from a user. The various devices in the processing system 1, including the processing device 100 and the information providing device 200, are connected to each other so as to be able to communicate with each other by at least one of a wireless network and a wired network.

[0019] 2. Configuration of the processing unit 100 Figure 2 is a block diagram showing the configuration of a processing unit 100 according to one embodiment of the present disclosure. According to Figure 2, the processing unit 100 includes a processor 111, a memory 112, an input interface 113, an output interface 114, and a communication interface 115. These components are electrically connected to each other via control lines and data lines. Note that the processing unit 100 does not need to include all of the components shown in Figure 2; it is possible to omit some components or add other components. For example, the processing unit 100 may include a battery for powering each component.

[0020] Such a processing device 100 can preferably be any device capable of performing the processing related to this disclosure, such as a laptop computer, a desktop computer, a smartphone, a tablet device, an on-premise server device, and a cloud-based server device. Furthermore, the processing device 100 can also perform at least some of the processing on one or more server devices on the cloud or one or more server devices operated within a specific organization. Therefore, the processing device 100 includes combinations of laptop computers, desktop computers, smartphones, tablet devices, on-premise server devices, and cloud-based server devices.

[0021] In the processing unit 100, the processor 111 functions as a control unit that controls the processing unit 100 or other components of the processing system 1 based on a program stored in the memory 112. Specifically, the processor 111 executes the following based on a program stored in the memory 112: "a process to determine the type of medical document to be created from among medical documents categorized based on multiple types," "a process to output a first screen containing first medical information, which is medical information acquired based on the determined type from among multiple medical information associated with one or more subjects," "a process to receive editing instructions from the user for the medical information output on the first screen," and "a process to output a second screen containing a medical document generated based on at least the determined type and second medical information, which is medical information edited based on the instruction input." The processor 111 is mainly composed of one or more CPUs, but may be combined with a GPU or FPGA as appropriate.

[0022] Memory 112 is composed of RAM, ROM, non-volatile memory, HDD, SSD, etc., and functions as a storage unit. Memory 112 stores instruction commands for various controls of the processing system 1 according to this embodiment as programs. Specifically, Memory 112 stores programs for the processor 111 to execute processes such as: "a process to determine the type of medical document to be created from among medical documents categorized based on multiple types"; "a process to output a first screen containing first medical information, which is medical information acquired based on the determined type from among multiple medical information associated with one or more subjects"; "a process to receive editing instruction input from the user for the medical information output on the first screen"; and "a process to output a second screen containing a medical document generated based on at least the determined type and second medical information, which is medical information edited based on the instruction input." In addition to these programs, Memory 112 may also store various information stored in the subject management table, template management table, and user attribute management table (Figures 3A to 3C). Furthermore, this information does not necessarily have to be stored in the memory 112 located inside the processing unit 100; it may also be stored in a database device connected externally via a wireless or wired network. Therefore, in such cases, the database device may also be included in the memory 112.

[0023] The input interface 113 functions as an input unit that receives user instructions to the processing unit 100. Examples of the input interface 113 include various hard keys such as a keyboard or mouse, and a touch panel superimposed on the display of a display device, having an input coordinate system corresponding to the display coordinate system of the display device. In the case of a touch panel, icons corresponding to the command to be entered are displayed on the display, and the user can select or specify each icon by giving instructions via the touch panel. The method for detecting user instructions via the touch panel may be any method, such as capacitive or resistive touch. The input interface 113 does not always need to be physically provided on the processing unit 100, and may be connected via a wired or wireless network as needed.

[0024] The output interface 114 functions as an output unit for outputting medical documents generated by the processing unit 100. An example of the output interface 114 is an interface for connecting to an external device or equipment, such as a display device consisting of a liquid crystal panel, an organic EL display, or a plasma display. However, if the processing unit 100 itself has a display, that display can function as the output interface. Also, if it is connected to a display device or the like via a communication interface 115, that communication interface 115 can also function as the output interface 114.

[0025] The communication interface 115 functions as a communication unit for sending and receiving medical information and the like, as exemplified above, to and from the information providing device 200 via a wired or wireless communication network. Examples of the communication interface 115 include wired communication connectors such as USB and SCSI, wireless communication transceivers such as LTE, Wi-Fi, Bluetooth®, and infrared, and various connection terminals for printed circuit boards and flexible circuit boards.

[0026] The specific configuration of the information providing device 200 will not be described in detail, but it has at least a processor, memory, and a communication interface, and may include input and output interfaces as needed. Examples of such information providing devices 200 include various medical devices such as CT scanners, MRI scanners, X-ray machines, electrocardiographs, ultrasound diagnostic devices, endoscopes, blood pressure monitors, or angiography machines; control devices for controlling these medical devices; medical interview devices; electronic medical record devices; PACS; medical professional terminal devices; patient terminal devices; database devices that record information entered into these devices; or combinations thereof. The information providing device 200 reads necessary information in response to a request received from the processing device 100 and provides it to the processing device 100.

[0027] 3. Information stored in each management table Figure 3A is a conceptual diagram showing a target management table stored in an information providing device 200 according to one embodiment of the present disclosure. The information stored in the target management table is read from the information providing device 200 in accordance with the progress of processing by the processor 111 of the processing device 100, and is updated and stored in the information providing device 200.

[0028] According to Figure 3A, the subject management table stores attribute information, medical history information, findings information, and diagnostic information, associated with the subject ID information. "Subject ID information" is unique information for each subject and is used to identify each subject. Subject ID information is generated each time a new subject is registered by the user or the subject themselves. "Attribute information" is information that indicates the attributes of each subject. Attribute information is entered, for example, by the subject or medical professionals. Examples of such attribute information include subject name, date of birth, age, gender, family structure, occupation, means of transportation, address, and contact information.

[0029] "Medical history information" is information entered, for example, by the patient or healthcare professional via a medical history device. Examples of such medical history information include subjective symptoms, medical history, current medications, family medical history, presence or absence of allergies and travel destinations, body temperature, presence or absence of underlying diseases, presence or absence of physical findings, vaccination history, and timing of vaccinations. This medical history information is generally entered either by the patient reporting it themselves or by healthcare professionals interviewing the patient. "Physical findings information" is information entered by healthcare professionals such as doctors. Examples of such physical findings information include information indicating abnormalities obtained through examinations such as digital examination, medical history taking, and palpation.

[0030] "Diagnostic information" refers to information that includes at least one of the following: information that assists in diagnosis at a medical institution, information that shows the result of the diagnosis, information that shows the treatment performed based on the result of the diagnosis, and information that shows the history of the diagnosis. Examples of such diagnostic information include information obtained from various medical devices such as CT scanners, MRI scanners, X-ray machines, electrocardiographs, ultrasound diagnostic devices, endoscopes, blood pressure monitors, or angiography equipment, chief complaint, name of the disease (diagnosis), location and severity, examination content and findings (examinations using the above medical devices, blood tests, physiological tests and the dates of these examinations), treatment content (type and date of surgery, drug administration and duration of administration), prescriptions at discharge, patient condition (degree of patient independence), degree of dementia, paralysis, limb loss, need for medical management (need for medical, care, and nursing-related services), outcome at discharge, medical devices used, rehabilitation content, admission route (emergency transport or referral), date of arrival, date of discharge, and progress information.

[0031] In this disclosure, as stated above, medical information may include any of the following: attribute information, medical history information, findings information, and diagnostic information.

[0032] Figure 3B shows an example of a template management table stored in a processing unit 100 according to one embodiment of the present disclosure. The information stored in the template management table is read from memory 112 in accordance with the progress of processing by the processor 111 of the processing unit 100, and is updated and stored at any arbitrary timing.

[0033] According to Figure 3B, the template management table stores template ID information, part ID information, placement information, and medical information for each type of information. "Type information" is information used to identify the type of medical document. Examples of such type information include referral letters to other medical institutions, permission letters to attend school or work, reports to national or local governments reporting the onset of a specific disease, reports reporting the progress of medical treatment within an institution, discharge summaries recording the progress during hospitalization, nursing summaries recording the patient's condition and nursing care at a medical institution, medical fee statements (so-called claims), detailed symptom descriptions related to medical fees, surgical records performed on the patient at a medical institution, opinion letters submitted to life insurance operators, attending physician's opinion letters, home nursing instruction forms, visit reports, special instruction forms, death certificates, or autopsy reports.

[0034] "Template ID information" is unique to each template information and is used to identify each template information. Template ID information is generated each time new template information is created. "Template information" is information used as a template in the generation of medical documents. As an example of such template information, document data that is common to multiple subjects, excluding the parts of a medical document that contain information specific to each subject. The data format of such document data can be any format that can be processed by the processing device 100 or terminal devices used by medical professionals.

[0035] "Part ID information" is information unique to each part of the medical document and is used to identify each part. Here, "part information" refers to information about the components that make up template information, which serves as a model for medical documents. For example, taking a referral letter as an example, a referral letter is composed of multiple parts such as the introductory and concluding parts, item name parts, diagnosis name parts, referral purpose parts, medical history parts, progress parts, and discharge prescription parts. In other words, part information can be, as an example, the document data that makes up these parts. Furthermore, parts whose content changes according to diagnostic information, such as progress, may be a combination of multiple further subdivided parts such as examination parts, surgery parts, and drug treatment parts. Part ID information stores one or more pieces of information to identify the part information that makes up the medical document. For example, if "L1, L2, L3..." is stored as part ID information corresponding to template ID information "K1", it means that the template information identified by template ID information "K1" is composed of part information identified by L1~L3, etc. Furthermore, the data format of such document data can be any format that can be processed by the processing device 100 or terminal devices used by medical professionals.

[0036] "Placement information" refers to information indicating the location of part information identified by part ID information within a medical document. For example, information such as the order in which part information identified by each part ID information is placed, or coordinates indicating its position within the medical document, can be used as placement information. Furthermore, this placement information may not only indicate the location within a medical document on its own, but may also indicate the location within a medical document when combined with diagnostic information.

[0037] The template management table stores one or more parts of information for each type of medical document, associated with part ID information. In addition, it is possible to further subdivide and store different template information for each type of medical information (e.g., diagnosis). For example, if the type information is "referral letter," it may be further subdivided by diagnosis (medical information), and different template information may be stored for "disease A" and "disease B," even if they are both referral letters. This makes it possible to use a wider variety of template information.

[0038] "Medical information" includes at least one of the attribute information, medical history information, findings information, and diagnostic information shown in Figure 3A. In other words, it stores information that identifies one or more pieces of medical information necessary for generating various types of medical documents.

[0039] Furthermore, the information stored in the template management table may be stored in the memory 112 of the processing unit 100, but it may also be stored in other devices such as other processing units or database devices.

[0040] Figure 3C shows an example of a user attribute management table stored in a processing unit 100 according to one embodiment of the present disclosure. The information stored in the user attribute management table is read from memory 112 in accordance with the progress of processing by the processor 111 of the processing unit 100, and is updated and stored at any arbitrary timing.

[0041] According to Figure 3C, the user attribute management table stores user attribute information and type information in a corresponding manner. "User attribute information" is information that indicates the attributes of the user. Examples of such user attribute information include healthcare professionals, patients, and others. It is also possible to further subdivide and distinguish the above user attribute information. In that case, examples of user attributes include doctors, nurses, laboratory technicians, medical office staff, other staff and managers of medical institutions, paramedics, personnel in charge of medical devices and equipment, patients, and others.

[0042] "Type information" is information that identifies the type of medical document, similar to the type information shown in Figure 3B. In Figure 3C, one or more types of type information can be included as type information. That is, one or more types of type information may be stored corresponding to each attribute information. For example, if the type information "J1, J2, J3" is stored as type information corresponding to the user attribute information of "physician," it indicates that the physician can select from the various types of medical documents J1, J2, and J3.

[0043] The information stored in the user attribute management table may be stored in the memory 112 of the processing unit 100, but it may also be stored in other devices such as other processing units or database devices.

[0044] Furthermore, while Figure 3C illustrates a user management table that manages user attribute information and type information in association, any method is acceptable as long as it allows for the management of medical document types according to the user. For example, it is also possible to manage user authority information and type information in association, or to manage each user directly in association with type information.

[0045] Furthermore, although not specifically illustrated in Figure 3C, the type information associated with user attribute information may be further subdivided and categorized based on the format of the medical document. For example, a type management table may be prepared in which one or more format ID information is associated with type information J1, and one or more format ID information is associated with type information J2. Specifically, for the "referral letter" type identified by type information J1, format ID information indicating "treatment," format ID information indicating "examination," format ID information indicating "rehabilitation," format ID information indicating "follow-up observation," format ID information indicating "examination result report," and progress ID information indicating "progress report" are associated and stored.

[0046] In this case, the template management table in Figure 3B stores various information associated with each type of information, but in this case, various information will be stored associated with each format ID information. Also, in this case, the various processes in Figures 4A and 4B are performed based on the type of information, but in this case, the various processes are performed based on the format ID information. In this way, it becomes possible to manage a wider variety of medical documents with different formats.

[0047] Although not specifically illustrated, in addition to the tables in Figures 3A to 3C, other information may be stored in memory 112, such as a user management table in which user identification information, such as user ID information, and user attribute information are associated and stored.

[0048] 4. Processing flow executed by the processing unit 100 (1) Processing flow for outputting the first screen including medical information Figure 4A is a diagram showing a processing flow executed in a processing device 100 according to one embodiment of the present disclosure. Specifically, Figure 4A is a diagram showing a series of processing flows from receiving a request from a user to generate a medical document to outputting medical information used to generate the medical document. This processing flow is mainly performed by the processor 111 of the processing device 100 reading and executing a program stored in the memory 112.

[0049] (A) Processing of requests for the generation of medical documents As shown in Figure 4A, the processor 111 receives a request from the user to generate a medical document (S111). One example of this process is to receive instructions from the user via the input interface 113 of the processing unit 100 to select a subject for which a medical document will be generated, and instructions to execute the generation of the medical document. That is, the generation request includes subject ID information to identify the selected subject and information indicating that a medical document is being requested. Another example of this process is to generate a generation request by receiving instructions from the user via the input interface of the user terminal device used by the user to select a subject for which a medical document will be generated, and instructions to execute the generation of the medical document, and then receiving the generation request from the user terminal device via the communication interface 115.

[0050] (B) Selection process for the type of medical document Next, the processor 111 selects the type of medical document to be generated (S112). As an example of this process, the processor 111 receives user instructions via the input interface 113 regarding the selection of user attribute information, according to a screen output via the output interface 114 (for example, Figure 9A). The processor 111 refers to the user attribute management table (Figure 3C) and identifies one or more type information associated with the selected user attribute information. The processor 111 outputs a screen containing the one or more type information identified via the output interface 114 and receives user instructions via the input interface 113 regarding the selection of specific type information. As a result, the processor 111 selects the type identified by the received type information as the type of medical document to be generated.

[0051] Another example of this process is that the processor 111 identifies user attribute information based on pre-entered user ID information. The processor 111 refers to the user attribute management table (Figure 3C) to identify one or more type information associated with the identified user attribute information. The processor 111 outputs a screen containing the identified one or more type information via the output interface 114 and accepts user instructions regarding the selection of specific type information via the input interface 113. As a result, the processor 111 selects the type identified by the accepted type information as the type of medical document to be generated.

[0052] In this way, appropriate categories are presented to the user according to their attributes, and the user can select the desired category from among them, allowing the user to select a category more efficiently. Note that the process related to category selection may be based on the user's authority information or information identifying the user, rather than user attribute information.

[0053] (C) Processing of medical information of the subject Next, the processor 111 reads the subject's medical information (S113). As an example of this process, the processor 111 refers to the subject management table and reads the subject's medical information based on the subject ID information from S111.

[0054] (D) Extraction of medical information of the subject (D-1) Example of extraction process (Part 1) Next, the processor 111 extracts the medical information necessary for generating a medical document from the read medical information (S114). As an example of this process, the processor 111 refers to the template management table (Figure 3B) and identifies the medical information associated with the type information identified in S112. Then, the processor 111 extracts only the identified medical information (i.e., the medical information necessary for generating the medical information) from the medical information of the subject read in S113. For example, the medical information read in S113 includes all of the attribute information, medical history information, findings information, and diagnostic information (Figure 3A) associated with the subject ID information. Of these, for the generation of a referral letter selected as the type, only admission / discharge information, diagnostic information, treatment details, and discharge prescription are necessary. Therefore, only the necessary information is extracted from the attribute information, medical history information, findings information, and diagnostic information. Furthermore, the extracted medical information may be based on information stored as interview information, findings information, or diagnostic information. Specifically, information of higher importance or priority may be extracted based on the name of the disease, which is one of the pieces of information stored as interview information, findings information, or diagnostic information. For example, if pneumonia is stored as the name of the disease, information on test data and imaging findings that can confirm inflammatory responses may be preferentially extracted, or information on antibiotics may be preferentially extracted among the information on drug treatment (although saline may be administered during hospitalization, its importance as medical information for pneumonia is low).

[0055] (D-2) Example of extraction process (Part 2) Here, among attribute information, medical history information, findings information, and diagnostic information, some information is systematically managed in terms of its type and content, while other information is entered in a free-form text format, for example. Figure 5 is a diagram showing an example of medical information according to one embodiment of the present disclosure. Specifically, Figure 5 is a diagram showing an example of medical record information 10 stored as one of the medical information. According to Figure 5, the medical record information 10 is systematically entered by a physician in the order of "subjective information," "objective information," "evaluation," and "plan." Such medical record information 10 is entered via the input interface of a medical professional terminal device, etc., and is stored in the patient management table in association with the patient.

[0056] Medical record information 10 includes, as "S" (subjective information), information expressed in free-form text such as, "The patient has had a fever and chills for the past three days. In addition to a history of right rib fracture, lumbar vertebral compression fracture, high blood pressure, diabetes, and dyslipidemia." Medical record information 10 also includes, as "O" (objective information), information expressed in free-form text such as, "38.5℃, oxygen saturation 97%, negative result from influenza rapid diagnostic kit, abnormal findings in CT scan and blood test." Medical record information 10 also includes, as "A" (evaluation), information such as, "Pneumonia was diagnosed based on the results of the CT scan and blood test." Medical record information 10 also includes, as "P" (plan), information such as, "ABPC / SBT was administered, and hospitalization for follow-up was instructed." In other words, medical record information 10 includes information such as chief complaint, medical history, disease name, test results and treatment details.

[0057] Returning to Figure 4A, the processor 111 can also extract medical information necessary for generating medical documents from the medical record information exemplified in Figure 5. This process can be performed, for example, by using a first pre-trained model. This first pre-trained model is a pre-trained model generated by the processor 111 or the processor of the model generation device by performing machine learning using a predetermined dataset. Specifically, the first pre-trained model uses a combination of pre-prepared training strings (for example, medical record information similar to the medical record information 10 in Figure 5) and label information assigned to the medical information contained in the training strings (for example, assigning the "chief complaint" label to "fever" and "chills," and assigning the "admission route" label to "emergency transport") to train a learner to assign label assignment patterns. This machine learning can be performed, for example, by providing these combinations of information to a neural network made up of neurons, and repeatedly adjusting the parameters of each neuron so that the output from the neural network matches the correct label. The first pre-trained model is then obtained through this machine learning process.

[0058] The first trained model can be generated not only using the neural networks exemplified above, but also using methods employing neural networks such as convolutional neural networks, multilayer herceptons (MLP), LSTM (Long Short-Term Memory), GRU (Gated Recurrent Unit), GNN (Graph Neural Network), and Transformers; methods employing gradient boosting decision trees (GBDT) such as LightGBM (Light Gradient Boosting Machine), XGBoost, and CatBoost; and machine learning methods such as ridge regression, logistic regression, support vector regression (SVR), nearest neighbor, decision trees, regression trees, and random forests.

[0059] In S114 of Figure 4A, the processor 111 reads the first trained model generated as described above from memory 112 and executes it. Specifically, the processor 111 inputs the patient's medical record information 10, exemplified in Figure 5, as input information to the first trained model and obtains medical information for each item as output information (for example, medical information for "fever" and "chills" is obtained for the "chief complaint" item, and medical information for "emergency transport" is obtained for the "admission route" item). Then, the processor 111 refers to the template management table (Figure 3B) and identifies the medical information associated with the type information identified in S112. The processor 111 extracts only the identified medical information (i.e., the medical information necessary for generating medical information) from the medical information for each item obtained as output information. For example, the medical information obtained as output information includes various medical information, but for the generation of a referral letter selected as the type, only admission / discharge information, diagnostic information, treatment details, and discharge prescription are necessary. Therefore, only the necessary information is extracted from a variety of medical information.

[0060] The explanation described the case where medical information is extracted using a first pre-trained model obtained by training with a combination of training strings and label information. However, the first pre-trained model is not limited to such a pre-trained model; it is also possible to use a pre-trained large-scale language model (i.e., a natural language processing model trained using a large amount of text data). In this case, various models can be used, such as general-purpose language models like GPT-3, GPT-4, Claude, PaLM, NeMo LLM, or LLaMA, or language models related to the medical field such as GPT-MD and MED-PaLM. However, it is not limited to these; models such as BERT and Word2vec, other neural networks, support vector machines, logistic regression, decision trees, random forests, or combinations of these models may also be used as pre-trained models. Furthermore, morphological analysis algorithms using dictionaries related to medical information may also be used in combination.

[0061] When a large-scale language model is used as the first trained model, in S114 of Figure 4A, the processor 111 generates query information to be input to the large-scale language model. An example of such query information is: "From the following medical record information, extract the information necessary for generating a referral letter, including admission / discharge information, diagnostic information, treatment details, and prescriptions at discharge, and classify them by item. (The string of medical record information 10 is written after this statement, but is omitted here.)" Such query information may be generated by the user through the input interface 113, or it may be generated automatically by the processing of the processor 111.

[0062] The processor 111 inputs the generated query information into a large-scale language model and extracts medical information necessary for generating medical documents as output information.

[0063] As described above, the medical information of the subject contains a large amount of information and is expressed in free-form text, making it cumbersome for medical professionals to find the necessary information each time. However, by extracting the medical information necessary for generating medical documents through the processing of processor 111, as in S114, it becomes possible to generate medical documents more efficiently. Although various methods for extracting the medical information of the subject are exemplified in items (D-1) and (D-2), this processing can also be performed by combining these methods.

[0064] (E) Processing of the subject's medical information Next, the processor 111 performs a process to convert the extracted medical information into a regular expression in order to correct inconsistencies in the notation of each extracted medical information (S115). As an example of this process, the processor 111 converts each extracted medical information by referring to a pre-prepared regular expression dictionary table (not shown). For example, the regular expression dictionary table has "ABPC / SBT" stored as a normalized expression, associated with "ABPC / SBT", "Ampicillin-Sulbactam", and "Ampicillin / Sulbactam". Therefore, if "Ampicillin-Sulbactam" is extracted as medical information, the processor 111 refers to the regular expression dictionary table and converts "Ampicillin-Sulbactam" to "ABPC / SBT". The processor 111 stores the converted medical information in the patient management table, associated with the patient ID information.

[0065] Furthermore, this conversion process is not limited to the method using the regular expression dictionary table described above; various methods, such as using a pre-trained model, can be employed. Also, this conversion process does not need to be performed on all extracted medical information; it may be performed on only a portion of the extracted medical information, or not at all.

[0066] (F) Output processing of the subject's medical information Next, the processor 111 outputs at least one of the medical information extracted in S114 and the medical information converted in S115 as first medical information (S116). As an example of this process, the processor 111 acquires the medical information from S114 and S115 as first medical information and generates a first screen including the first medical information. Then, the processor 111 outputs the generated first screen to a display or the like via the output interface 114.

[0067] The details of the first screen will be described later, but as an example, the first screen is output adjacent to the second screen, which contains the generated medical document. In other words, the first screen is displayed in a manner that allows the user to view it simultaneously with the second screen. Therefore, the user can refer to the first medical information contained in the first screen while checking the medical document contained in the second screen, making it possible for the user to check the medical document more efficiently.

[0068] The processing flow is now terminated.

[0069] (2) Processing flow for outputting the second screen, including medical documents Figure 4B is a diagram showing the processing flow executed in a processing device 100 according to one embodiment of the present disclosure. Specifically, Figure 4B is a diagram showing a series of processing flows until a second screen containing a medical document is output. This processing flow is mainly performed by the processor 111 of the processing device 100 reading and executing a program stored in the memory 112.

[0070] (A) Editing process for medical information As shown in Figure 4B, when the first screen containing the first medical information is displayed, the system determines whether or not it has received an instruction from the user to edit the first medical information via the input interface 113 (S211). If such an instruction is received, the processor 111 edits the corresponding first medical information based on that instruction (S212). As an example of this process, if there is an error in the first medical information displayed on the first screen, or if the first medical information does not contain medical information that should be included, the processor 111 receives an instruction from the user via the input interface 113 to correct the first medical information or input new medical information. The processor 111 then stores the corrected or input medical information as second medical information in the subject management table, associated with the subject ID information, and outputs it on the first screen, replacing the medical information before editing. Details of this editing process will be described later. Furthermore, if no instruction input is received in S211, the processor 111 skips the editing process in S212.

[0071] (B) Process for generating template information that will serve as templates for medical documents Next, the processor 111, based on the type information in S112 of Figure 4A, refers to the template management table in memory 112 and obtains template information that will serve as a template for the desired medical document (S213). One example of this process is when the processor 111 refers to the template management table (Figure 3C) and identifies a template ID that is associated with the type information included in the generation request and the medical information that has been read. In addition, the template information may be identified not only using medical information and type information, but also using a clinical path determined from the medical information.

[0072] Here, Figure 4C is a diagram showing an example of a processing flow executed in a processing apparatus 100 according to one embodiment of the present disclosure. Specifically, Figure 4C is a diagram showing a detailed processing flow of the process of acquiring template information in S213 of Figure 4B. This processing flow is mainly performed by the processor 111 of the processing apparatus 100 reading and executing a program stored in memory 112.

[0073] According to Figure 4C, the processor 111 reads at least one of the medical information (first medical information) output in S116 of Figure 4A and the edited medical information (second medical information) in S212 of Figure 4B (S311). Once the medical information is read, the processor 111 refers to the template management table (Figure 3C) (S312). At this time, the processor 111 identifies one template ID information from among multiple template ID information based on the type information selected in S112 of Figure 4A and the medical information. Then, based on the identified template ID information, the processor 111 identifies one or more part ID information that constitute the template information. Once the part ID information is identified, the processor 111 reads the part information associated with the identified part ID information (S313). The processor 111 generates a template information by concatenating each read part information according to the placement information associated with the template ID information (S314).

[0074] Figure 6 shows an example of template information processed in a processing apparatus 100 according to one embodiment of the present disclosure. Specifically, it shows an example of template information generated according to the processing in Figure 4C. According to Figure 6, template information 20 is shown, which is generated by a plurality of part ID information and arrangement information associated with template ID information identified by type information (e.g., letter of introduction) and medical information (e.g., gallstone disease (diagnosis)). In the template information 20, each part information is arranged in order according to the arrangement information. Specifically, the introductory text part 21 is placed at the beginning of the template information 20. Below it, • Item name part 22a: “Disease Name” and diagnostic name part 22b: “<Diagnosis Name>” • Item name part 23a: "Purpose of Referral" and Item name part 23b: "Request for <Purpose of Referral>" • Item name part 24a: "Past Medical History" and past medical history part 24b: "<Past Medical History>" • Item name part 25a and progress parts 25b to progress parts 25e • Item name part 26a: “Discharge prescription” and multiple discharge prescription part 26b: “<Discharge prescription>” • Ending sentence part 27 Each of these includes:

[0075] Thus, the processor 111 acquires template information by generating a single template information by combining multiple parts information according to the processing flow in Figure 4C.

[0076] (C) Generation process of query information Returning to Figure 4B, the processor 111 generates query information (S214) based on at least one of the medical information output in S116 of Figure 4A (first medical information) and the medical information edited in S212 (second medical information). In the processing flow of Figure 4B, a second trained model is used as an example for generating medical documents. An example of such a second trained model is a trained large-scale language model. Query information is information indicating the request to be input to such a trained large-scale language model. The processor 111 refers to a query management table (not shown) stored in memory 112, etc., and reads a query form information identified based on the above medical information and the type information in S112 of Figure 4A. Then, the processor 111 generates query information by overwriting the read query form information with the above medical information and the template information generated in S213, respectively.

[0077] Figure 7 shows an example of query information processed in a processing device 100 according to one embodiment of the present disclosure. Specifically, it shows an example of query information 30 generated by the processing in S214 of Figure 4B. According to Figure 7, the query information 30 includes a standard area 31 and a standard area 33, which contain content common to each type of information, a medical information area 32 into which at least one of the medical information (first medical information) output in S116 of Figure 4A and the medical information (second medical information) edited in S212 is input, and a template area 34 into which the template information generated in S213 is input. Thus, according to the query information exemplified in Figure 7, the standard area 31 includes, in plain text format, a request to the trained large-scale language model, "Please create a referral letter to introduce a patient to an external medical institution, as a polite document to be conveyed to the medical institution, based on the following information," and a request to the trained large-scale language model, "Please create a document by filling in the "<>" part of the following template." Although the example in Figure 7 uses plain text format, the query information can be in any language or model that can be processed by the trained model, and may include text data, image data, raw diagnostic data, diagnostic data in tabular form, or combinations thereof.

[0078] (D) Processing of medical documents Returning to Figure 4B, the processor 111 obtains the medical document generated based on the query information in S214 (S215). One example of this process is that the processor 111 obtains the generated query information by sending it to the second trained model. Specifically, the processor 111 inputs the query information into the second trained model and obtains the medical document requested by the query information as output.

[0079] Here, the second pre-trained model can be any model generated by machine learning. When using a pre-trained large-scale language model (i.e., a natural language processing model trained using a large amount of text data) as the second pre-trained model, various models can be used, such as general-purpose language models like GPT-3, GPT-4, Claude, PaLM, NeMo LLM, or LLaMA, or language models related to the medical field such as GPT-MD or MED-PaLM. However, it is not limited to these; models such as BERT, Word2vec, other neural networks, support vector machines, logistic regression, decision trees, random forests, or combinations of these models may also be used as pre-trained models.

[0080] Figure 8 shows an example of a medical document output by a processing device 100 according to one embodiment of the present disclosure. Specifically, it shows an example of a medical document 40 obtained by the processing of S215 in Figure 4B. According to Figure 8, in the medical document 40, the medical information contained in the query information is filled into the "<○○○>" portion of the template information according to the request contained in the query information. Furthermore, in the medical document 40, in order to make the document more polite according to the request contained in the query information, the medical information is not only embedded into the template information, but the template information is also modified to use more natural language expressions and more general terminology.

[0081] Specifically, in areas 41-43 and 57-59, medical information included in the query information is embedded according to the "<○○○>" specification in the template information. In addition, in areas 44-56, medical information included in the query information is embedded according to the "<○○○>" specification in the template information, and the text of the medical information and template information is modified by adding particles and auxiliary verbs or revising them to more general terms to make the language expression more natural.

[0082] Thus, by utilizing a pre-trained large-scale language model, it becomes possible to generate desired medical documents using more natural language expressions, rather than simply creating formal textual representations that merely embed template information and medical information.

[0083] When using a model other than a large-scale language model, or a combination thereof, as the second pre-trained model, it is possible to generate medical documents by numerically feature-coding the information contained in the query information using the pre-trained model and linking these numerical features to relevant medical terms and medical documents through clustering or other methods. However, medical documents may also be generated by other processing methods using pre-trained models, such as methods that directly classify the information contained in the query information into medical terms and documents generated using the pre-trained model.

[0084] Returning to Figure 4B, when the processor 111 acquires a medical document, it stores the acquired medical document in memory 112 and outputs a second screen containing the medical document (S216). As an example of this process, the processor 111 acquires the medical document generated in S215 and generates a second screen containing the medical document. Then, the processor 111 outputs the generated second screen to a display or the like via the output interface 114.

[0085] The details of the second screen will be described later, but this second screen is output adjacent to the first screen, which contains the first and second medical information. In other words, the second screen is displayed in a manner that allows the user to view it simultaneously with the first screen. Therefore, when the user checks a medical document displayed on the second screen, they can simultaneously refer to the first and second medical information from which that information originated, making it possible for the user to check medical documents more efficiently.

[0086] The above concludes the processing flow. Although not specifically illustrated in Figure 4B, this process may be performed periodically at predetermined intervals, each time a user input is received, or at both of these times.

[0087] 5. Example of a screen output from the processing unit 100 Figures 9A to 9C show examples of screens output from a processing device 100 according to one embodiment of the present disclosure. Specifically, Figure 9A shows an example of screen 70a when a first screen containing first medical information, which is output in S116 of Figure 4A, is output. Figure 9B shows an example of screen 70b when an editing screen, which is output in S212 of Figure 4B, is output. Figure 9C shows an example of screen 70c when a second screen containing a medical document, which is generated based on the edited medical information (second medical information), is output in S216 of Figure 4B. Each of these screens is output via the output interface 114 by processing by the processor 111 of the processing device 100. The output destination may be the display of the processing device 100, a display device connected to the processing device 100 via a wired cable, or a medical professional terminal device or a patient terminal device.

[0088] Figure 9A shows screen 70a when the first screen containing the first medical information output at S116 in Figure 4A is displayed. Screen 70a includes a user attribute tab at its top for selecting user attribute information. On this screen, the processor 111 selects the desired user attribute by receiving instruction input from the user via the input interface 113 for one of the tabs included in the user attribute tab (doctor tab 71a, nurse tab 71b, and other tab 71c). Screen 70a also includes a type candidate selection area 72 at the bottom of the user attribute tab, which is selected according to the selected user attribute. The type candidate selection area 72 includes type information associated with the user attribute management table as options, according to the selected user attribute. The processor 111 determines the desired medical document type by receiving instruction input from the user via the input interface 113 for one of the multiple options displayed in the type candidate selection area 72.

[0089] In the example in Figure 9A, the Doctor tab 71a is displayed in a identifiable manner for the Nurse tab 71b and the Other tab 71c among the User Attributes tabs. This indicates that "Doctor" is currently selected as the user attribute. In addition, the Type Candidate Selection Area 72 displays "Referral Letter," "Reply," and "Discharge Summary" as candidate type information. This indicates that the type information associated with "Doctor," the user attribute selected in the User Attribute Management Table, is output as a list. Furthermore, the checkbox for the "Referral Letter" type is checked. This indicates that "Referral Letter" has been selected as the type of medical document to be created.

[0090] Although not specifically illustrated in Figure 9A, for example, if the Nurse tab 71b is selected, the Doctor tab 71a and the Other tab 71c will be displayed in a way that allows the Nurse tab 71b to be identified. In addition, the Type Candidate Selection Area 72 will display a list of type information associated with "Nurse" in the User Management Table as candidate type information. The same applies when the Other tab 71c is selected.

[0091] Furthermore, the selectable user attribute tabs and selectable type information candidates are not limited to those shown in Figure 9A. Naturally, there may be a wider variety of tabs depending on the number of user attributes, and a wider variety of candidates depending on the number of type information entries associated with each user attribute.

[0092] Furthermore, screen 70a includes a first screen 73 which contains at least first medical information, which is medical information acquired based on the determined type. The first screen 73 includes a format selection area 73a at its top for selecting one format from a plurality of formats for the medical document to be generated. The format selection area 73a contains a list of formats that are pre-associated with the determined type information. The processor 111 selects the desired medical document format by receiving user instruction input for one of the plurality of formats displayed in the format selection area 73a via the input interface 113.

[0093] In the example shown in Figure 9A, the format selection area 73a displays "Medical Treatment," "Examination," "Rehabilitation," "Follow-up Observation," "Examination Result Report," and "Follow-up Report" as format candidates. This is because the format ID information corresponding to these formats is stored in the type information management table, associated with the type information of "Referral Letter." Furthermore, the checkbox for the "Follow-up Observation" format is checked. This indicates that the format of the medical document to be created has been decided as "Follow-up Observation." In other words, the final medical document generated will be a medical document that is a referral letter related to follow-up observation.

[0094] Although not specifically illustrated in Figure 9A, if, for example, "Medical Treatment" is selected in the format selection area 73a, the first medical information output on the first screen 73 and the medical document output on the second screen will also be changed accordingly according to the selected format. Furthermore, if, for example, "Reply" is selected in the type candidate selection area 72, the format candidates displayed in the format selection area 73a will also be changed to different ones.

[0095] Furthermore, the first screen 73 includes the first medical information from S116 in Figure 4A at the bottom of the format selection area 73a. That is, the first screen 73 includes each medical information item extracted or converted in S115 and S116 of Figure 4A, and their specific information, respectively.

[0096] In the example shown in Figure 9A, the first screen 73 displays the following items as the first medical information extracted or converted in S115 and S116 of Figure 4: admission route, date of arrival, chief complaint, discharge date, discharge outcome, medical history, diagnosis, date of onset, treatment details, and prescription at discharge. In addition, various information is output corresponding to each item as extracted specific information, such as "emergency transport" (checked box), date of arrival (2023 / 08 / 23), and content of chief complaint (fever, chills). This allows the user to quickly confirm the medical information necessary for generating the determined medical document.

[0097] Furthermore, screen 70a includes a second screen 74 which contains at least a medical document (a referral letter in follow-up format) generated based on the medical information output on the first screen 73. Note that this includes information on the medical document generated before the editing process S212 shown in Figure 4B has been performed. Therefore, for example, the medical treatment details on the first screen 73 show "2023 / 08 / 23: X-ray," and correspondingly, the medical progress on the second screen 74 shows "...based on the results of the X-ray...."

[0098] Furthermore, as is clear from Figure 9A, the first screen 73 and the second screen 74 are displayed adjacent to each other on screen 70a. In other words, the user can simultaneously view the first screen 73, which contains the medical information used to generate the medical document (first medical information), and the second screen 74, which contains the medical document generated based on that information. Therefore, when the user checks the generated medical document, they can simultaneously refer to the medical information that serves as its source, allowing them to check the medical document more efficiently.

[0099] In the processes S115 and S116 in Figure 4A, the desired information may not be extracted or converted correctly. Furthermore, the medical information necessary for generating medical documents may not be stored in the subject management table. To flexibly address such situations, as shown in S212 in Figure 4B, it is possible to edit the outputted medical information based on the user's input instructions.

[0100] Figure 9B shows an example of screen 70b when the editing screen output in S212 of Figure 4B is displayed, as described above. Specifically, screen 70b includes editing screens 91 and 3rd screen 92 which are displayed superimposed on the first screen 73 and the second screen 74. Screen 70b is output when the processor 111 receives user instruction input for the item to be edited via the input interface 113 in the first screen 73 of screen 70a.

[0101] An example of the screen output when the user enters instructions for the "Medical Treatment Details" item on the first screen 73 of screen 70a is shown. Therefore, the editing screen 91 includes input boxes (boxes 93a, 93b, and 93c) for the period, classification, and details to be entered as medical treatment details, below the medical treatment details item. In addition, although the information already output as the first medical information is displayed in each input box on the editing screen 91, it includes add icons 94 and delete icons 95 for adding new medical treatment details or deleting already entered medical treatment details. Furthermore, the editing screen 91 includes a confirm icon 96 for confirming the edited content and returning to screen 70a.

[0102] Furthermore, the medical information entered in the medical treatment details field is information extracted from the medical information stored in the patient management table based on the medical record information, and the third screen 92 includes the medical record information used in the medical treatment details field. In other words, the processor 111 outputs the third screen 92, which includes the medical information (third medical information) that became the source of the first medical information output on the first screen, selected from among the multiple medical information stored in the patient management table. The third screen 92 also includes a "back" icon 98 and a "next" icon 97 for switching the output medical information to other medical information (other third medical information) that became the source of the first medical information.

[0103] In the example in Figure 9B, the medical record information 10, which was the source of the first medical information extracted in S115 and S116 of Figure 4A, "August 23, 2023: X-ray," is included in the third screen 92. However, when referring to the medical record information 10, it states, "Pneumonia was diagnosed based on the results of the CT scan and blood test," but there is no mention of "X-ray." In other words, by referring to the medical record information 10 entered on August 23, 2023, the information "X-ray" entered in the classification input box 93b of the editing screen 91 is incorrect. Therefore, the processor 111 receives a user instruction input via the input interface 113 for the input box 93b that contains "X-ray," and edits it to the correct information, "blood test."

[0104] Furthermore, the processor 111 receives user input via the input interface 113 for the "Back" icon 98 and the "Next" icon 97 on the third screen 92, and switches the medical information that serves as the source of information, such as the medical record information, to be referenced. This makes it possible to check for errors or omissions in the medical information entered on the editing screen 91. Then, depending on the results of the check, the processor 111 receives user input for the add icon 94, delete icon 95, and each input box, and edits the medical information.

[0105] In this way, when editing medical information, displaying the source information in parallel makes it possible to edit more quickly and accurately.

[0106] Figure 9C shows an example of screen 70c when the second screen containing the medical document generated based on the edited medical information (second medical information) in S216 of Figure 4B is output. Screen 70c, like Figure 9A, includes user attribute tabs (doctor tab 71a, nurse tab 71b, and other tab 71c), type candidate selection area 72, first screen 73, and second screen 74. Of these, the user attribute tabs and type candidate selection area 72 are the same as in Figure 9A, so their explanation is omitted.

[0107] According to Figure 9C, the first screen 73, like Figure 9A, includes each medical information item and its specific information. However, the first screen 73 in Figure 9C includes the medical information (second medical information) after editing in S212 of Figure 4B. Specifically, because the medical history and treatment details items were edited in the editing screen shown in Figure 9B, the following edited medical information (second medical information) is output to the first screen 73 in Figure 9C. • Dashed box 81: Newly enter the information "Diabetes, dyslipidemia" in the medical history section. • Dashed box 82: In the section on medical treatment details, the information "X-ray" has been corrected to "blood test". • In dashed box 83: In the section on medical treatment details, please enter the following new information: "2023 / 08 / 24~2023 / 08 / 28: Medication treatment (Furosemide tablets 40mg "NP")" • In the dashed box 83: In the section on medical treatment details, the information for the administration period of Hump Injection 1000, which was "2023 / 08 / 24", has been corrected to "2023 / 08 / 24~2023 / 08 / 28". • In dashed box 84: In the section on medical treatment details, please enter the following new information: "2023 / 08 / 28~2023 / 08 / 30: Medication treatment (Entresto 50mg tablets, Samsca 7.5mg tablets)"

[0108] Of the medical information included in the first screen 73, all information other than the medical information indicated by the dashed lines 81 to 84 (second medical information) has not been edited or otherwise modified. Therefore, the first medical information output on the first screen 73 in Figure 9A will be output as is.

[0109] The second screen 74 includes a medical document output by the processing in S216 of Figure 4B, based on the edited medical information (second medical information) and the unedited medical information (first medical information). Specifically, the second screen 74 includes a medical document of type referral letter and in the format of follow-up observation. Since this medical document is generated based on the edited medical information (second medical information), the following changes have been made to the medical document generated based on the unedited medical information (Figure 9A). • Dashed box 85: Added the information "Diabetes, dyslipidemia" to the medical history section. • Dashed box 86: In the section on the course of medical treatment, the description "X-ray" has been corrected to "blood test". • In the dashed box 87: In the section on the course of treatment, the statement "Furosemide-Hamp was administered the following day." has been corrected to "Furosemide-Hamp administration was started the following day and continued until August 28." • In dashed box 88: In the section on the course of treatment, add the following statement: "Furthermore, Entresto-Samsca was administered from August 28 until discharge."

[0110] In this way, the user can simultaneously view the first screen 73, which contains the medical information (first medical information) used to generate the medical document, and the second screen 74, which contains the medical document generated based on that information. Therefore, when the user checks the generated medical document, they can simultaneously refer to the medical information that serves as its source, allowing them to check the medical document more efficiently. Furthermore, when the medical information is edited on the first screen 73, the medical document generated based on the edited medical information is output to the second screen 74. Therefore, the user can check the medical document generated based on the edited medical information in real time.

[0111] In Figure 9C, the first screen 73 includes edited medical information (second medical information) and unedited medical information (first medical information), as described above. Therefore, it is possible to output both types of medical information separately on the first screen 73. Specifically, the processor 111 displays, for example, dashed frames 81 to 84 shown in Figure 9C for the edited medical information (second medical information) to distinguish it from the unedited medical information (first medical information).

[0112] Similarly, in Figure 9C, the second screen 74 includes a medical document generated based on the edited medical information (second medical information) and the unedited medical information (first medical information) as described above. Therefore, in the second screen 74, it is possible to distinguish and output the parts of the medical document generated based on the second medical information from the parts of the medical document generated based on the first medical information. Specifically, the processor 111 displays, for example, dashed frames 85 to 88 shown in Figure 9C for the parts generated based on the edited medical information (second medical information), to distinguish them from the parts generated based on the unedited medical information (first medical information).

[0113] It should be noted that the use of dashed lines for distinction described above is merely one example. For example, various methods can be employed, such as highlighting the relevant section instead of using dashed lines, displaying the information before editing by inputting instructions to the relevant section via the input interface 113, or displaying an identification mark to indicate that it has been edited.

[0114] In this embodiment, we can provide a processing apparatus, a processing program, and a processing method that can generate medical documents more efficiently.

[0115] 6. Others <Second pre-trained model> In the above embodiment, the case where a pre-trained large-scale language model is used to generate medical documents has been mainly described. However, it is also possible to use other second pre-trained models or to generate medical documents using predetermined medical document generation rules. For example, a second pre-trained model is generated by the following processing flow. The processor 111 acquires type information and medical information actually specified by medical professionals, etc., and used when creating training medical documents, respectively, as training data. Next, the processor 111 acquires document data of training medical documents that were actually created using this training data. Then, the processor 111 performs a step of machine learning of medical document creation patterns using the combination of training data of type information and medical information and training medical documents. As an example, this machine learning is performed by providing these sets of information to a neural network made up of neurons and repeating the learning process while adjusting the parameters of each neuron so that the output from the neural network is the same as the training medical document which is the correct label. Then, through this learning, the processor 111 performs a step of acquiring a pre-trained model (S215). The acquired trained model may be stored as a second trained model in the memory 112 of the processing unit 100 or in another device connected to the processing unit 100 via a wired or wireless network.

[0116] Then, the processor 111 inputs the type information and medical information included in the generation request into the second trained model generated as described above, thereby obtaining a medical document as output.

[0117] <Medical Information and Query Information> In the above embodiment, the case in which medical information is read from the subject management table in S112 of Figure 4A was described. However, instead, it is also possible to accept input of necessary medical information from the user via the input interface 113, for example, and use that medical information for subsequent processing. Furthermore, the case in which query information is generated based on medical information, etc., in S214 of Figure 4B was described. However, instead, it is also possible to generate query information by accepting input from the user via the input interface 113 while the user refers to medical information output to the display device via the output interface 114, for example.

[0118] <Template Information> In the above embodiment, the template management table was described in which type information and medical information are stored in association with template ID information, and a single template information is obtained based on the type information and medical information. However, instead of, or in addition to, type information and medical information, attribute information may also be stored in association with template ID information, and a single template information may be generated based on the attribute information. Examples of such attribute information include the sentence endings of the medical document ("nominalization" or "verbialization"), the level of detail (version with many items or with few items), whether or not personal information is included, and whether or not measurement data is attached. By obtaining template information while further considering attribute information in this way, it becomes possible to set more detailed template information.

[0119] <Using editing processes> In the above embodiment, as shown in Figure 4A, the case in which the first medical information is extracted using the first trained model when outputting the first screen containing the first medical information was described. Furthermore, in the above embodiment, as shown in Figure 4B, the case in which a medical document is generated based on the first medical information contained in the first screen, which is edited by receiving instruction input from the user.Therefore, the first medical information or the first screen containing the first medical information is optimized using at least one of the user's editing instruction input and the edited second medical information.

[0120] Specifically, the processor 111 provides the model generation device of the first trained model with the second medical information obtained by receiving the instruction input in S211 in Figure 4B or by editing in S212 as training data. The processor of the model generation device then performs additional training on the first trained model based on the acquired instruction input or second medical information. When the processor 111 receives a new patient selection in S111 in Figure 4, it outputs a new first medical screen containing new first medical information that is different from the first screen containing the edited first medical information (S116). At this time, since the processor 111 extracts the first medical information using the newly trained first trained model (S114), it is possible to output an optimized first screen that takes into account the instruction input received in S211 or the content edited in S212.

[0121] Furthermore, the optimization processes described above are not limited to the method of additional learning. They can also be performed by modifying the parameters used in the extraction (S114) and conversion (S115) of the first medical information contained in the first screen, or by updating the contents of the extraction table and conversion table used in the above processes, based on the input of editing instructions and the information of the second medical information after editing.

[0122] Furthermore, the above modifications can, of course, be combined as appropriate.

[0123] The processes and procedures described herein can be implemented not only by those explicitly described in the embodiments, but also by software, hardware, or a combination thereof. Specifically, the processes and procedures described herein can be implemented by implementing the logic corresponding to the process on a medium such as an integrated circuit, volatile memory, non-volatile memory, magnetic disk, or optical storage. Furthermore, the processes and procedures described herein can be implemented as computer programs and executed by various computers, including processing units and server devices.

[0124] Even if it is stated that the processes and procedures described herein are performed by a single device, software, component, or module, such processes or procedures may be performed by multiple devices, multiple software programs, multiple components, and / or multiple modules. Similarly, even if it is stated that the various types of information described herein are stored in a single memory or storage unit, such information may be distributed and stored in multiple memories within a single device or in multiple memories distributed across multiple devices. Furthermore, the software and hardware elements described herein may be implemented by integrating them into fewer components or by decomposing them into more components. [Explanation of Symbols]

[0125] 1. Processing System 100 Processing Units 200 Information provision device

Claims

1. A processing unit comprising at least one processor, The at least one processor is From among medical documents categorized based on multiple types, the type to be created is determined. A first screen is output that includes first medical information, which is medical information obtained based on the determined type from among multiple pieces of medical information associated with one or more subjects. The system accepts editing instructions from the user for the medical information displayed on the first screen. Outputs a second screen which includes a medical document generated based on at least the determined type and second medical information which is medical information edited based on the instruction input. A processing unit configured to perform a process for that purpose.

2. The processing apparatus according to claim 1, wherein the type is determined according to the user's attributes.

3. The processing apparatus according to claim 1, wherein the aforementioned plurality of medical documents are classified based on a plurality of formats in addition to the aforementioned type.

4. The processing apparatus according to claim 3, wherein the first screen includes a selection area for selecting one of the plurality of formats.

5. The processing apparatus according to claim 1, wherein the first medical information is information that may be used in generating a medical document of the determined type.

6. The processing apparatus according to claim 1, wherein the first medical information is information converted from medical information obtained based on the type to a regular expression.

7. The processing apparatus according to claim 1, wherein a template for the medical document to be generated based on the information output to the first screen is determined.

8. The processing apparatus according to claim 1, wherein the first screen includes the second medical information.

9. The processing apparatus according to claim 1, wherein the edited medical information and the unedited medical information are output separately on the second screen.

10. The processing apparatus according to claim 1, wherein the first screen and the second screen are output in a manner that can be viewed simultaneously by the user.

11. The apparatus according to claim 1, wherein at least one processor is configured to receive instruction input from the user and to perform a process for outputting a third screen which includes a third medical information related to the first medical information included in the first screen from among the plurality of medical information.

12. The processing apparatus according to claim 1, wherein, based on the editing instruction input or the second medical information, another first screen different from the first screen that is newly output is optimized.

13. In a computer comprising at least one processor, the at least one processor is: From among medical documents categorized based on multiple types, the type to be created is determined. A first screen is output that includes first medical information, which is medical information obtained based on the determined type from among multiple pieces of medical information associated with one or more subjects. The system accepts editing instructions from the user for the medical information displayed on the first screen. Outputs a second screen which includes a medical document generated based on at least the determined type and second medical information which is medical information edited based on the instruction input. A processing program that makes it function in that way.

14. A processing method performed by at least one processor in a computer having at least one processor, The stage of determining the type of medical document to be created from among medical documents categorized based on multiple categories, A step of outputting a first screen that includes first medical information, which is medical information obtained based on the determined type from among multiple medical information associated with one or more subjects, The process includes receiving editing instructions from the user for the medical information displayed on the first screen, A step of outputting a second screen that includes a medical document generated based on at least the determined type and second medical information which is medical information edited based on the instruction input, A processing method that includes this.

Images