Processing equipment, processing program and processing method

Abstract

To provide processing equipment that enables the efficient generation of a medical document.SOLUTION: A processing equipment comprises at least one processor, and the at least one processor acquires medical information, acquires template information for generating a medical document based on the acquired medical information, and outputs the medical document generated based on the acquired medical information and the template information.SELECTED DRAWING: Figure 4

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. Patent Document 1 describes 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 a second processing unit that records information on one or more of the items of the preventive vaccinations displayed on the input support screen in an electronic medical record based on a user operation on the input support screen. An electronic medical record system is described.

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, there is provided "a processing device including at least one processor, wherein the at least one processor is configured to acquire medical information, acquire template information used for generating a medical document based on the acquired medical information, and execute processing for outputting the medical document generated based on the acquired medical information and the template information."

[0006] According to one aspect of the present disclosure, there is provided "a processing program that causes at least one processor in a computer including the at least one processor to acquire medical information, acquire template information used for generating a medical document based on the acquired medical information, and output the medical document generated based on the acquired medical information and the template information."

[0007] According to one aspect of the present disclosure, there is provided "a processing method executed by at least one processor in a computer including the at least one processor, the processing method including: acquiring medical information; acquiring template information used for generating a medical document based on the acquired medical information; and outputting the medical document generated based on the acquired medical information and the template information."

Advantages of the Invention

[0008] According to the present disclosure, it is possible to provide a processing device, a processing program, and a processing method capable of more efficiently generating a medical document.

[0009] Note that the above effects are merely exemplary for convenience of explanation and are not limiting. In addition to or instead of the above effects, any effects described in the present disclosure or effects obvious to those skilled in the art can also be achieved.

Brief Description of the Drawings

[0010]

Figure 1

Figure 2

Figure 3A

Figure 3B

Figure 3C

Figure 4

Figure 5A

Figure 5B

Figure 6

Figure 7A

Figure 7B

Figure 8

Figure 9

Figure 10

Figure 11

Figure 12

Figure 13

Figure 14

Figure 15

DETAILED DESCRIPTION OF THE INVENTION

[0011] 1. Overview of the processing system 1 The processing system 1 according to the present disclosure is used to output medical information based on medical information acquired from an information providing device 200 such as various medical devices, an interview device, an electronic medical record device, a PACS (Picture Archiving and Communication Systems), or a database device in which information input thereto is recorded. In particular, the processing system 1 acquires template information of a medical document based on the medical information acquired from the information providing device 200, and is used to output a medical document such as a referral letter of another medical institution based on the acquired template information and the medical information. In this way, when outputting a medical document, the processing system 1 can acquire appropriate template information of the medical document, and further output a medical document based on the template information and the medical information, so that an appropriate medical document can be acquired. Further, since the medical document is generated based on the medical information, an efficient medical document can be acquired.

[0012] The processing system 1 according to the present disclosure is typically used in institutions related to medical care. Examples of such facilities include medical institutions, operating institutions of welfare facilities, operating institutions of nursing facilities, operating institutions of various schools, or operating institutions of public facilities. Preferably, a medical institution is an example thereof. In such a medical institution, various medical documents need to be created, such as referral letters to other medical institutions, permission letters permitting entry to school or commuting to workplaces such as schools and workplaces, reports reporting the occurrence of specific diseases for a specified period by countries or local governments, or reports reporting the progress of the medical treatment situation within the institution. Therefore, by using the processing system 1, it becomes possible to efficiently output such medical documents.

[0013] In the present disclosure, the "medical document" may be any document generated using medical information. Therefore, for example, it is not limited to documents generated only in medical institutions or used only in medical institutions. Such medical documents include, in addition to the referral letters to other medical institutions exemplified above, permission letters permitting entry to school or commuting to workplaces such as schools and workplaces, reports reporting the occurrence of specific diseases for a specified period by countries or local governments, or reports reporting the progress of the medical treatment situation within the institution, discharge summaries recording the progress during hospitalization, nursing summaries recording the status of the subject and nursing details in a medical institution, medical fee statements (so-called receipts), detailed descriptions of symptoms related to medical fees, surgical records made on the subject in a medical institution, opinions submitted to the operating institution of life insurance, opinions of attending physicians, home nursing instructions, hospital visit reports, special instructions, death certificates, or autopsy reports. Various documents such as these are given as an example.

[0014] In the present disclosure, "medical information" may be any information that is obtained or used in institutions related to medical care. Therefore, it is not limited to information that is only obtained and used in medical institutions. Such medical information includes information obtained from various medical devices such as CT scanners, MRI scanners, X-ray machines, electrocardiographs, ultrasonic diagnostic devices, endoscopes, sphygmomanometers, or angiographs, interview information input by the subject or medical staff, etc., findings information input by medical staff, etc., diagnostic information as the result of diagnosis by medical staff, etc., or medical history information indicating the medical treatment history in a medical institution, various information such as subject information of the subject, etc., which are given as an example. Specifically, medical information includes chief complaint, past history, allergy history, drug history, name, location, and severity of the disease, examination content and examination findings (examinations using the above medical devices, blood sampling, physiological examinations, and the dates of these examinations), treatment content (surgical procedures, drug administration, and the dates of these treatments), discharge prescription, patient status (patient's degree of independence), degree of dementia, paralysis, limb defects, means of mobility, necessity of medical management (necessity of services related to medical treatment, nursing care, and nursing), outcome at the time of discharge, medical devices used, rehabilitation content, admission route (emergency transport or referral), attached materials (examination results, etc.), date of visit, date of discharge, or progress, etc.

[0015] In the present disclosure, the "subject" may 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 subjects include all humans such as patients, examinees, diagnostic subjects, healthy persons, etc. Also, the "user" may be any person who uses the processing device 100 in the processing system 1, and is not limited to persons with specific attributes. Such subjects include persons belonging to the institutions exemplified above such as medical staff in medical institutions (doctors, nurses, medical technologists, medical office workers, medical institution staff and administrators, emergency team members, persons in charge of medical devices and medical facilities, etc.), the subject himself / herself, etc., including all humans.

[0016] FIG. 1 is a block diagram showing the configuration of a processing system 1 according to an embodiment of the present disclosure. According to FIG. 1, the processing system 1 includes at least a processing device 100 for outputting a medical document based on medical information, and an information providing device 200 for providing medical information to the processing device 100. Further, the processing system 1 may optionally include a measuring device for acquiring measurement data, a learned medical document generation device used for generating a medical document, an output device (for example, a display device, a printer device, or a terminal device of another institution, etc.) to which the medical document is output, or an input device for receiving an operation input by a user. In the processing system 1, various devices including the processing device 100 and the information providing device 200 are communicably connected to each other by at least one of a wireless network and a wired network.

[0017] 2. Configuration of the processing device 100 FIG. 2 is a block diagram showing the configuration of a processing device 100 according to an embodiment of the present disclosure. According to FIG. 2, the processing device 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 device 100 does not necessarily need to include all of the components shown in FIG. 2, and it is possible to configure by omitting some of them, or to add other components. For example, the processing device 100 can include a battery or the like for driving each component.

[0018] As such a processing device 100, any device capable of executing the processing according to the present disclosure, such as a laptop computer, a desktop computer, a smartphone, or a tablet terminal, can be preferably applied. Further, the processing device 100 can also perform at least a part of the processing on one or more server devices on the cloud or one or more server devices operated within a specific institution. Therefore, the processing device 100 includes a laptop computer, a desktop computer, a smartphone, a tablet terminal, a server device, or a combination thereof.

[0019] In the processing device 100, the processor 111 functions as a control unit that controls the processing device 100 or other components of the processing system 1 based on a program stored in the memory 112. Specifically, the processor 111 executes "processing for acquiring medical information corresponding to a subject selected by a user among one or more subjects", "processing for acquiring template information used for generating a medical document based on the acquired medical information", "processing for outputting a medical document generated based on the acquired medical information and template information", etc. based on a program stored in the memory 112. The processor 111 is mainly composed of one or more CPUs, but may appropriately combine a GPU, an FPGA, etc.

[0020] The memory 112 is composed of a RAM, a ROM, a non-volatile memory, an HDD, an SSD, etc. and functions as a storage unit. The memory 112 stores, as a program, instruction commands for various controls of the processing system 1 according to the present embodiment. Specifically, the memory 112 stores programs for the processor 111 to execute "processing for acquiring medical information corresponding to a subject selected by a user among one or more subjects", "processing for acquiring template information used for generating a medical document based on the acquired medical information", "processing for outputting a medical document generated based on the acquired medical information and template information", etc. In addition to the program, the memory 112 may store various information stored in the subject management table and the template management table. Note that these pieces of information do not necessarily have to be always stored in the memory 112 mounted inside the processing device 100, and may be stored in a database device connected externally via a wireless or wired network. Therefore, in such a case, the database device may also be included in the memory 112.

[0021] The input interface 113 functions as an input unit that receives user instructions for the processing device 100. Examples of the input interface 113 include various hard keys such as a keyboard and a mouse, and a touch panel provided superimposed on the display of the display device and having an input coordinate system corresponding to the display coordinate system of the display. In the case of a touch panel, an icon corresponding to a command to be input to the display is displayed, and by the user performing an instruction input via the touch panel, selection and designation of each icon are performed. The detection method of the user's instruction input by the touch panel may be any method such as a capacitance type or a resistive film type. The input interface 113 does not always have to be physically provided in the processing device 100, and may be connected as needed via a wired or wireless network.

[0022] The output interface 114 functions as an output unit for outputting a medical document generated from the processing device 100. Examples of the output interface 114 include an interface for connecting to an external device or external equipment such as a display device composed of a liquid crystal panel, an organic EL display, or a plasma display. However, when the processing device 100 itself has a display, the display can function as an output interface. Also, when connected to a display device or the like via the communication interface 115, the communication interface 115 can also function as the output interface 114.

[0023] The communication interface 115 functions as a communication unit for transmitting and receiving the medical information and the like exemplified above to and from the information providing device 200 via a communication network configured by wire or wirelessly. Examples of the communication interface 115 include various ones such as a wired communication connector such as USB and SCSI, a wireless communication transceiver device such as LTE, wireless LAN, Bluetooth (registered trademark), and infrared rays, and various connection terminals for a printed mounting board and a flexible mounting board.

[0024] Although the specific configuration of the information providing device 200 will not be described in detail, it has at least a processor, a memory, and a communication interface, and includes an input interface, an output interface, etc. as necessary. Examples of such an information providing device 200 include a device for controlling various medical devices, an interview device, an electronic medical record device, a PACS (Picture Archiving and Communication Systems), a database device in which information input thereto is recorded, or a combination thereof. The information providing device 200 reads out necessary information in response to a request received from the processing device 100, for example, and provides it to the processing device 100.

[0025] 3. Information stored in each management table FIG. 3A is a diagram conceptually showing a subject management table stored in the information providing device 200 according to an embodiment of the present disclosure. The information stored in the subject management table is read out from the information providing device 200 in accordance with the progress of the processing of the processor 111 of the processing device 100, and is updated and stored in the information providing device 200.

[0026] According to FIG. 3A, in the subject management table, subject information, interview information, findings information, medical treatment information, etc. are stored in association with the subject ID information. The "subject ID information" is information unique to each subject and is used to identify each subject. The subject ID information is generated each time a new subject is registered by the user or the subject himself / herself. The "subject information" is information regarding the attributes of each subject. Examples of such subject information include subject name information, date of birth information, gender information, means of transportation, and address information, etc.

[0027] "Medical interview information" is information input, for example, by a subject, a medical professional, etc. via a medical interview device. Such medical interview information includes, as an example, information input by the subject himself / herself reporting or a medical professional asking the subject about subjective symptoms, past medical history, current medications, family past medical history, presence or absence of allergies, travel destination, etc. Such medical interview information includes, in addition to the subjective symptoms, past medical history, current medications, family past medical history, presence or absence of allergies, and travel destination exemplified above, information such as body temperature, presence or absence of underlying diseases, presence or absence of physical findings, or vaccination history and its timing. "Findings information" is information input by medical professionals such as doctors, and is information indicating an abnormal condition obtained through examinations such as digital rectal examination, medical interview, and palpation. "Medical treatment information" is information indicating the results and history of medical treatment in a medical institution. Such medical treatment information includes, as an example, information obtained from various medical devices such as CT devices, MRI devices, X-ray devices, electrocardiograph devices, ultrasonic diagnostic devices, endoscope devices, sphygmomanometers, or angiography, chief complaints, disease names (diagnosis names), sites and their severities, examination contents and examination findings (examinations using the above medical devices, blood sampling, physiological examinations, and the dates of these examinations), treatment contents (surgical procedures and surgery dates, drug administrations and administration periods), discharge prescriptions, patient status (patient's degree of independence), degree of dementia, paralysis, limb deficiencies, necessity of medical management (necessity of medical treatment, care, and nursing-related services), outcomes at discharge, medical devices used, rehabilitation contents, admission routes (emergency transfer or referral), visit dates, discharge dates, or progress information, etc.

[0028] Note that in the present disclosure, as described above, the medical information may include any of the subject information, medical interview information, findings information, and medical treatment information.

[0029] FIG. 3B is a diagram conceptually showing a template management table stored in the processing device 100 according to an embodiment of the present disclosure. The information stored in the template management table is read from the memory 112 according to the progress of the processing of the processor 111 of the processing device 100 and updated and stored at an arbitrary timing.

[0030] According to FIG. 3B, in the template management table, for each type of information, template ID information, template information, medical information, etc. are stored. The "type of information" is information for specifying the type of medical document. As an example of the type of information, there are letters of introduction to other medical institutions, permission letters permitting entry to school or commuting to workplaces such as schools and workplaces, reports reporting the occurrence of a specific disease for a predetermined period by countries, local governments, etc., reports reporting the progress of the medical treatment situation within the institution, discharge summaries recording the progress during hospitalization, nursing summaries recording the status of the subject and nursing content in a medical institution, medical fee statements (so-called receipts), detailed descriptions of symptoms related to medical fees, surgical records made on the subject in a medical institution, opinions submitted to the operating agency of life insurance, opinions of the attending physician, home nursing instructions, hospital visit reports, special instructions, death certificates, or autopsy reports, etc.

[0031] The template ID information is information unique to each template information and is information for specifying each template information. The template ID information is generated each time new template information is created. The "template information" is information used as a prototype in the generation of medical documents. As an example of the template document, there is the part excluding the place where information unique to each subject is described in the medical document, that is, the document data of the part common to a plurality of subjects. The data format of such document data may be any format that can be processed in the processing device 100, the terminal device used by medical staff, etc. The "medical information" includes at least any one of the subject information, inquiry information, findings information, and medical treatment information shown in FIG. 3A. A typical example of the medical information shown in FIG. 3B is the diagnosis name.

[0032] According to FIG. 3B, in the template management table, for each type of information of medical documents, one or a plurality of template information are stored in association with the template ID information. That is, for example, even if the type of information is "letter of introduction", different template information is stored for each diagnosis name (medical information).

[0033] The information stored in the template management table may be stored in the memory 112 of the processing device 100, or may be stored in other devices such as other processing devices or database devices.

[0034] FIG. 3C is a diagram showing another example of a template management table stored in the processing device 100 according to an embodiment of the present disclosure. The information stored in the template management table is read from the memory 112 according to the progress of the processing of the processor 111 of the processing device 100, and is updated and stored at an arbitrary timing.

[0035] According to FIG. 3C, in the template management table, for each type of information, template ID information, part ID information, arrangement information, medical information, etc. are stored. The "type of information", "template ID information", and "medical information" are the same as the type of information, template ID information, and medical information shown in FIG. 3B. The part ID information is information unique to each part information and is information for identifying each part information. Here, the "part information" is information on the components that make up the template information that is the prototype of the medical document. For example, taking a letter of introduction as an example, the letter of introduction is composed of a plurality of parts such as a preamble and a closing part, an item name part, a diagnosis name part, a progress part, and a discharge prescription part. That is, as an example, the part information includes the document data that makes up these parts. In addition, parts where the content changes according to medical information such as progress may also be a combination of a plurality of subdivided parts such as an examination part, a surgery part, and a drug treatment part. The part ID information stores one or more pieces of information for identifying the part information that makes up the medical document. For example, when "P1, P2, P3···" is stored as part ID information in association with the template ID information "I1", it means that the template information specified by the template ID information "I1" is composed of the part information specified by P1 to P3, etc. Note that the data format of such document data may be any format that can be processed by the processing device 100 or the terminal device used by medical staff. The "arrangement information" is information indicating the location where the part information specified by the part ID information is arranged in the medical document. For example, information such as the order in which the part information specified by each part ID information is arranged or the coordinates indicating the position within the medical document is used as the arrangement information. In addition, this arrangement information may also be information indicating the location where it is arranged in the medical document by combining with medical information, in addition to the case where it is information indicating the location where it is arranged alone in the medical document.

[0036] According to FIG. 3C, in the template management table, for each type information of medical documents, one or more part information is stored in association with the part ID information. That is, for example, even if the type information is "introduction letter", different template information is stored for each diagnosis name (medical information).

[0037] The information stored in the template management table may be stored in the memory 112 of the processing device 100, or may be stored in other devices such as other processing devices or database devices.

[0038] 4. Processing flow executed by the processing device 100 FIG. 4 is a diagram showing a processing flow executed in the processing device 100 according to an embodiment of the present disclosure. Specifically, FIG. 4 is a diagram showing a series of processing flows from receiving a generation request for a medical document by a user to outputting the medical document. The processing flow is mainly performed by the processor 111 of the processing device 100 reading and executing a program stored in the memory 112.

[0039] According to FIG. 4, the processor 111 receives a generation request for a medical document by a user (S111). As an example of this process, through the input interface 113 of the processing device 100, an instruction input for selecting a subject to be the generation target of the medical document and a type of the medical document, and an instruction input for executing the generation of the medical document are received from the user. That is, the generation request includes subject ID information for identifying the selected subject, type information indicating the type of medical document desired to be generated, and information indicating that the generation of the medical document is requested. As another example of this process, through the input interface of the user terminal device used by the user, an instruction input for selecting a subject to be the generation target of the medical document and an instruction input for executing the generation of the medical document are received from the user to generate a generation request, and the generation request is received from the user terminal device via the communication interface 115.

[0040] Upon receiving a generation request, the processor 111 refers to the subject management table in the memory 112 based on the subject ID information included in the generation request, and reads out medical information associated with the subject ID information (for example, including at least a diagnosis name) (S112).

[0041] FIG. 6 is a diagram showing an example of medical information processed in the processing apparatus 100 according to an embodiment of the present disclosure. Specifically, it shows an example of medical information read by the processor 111 in S112 of FIG. 4. According to FIG. 4, the medical information 10a includes, in association with the subject ID information included in the generation request, stored subject information, interview information, findings information, medical treatment information, etc. stored in the subject management table, information regarding the admission route, the date of visit, the chief complaint, the past medical history, the diagnosis name, examination findings (examination date and examination content), the type of surgery, the surgery date, information regarding drug treatment, the discharge date, the outcome at the time of discharge, and the prescription at the time of discharge, etc.

[0042] Returning to FIG. 4 again, when the medical information is read out, the processor 111 refers to the template management table in the memory 112 based on the read medical information (for example, the diagnosis name) and the type information (for example, the referral letter) included in the generation request, and acquires template information that is a prototype of a desired medical document (S113). Here, as an example of this process, the processor 111 refers to the template management table shown in FIG. 3B and identifies one template information associated with the type information included in the generation request and the read medical information. Details of this process will be described in FIG. 5A. Further, as another example of this process, the processor 111 refers to the template management table shown in FIG. 3C and identifies one template ID information associated with the type information included in the generation request and the read medical information. Details of this process will be described in FIG. 5B. Also, the template information may be specified using a clinical path determined from the medical information as well as the medical information and the type information.

[0043] Here, FIG. 5A is a diagram showing an example of a processing flow executed in the processing device 100 according to an embodiment of the present disclosure. Specifically, FIG. 5A is a diagram showing a detailed processing flow of the process of acquiring the template information of S113 in FIG. 4. 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.

[0044] According to FIG. 5A, the processor 111 reads the medical information of the target person according to S112 in FIG. 4 (S211). When the medical information of the target person is read, the processor 111 refers to the template management table shown in FIG. 3B (S212). At this time, the processor 111 selects one template ID information from a plurality of template ID informations based on the type information included in the generation request received in S111 in FIG. 4 and the read medical information. Then, the processor 111 refers to the template management table in FIG. 3B based on the selected template ID information, and reads the template information associated with the template ID information (S213).

[0045] FIG. 7A is a diagram showing an example of template information processed in the processing device 100 according to an embodiment of the present disclosure. Specifically, it is a diagram showing an example of the template information read according to the process of FIG. 5A. According to FIG. 5A, template information 10b-1 is shown when "introduction letter" is specified as the type information and "cholelithiasis" is specified as the medical information (diagnosis name). The template information 10b-1 includes a preamble and a postscript (for example, a sentence such as "Thank you for your continued support."), item names (for example, "disease name", "course of treatment", etc.), sentences common to each target person (for example, a sentence such as "The patient was introduced to our hospital by... and visited our hospital with... as the main complaint."), and input areas for embedding information specific to the target person (for example, "<diagnosis name>", "<date of visit>", etc.).

[0046] In this way, the processor 111 obtains the template information by reading out one piece of template information from a plurality of pieces of template information according to the processing flow of FIG. 5A.

[0047] FIG. 5B is a diagram showing another example of a processing flow executed in the processing apparatus 100 according to an embodiment of the present disclosure. Specifically, FIG. 5B is a diagram showing a detailed processing flow of the process of obtaining the template information in S113 of FIG. 4. This processing flow is mainly performed by the processor 111 of the processing apparatus 100 reading and executing a program stored in the memory 112.

[0048] According to FIG. 5B, the processor 111 reads out the medical information of the target person according to S112 of FIG. 4 (S311). When the medical information of the target person is read out, the processor 111 refers to the template management table shown in FIG. 3C (S312). At this time, the processor 111 specifies one piece of template ID information from a plurality of pieces of template ID information based on the type information included in the generation request received in S111 of FIG. 4 and the read medical information. Then, the processor 111 specifies one or a plurality of part ID information constituting the template information based on the specified template ID information. When the part ID information is specified, the processor 111 reads out the part information associated with the specified part ID information (S313). The processor 111 generates one piece of template information by connecting the read pieces of part information according to the arrangement information associated with the template ID information (S314).

[0049] FIG. 7B is a diagram showing another example of template information processed in the processing apparatus 100 according to an embodiment of the present disclosure. Specifically, it is a diagram showing an example of template information generated according to the process of FIG. 5B. According to FIG. 5B, template information 10b-2 generated by a plurality of part ID information associated with template ID information specified by type information (for example, an introduction letter) and medical information (for example, cholelithiasis (diagnosis name)) and arrangement information is shown. The template information 10b-2 has each part information arranged side by side according to the arrangement information. Specifically, a preamble part 21a is arranged at the beginning of the template information 10b-2. Below it, there are an item name part 22a of "disease name", a diagnosis name part 23 of "<diagnosis name>", an item name part 22b of "course of treatment", course parts 24a to 24b, an item name part 22c of "prescription at discharge", a prescription at discharge part 25, and a postscript part 21b, respectively.

[0050] In this way, the processor 111 obtains the template information by generating one template information by combining a plurality of part information according to the processing flow of FIG. 5B.

[0051] Returning to FIG. 4 again, when the template information is obtained according to the processing flow of FIG. 5A or FIG. 5B, the processor 111 performs a conversion process on the medical information read in S112 (S114). Specifically, it is desirable that the medical information read in S112 does not preferably include personal information that can identify the individual of the subject. For example, the subject management table includes subject name information, address information, date of birth information, etc. as subject information. In addition, information obtained by a medical device read as the examination content (for example, CT image information) may include subject name information, etc. for identifying the subject. Therefore, when the medical information read includes personal information, the processor 111 executes an anonymization process by character recognition technology or image analysis technology, deletes or masks the personal information, and obtains anonymized information from which the personal information has been removed. Thereby, it is possible to provide a highly secure processing system 1 that takes more security considerations.

[0052] Next, the processor 111 generates query information based on the medical information read in S112 (S115). Here, as an example of the generation of a medical document in the processing flow of FIG. 4, a learned medical document generation model is used. Examples of such a learned medical document generation model include a learned large language model. Query information is information indicating a request input to the learned model. The processor 111 refers to a query management table (not shown) stored in the memory 112 or the like, and reads out one query form information specified based on the read medical information and the type information included in the generation request. Then, the processor 111 generates query information by overwriting the read query form information with the read medical information and the template information acquired in S113, respectively. At this time, the processor 111 may acquire anonymized information from which personal information has been removed as medical information, and generate query information based on the anonymized information.

[0053] FIG. 8 is a diagram showing an example of query information processed in the processing device 100 according to an embodiment of the present disclosure. Specifically, it is a diagram showing an example of query information generated by the process of S115 in FIG. 4. According to FIG. 8, the query information 10c includes a fixed-form area 31a and a fixed-form area 31b that are common contents for each type of information, a medical information area 32 into which the medical information subjected to the conversion process of S114 is input, and a template area 33 into which the template information acquired in S113 is input. Thus, according to the query information illustrated in FIG. 8, the fixed-form area 31a includes, in plain text form, a request for a learned large language model such as "Please create the following information as a polite sentence." and a request for a learned large language model such as "Please formulate the sentence by filling in the '<>' part of the following template." Although it is in plain text form in the example shown in FIG. 8, the form of the query information may be any as long as it is a language or model processable by the learned model, and may be text data, image data, raw data of medical information, data in which medical information is tabulated, a combination thereof, or the like.

[0054] Returning to FIG. 4 again, the processor 111 acquires the medical document generated based on the query information of S115 (S116). As an example, the medical document is acquired by the processor 111 transmitting the query information generated to the processing device that stores the learned large language model via the communication interface 115. In the processing device, when the query information is received, the medical document requested by the query information is created by inputting the query information into the learned large language model. Then, the processor 111 acquires the created medical document by receiving it via the communication interface 115.

[0055] Here, the pre-trained model can be any model generated by machine learning. When using a pre-trained large language model (i.e., a natural language processing model trained using a large amount of text data) as the pre-trained model, various models 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, MED-PaLM, etc. can be utilized. However, it is not limited to this, and models such as BERT, Word2vec, or other neural networks, support vector machines, logistic regression, decision trees, random forests, combinations of these models, etc. may also be used as the pre-trained model.

[0056] FIG. 9 is a diagram showing an example of a medical document output by the processing device 100 according to an embodiment of the present disclosure. Specifically, it is a diagram showing an example of a medical document obtained by the process of S116 in FIG. 4. According to FIG. 9, in the medical document 10d, according to the requirements included in the query information, the medical information included in the query information is filled in the "<○○○>" part in the template information to form a text. Also, in the medical document 10d, according to the requirements included in the query information, not only is the medical information simply embedded in the template information so as to form a more polite text, but the template information is also modified into a more natural language expression.

[0057] Specifically, in regions 41 to 43, region 46, region 48, and region 49, the medical information included in the query information is embedded according to the specification by "<○○○>" in the template information. Also, in regions 44, regions 45a and 45b, and regions 47a and 47b, while embedding the medical information included in the query information according to the specification by "<○○○>" in the template information, terms such as auxiliary words and auxiliary verbs are supplemented or the text of the template information is corrected so as to form an even more natural language expression.

[0058] In this way, by using a pre-trained large language model, it becomes possible to generate a desired medical document not in a formal text expression that simply embeds template information and medical information, but in a more natural language expression.

[0059] When using a model other than a large language model or a combination thereof as a pre-trained model, the information included in the query information is numerically feature-quantified by the pre-trained model, and the medical document can be generated by associating the numerical features with related medical terms or medical documents by clustering or the like. However, it is not limited to this, and a medical document may be generated by other processing using a pre-trained model, such as a method of directly classifying the information included in the query information into medical terms or documents generated using the pre-trained model.

[0060] Returning to FIG. 4 again, when the processor 111 acquires a medical document, the acquired medical document is stored in the memory 112 and the medical document is output (S117). At this time, the processor 111 may determine an output destination according to the content of the acquired medical document. As an example, the processor 111 determines an output destination according to the type of the medical document. Specifically, the processor 111 stores in advance in the template management table the output destination information (for example, email address, IP address, SNS account, or phone number, etc.) that is the output destination of the medical document in association with each template ID information. Then, the processor 111 refers to the template management table based on the template ID information specified in S113 or the like to specify the output destination information, and outputs the acquired medical document to the output destination specified as the output destination information via the output interface 114 or the communication interface 115. As another example, the processor 111 determines an output destination suitable for the treatment of the disease according to the disease name or severity described in the medical document.

[0061] As another example, in the process of a series of processes shown in FIG. 4, an instruction input for specifying output destination information of a medical document is received from a user via the input interface 113, and the acquired medical document is output via the output interface 114 or the communication interface 115 to the received destination information. Such output destinations include those installed in a medical institution to which the user belongs, other medical institutions, an operator of a welfare facility, an operator of a nursing facility, an operator of various schools, or an operator of a public facility, etc., or terminal devices, display devices, control devices of medical equipment, printer devices, etc. that can be used by the persons in charge of these institutions.

[0062] In this way, also for the output destination, by processing it with the processing device 100, it is possible to efficiently output to the output destination according to the type of the medical document.

[0063] Although not particularly detailed about the acquired medical document, the processor 111 can receive an instruction input from the user via the input interface 113 and further modify the acquired medical document. For example, it is possible to modify the text described in the medical document to a more preferred expression, newly add medical information not stored in the subject management table, delete excessive information, or further add information of the medical institution.

[0064] Thus, the said processing flow ends.

[0065] 5. Other examples such as medical documents <When the diagnosis names are different> FIG. 10 is a diagram showing another example of medical information processed in the processing device 100 according to an embodiment of the present disclosure. Further, FIG. 11 is a diagram showing another example of template information processed in the processing device 100 according to an embodiment of the present disclosure. Specifically, FIG. 10 is a diagram showing another example of medical information read out in S112 of FIG. 4. Further, FIG. 11 is a diagram showing another example of template information acquired in S113 of FIG. 4.

[0066] According to FIG. 10, the medical information 20a is medical information that is read out when "introduction letter" is specified as the type information, similar to the example of FIG. 6. Similar to the example of FIG. 6, the medical information 20a includes information regarding the hospitalization route, the date of visit, the chief complaint, the medical history, the diagnosis name, the examination findings (examination date and examination content), information regarding drug treatment, the discharge date, the outcome at the time of discharge, and the prescription at the time of discharge, respectively. On the other hand, in the medical information 20a, the chief complaint is shortness of breath and fever, and the diagnosis name is an internal medicine disease called aspiration pneumonia. Therefore, the type of the diagnosis name is different from that of the medical information 10a in FIG. 6, which is a surgical disease called cholelithiasis. In this way, by setting medical information to be read out for each type information indicating the type of disease (for example, internal medicine disease or surgical disease) specified in advance by the diagnosis name, the processor 111 may be able to read out medical information according to the type information of the disease according to the setting.

[0067] Also, according to FIG. 11, template information 20b generated based on the medical information of FIG. 10 is shown. Specifically, it is shown that the template information 20b is such that template information different from that in FIGS. 7A and 7B (diagnosis name is cholelithiasis) is selected by the processor 111 based on the diagnosis name (for example, aspiration pneumonia) read out as medical information. According to FIG. 11, the template information 20b, unlike the template information 10b-1 and the template information 10b-2 in FIGS. 7A and 7B, includes the description "Improvement was observed due to the administration of <drug content>, so the administration was terminated on <drug administration end date>."

[0068] Note that in the examples of FIGS. 10 and 11, examples of query information and medical documents are not shown, but query information and medical documents are obtained in the same manner except for the differences described in FIGS. 10 and 11. Therefore, the details are omitted.

[0069] <When medical information other than the diagnosis name is different> FIG. 12 is a diagram showing another example of medical information processed in the processing device 100 according to an embodiment of the present disclosure. FIG. 13 is a diagram showing another example of template information processed in the processing device 100 according to an embodiment of the present disclosure. FIG. 14 is a diagram showing another example of query information processed in the processing device 100 according to an embodiment of the present disclosure. FIG. 15 is a diagram showing another example of a medical document output in the processing device 100 according to an embodiment of the present disclosure. Specifically, FIG. 12 is a diagram showing another example of medical information read in S112 of FIG. 4. Further, FIG. 13 is a diagram showing another example of template information acquired in S113 of FIG. 4. Further, FIG. 14 is a diagram showing another example of query information generated in S115 of FIG. 4. Further, FIG. 15 is a diagram showing another example of medical information acquired in S116 of FIG. 4.

[0070] According to FIG. 12, the medical information 30a indicates medical information that is read when "introduction letter" is specified as the type information and "cholelithiasis" is included as the medical information (diagnosis name), similar to the example of FIG. 6. According to the medical information 30a, although the items of the medical information read are the same as those in the example of FIG. 6, the specific content is different in that the examination findings include information such as "2023 / 07 / 10 / chest CT / confirmed / aspiration pneumonia, influenza negative, coronavirus negative".

[0071] Also, according to FIG. 13, template information 30b generated based on the medical information in FIG. 12 is shown. Specifically, it is shown that the template information 30b is such that different template information from that in FIG. 7A was selected by the processor 111 based on the information regarding the examination findings read as medical information. Specifically, according to FIG. 13, the template information 30b includes, based on the examination findings, the description "Admitted on the same day for <Examination Content 1>, <Examination Content 2>, <Examination Content 3>." In this way, by further associating the medical information stored in the template management table with other medical information other than the diagnosis name, it is possible to more flexibly select the template information according to the specific content of the read medical information. The same applies when generating template information by combining part information as shown in FIG. 7B.

[0072] Also, according to FIG. 14, query information 30c generated based on the medical information in FIG. 12 and the template information in FIG. 13 is shown. Specifically, the query information 30c includes, in the same manner as in the example of FIG. 8, a fixed-form area 61a and a fixed-form area 61b that are common contents for each type of information, a medical information area 62 into which the medical information subjected to the conversion process of S114 is input, and a template area 63 into which the template information 30b obtained in S113 is input. In this way, the query information 30c includes, in the same manner as in the example of FIG. 8, a request to the learned large language model in plain text form, "Please create the following information as a polite sentence," and a request to the learned large language model in plain text form, "Please formulate the text by filling in the '<>' part of the following template." On the other hand, when compared with the example of FIG. 8, as shown in FIG. 12, the read medical information is different. Therefore, the query information 30c includes information such as "Influenza negative," "Coronavirus negative," "Drug 1," and "Drug 2" as information regarding the examination findings and drug treatment according to the medical information 30a. Also, when compared with the example of FIG. 9, as shown in FIG. 13, the content of the template information is different. Therefore, the query information 30c includes the information of the template information 30b in the template area 63.

[0073] Also, according to FIG. 15, a medical document acquired based on the query information in FIG. 14 is shown. Specifically, the medical document 30d includes each of the regions 51 to 53, regions 57 and 58, and each of the regions 54a to 56. Among these, in the regions 51 to 53, regions 57 and 58, medical information included in the query information is embedded according to the specification by "<○○○>" of the template information. Also, in the regions 54a to 56, while embedding the medical information included in the query information according to the specification by "<○○○>" of the template information, terms such as auxiliary words and auxiliary verbs are supplemented or the sentences of the template information are corrected so as to have a more natural language expression. In this way, by setting the medical information stored in the template management table in more detail, it is possible to generate the finally generated medical document more flexibly according to the setting.

[0074] As described above, in the present embodiment, it is possible to provide a processing device, a processing program, and a processing method suitable for generating a medical document.

[0075] 6. Others <Trained Medical Document Generation Model> In the above embodiment, the description mainly focuses on the case of generating a medical document by using a pre-trained large language model. However, instead of this, it is also possible to generate a medical document by using other pre-trained medical document generation models or by using pre-determined medical document generation rules. For example, a pre-trained medical document generation model is generated by the following processing flow. The processor 111 acquires, as learning data, the type information and the medical information actually specified by medical staff, etc. when creating a learning medical document. Next, the processor 111 acquires the document data of the learning medical document actually created by using these learning data. Then, the processor 111 executes a step of performing machine learning on the creation pattern of the medical document by using the combination of the learning data of the type information and the medical information and the learning medical document. As an example, in this machine learning, a set of these information is given to a neural network combining neurons, and learning is repeated while adjusting the parameters of each neuron so that the output from the neural network becomes the same as the learning medical document which is the correct label. And through this learning, the step of the processor 111 acquiring a pre-trained medical document generation model is executed (S215). The acquired pre-trained determination model may be stored in the memory 112 of the processing device 100 or in another device connected to the processing device 100 via a wired or wireless network.

[0076] Then, the processor 111 inputs the type information included in the generation request and the medical information converted in S114 of FIG. 4 into the pre-trained medical document generation model generated as described above, and acquires the medical document as an output. In this case, the process related to the generation of the query information in S115 of FIG. 4 can be omitted.

[0077] <Medical Information and Query Information> In the above embodiment, the case where medical information is read from the subject management table in S112 of FIG. 4 has been described. However, instead of this, for example, it is also possible to accept an input of necessary medical information by the user via the input interface 113 and use the medical information for subsequent processing. Also, the case where query information is generated based on medical information and the like in S115 of FIG. 4 has been described. However, instead of this, for example, while the user refers to the medical information output to the display device via the output interface 114, it is also possible to generate query information by accepting an input by the user via the input interface 113.

[0078] <Template information> In the above embodiment, the case where type information and medical information are stored in association with template ID information in the template management table and one template information is acquired based on the type information and the medical information has been described. However, instead of or in addition to the type information and the medical information, further attribute information may be stored in association with the template ID information, and one template information may be generated based on the attribute information. Examples of such attribute information include the ending expression of the text in the medical document ("noun ending" or "verb ending"), the level of detail (a version with many items or a version with few items), the presence or absence of personal information, and the presence or absence of attached measurement data. Thus, by acquiring template information while further considering the attribute information, it becomes possible to set more detailed template information.

[0079] In addition, in the above-described embodiment, the case where the medical document acquired in S116 of FIG. 4 can be modified according to the user's desire has been described. In this regard, when the modification is made to an area other than the area in which the medical information is embedded in the medical document, the processor 111 may read out the template information used for generating the medical document and correct the corresponding area of the template information. Then, the processor 111 stores the corrected template information in association with the new template ID information and makes it available for use in subsequent processing. In this way, when the medical document is modified by the user, by also modifying the corresponding template information, it becomes possible to more efficiently obtain a medical document according to the user's preference.

[0080] Note that the above-described modifications can of course be implemented in appropriate combinations as needed.

[0081] The processes and procedures described in this specification can be realized not only by those explicitly described in the embodiments, but also by software, hardware, or a combination thereof. Specifically, the processes and procedures described in this specification are realized by implementing the logic corresponding to the processes in media such as integrated circuits, volatile memories, non-volatile memories, magnetic disks, and optical storage. In addition, the processes and procedures described in this specification can be implemented as a computer program for those processes and procedures and executed on various computers including a processing device and a server device.

[0082] Even if it is described that the processes and procedures described in this specification are executed by a single device, software, component, or module, such processes or procedures can be executed by a plurality of devices, a plurality of software, a plurality of components, and / or a plurality of modules. Also, even if it is described that various information described in this specification is stored in a single memory or storage unit, such information can be distributed and stored in a plurality of memories provided in a single device or a plurality of memories distributed and arranged in a plurality of devices. Furthermore, the software and hardware elements described in this specification can be realized by integrating them into fewer components or decomposing them into more components.

Description of Reference Numerals

[0083] 1 Processing System 100 Processing Device 200 Information Providing Device

Claims

1. A processing device comprising at least one processor, wherein the at least one processor acquires medical information, acquires template information used for generating a medical document based on the acquired medical information, and outputs the medical document generated based on the acquired medical information and the template information. A processing device configured to execute processing for this purpose.

2. The processing device according to claim 1, wherein the medical document is generated by processing using a learned model.

3. The processing device according to claim 1, wherein the medical document is generated by processing using a learned model based on query information generated using the medical information and the template information.

4. The processing device according to claim 1, wherein the template information is selected from a plurality of template information based on the medical information.

5. The processing device according to claim 1, wherein the template information is selected from a plurality of template information having different contents for each type of medical document to be generated, based on the medical information.

6. The processing device according to claim 5, wherein the template information is selected from the plurality of template information based on the type of medical document selected by the user and the medical information.

7. The at least one processor acquires anonymized information obtained by removing at least a part of the personal information of the subject from the acquired medical information, and the medical document is generated based on the anonymized information and the template information.

8. The processing device according to claim 1, wherein the at least one processor determines an output destination according to the content of the medical document as the output destination of the generated medical document.

9. In a computer comprising at least one processor, causing the at least one processor to acquire medical information, acquire template information used for generating a medical document based on the acquired medical information, and output the medical document generated based on the acquired medical information and the template information. A processing program for functioning in this way.

10. A processing method executed by at least one processor in a computer comprising at least one processor, the method comprising: a step of acquiring medical information, Obtaining template information used for generating a medical document based on the obtained medical information; Outputting the medical document generated based on the obtained medical information and the template information; A processing method including the above.

Images