Information processing system, information processing method and program

Abstract

To provide an information processing system etc. for doctors etc. to more efficiently generate letters of referral to other medical institutions. [Solution] According to one aspect of the present invention, an information processing system is provided, which includes at least one processor, and the processor is configured to execute the following steps by reading a program: in an acquisition step, medical institution information regarding the medical institution that is the user and diagnostic information of a specific patient diagnosed at the medical institution are acquired, the diagnostic information is managed for each patient and includes at least first date information regarding the date the diagnosis was made; and in a first output step, written data for referring the specific patient to another medical institution different from the user is output based on the diagnostic information and at least one reference information, and the written data has medical institution information pre-filled in and uses at least one of the first date information.

Description

[Technical Field]

[0001] The present invention relates to an information processing system, an information processing method, and a program. [Background technology]

[0002] Patent Literature 1 discloses a business support device that facilitates the exchange of information about patients between a referral source medical institution and a referral destination medical institution. The business support device includes a control unit that, each time it detects the occurrence of an event included in a plurality of events related to a patient who visits a second medical institution after being referred from a first medical institution, refers to definition information that defines a time interval until the next report from the second medical institution to the first medical institution, corresponding to each of the plurality of events, calculates a notification time as the time when the time interval corresponding to the event has elapsed from the time the occurrence of the event is detected, and presents notification information that prompts a user to create the next report at the arrival of the calculated notification time. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Publication No. 2023-079933 Summary of the Invention [Problem to be solved by the invention]

[0004] However, the publicly known technology disclosed in Patent Document 1 does not disclose an efficient technology for creating a referral letter, which is the first step in making a referral. There is a demand for a technology that allows doctors and others to more efficiently create referral letters to other medical institutions.

[0005] In view of the above circumstances, the present invention provides an information processing system and the like for doctors and others to more efficiently generate referral letters to other medical institutions. [Means for solving the problem]

[0006] According to one aspect of the present invention, there is provided an information processing system comprising at least one processor, the processor being configured to execute each of the following steps by reading a program: in an acquisition step, medical institution information regarding the medical institution that is the user and diagnostic information of a specific patient diagnosed at the medical institution are acquired, the diagnostic information is managed for each patient and includes at least first date information regarding the date the diagnosis was made; and in a first output step, written data for referring the specific patient to another medical institution different from the user is output based on the diagnostic information and at least one reference information, the written data having medical institution information pre-filled in and using at least one of the first date information.

[0007] According to this aspect, letters of referral to other medical institutions, which are typically issued by doctors, can be generated more efficiently. [Brief explanation of the drawings]

[0008] [Figure 1] 1 is a configuration diagram illustrating an information processing system 1 according to an embodiment. [Figure 2] FIG. 2 is a block diagram showing the hardware configuration of the server device 2. [Figure 3] FIG. 2 is a block diagram showing the hardware configuration of a terminal 3. [Figure 4] FIG. 2 is a block diagram illustrating a functional configuration according to an embodiment. [Figure 5] 1 is a flowchart showing an outline of an information processing method. [Figure 6] 2 is an activity diagram showing a specific example of processing executed by the information processing system 1. FIG. [Figure 7] 1 shows an example of a table 4 storing diagnostic information IF2 and prescription information IF3 accumulated for each patient. [Figure 8] 10 shows a template (an example of reference information IF0) used to create document data 5 that serves as a letter of introduction. [Figure 9]A draft generated based on the diagnostic information IF2 and the like is shown. [Figure 10] This illustrates an example in which there is a discrepancy in dates in the draft of the document data 5, with FIG. 10A showing an example of the details area 56 and FIG. 10B showing an example of the alert to be output. [Figure 11] 1 shows an example of editing by a user on a draft of document data 5. DETAILED DESCRIPTION OF THE INVENTION

[0009] DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS The present invention will be described below with reference to the accompanying drawings. Various features shown in the following embodiments can be combined with each other.

[0010] Incidentally, the program for realizing the software appearing in one embodiment may be provided as a non-transitory computer-readable medium, or may be provided so that it can be downloaded from an external server, or may be provided so that the program is started on an external computer and its functions are realized on a client terminal (so-called cloud computing).

[0011] Furthermore, various information processing according to an embodiment may realize input and output corresponding to the input. Here, the form of information referenced in such information processing (hereinafter referred to as reference information) is not limited as long as an output is obtained as a result of the input. The reference information may be, for example, rule-based information such as a database, a lookup table, or a predetermined function (including a decision formula such as a regression formula constructed using a statistical method), a trained model that has previously trained the correlation between input and output, or a large-scale language model that can output a desired result by inputting a prompt.

[0012] In one embodiment, a "unit" may include, for example, a combination of hardware resources implemented by a circuit in the broad sense and software information processing that can be specifically realized by these hardware resources. In one embodiment, various information is handled, and this information is represented, for example, by physical values ​​of signal values ​​representing voltage and current, high and low signal values ​​as a binary bit set consisting of 0 or 1, or quantum superposition (so-called quantum bits), and communication and calculations can be performed on a circuit in the broad sense.

[0013] Furthermore, a circuit in the broad sense is a circuit realized by at least an appropriate combination of a circuit, circuitry, processor, memory, etc. The processor may be a general-purpose processor or a dedicated circuit. That is, it includes an application specific integrated circuit (ASIC), a programmable logic device (e.g., a simple programmable logic device (SPLD), a complex programmable logic device (CPLD), and a field programmable gate array (FPGA)), etc.

[0014] [Embodiment] 1. Hardware Configuration This section explains the hardware configuration.

[0015] 1.1 Information Processing System 1 FIG. 1 is a configuration diagram illustrating an information processing system 1 according to an embodiment. The information processing system 1 includes a server device 2 and n (n≧1) terminals 3 (e.g., terminals 3-1, 3-2, ..., 3-n), which are connected via a communication network 11. These components will be further described. Here, a system exemplified as the information processing system 1 is made up of one or more devices or components. Therefore, even a single server device 2 or terminal 3 is an example of a system. More specifically, the information processing system 1 may include an element selected from the group consisting of the server device 2 and the terminal 3. Alternatively, multiple server devices 2 or terminals 3 may be used. The unselected elements may not be included in the information processing system 1, but may be electrically connected to the selected elements as external elements.

[0016] 1.2 Server device 2 2 is a block diagram showing the hardware configuration of the server device 2. The server device 2 includes a communication bus 20, a communication unit 21, a storage unit 22, and a processor 23. The communication unit 21, the storage unit 22, and the processor 23 are electrically connected via the communication bus 20 inside the server device 2.

[0017] The communication unit 21 is preferably a wired communication means such as USB, IEEE1394, Thunderbolt (registered trademark), or wired LAN network communication, but may also include wireless LAN network communication, mobile communication such as 3G / LTE / 5G, or BLUETOOTH (registered trademark) communication as needed. That is, it is more preferable to implement it as a collection of multiple communication means. That is, the server device 2 may communicate various information from the outside via the communication unit 21 and the network.

[0018] The storage unit 22 stores various pieces of information defined above. This may be implemented as a storage device such as a solid state drive (SSD), a solid state hybrid drive (SSHD), a hard disk drive (HDD), a universal serial bus (USB) flash drive (USB memory), or an SD memory card that stores various programs and the like related to the server device 2 executed by the processor 23, or as a memory such as a random access memory (RAM) that stores temporarily required information (arguments, arrays, etc.) related to the program operations. The storage unit 22 stores various programs, variables, etc. related to the server device 2 executed by the processor 23.

[0019] The processor 23 processes and controls the overall operations related to the server device 2. The processor 23 is, for example, a central processing unit (CPU) (not shown). The processor 23 realizes various functions related to the server device 2 by reading out predetermined programs stored in the storage unit 22. That is, information processing by software stored in the storage unit 22 is specifically realized by the processor 23, which is an example of hardware, and can be executed as each functional unit included in the processor 23. These will be described in more detail in the next section. Note that the processor 23 is not limited to being single, and multiple processors 23 may be provided for each function. A combination of these may also be used. Furthermore, instead of the processor 23, some or all of these components may be realized by dedicated hardware such as the broadly defined circuit described above.

[0020] 1.3 Terminal 3 3 is a block diagram showing the hardware configuration of the terminal 3. The terminal 3 may be in any form, such as a smartphone, a tablet terminal, a computer, or any other device that can access the server device 2 via an electric communication line. The terminal 3 includes a communication bus 30, a communication unit 31, a storage unit 32, a processor 33, a display unit 34, and an input unit 35. The communication unit 31, the storage unit 32, the processor 33, the display unit 34, and the input unit 35 are electrically connected via the communication bus 30 inside the terminal 3. The description of the communication unit 31, the storage unit 32, and the processor 33 is omitted here because they are the same as the description of each unit in the server device 2.

[0021] The display unit 34 displays a screen of a graphical user interface (GUI) that can be operated by the user. The display unit 34 may be included in the housing of the terminal 3 or may be externally attached. Specifically, the display unit 34 may be implemented as a display device such as a CRT display, a liquid crystal display, an organic EL display, or a plasma display. It is preferable that these display devices are implemented by selectively using them depending on the type of the terminal 3.

[0022] The input unit 35 accepts operation inputs made by the user. The operation inputs are transferred as command signals to the processor 33 via the communication bus 30. The processor 33 can execute predetermined control or calculations based on the transferred command signals as necessary. The input unit 35 may be included in the housing of the terminal 3 or may be externally attached. For example, the input unit 35 may be implemented as a touch panel integrated with the display unit 34. When the input unit 35 is implemented as a touch panel, the user can input tap operations, swipe operations, etc. to the input unit 35. Instead of a touch panel, the input unit 35 may be implemented as a switch button, a mouse, a QWERTY keyboard, etc. Furthermore, the input unit 35 is not limited to the above-mentioned input operations by contact, and may also be implemented as equipment that accepts audio input from a microphone, etc.

[0023] 2. Functional configuration Next, each functional configuration of the information processing system 1 will be described with reference to Fig. 4. Fig. 4 is a block diagram showing the functional configuration according to one embodiment. As shown in Fig. 4, in the server device 2, the processor 23 executes various programs stored in the storage unit 22, thereby functioning as an acquisition unit 231, a reception unit 232, an extraction unit 233, a prediction unit 234, an output unit 235, a display control unit 236, and a calculation unit 237. In other words, information processing by software stored in the storage unit 22 is specifically realized by the processor 23, which is an example of hardware, and can be executed as each functional unit included in the processor 23.

[0024] The acquisition unit 231 is configured to acquire various information as an acquisition step. Specifically, the acquisition unit 231 is configured to be able to receive information via the communication unit 21 or the storage unit 22 and read the information into a working memory. Preferably, the acquisition unit 231 acquires, as an acquisition step, medical institution information IF1 related to a medical institution that is the user and diagnosis information IF2 of a specific patient diagnosed at the medical institution.

[0025] The receiving unit 232 is configured to receive various information or inputs as a receiving step. Preferably, the receiving unit 232 receives editing of the document data 5 by the user as a receiving step.

[0026] The extraction unit 233 is configured to extract various information as an extraction step. Preferably, the extraction unit 233 extracts, from the prescription information IF3, predetermined prescription information IF3 having a relationship with the disease name NM at a predetermined degree or more as an extraction step.

[0027] The prediction unit 234 is configured to predict various information as a prediction step. When making the prediction, some information may be referenced, rule-based information may be referenced, or AI technology such as a trained model or a large-scale language model may be used. Preferably, as a prediction step, the prediction unit 234 predicts the name of an injury or illness NM related to a specific patient based on a diagnostic method, keywords, or diagnostic images included in the diagnostic information IF2.

[0028] The output unit 235 is configured to output various information as an output step. Preferably, as a first output step, the output unit 235 outputs written data 5 for referring a specific patient to another medical institution different from the user's, based on the diagnosis information IF2 and at least one reference information IF0. Also preferably, as a second output step, the output unit 235 outputs an alert (warning information IF4) to the user when there is a discrepancy between the first date information DT1 and the second date information DT2.

[0029] As a display control step, the display control unit 236 executes processing for displaying various pieces of information on a display medium in a manner recognizable to a user. When the phrase "display" is used, it does not matter whether the display medium to be displayed is in a local environment or whether the processing for displaying is performed via the communication network 11. As a result of processing by the display control unit 236, various pieces of information are presented to various users operating the terminal 3, for example, via the display unit 34. The presented various pieces of information are visual information such as screens, images, icons, and messages. The display control unit 236 may generate the visual information itself, or may generate only rendering information for displaying the visual information on the display unit 34.

[0030] The calculation unit 237 is configured to execute, as calculation steps, various calculations related to the server device 2. There is no particular restriction on the type of calculation.

[0031] 3. Information Processing Method This section describes an information processing method executed by the information processing system 1. Note that the order of processes included in the information processing method can be changed as appropriate, multiple processes may be executed simultaneously, or some processes may be omitted.

[0032] 3.1 Overview 5 is a flowchart showing an outline of the information processing method. Each step shown in FIG. 5 will be described below.

[0033] The information processing system 1 includes at least one processor 23, and the processor 23 is configured to execute the following steps by reading a program. That is, an information processing method according to one embodiment includes the following steps. First, in an acquisition step, medical institution information IF1 related to the medical institution that is the user and diagnostic information IF2 of a specific patient diagnosed at the medical institution are acquired (step S001). The diagnostic information IF2 is managed for each patient and includes at least first date information DT1 related to the date the diagnosis was made. Next, in a first output step, written data 5 for introducing the specific patient to another medical institution different from the user is output based on the diagnostic information IF2 and reference information IF0 (step S002). The written data 5 is pre-filled with medical institution information IF1 and uses at least one piece of first date information DT1.

[0034] Furthermore, a program for causing a computer to execute each step of the information processing method may be provided.

[0035] According to this aspect, it is possible to more efficiently generate letters of referral to other medical institutions, as is done by doctors, etc. Conventionally, when creating a letter of referral, a user has had to go through a process of trial and error, taking into consideration past diagnostic results, etc., which has resulted in the blind use of a computer, wasting time, processing, and power, but by realizing information processing in a seamless manner as in this configuration, it is possible to improve the efficiency of processing and reduce wasted power.

[0036] 3.2 Specific examples A specific example may be included within the scope specified in the above-mentioned overview. In this specific example, the following situation is assumed. First, an administrator managing the server device 2 provides a service (hereinafter referred to as the present service) via the Internet that enables one medical institution to efficiently create referral letters for referring patients to another medical institution. In other words, the present service is a type of SaaS that uses a website (hereinafter referred to as the specific site) provided by the server device 2. Various medical institutions employing medical professionals such as doctors and nurses use the service. A user account may be issued for each medical institution or its department, individual doctor, etc., and such user information will be referred to as medical institution information IF1.

[0037] When using this service, the user provides data on the results of previous patient diagnoses, i.e., diagnostic information IF2, to the server device 2. The method of providing the diagnostic information IF2 is not particularly limited; this service may be used for the official management of the diagnostic information IF2, or the diagnostic information IF2 may be provided to this service by API linking this service with an electronic medical record system used separately within the medical institution. The user can use this service to register new diagnostic information IF2 for a patient and / or view diagnostic information IF2 that has already been registered.

[0038] A certain medical institution conducts simple tests related to cognitive function. That is, in one embodiment, a patient is at risk of cognitive decline and is undergoing tests related to cognitive function at a medical institution. It is assumed that the test results are problematic and a referral letter needs to be sent to another medical institution for more detailed testing. In other words, the diagnostic information IF2 includes information related to the patient's cognitive function. According to this embodiment, a specific patient with an illness or injury related to cognitive function can be efficiently referred to another medical institution while reducing the workload of the referring institution.

[0039] 6 is an activity diagram showing a specific example of processing executed by the information processing system 1. Below, an explanation will be given along with each activity shown in FIG.

[0040] In providing this service, the server device 2 successively receives new diagnostic information IF2 provided by various users (e.g., medical institutions) (activity A101). The received diagnostic information IF2 is associated with a patient ID for identifying the patient and stored in the storage unit 22 of the server device 2. That is, the diagnostic information IF2 is accumulated as data of the corresponding patient (activity A102). The association of the patient ID, diagnostic information IF2, and other information will be described later with reference to FIG. 7.

[0041] Below, we will explain the processing related to activities A201 to A215, assuming that a certain user uses this service, separately from activities A101 and A102. First, the processor 33 of the terminal 3 held by the user accesses a specific site provided by the server device 2 via the communication network 11 (activity A201).

[0042] Next, account information corresponding to the user is input via the input unit 35 of the terminal 3 within the specific site, and authentication processing is performed, whereby the calculation unit 237 of the server device 2 performs processing to identify the user (activity A202). In other words, in the server device 2, the acquisition unit 231 acquires medical institution information IF1 related to the medical institution that is the user as an acquisition step. This allows the user to view a screen (not shown) for enjoying this service. Note that the user's account may be registered in advance, or the user may register a new account immediately before activity A202. The user's account may be an account having information registered for this service, or may be an account associated with an account for another service or system, for example, linked to an account for an existing electronic medical record system.

[0043] Next, the user inputs a patient ID for identifying the patient via the input unit 35 (activity A203), and the input patient ID is transmitted to the server device 2 via the communication network 11. In the server device 2, the calculation unit 237 identifies the patient based on the patient ID (activity A204). Thereafter, the display control unit 236 displays a screen (not shown) including information about the corresponding patient (hereinafter referred to as the “specific patient”) on the display unit 34 of the terminal 3 (activity A205). In other words, the acquisition unit 231 acquires diagnostic information IF2 of the specific patient diagnosed at a medical institution as an acquisition step. The diagnostic information IF2 is managed for each patient and includes at least first date information DT1 related to the date the diagnosis was made. Preferably, the acquisition unit 231 also acquires prescription information IF3 related to the prescribed medication in addition to the diagnostic information IF2 as an acquisition step. The prescription information IF3 further includes second date information DT2 related to the date the medication was prescribed.

[0044] Here, we will provide the following additional information regarding prescription information IF3. The method by which pharmacies can access prescription information may involve assigning an ID and password to each pharmacy or pharmacist, allowing access only to prescription information based on such information, or it may be in the form of a login to a website dedicated to pharmacies or pharmacists. In the above case, it is preferable that diagnostic information IF2 not be included in the information that pharmacists or pharmacies can view, regardless of the login method. By not including diagnostic information IF2, it is possible to digitize prescription information while maintaining security.

[0045] Next, the screen displayed on the display unit 34 includes, for example, a button (not shown), and when the user presses the button (activity A206), the creation of the referral letter provided by this service is executed. In other words, in the server device 2, when the reception unit 232 receives a process related to the button press, the calculation unit 237 starts various processes for creating the referral letter. Here, as one of the various processes, the prediction unit 234 predicts the illness / injury name NM related to the specific patient based on the diagnostic method, keywords, or diagnostic image included in the diagnostic information IF2 as a prediction step. For the prediction by the prediction unit 234, a trained model (an example of reference information IF0) that has trained the relationship between the diagnostic information IF2 and the illness / injury name NM so as to output the illness / injury name NM when the diagnostic information IF2 is input may be employed. Thereafter, the display control unit 236 displays the predicted illness / injury name NM on the display unit 34 so that it can be presented to the user as a candidate (activity A207). Note that multiple candidate illness / injury names NM may be presented. In particular, by employing a plurality of pieces of information contained in the diagnostic information IF2, such as the diagnostic method, keywords, or diagnostic images, the accuracy of prediction can be improved.

[0046] Next, the user visually checks the candidate illness / disease names NM displayed on the display unit 34 and performs a selection operation (activity A208). For example, text information such as "suspected mild dementia" is presented as a candidate, and the user visually checks it and performs a selection operation. When the receiving unit 232 receives a process related to the selection operation, the output unit 235 generates a draft of a referral letter by embedding various information identified or generated from the diagnostic information IF2 in a preset template (an example of reference information IF0) (activity A209), and outputs the generated draft. In other words, as a first output step, the output unit 235 outputs document data 5 (including a draft) for referring a specific patient to a medical institution other than the user, based on the diagnostic information IF2 and at least one piece of reference information IF0. Preferably, as the first output step, the output unit 235 outputs document data 5 including the predicted illness / disease name NM. This aspect is preferable because it reduces the workload of the referral source and creates a referral letter in which the illness / disease name NM is clearly written for the referral destination.

[0047] The disease name NM may include various disease candidates, such as cancer (including various cancers such as breast cancer, prostate cancer, and pharyngeal cancer), mild cognitive impairment (MCI), dementia, high blood pressure, myocardial infarction, cerebral infarction, ALS, Parkinson's disease, Hashimoto's disease, diabetes, pneumonia, and conjunctivitis. For example, if the disease name is cancer, the data may include data from genetic testing of a portion of the cancer tissue. Using the results of genetic testing, such as those described above, it is possible to predict the risk of recurrence and organs prone to recurrence using machine learning and other methods. Furthermore, since the predictions can help patients and doctors decide on treatment options (e.g., whether to use medication or radiation therapy, and what medications to administer), it is preferable that the data also include data from genetic testing, such as those described above. Furthermore, if the disease name is dementia or mild cognitive impairment (MCI), the severity of the disease may be predicted using a minimally invasive method using biometric data such as voice. The prediction method may also predict the correlation with neuropsychological test values. Neuropsychological tests include the MOCA and MMSE. It is preferable to predict the degree of cognitive function using voice, because predicting the correlation with the indicators of the neuropsychological test described above allows for a simple test without placing a burden on the subject for a long period of time, as is the case with neuropsychological tests.

[0048] Furthermore, if the above-mentioned illness is dementia or mild cognitive impairment (MCI), a method capable of measuring the amount of amyloid beta in the body may be used. A method capable of measuring amyloid beta may be used alone or in combination with voice diagnosis. Combining it with voice diagnosis can improve the degree of prediction of the level of cognitive function. Methods for measuring amyloid beta include blood tests and amyloid PET (a method of imaging the amount of amyloid beta protein accumulated in the brain using a drug that accumulates in amyloid beta protein).

[0049] More specifically, in the process of generating a draft related to activity A209, a trained model or a large-scale language model may be used as an example of reference information IF0. By using the trained model or the large-scale language model with the injury / illness name NM and the diagnostic information IF2 selected by the user as input parameters, a draft sentence for explaining the condition of the injury / illness name NM may be generated based on the injury / illness name NM. In other words, the reference information IF0 is a machine learning model or a large-scale language model (hereinafter referred to as a model) configured to generate information for introduction when the diagnostic information IF2 is input. As a first output step, the output unit 235 inputs the diagnostic information IF2 into the model to generate information contained in the written data 5, and outputs the written data 5 including the generated information. According to this aspect, information presented by AI technology can be easily reflected in generating a letter of introduction.

[0050] In addition, it is preferable to extract prescription information IF3 whose relevance is inferred from the disease name NM. In other words, the extraction unit 233 extracts, as an extraction step, from the prescription information IF3, predetermined prescription information IF3 that has a relationship with the disease name NM at a predetermined level or higher. As a first output step, the output unit 235 outputs written data 5 in a manner that allows the extracted predetermined prescription information IF3 to be understood. According to this embodiment, a letter of referral is created after predetermined prescription information IF3 that is considered to be particularly highly relevant to a specific disease or injury is identified in advance from various prescription information IF3, thereby reducing the workload of the referral source. More specifically, the calculation unit 237 first calculates parameters indicating the relevance between the disease name NM and various prescription information IF3. Next, the calculation unit 237 calculates the number of days elapsed from the date of medication or prescription to the present. Next, the prediction unit 234 predicts the impact of the prescription based on the previously calculated parameters and the number of days elapsed. For the prediction, a model such as a trained model or a large-scale language model may be used as reference information IF0. Then, the extraction unit 233 extracts prescription information IF3 in which the influence of the prescription on the disease name NM is expected to be greater than or equal to a predetermined value.

[0051] More specifically, it is known that antipsychotics, antidepressants, hypnotics, sedatives, antiparkinsonian drugs, antiepileptic drugs, antihypertensive drugs, antiarrhythmic drugs, diuretics, digitalis preparations, analgesics (NSAIDs, opioids), corticosteroids, antibiotics, antiviral drugs, anticancer drugs, drugs for overactive bladder, gastrointestinal drugs (H2 receptor antagonists, anticholinergics), asthma drugs, allergy drugs (antihistamines), etc. may cause dementia-like symptoms as side effects. Therefore, in order to make it easier for specialists to make judgments based on the effects of medication or medication that may cause side effects such as those described above, it is preferable to calculate the effects of medication or prescription (effects due to the number of days elapsed, dosage, etc.), and to display the calculation results if they are equal to or greater than a predetermined value.

[0052] Furthermore, as people age, at a time when they are more susceptible to the development of dementia, their physical strength declines and they are more likely to suffer injuries from falls, etc. In particular, if the injury is to the head, symptoms of cognitive decline similar to dementia may appear. Examples of cognitive decline include traumatic subarachnoid hemorrhage and traumatic brain injury. Therefore, information about past trauma can be an important clue for specialists to make a diagnosis, and it is required to be included in referral letters as necessary. Therefore, it is recommended that information about past trauma be included based on its relevance to the diagnosed illness.

[0053] Furthermore, it is assumed that the draft of the letter of introduction includes a diagnosis based on the diagnosis information IF2 along with the date of diagnosis (an example of first date information DT1), and a prescription based on the prescription information IF3 along with the date of prescription (an example of second date information DT2) (see FIG. 9, etc., described later). Subsequently, in the server device 2, the calculation unit 237 executes a process of comparing the first date information DT1 and the second date information DT2 included in the generated draft and determining whether there is any discrepancy between them (activity A210). Thereafter, as a second output step, the output unit 235 outputs an alert (warning information IF4) to the user if there is a discrepancy between the first date information DT1 and the second date information DT2 (activity A211). This will be described in detail later using FIG. 10, etc.

[0054] Next, regardless of whether an alert related to activity A211 is issued, the user visually checks the generated draft and performs the necessary addition operation. In other words, in the server device 2, the receiving unit 232 receives a process related to the addition operation. The draft is updated by the addition operation, and the draft after the addition operation is sequentially presented to the user (activity A213). Then, when the user determines that proofreading of the draft is complete, the user presses a confirm button (not shown) (activity A214). In the server device 2, when the receiving unit 232 receives a process related to pressing the confirm button, formal document data 5 is output to the local environment of the terminal 3. The format of the document data 5 is not particularly limited, and may be a PDF format or a format editable by general-purpose software such as MS Word.

[0055] The above is the process flow according to the specific example. Note that the above assumptions and process flow are merely examples and are not limited to these.

[0056] 4. Related technical matters The following describes in detail technical matters related to the above-mentioned information processing method.

[0057] 4.1 Table 4 FIG. 7 shows an example of Table 4 storing diagnostic information IF2 and prescription information IF3 accumulated for each patient. In Table 4, "patient name," "diagnostic information IF2," and "prescription information IF3" are stored in association with a "patient ID." As shown in the figure, a patient with a patient ID of "100001" has a patient name of "Takken Taro" and is associated with three pieces of diagnostic information IF2 and three pieces of prescription information IF3. Preferably, the diagnostic information IF2 includes, in association with first date information DT1, a symptom severity DG corresponding to the first date information DT1. More specifically, the diagnostic information IF2 includes a "date" (first date information DT1), a "detail," and a "symptom level" (symptom severity DG), and the prescription information IF3 includes a "date" (second date information DT2) and a "detail." The symptom severity DG is preferably quantitative information, and may be, for example, a score equivalent to the MOCA-J. Furthermore, the patient with patient ID "100002" has the patient name "Trademark Hanako" and is associated with four pieces of diagnosis information IF2 and three pieces of prescription information IF3. Specifically, the first date information DT1 includes November 30, 2019, but the second date information DT2 does not include the same date. In other words, it can be inferred that only a diagnosis was made on that day, and no medication was prescribed.

[0058] In this way, by associating the patient ID, the diagnosis information IF2, and the prescription information IF3, it is possible to extract the associated information using the patient ID as an index. It is also possible to perform filtering using detailed items such as the date and the level of the condition. Note that other information not shown may also be stored in Table 4.

[0059] 4.2 Written Data5 FIG. 8 shows a template (an example of reference information IF0) used to create document data 5 that will serve as a letter of referral. FIG. 9 shows a draft generated based on diagnosis information IF2 and the like. As shown in FIGS. 8 and 9, the document data 5 and its template include areas 51 to 55 and a details area 56. It should be noted that in one embodiment, medical institution information IF1 is pre-filled in the document data 5, and at least one piece of first date information DT1 is used.

[0060] Specifically, area 51 displays text information such as "Name of Referral Medical Institution, etc.", allowing input of information about the referring physician, etc. In this service, as shown in FIG. 9, the draft may be output blank. However, the referral medical institution may be registered in this service and output via this service. Area 52 displays the current date of output of document data 5, which may be automatically entered when the draft is generated. Area 53 displays text information such as "Address and Name of Referral Medical Institution," which corresponds to the information to be entered, such as the medical institution information IF1 described above. In one embodiment, this may be automatically entered when the draft is generated. Area 54 displays text information such as "Name of Injury or Illness," which corresponds to the information to be entered, such as the name of the injury or illness NM predicted by the prediction unit 234 and selected by the user. In one embodiment, this may be automatically entered when the draft is generated. Area 55 displays text information such as "Purpose of Referral," allowing input of the purpose of referring a specific patient to the referral medical institution. When generating the draft, a sentence indicating the purpose inferred from the diagnostic information IF2 may be generated and automatically entered using a model such as a trained model or a large-scale language model (an example of reference information IF0). Furthermore, detailed information based on the diagnostic information IF2 and prescription information IF3 is entered in the details area 56.

[0061] The details area 56 includes areas 561 to 564. Areas 561 to 564 respectively depict text information such as "Medical History," "Progress of Medical Condition and Test Results," "Treatment Progress," and "Current Prescription." In one embodiment, "Medical History" and "Treatment Progress" may be output as blank fields for the user to fill in.

[0062] In the "Disease Progress and Test Results" column, information should be entered based on the accumulated diagnostic information IF2 so that the first date information DT1 and the entered items can be understood. The entered items should include the disease level (an example of the degree of disease DG). The entered items may be generated using a model, or text information included in the diagnostic information IF2 itself may be entered. In other words, as a first output step, the output unit 235 outputs written data 5 including the associated first date information DT1 and the degree of disease DG. This embodiment is preferable because it reduces the workload of the referring source and creates a letter of referral in a manner that makes it easy for the referred patient to understand the date and the patient's condition at the time.

[0063] In the "Current Prescription" column, information may be entered based on the accumulated prescription information IF3 so that the second date information DT2 and its description can be understood. The description may be generated using a model, or text information contained in the prescription information IF3 itself may be entered. In other words, the output unit 235 outputs written data 5 including the prescription information IF3 as a first output step. This embodiment is preferable because it reduces the workload of the referring party and creates a letter of introduction in a manner that allows the referring doctor to easily understand the medications that have already been prescribed.

[0064] 10A shows an example of a detailed area 56, and FIG. 10B shows an example of an alert (warning information IF4) that is output. FIG. 11 shows an example of editing by a user on a draft of document data 5. As shown in FIG. 10A, first date information DT1 drawn in area 562 is July 25, 2024, while second date information DT2 drawn in area 564 is June 17, 2024.

[0065] While the diagnosis date and prescription date are typically the same, this is not always the case, potentially resulting in an incorrect extraction by this service. Therefore, to encourage users with accurate medical knowledge to make a final decision, if there is a discrepancy between the first date information DT1 and the second date information DT2, the system presents the user with warning information IF4 (alert), as shown in FIG. 10B . Specifically, the warning information IF4 is displayed in area 61 of the pop-up 6, stating, "The dates in the symptom progression and test results fields do not match the dates in the current prescription field! Please check and correct if necessary!" This configuration allows referral sources using the system to be notified of system errors and subsequent human errors resulting from manual editing.

[0066] When an alert is issued, the user edits the draft of the document data 5, as shown in FIG. 11 . In one embodiment, the first date information DT1 in the area 562 is revised to June 17, 2024. At this time, a display 57 containing the text information "revised" may be visibly displayed, for example, in the lower right corner of the area 562. This allows the user to visually understand that the automatic input by the service has been revised by the user. Furthermore, when a model such as a trained model or a large-scale language model is used as the reference information IF0, re-learning may be performed using the user's edits as training data. In other words, the receiving unit 232 receives the user's edits of the document data 5 as a receiving step. The model is configured to re-learn using information included in the edited document data 5. According to this aspect, the accuracy of the system can be improved with repeated use.

[0067] [others] The information processing system 1 according to the above embodiment may be configured as follows.

[0068] At least one of the devices included in the information processing system 1 may be installed outside Japan. For example, the server device 2 or a server may be installed outside Japan, and the terminal 3 may be installed inside Japan. Similarly, a user may access the server device 2 installed inside Japan from outside Japan using his / her own terminal 3. According to such an embodiment, a more convenient experience can be provided to the user through various management modes.

[0069] In one embodiment, the acquisition unit 231, the reception unit 232, the extraction unit 233, the prediction unit 234, the output unit 235, the display control unit 236, and the calculation unit 237 are described as functional units implemented by the processor 23 of the server device 2, but at least some of these may be implemented as functional units implemented by another server. Alternatively, they may be implemented as functional units implemented by the processor 33 of the terminal 3. Furthermore, the various pieces of information described in the above example may be stored not only in the storage unit 22 of the server device 2, but also in a distributed manner in other external devices.

[0070] The user's input or editing operations may be voice input. Furthermore, the diagnostic information IF2 is not limited to text information, and may include a doctor's voice explaining the procedure or medical images captured by a medical imaging device.

[0071] In one embodiment, warning information IF4 (alert) is output when there is a discrepancy between the first date information DT1 and the second date information DT2. However, this is not limiting and various types of warning information IF4 indicating the possibility of an error may be output. Since lies and mistakes are likely to occur, particularly when a large-scale language model is employed, some kind of reference information IF0 (preferably rule-based) for checking authenticity may be separately employed. If the check items are met, i.e., if a lack of authenticity is anticipated, some kind of warning information IF4 (alert) may be output. Furthermore, the warning information IF4 is not limited to the pop-up 6 shown in FIG. 10A , but may also be implemented, for example, by a function such as that of MS WORD, which adds a comment to the relevant section.

[0072] When accessing the Service, measures may be added to further strengthen security. For example, unauthorized access using programs can be prevented by various measures, such as authentication using character reading called CAPTCHA or by clicking a check box that says "I am not a robot."

[0073] In one embodiment, the document data 5 is ultimately output to the local environment of the terminal 3. Alternatively, the document data 5 may be printed on paper using a printer installed at the user's medical institution. Alternatively, the document data 5 may be sent to the referral medical institution, for example, as an attachment to an email. Furthermore, the service may have a direct message function, and the document data 5 may be shared with the referral medical institution using this function. When sending the document data 5 via email or direct message, not only the document data 5 but also at least a portion of the diagnostic information IF2 (hereinafter referred to as related data) may be sent together with the document data 5. In such a case, a method may be used in which, after a certain period of time has passed, a notification is sent to the referring medical institution, and the related data is returned to the referring medical institution. Furthermore, the related data may be deleted after the referring medical institution confirms receipt.

[0074] Furthermore, it may be provided in the following aspects.

[0075] (1) An information processing system comprising at least one processor, the processor being configured to execute each of the following steps by reading a program: in an acquisition step, medical institution information regarding a medical institution that is a user and diagnostic information of a specific patient diagnosed at the medical institution are acquired, wherein the diagnostic information is managed for each patient and includes at least first date information regarding the date the diagnosis was made; and in a first output step, written data for referring the specific patient to another medical institution different from the user is output based on the diagnostic information and at least one reference information, wherein the medical institution information is pre-filled in the written data and at least one of the first date information is used.

[0076] According to this aspect, it is possible to more efficiently generate letters of referral to other medical institutions, as is done by doctors, etc. Conventionally, when creating a letter of referral, a user has had to go through a process of trial and error, taking into consideration past diagnostic results, etc., which has resulted in the blind use of a computer, wasting time, processing, and power, but by realizing information processing in a seamless manner as in this configuration, it is possible to improve the efficiency of processing and reduce wasted power.

[0077] (2) In the information processing system described in (1) above, the diagnostic information includes the first date information and the degree of the condition corresponding to the first date information in association with each other, and in the first output step, the written data including the associated first date information and the degree of the condition is output.

[0078] This is preferable because it reduces the workload of the referring party and creates a letter of referral in a way that makes it easy for the referred party to understand the date and the patient's condition at the time.

[0079] (3) In the information processing system described in (1) or (2) above, the acquisition step further acquires prescription information regarding the prescribed drug, and the first output step outputs the written data including the prescription information.

[0080] This type of configuration is preferable because it reduces the workload of the referring party while creating a referral letter in a manner that allows the referring doctor to easily understand the medications that have already been prescribed.

[0081] (4) In the information processing system described in (3) above, the prescription information further includes second date information regarding the date on which the drug was prescribed, and further, in the second output step, an alert is output to the user if there is a discrepancy between the first date information and the second date information.

[0082] According to this aspect, system errors and subsequent human errors caused by manual editing can be notified to referral sources using the system.

[0083] (5) In the information processing system described in any one of (1) to (4) above, the prediction step further predicts the name of the injury or illness related to the specific patient based on the diagnostic method, keyword, or diagnostic image contained in the diagnostic information, and the first output step outputs the written data including the predicted name of the injury or illness.

[0084] This is preferable because it reduces the workload of the referral source and creates a referral letter that clearly states the name of the illness or injury for the referral recipient.

[0085] (6) In the information processing system described in (5) above, the acquisition step further acquires prescription information regarding the prescribed medicine, and the extraction step further extracts, from the prescription information, specific prescription information that has a relationship with the name of the injury or illness to a specified degree or more, and the first output step outputs the written data in a manner that allows the extracted specific prescription information to be understood.

[0086] According to this aspect, a letter of referral is created after specific prescription information that is considered to be particularly relevant to a specific injury or illness is identified in advance from among various prescription information, thereby reducing the workload of the referring party.

[0087] (7) The information processing system according to any one of (1) to (6) above, wherein the diagnostic information includes information about the patient's cognitive function.

[0088] According to this aspect, a specific patient with an injury or illness related to cognitive function can be efficiently referred to another medical institution while reducing the workload of the referring institution.

[0089] (8) In the information processing system described in any one of (1) to (7) above, the reference information is a machine learning model or a large-scale language model (hereinafter referred to as a model) configured to generate information to be introduced when the diagnostic information is input, and in the first output step, the diagnostic information is input into the model to cause the model to generate information contained in the written data, and the written data including the generated information is output.

[0090] According to this aspect, when generating a letter of introduction, it is possible to easily reflect information presented by AI technology.

[0091] (9) In the information processing system described in (8) above, the system further comprises a receiving step for receiving edits to the written data by the user, and for the model to be re-learned using information contained in the edited written data.

[0092] This allows the accuracy of the system to improve with use.

[0093] (10) An information processing method, comprising the steps of the information processing system according to any one of (1) to (9) above.

[0094] According to this aspect, it is possible to more efficiently generate letters of referral to other medical institutions, as is done by doctors, etc. Conventionally, when creating a letter of referral, a user has had to go through a process of trial and error, taking into consideration past diagnostic results, etc., which has resulted in the blind use of a computer, wasting time, processing, and power, but by realizing information processing in a seamless manner as in this configuration, it is possible to improve the efficiency of processing and reduce wasted power.

[0095] (11) A program that causes a computer to execute each step of the information processing system according to any one of (1) to (9) above.

[0096] According to this aspect, it is possible to more efficiently generate letters of referral to other medical institutions, as is done by doctors, etc. Conventionally, when creating a letter of referral, a user has had to go through a process of trial and error, taking into consideration past diagnostic results, etc., which has resulted in the blind use of a computer, wasting time, processing, and power, but by realizing information processing in a seamless manner as in this configuration, it is possible to improve the efficiency of processing and reduce wasted power. Of course, this is not the case.

[0097] Finally, while various embodiments of the present disclosure have been described, they are presented as examples and are not intended to limit the scope of the invention. The novel embodiments may be embodied in various other forms, and various omissions, substitutions, and modifications may be made without departing from the spirit of the invention. Such embodiments and modifications are intended to be included within the scope and spirit of the invention, as well as within the scope of the inventions and their equivalents as defined in the claims. [Explanation of symbols]

[0098] 1: Information processing system 11: Communication Network 2: Server device 20: Communication bus 21: Communications Department 22: Storage section 23: Processor 231: Acquisition Department 232: Reception 233:Extraction part 234: Prediction section 235: Output section 236: Display control unit 237: Arithmetic section 3: Terminal 30: Communication bus 31: Communications Department 32: Storage section 33: Processor 34: Display section 35: Input section 4: Table 5: Written data 51 :Area 52 :Area 53: Area 54 :Area 55 :Area 56 :Detail area 561 :Area 562: area 563 :Area 564 :Area 57 :Display 6: Pop-up 61 :Area DG: Degree DT1: First date information DT2: Second date information IF0 : Reference Information IF1: Medical institution information IF2: Diagnostic information IF3: Prescribing Information IF4: Warning information NM:Injury / illness name

Claims

1. An information processing system, At least one processor is provided, the processor being configured to execute the following steps by reading a program: In the acquisition step, medical institution information relating to the medical institution that is the user and diagnostic information of a specific patient diagnosed at the medical institution are acquired, and the diagnostic information is It is managed for each patient at least first date information relating to the date the diagnosis was made; In a first output step, the system outputs written data for referring the specific patient to another medical institution different from the user based on the diagnostic information and at least one reference information, wherein the written data has the medical institution information pre-filled in and at least one of the first date information is used.

2. 2. The information processing system according to claim 1, the diagnosis information includes the first date information and a degree of a disease corresponding to the first date information in association with each other; In the first output step, the system outputs the written data including the associated first date information and the severity of the medical condition.

3. 2. The information processing system according to claim 1, The obtaining step further includes obtaining prescription information regarding the prescribed drug; In the first output step, the system outputs the written data including the prescription information.

4. 4. The information processing system according to claim 3, the prescription information further includes second date information relating to the date the drug was prescribed; Furthermore, in the second output step, if there is a discrepancy between the first date information and the second date information, an alert is output to the user.

5. 2. The information processing system according to claim 1, Furthermore, in the prediction step, a name of an injury or illness related to the specific patient is predicted based on a diagnostic method, a keyword, or a diagnostic image included in the diagnostic information; In the first output step, the system outputs the written data including the predicted name of the injury or illness.

6. 6. The information processing system according to claim 5, The obtaining step further includes obtaining prescription information regarding the prescribed drug; Furthermore, in the extraction step, predetermined prescription information having a relationship with the disease name of a predetermined degree or more is extracted from the prescription information, In the first output step, the system outputs the written data in a manner that allows the extracted predetermined prescription information to be understood.

7. 2. The information processing system according to claim 1, The diagnostic information includes information regarding the patient's cognitive function.

8. 2. The information processing system according to claim 1, The reference information is a machine learning model or a large-scale language model (hereinafter referred to as a model) configured to generate information to be introduced when the diagnostic information is input, In the first output step, the system inputs the diagnostic information into the model to cause the model to generate information contained in the written data, and outputs the written data including the generated information.

9. 9. The information processing system according to claim 8, Furthermore, in the receiving step, editing of the document data by the user is received, The system is configured to retrain the model using information contained in the edited written data.

10. An information processing method, comprising: A method comprising the steps of the information processing system according to any one of claims 1 to 9.

11. A program, A program that causes a computer to execute each step of the information processing system according to any one of claims 1 to 9.

Images