Computer program, information processing method, and information processing device

Abstract

Provided are a computer program, an information processing method, and an information processing device.　For a patient suffering from chronic kidney disease, the computer program causes a computer to execute a process of: acquiring patient information including a stage of acceptance of the chronic kidney disease of the patient determined at a first timing, and a stage of acceptance of the chronic kidney disease of the patient determined at a second timing before the first timing; and inputting the acquired patient information to a language model to output a sentence indicating an intervention method for the patient.

Description

Computer program, information processing method, and information processing device

[0001] The present disclosure relates to a computer program, an information processing method, and an information processing device.

[0002] Kidney disease, excluding acute nephritis, is a long-term condition that can eventually progress to end-stage renal failure. In the early stages of the disease, when kidney function is relatively well-maintained and the only abnormality is in the urine, there are few symptoms. However, once kidney function drops to around 50%, symptoms such as nocturnal polyuria, renal anemia, and elevated blood pressure begin to appear. When kidney function drops below 15%, the excretion of salt, water, acid, and waste products in the urine decreases, causing the symptoms of uremia to become more severe, making it highly likely that the condition will progress to end-stage renal failure, and the condition will often progress to the point where dialysis is required.

[0003] For patients with chronic kidney disease (CKD) who have not yet reached the stage where dialysis is required, the goal is to slow the progression of the disease and preserve kidney function as long as possible, and there is no treatment that can cure the disease itself. Currently, dietary therapy and drug therapy for renal failure are used to slow the progression of the disease and prolong the remaining function of the kidneys. Dietary therapy is an effective treatment strategy, but in reality it is often not adhered to due to factors such as the psychological burden on patients and loss of appetite due to bland flavors.

[0004] Therefore, a method has been proposed in which a patient's motivation to reduce salt intake is divided into stages and an intervention method is proposed for each stage (see Non-Patent Documents 1 to 5).

[0005] Special Publication No. 2011-509941

[0006] Mai Yanagi, Treatment and Countermeasures (CKD and Dialysis) (1) Salt Reduction Guidance, Clinical Dialysis Vol. 37 No. 10 2021 79・1159-84・1164 Shino Fujimoto and two others, "Understanding Chronic Illness and the Mind: Focusing on the Mind Accepting Illness," [online], November 13, 2015, Medical Note, [Retrieved December 8, 2023], Internet <https: / / medicalnote.jp / contents / 151019-000029-TGCJDX> Shino Fujimoto and two others, "The Mind of the Loss Stage in Chronic Illness and How to Deal with It: When You Feel Depressed Due to Chronic Illness," [online], November 14, 2015, Medical Medical Note, [Retrieved December 8, 2023], Internet: https: / / medicalnote.jp / contents / 151019-000030-CURDJA; Shino Fujimoto and two others, “The Mindset of the Denial and Struggle Stages of Chronic Illness and How to Deal with Them – When You Don’t Want to Think About Having a Chronic Illness,” [online], November 15, 2015, Medical Note, [Retrieved December 8, 2023], Internet: https: / / medicalnote.jp / contents / 151019-000031-KSOKXB; Shino Fujimoto and two others, “The Mindset of the Compromise Stage of Chronic Illness and How to Deal with It – When Dietary Management and Restrictions Don’t Work,” [online], November 16, 2015, Medical Note, [Retrieved December 8, 2023], Internet: https: / / medicalnote.jp / contents / 151019-000032-KTIYWD

[0007] Patent Document 1 discloses a drug therapy for kidney disease, etc., but does not disclose any psychological approach to patients.

[0008] Furthermore, although Non-Patent Documents 1 to 5 disclose psychological approaches to patients, they do not specifically disclose intervention methods for individual patients or intervention methods that respond to psychological changes, and in such cases, the approach relies heavily on the experience of medical professionals such as doctors.

[0009] In one aspect, an object of the present invention is to provide a computer program, an information processing method, and an information processing device that can propose an intervention method according to psychological changes in a patient.

[0010] (1) The computer program disclosed herein is a computer program for causing a computer to execute a process of acquiring patient information for a patient suffering from chronic kidney disease, the patient including the patient's acceptance stage for chronic kidney disease determined at a first timing and the patient's acceptance stage for chronic kidney disease determined at a second timing prior to the first timing, and inputting the acquired patient information into a language model to output a sentence indicating an intervention method for the patient.

[0011] (2) In the computer program of (1) above, the patient information further includes answers from the patient to a plurality of questions at the first timing and answers from the patient at the second timing.

[0012] (3) In the computer program of (1) or (2) above, the questions include questions inquiring about at least one of the patient's psychological state, preferences, physical condition, and behavior, and the computer is caused to execute a process of estimating the patient's psychological tendency based on answers to the questions at the first timing and answers to the questions at the second timing, and inputting patient information including the estimated psychological tendency of the patient into the language model, thereby outputting a sentence indicating an intervention method for the patient.

[0013] (4) In any one of the computer programs (1) to (3) above, the patient information further includes at least one of the patient's age, sex, and family structure.

[0014] (5) In the computer program of (4) above, a prompt including the patient information and instructing the generation of the sentence is generated, and the generated prompt is input into the language model, thereby causing the computer to execute a process of outputting a sentence indicating an intervention method for the patient.

[0015] (6) In any one of the computer programs (1) to (5) above, a dialogue log relating to the dialogue between the dialogue system and the patient is acquired, and the computer is caused to execute a process of estimating the patient's stage of acceptance of chronic kidney disease based on the acquired dialogue log.

[0016] (7) In any one of the computer programs (1) to (6) above, the dialogue includes a question from the dialogue system and the patient's answer to the question, and the computer is caused to execute a process of deriving a score based on the patient's answer and estimating the acceptance stage based on the derived score.

[0017] (8) The information processing method disclosed herein acquires patient information for a patient suffering from chronic kidney disease, including the patient's acceptance stage for chronic kidney disease determined at a first timing and the patient's acceptance stage for chronic kidney disease determined at a second timing prior to the first timing, and inputs the acquired patient information into a language model, thereby performing a process by a computer to output a sentence indicating an intervention method for the patient.

[0018] (9) The information processing device of the present disclosure includes at least one processor, which acquires patient information for a patient suffering from chronic kidney disease, including the patient's acceptance stage for chronic kidney disease determined at a first timing and the patient's acceptance stage for chronic kidney disease determined at a second timing prior to the first timing, and outputs a sentence indicating an intervention method for the patient by inputting the acquired patient information into a language model.

[0019] On the one hand, it can suggest intervention methods that correspond to the psychological changes of patients.

[0020] FIG. 1 is a schematic diagram showing an example of the configuration of an intervention support system according to an embodiment. FIG. 2 is a block diagram illustrating the internal configuration of a server device. FIG. 3 is a block diagram illustrating the internal configuration of a doctor terminal. FIG. 4 is a block diagram illustrating the internal configuration of a patient terminal. FIG. 5 is a block diagram illustrating the internal configuration of an LLM server. FIG. 6 is a conceptual diagram showing an example of patient information input through a doctor terminal. FIG. 7 is a schematic diagram showing an example of a patient information input screen on a patient terminal. FIG. 8 is a flowchart illustrating the procedure of processing executed by a server device. FIG. 9 is a conceptual diagram showing an example of a prompt input to an LLM. FIG. 10 is a diagram showing an example of an output of a sentence indicating an intervention method. FIG. 11 is a diagram showing an example of an output of a sentence indicating an intervention method. FIG. 12 is a diagram showing an example of a derivation of a score. FIG. 13 is a diagram showing an example of a derivation of a score. FIG. 14 is a flowchart illustrating the procedure of processing executed by a server device according to embodiment 2.

[0021] The present invention will be described in detail below with reference to the drawings illustrating embodiments. (Embodiment 1) FIG. 1 is a schematic diagram illustrating an example of the configuration of an intervention support system according to an embodiment. The intervention support system according to the embodiment includes a server device 10, a doctor terminal 20, a patient terminal 30, and an LLM server 40. The server device 10 is a server computer installed by a medical institution. The doctor terminal 20 is a client computer used by medical professionals such as doctors, and the patient terminal 30 is a client computer used by patients. The LLM server 40 is a server computer that provides services using a large language model (LLM). The server device 10, the doctor terminal 20, the patient terminal 30, and the LLM server 40 are connected to each other so as to be able to communicate with each other via a communication network NW.

[0022] The patient in this embodiment is a patient suffering from chronic kidney disease (more specifically, a patient with conservative CKD who has not yet reached end-stage renal failure). Chronic kidney disease is defined as a condition in which some kind of renal disorder or reduced renal function persists for more than three months, and is diagnosed by measuring proteinuria and glomerular filtration rate. There is currently no treatment for chronic kidney disease, and the goal is to slow the progression of the disease and preserve renal function as long as possible.

[0023] When patients are diagnosed with chronic kidney disease, it is believed that they undergo a series of psychological processes to accept the condition, and there are five stages of acceptance that patients go through: loss, denial, struggle, compromise, and acceptance (Non-Patent Documents 1 to 5).

[0024] "Loss" is a state in which patients lose the will to face the illness. Patients in this stage tend to feel discouraged and lethargic, and may become depressed. Sometimes, patients lose the ability to control things that they were previously able to do.

[0025] "Denial" is a state in which patients are unable to face their illness, avoid it, and treat it as if it were someone else's problem. Patients in this stage of "denial" tend to avoid thinking about their illness or treatment. Some patients even refuse to manage themselves.

[0026] "Struggle" is the state of trying to overcome and face the illness. Patients in the "struggle" stage tend to become dominated by thoughts about the illness and treatment. Sometimes, patients' daily lives become centered around self-management.

[0027] "Attunement" is a state in which patients come to terms with and accept their illness, making it a part of their daily lives. Patients in this stage are able to cope well with their thoughts about the illness and treatment, and are psychologically stable. However, they may be unable to change their habitual behaviors, which can lead to problems with self-management.

[0028] "Acceptance" is a state in which patients accept their illness and find a new purpose in life. Patients who reach the "acceptance" stage often see self-management as a part of their life and practice it, and often enjoy their own lives.

[0029] Although patients are said to have five stages of acceptance, as described above, they do not necessarily progress in a sequential order from "loss" to "acceptance." It is also said that patients' acceptance of their illness goes through a circular acceptance process. For example, even if a patient's acceptance stage changes from "loss" to "struggle," they may not subsequently change from "struggle" to "compromise" or "acceptance." They may also return from "struggle" to "denial" or "loss." This is because, as treatment for chronic kidney disease continues over a long period of time, the patient's mind changes to adapt to each change as the disease worsens and major changes occur in their lifestyle. A patient's acceptance stage is determined by medical professionals, such as doctors and clinical psychologists, based on the patient's behavior and comments during each consultation.

[0030] In this embodiment, the patient's acceptance stage will be described as having five stages: "loss," "denial," "struggle," "compromise," and "acceptance." However, the classification of the acceptance stage is not limited to the above and can be determined as appropriate. For example, there may be five stages: "shock stage," "denial stage," "confusion stage," "efforts to resolve stage," and "acceptance stage."

[0031] The server device 10 according to this embodiment acquires patient information from the doctor terminal 20 and the patient terminal 30. The patient information acquired by the server device 10 includes the patient's chronic kidney disease treatment stage determined at a first timing and the patient's chronic kidney disease treatment stage determined at a second timing prior to the first timing. The patient information may also include information on the time of the initial consultation at the medical institution. This patient information is information input into the doctor terminal 20 by a medical professional such as a doctor. The server device 10 acquires the above patient information from the doctor terminal 20.

[0032] The patient information acquired by the server device 10 may include the patient's answers to a plurality of questions at a first timing and the patient's answers at a second timing prior to the first timing. Furthermore, the patient information acquired by the server device 10 may include at least one of the patient's age, gender, and family structure. This patient information is input into the doctor terminal 20 by a medical professional. Alternatively, it is input into the patient terminal 30 by the patient himself / herself.

[0033] The server device 10 outputs a sentence indicating an intervention method for the patient based on patient information acquired from the doctor terminal 20 and the patient terminal 30. In the system configuration of this embodiment, the server device 10 outputs the sentence indicating the intervention method using the LLM server 40. Specifically, the server device 10 generates a prompt including the acquired patient information and transmits the generated prompt to the LLM server 40. The LLM server 40 generates a sentence specified in the prompt and returns the generated sentence data to the server device 10. The server device 10 receives the sentence data returned from the LLM server 40 and outputs it as a sentence indicating an intervention method for the patient. The server device 10 may display the sentence indicating the intervention method for the patient on its own display screen or may notify the doctor terminal 20 via the communication network NW.

[0034] The text of the intervention method output by the server device 10 is presented to the doctor. The doctor can refer to the text presented by the server device 10 and ultimately decide on the intervention method for the patient (how to interact with the patient).

[0035] In this embodiment, an LLM server 40 is provided separately from the server device 10, patient information is transmitted from the server device 10 to the LLM server 40, and a sentence indicating an intervention method for the patient is generated by the LLM server 40. Alternatively, the server device 10 may be provided with a language model such as an LLM, and a sentence indicating an intervention method for the patient may be generated within the server device 10.

[0036] The configuration of each device constituting the intervention support system will be described below. Fig. 2 is a block diagram illustrating the internal configuration of the server device 10. The server device 10 is a dedicated or general-purpose computer, and includes a control unit 11, a storage unit 12, a communication unit 13, an operation unit 14, and a display unit 15.

[0037] The control unit 11 includes, for example, a CPU (Central Processing Unit), a ROM (Read Only Memory), and a RAM (Random Access Memory). The ROM included in the control unit 11 stores a control program that controls the operation of each hardware unit included in the server device 10. The CPU in the control unit 11 reads and executes the control program stored in the ROM and a computer program (described below) stored in the storage unit 12, and controls the operation of each hardware unit, thereby causing the entire device to function as the server device 10 (information processing device) of the present disclosure. The RAM included in the control unit 11 temporarily stores data used during calculation and control.

[0038] In the embodiment, the control unit 11 is configured to include a CPU, a ROM, and a RAM, but the configuration of the control unit 11 is not limited to the above. The control unit 11 may be, for example, one or more control circuits or arithmetic circuits including a GPU (Graphics Processing Unit), an FPGA (Field Programmable Gate Array), a DSP (Digital Signal Processor), a quantum processor, volatile or non-volatile memory, etc. The control unit 11 may also have functions such as a clock that outputs date and time information, a timer that measures the elapsed time from when a measurement start instruction is given until when a measurement end instruction is given, and a counter that counts numbers.

[0039] The storage unit 12 includes a storage device such as a hard disk drive (HDD), a solid state drive (SSD), etc. The storage unit 12 stores various computer programs executed by the control unit 11 and various data used by the control unit 11.

[0040] The computer program (program product) stored in the storage unit 12 includes an intervention support program PG1 for causing a computer to execute a process of acquiring patient information, inputting the acquired patient information into the LLM, and outputting a sentence indicating an intervention method for the patient. The intervention support program PG1 may be a single computer program or a program group consisting of multiple computer programs. Furthermore, the intervention support program PG1 may partially use an existing library. The intervention support program PG1 may be executed by a single computer or may be executed by multiple computers working together.

[0041] A computer program including the intervention support program PG1 is provided by a non-transitory recording medium RM on which the computer program is readably recorded. The recording medium RM is a portable memory such as a CD-ROM, a USB memory, or an SD (Secure Digital) card. The control unit 11 reads various computer programs from the recording medium RM using a reading device (not shown) and stores the read various computer programs in the memory unit 12. The computer program including the intervention support program PG1 may be provided via communication. The control unit 11 acquires the computer program including the intervention support program PG1 by communication via the communication unit 13 and stores the acquired computer program in the memory unit 12.

[0042] The communication unit 13 includes a communication interface for transmitting and receiving various data to and from an external device. The communication interface of the communication unit 13 may be a communication interface conforming to a communication standard such as Wi-Fi (registered trademark), LAN (Local Area Network), Bluetooth (registered trademark), ZigBee (registered trademark), 3G, 4G, 5G, or LTE (Long Term Evolution). When data to be transmitted is input from the control unit 11, the communication unit 13 transmits the data to the destination external device. When data transmitted from the external device is received, the communication unit 13 outputs the received data to the control unit 11. In this embodiment, examples of external devices are the doctor terminal 20 and the patient terminal 30.

[0043] The operation unit 14 includes operation devices such as a touch panel, a keyboard, and switches, and receives various operations and settings from a user, etc. The control unit 11 performs appropriate control based on various pieces of operation information provided by the operation unit 14, and stores setting information in the storage unit 12 as necessary.

[0044] The display unit 15 includes a display device such as a liquid crystal display or an organic EL (Electro-Luminescence) display, and displays information to be presented in response to an instruction from the control unit 11 .

[0045] In this embodiment, the server device 10 may be a single computer, or may be a computer system configured with multiple computers and peripheral devices, etc. Furthermore, the server device 10 may be a virtual machine whose entity is virtualized, or may be a cloud.

[0046] 3 is a block diagram illustrating the internal configuration of the doctor terminal 20. The doctor terminal 20 is a computer such as a smartphone, tablet terminal, or personal computer, and includes a control unit 21, a storage unit 22, a communication unit 23, an operation unit 24, and a display unit 25.

[0047] The control unit 21 includes, for example, a CPU, a ROM, a RAM, etc. The CPU of the control unit 21 controls the operation of the various hardware components described above by loading various programs stored in advance in the ROM or the storage unit 22 into the RAM and executing them, thereby causing the entire device to function as the doctor terminal 20 of the present disclosure.

[0048] The control unit 21 is not limited to the above configuration, and may be configured as a single piece of hardware (SoC: System On a Chip) that integrates a processor, memory, storage, communication interface, etc. The control unit 21 may also have functions such as a clock that outputs date and time information, a timer that measures the elapsed time from when an instruction to start measurement is given until when an instruction to end measurement is given, and a counter that counts numbers.

[0049] The storage unit 22 includes storage such as a memory and a hard disk. The storage unit 22 stores various computer programs executed by the control unit 21, data necessary for executing the computer programs, etc. The computer programs stored in the storage unit 22 include, for example, application programs for using services provided by the server device 10.

[0050] The programs stored in the storage unit 22 may be provided by a non-transitory storage medium on which the programs are readably recorded. The storage medium is, for example, a portable memory such as a CD-ROM, a USB memory, or an SD card. The control unit 21 reads the various programs from the storage medium using a reading device (not shown) and installs the read programs in the storage unit 22. The programs stored in the storage unit 22 may also be provided by communication. In this case, the control unit 21 acquires the various programs through the communication unit 23 and installs the acquired programs in the storage unit 22.

[0051] The communication unit 23 includes a communication interface for connecting to the communication network NW. The communication interface included in the communication unit 23 is a communication interface conforming to a communication standard such as Wi-Fi (registered trademark), LAN, Bluetooth (registered trademark), ZigBee (registered trademark), 3G, 4G, 5G, LTE, etc. The communication unit 23 transmits various information to be notified to the outside and receives various information transmitted from the outside to the device itself.

[0052] The operation unit 24 is equipped with input devices such as a touch panel and operation buttons, and receives various types of operation information and setting information. The operation unit 24 outputs the received operation information and setting information to the control unit 21. The control unit 21 performs appropriate control based on the operation information input from the operation unit 24, and stores the setting information in the storage unit 22 as necessary.

[0053] The display unit 25 includes a display device such as a liquid crystal display or an organic EL display, and displays information to be presented to medical personnel such as doctors based on a control signal output from the control unit 21 .

[0054] 4 is a block diagram illustrating the internal configuration of the patient terminal 30. The patient terminal 30 is a computer such as a personal computer, a tablet terminal, or a smartphone, and includes a control unit 31, a storage unit 32, a communication unit 33, an operation unit 34, and a display unit 35.

[0055] The control unit 31 includes, for example, a CPU, a ROM, a RAM, etc. The CPU of the control unit 31 controls the operation of the various hardware components described above by loading various programs stored in advance in the ROM or the storage unit 32 into the RAM and executing them, causing the entire device to function as the patient terminal 30 of the present disclosure.

[0056] The control unit 31 is not limited to the above configuration, and may be configured as a single piece of hardware (SoC: System On a Chip) that integrates a processor, memory, storage, communication interface, etc. The control unit 31 may also have functions such as a clock that outputs date and time information, a timer that measures the elapsed time from when an instruction to start measurement is given until when an instruction to end measurement is given, and a counter that counts numbers.

[0057] The storage unit 32 includes storage such as a memory and a hard disk. The storage unit 32 stores various computer programs executed by the control unit 31, data necessary for executing the computer programs, etc. The computer programs stored in the storage unit 32 include, for example, application programs for using services provided by the server device 10.

[0058] The programs stored in the storage unit 32 may be provided by a non-transitory storage medium on which the programs are readably recorded. The storage medium is, for example, a portable memory such as a CD-ROM, a USB memory, or an SD card. The control unit 31 reads the various programs from the storage medium using a reading device (not shown) and installs the read programs in the storage unit 32. The programs stored in the storage unit 32 may also be provided by communication. In this case, the control unit 31 acquires the various programs through the communication unit 33 and installs the acquired programs in the storage unit 32.

[0059] The communication unit 33 includes a communication interface for connecting to the communication network NW. The communication interface included in the communication unit 33 is a communication interface conforming to a communication standard such as Wi-Fi (registered trademark), LAN, Bluetooth (registered trademark), ZigBee (registered trademark), 3G, 4G, 5G, LTE, etc. The communication unit 33 transmits various information to be notified to the outside and receives various information transmitted from the outside to the device itself.

[0060] The operation unit 34 is equipped with input devices such as a keyboard and a mouse, and receives various types of operation information and setting information. The operation unit 34 outputs the received operation information and setting information to the control unit 31. The control unit 31 performs appropriate control based on the operation information input from the operation unit 34, and stores the setting information in the storage unit 32 as necessary.

[0061] The display unit 35 includes a display device such as a liquid crystal display or an organic EL display, and displays information to be presented to the patient based on a control signal output from the control unit 31 .

[0062] 5 is a block diagram illustrating the internal configuration of the LLM server 40. The LLM server 40 is a dedicated or general-purpose server computer, and includes a control unit 41, a storage unit 42, a communication unit 43, an operation unit 44, and a display unit 45.

[0063] The control unit 41 includes, for example, a CPU, a ROM, a RAM, etc. The CPU of the control unit 41 controls the operation of the various hardware components described above by loading various programs stored in advance in the ROM or the storage unit 42 into the RAM and executing them.

[0064] In the embodiment, the control unit 41 is configured to include a CPU, a ROM, and a RAM, but the configuration of the control unit 41 is not limited to the above. The control unit 41 may be one or more control circuits or arithmetic circuits including a GPU, an FPGA, a DSP, a quantum processor, a volatile or non-volatile memory, or the like.

[0065] The storage unit 42 includes storage devices such as a memory and a hard disk. The storage unit 42 stores various computer programs executed by the control unit 41, as well as data necessary for executing the computer programs. The computer programs stored in the storage unit 42 include a natural language processing program that causes the computer to interpret prompts received from outside and generate sentences using the LLM.

[0066] The storage unit 42 also includes an LLM such as GPT-3 (Generative Pretrained Transformer 3), LaMDA (Language Model for Dialogue Applications), PaLM (Pathways Language Model), LLaMA (Large Language Model Meta AI), and Weblab-10B. The LLM included in the LLM server 40 is not limited to the above, and may be any existing model or a model obtained by tuning an existing model.

[0067] The communication unit 43 includes a communication interface for connecting to the communication network NW. The communication interface included in the communication unit 43 is a communication interface conforming to a communication standard such as Wi-Fi (registered trademark), LAN, Bluetooth (registered trademark), ZigBee (registered trademark), 3G, 4G, 5G, LTE, etc. The communication unit 43 transmits various information to be notified to the outside and receives various information transmitted from the outside to the device itself.

[0068] The operation unit 44 is equipped with input devices such as a touch panel and operation buttons, and receives various types of operation information and setting information. The operation unit 44 outputs the received operation information and setting information to the control unit 41. The control unit 41 performs appropriate control based on the operation information input from the operation unit 44, and stores the setting information in the storage unit 42 as necessary.

[0069] The display unit 45 includes a display device such as a liquid crystal display or an organic EL display, and displays information to be presented to the administrator or the like based on a control signal output from the control unit 41 .

[0070] The operation of the intervention support system will be described below. The intervention support system according to this embodiment receives patient information at the doctor terminal 20 or the patient terminal 30 before generating a sentence indicating an intervention method.

[0071] Fig. 6 is a conceptual diagram showing an example of patient information input through the doctor terminal 20. When a medical professional such as a doctor diagnoses a patient, the medical professional inputs the patient information shown in Fig. 6 through the operation unit 24 of the doctor terminal 20. The patient information input through the operation unit 24 of the doctor terminal 20 is registered in an electronic medical record (database) within the medical institution. The electronic medical record may be stored in the memory unit 12 of the server device 10 or in a memory unit of another server computer.

[0072] In the example of Figure 6, the patient's name, date of birth, age, sex, family composition, date of first consultation, date of test, test results of multiple tests, and acceptance stage evaluation date and evaluation results are registered as patient information. Here, the tests include tests performed to evaluate the progression of chronic kidney disease, such as measuring urinary protein levels and serum creatinine concentrations. Measurement values ​​and evaluation values ​​obtained from the tests are registered as item values ​​of the test results. The acceptance stage evaluation results are evaluation results of the acceptance stage determined by a doctor or other doctor's diagnosis, and include five levels of evaluation: loss, rejection, struggle, compromise, and acceptance. In the example of Figure 6, the evaluation results determined by a doctor or other doctor at the current diagnosis (first timing) and the evaluation results determined by a doctor or other doctor at the previous diagnosis (second timing) are registered.

[0073] The example in Figure 6 shows patient information including the latest test results and the current and previous acceptance stages, but the electronic medical record may also register as history not only the latest test results and the current and previous acceptance stages, but also all test results performed in the past and information on all acceptance stages previously determined by doctors, etc.

[0074] Part of the patient information may be entered by the patient himself / herself. Fig. 7 is a schematic diagram showing an example of a patient information input screen on the patient terminal 30. The patient information input screen is displayed on the display unit 35 of the patient terminal 30 in response to an instruction from the server device 10 or the doctor terminal 20. Alternatively, the patient information input screen may be displayed on the display unit 35 of the patient terminal 30 when the server device 10 is accessed from the patient terminal 30 and a predetermined operation is performed.

[0075] The patient information input screen includes questions inquiring about at least one of the patient's psychological state, preferences, physical condition, and behavior, such as "Do you have an appetite?", "Do you like salty foods?", etc. The questions are not limited to the example shown in FIG. 7 and can be determined as appropriate.

[0076] The patient answers the questions using the operation unit 34. The patient information input screen in FIG. 7 has a slide bar for each question that can be slid left and right (in the direction of the arrow shown in the figure) using the operation unit 34 to accept answers to the questions. The patient answers the questions on a ten-point scale about their psychological state, preferences, physical condition, and behavior at this time (first timing) by sliding the slide bar left and right using the operation unit 34. In the example in FIG. 7, the patient's own answers from the previous time (second timing) are also displayed, but the previous answers may also be hidden.

[0077] In this embodiment, for example, when a doctor or the like determines the admission stage of a patient, the doctor or the like also interviews the patient and obtains answers to the questions described above. That is, in this embodiment, the timing when the doctor or the like determines the admission stage of a patient and the timing when the patient answers the questions are substantially the same (the same within the range of allowable error).

[0078] The patient information input to the doctor terminal 20 and the patient terminal 30 is transmitted to the server device 10 via the communication network NW. The server device 10 inputs the patient information received from the doctor terminal 20 and the patient terminal 30 into the LLM, thereby outputting a sentence of an intervention method for the patient. Specifically, the server device 10 generates a prompt including the patient information and transmits it to the LLM server 40, receives the sentence data returned from the LLM server 40 in response, and outputs the sentence of the intervention method by displaying it on the display unit 15 or notifying the doctor terminal 20.

[0079] FIG. 8 is a flowchart illustrating the processing steps executed by the server device 10. The control unit 11 of the server device 10 acquires patient information from the doctor terminal 20 and the patient terminal 30 via the communication network NW (step S101). The patient information acquired by the server device 10 includes information on the patient's chronic kidney disease treatment stage determined at a first timing and the patient's chronic kidney disease treatment stage determined at a second timing prior to the first timing. The patient information may also include the patient's answers to multiple questions at the first timing and the second timing. In addition to this information, the patient information may also include information on the time of the initial consultation at the medical institution, and may further include information on the patient's age, gender, and family composition. If the server device 10 has an electronic medical record, the control unit 11 may acquire part of the patient information from the electronic medical record.

[0080] The control unit 11 generates a prompt to be input to the LLM based on the acquired patient information (step S102). FIG. 9 is a conceptual diagram illustrating an example of a prompt to be input to the LLM. The prompt is an instruction to the LLM and includes a fixed phrase and patient information. In the example of FIG. 9, the patient information is underlined for convenience in order to distinguish between the fixed phrase and the patient information. The fixed phrase includes statements indicating that you (i.e., the creator of the text) are a physician, that the patient suffers from chronic liver disease, that the patient has answered the questionnaire (questions) as follows, and that an intervention method for the patient should be proposed taking this information into consideration. The patient information also includes the patient's gender, age, family composition, the admission stage determined at the first timing, the admission stage determined at the second timing, and answers to multiple questions.

[0081] The control unit 11 may estimate the patient's psychological tendency based on the patient's response to the questionnaire (question) at the first timing and the patient's response at the second timing, and include information on the estimated psychological tendency in the prompt. For example, the questionnaire in FIG. 7 includes a question asking about the patient's psychological state, such as "Do you ever feel anxious?" If the patient's response to that question changes from "No" or "Neither" to "Exactly," it can be estimated that the patient tends to become negative. If the response changes in the opposite direction, it can be estimated that the patient tends to become positive. In these cases, the control unit 11 may include in the prompt a statement indicating that the patient tends to become negative (or positive). Furthermore, if the patient's response does not change from "Exactly" to "No" or "Neither," it can be estimated that the patient tends to maintain a negative state. In this case, the control unit 11 may include in the prompt a statement indicating that the patient tends to maintain a negative state. The control unit 11 may also take into consideration answers to other questions (such as "Are you feeling well?" and "Do you often get angry?") to comprehensively estimate the patient's psychological tendency.

[0082] The format of the prompt is not limited to the example shown in Figure 9 and may be designed arbitrarily to obtain desired information (patient intervention methods). For example, when document data such as academic or specialized books on chronic kidney disease, care guides for the conservative phase of CKD, or lifestyle and dietary guidance manuals are available, the document data to be referenced may be specified in the prompt so that a sentence is generated by referencing the document data. The document data to be referenced may be stored in the memory unit 12 of the server device 10 or the memory unit 42 of the LLM server 40, or may be stored in any device in a manner that allows it to be referenced via the communication network NW.

[0083] In addition, a portion of the text may be extracted from the document data and added to the prompt. The control unit 11 may extract reference text from the document data based on patient information acquired from the doctor terminal 20 or the patient terminal 30 and include the extracted text in the prompt. For example, in the case of a patient whose acceptance stage has changed from "loss" to "rejection," the control unit 11 may extract a portion of the document data that contains explanations or advice about the patient in the "rejection" state (or a patient whose state has changed from "loss" to "rejection") and include the extracted portion of the text in the prompt. The same applies when the patient has changed to another acceptance stage. In addition, the control unit 11 may extract reference text from the document data based on other patient information, such as the patient's age, gender, and family structure, in addition to the patient's acceptance stage, and include the extracted portion of the text in the prompt.

[0084] The control unit 11 transmits the prompt generated in step S102 to the LLM server 40 (step S103). The prompt transmitted from the communication unit 13 of the server device 10 reaches the LLM server 40 via the communication network NW.

[0085] The LLM server 40 receives the prompt sent from the server device 10 (step S104). The LLM server 40 generates a sentence indicating an intervention method for the patient according to the instructions of the received prompt (step S105). Specifically, the control unit 41 of the LLM server 40 references the patient information included in the prompt and generates a sentence that closely matches the patient information using the LLM. The LLM server 40 transmits data of the generated sentence to the server device 10 as a response to the prompt received in step S104 (step S106).

[0086] The server device 10 receives the text data returned from the LLM server 40 (step S107) and outputs a text indicating an intervention method for the patient based on the received data (step S108). The server device 10 may display the text indicating the intervention method for the patient on the display unit 15, or may notify the doctor terminal 20 via the communication network NW.

[0087] 10 to 12 are diagrams showing example output sentences indicating intervention methods. Fig. 10 is an example output sentence of an intervention method for a patient whose acceptance stage has progressed from the previous "loss" stage to the "rejection" stage. This example shows sentences of an intervention method generated by the LLM for a patient whose acceptance stage has progressed from "loss" to the "rejection" stage but who continues to be in a negative psychological state.

[0088] Figure 11 shows an example of an output of an intervention method sentence for a patient whose acceptance stage has regressed from the previous "struggle" to "denial." This example shows an intervention method sentence generated by the LLM for a patient whose acceptance stage has regressed from "struggle" to "denial" and who has become even more negative.

[0089] Figure 12 is an example of an output of an intervention method sentence for a patient whose acceptance stage has progressed from the previous "rejection / fight" stage to the "compromise" stage. This example shows an intervention method sentence generated by the LLM for a patient whose acceptance stage has progressed from "rejection / fight" to "compromise" and who has changed to a more positive psychological state, but whose salt reduction efforts are not going well.

[0090] 10 to 12, not only the text indicating the intervention method but also the information on the acceptance stage at the first and second timings and the patient's responses at the first and second timings are displayed. Alternatively, the control unit 11 may present only the text indicating the intervention method to the doctor. Furthermore, the control unit 11 may also display either the information on the acceptance stage or the patient's responses together with the text indicating the intervention method.

[0091] As described above, in the first embodiment, a sentence indicating a method of intervention for the patient (how the doctor should interact with the patient) can be presented to the doctor in accordance with changes in the patient's acceptance state and psychological tendency. Changes in the patient's acceptance state represent psychological changes in the patient suffering from chronic kidney disease, and advice (intervention methods) suited to those psychological changes can be proposed to the doctor.

[0092] In the second embodiment, a configuration in which the server device 10 estimates the admission stage of a patient will be described. Note that the overall configuration of the system and the internal configuration of each device are the same as those in the first embodiment, and therefore the description thereof will be omitted.

[0093] The server device 10 according to the second embodiment acquires a dialogue log between the patient and the dialogue system in order to estimate the patient's acceptance stage. The dialogue log acquired by the server device 10 includes questions from the dialogue system and the patient's answers to the questions. The questions from the dialogue system may be fixed questions determined in advance, or may be questions that change depending on the patient's answers. An existing dialogue system can be used as the dialogue system (program). The dialogue system may be installed in the server device 10 or in the LLM server 40. The dialogue log may be text-based or voice-based.

[0094] The server device 10 derives a score according to the patient's answers included in the acquired dialogue log, and estimates the patient's acceptance stage based on the derived score.

[0095] 13 and 14 are diagrams showing examples of score derivation. The example in FIG. 13 shows an example of score derivation when questions about sports are asked and the patient answers them. Questions are not limited to sports-related questions, but may also include questions that can evaluate the patient's motivation in their overall life (such as questions about the patient's hobbies or current events). The example in FIG. 14 shows an example of score derivation when questions about the patient's health are asked to explore motivation related to their health condition and the patient answers them. The dialogue log may include dummy questions that are completely unrelated to the patient's life or health condition and the answers to those questions, and a score may be derived for each answer.

[0096] In this embodiment, multiple answers that the patient may give to each question may be assumed, and a score may be set in advance for each answer. In the examples of Figures 13 and 14, the scores for each answer are set so that the higher the score, the more the acceptance stage progresses toward "acceptance," and the lower the score, the more the acceptance stage regresses toward "loss." The control unit 11 of the server device 10 reads the scores for each answer included in the dialogue and sums them to derive a score for all answers.

[0097] In this embodiment, a score is calculated for each answer and then summed to derive a score for all the answers, but a single score may be calculated from all the answers. Alternatively, a learning model that learns the relationship between the patient's answers and the score may be used to derive the score.

[0098] The control unit 11 estimates the patient's acceptance stage based on the overall score of the responses (total score). For example, if the score is P1 to P2 (P1<P2), the patient's acceptance stage may be estimated as "loss," if the score is P2 to P3 (P2<P3), the patient's acceptance stage may be estimated as "rejection," if the score is P3 to P4 (P3<P4), the patient's acceptance stage may be estimated as "struggle," if the score is P4 to P5 (P4<P5), the patient's acceptance stage may be estimated as "compromise," and if the score is P5 to P6 (P5<P6), the patient's acceptance stage may be estimated as "acceptance."

[0099] 15 is a flowchart illustrating the procedure of processing executed by the server device 10 according to the second embodiment. The control unit 11 of the server device 10 acquires a dialogue log between the patient and the dialogue system (step S201). When using a dialogue log stored in the server device 10, the dialogue log is stored in the storage unit 12, and therefore the control unit 11 only needs to acquire the dialogue log from the storage unit 12. When using a dialogue log stored in an external server, the storage unit 12 only needs to acquire the dialogue log from the external server via the communication unit 13.

[0100] The control unit 11 derives a score according to the patient's answers based on the acquired dialogue log (step S202). The control unit 11 reads the score for each of the patient's answers included in the dialogue log and derives a score for all the answers (the sum of the scores). Alternatively, the control unit 11 may derive a score from all of the answers included in the dialogue log.

[0101] The control unit 11 estimates the patient's acceptance stage based on the derived score (step S203). For example, the acceptance stage may be estimated according to the score, such as "loss" when the score is P1 to P2 (P1<P2), "rejection" when the score is P2 to P3 (P2<P3), and so on.

[0102] The control unit 11 notifies the doctor terminal 20 of the estimated admission stage of the patient (step S204). After notifying the doctor terminal 20 of the estimated admission stage of the patient, the control unit 11 may accept corrections from the doctor or the like as necessary.

[0103] In embodiment 2, the patient's acceptance stage is estimated by referring to the dialogue log between the patient and the dialogue system and notified to the doctor terminal 20, so that the doctor can determine the patient's acceptance stage by referring to the information presented by the server device 10.

[0104] The embodiments disclosed herein are illustrative in all respects and should not be considered limiting. The scope of the present invention is defined by the claims, not by the above meaning, and is intended to include all modifications within the meaning and scope of the claims.

[0105] REFERENCE SIGNS LIST 10 Server device 11 Control unit 12 Storage unit 13 Communication unit 14 Operation unit 15 Display unit 20 Doctor terminal 30 Patient terminal 40 LLM server PG1 Intervention support program

Claims

1. A computer program for causing a computer to execute a process of acquiring patient information regarding a patient suffering from chronic kidney disease, the patient including an acceptance stage of the patient's chronic kidney disease determined at a first timing and an acceptance stage of the patient's chronic kidney disease determined at a second timing prior to the first timing, and inputting the acquired patient information into a language model to output a sentence indicating an intervention method for the patient.

2. The computer program according to claim 1, wherein the patient information further includes answers of the patient to a plurality of questions at the first timing and answers of the patient at the second timing.

3. The computer program of claim 2, for causing the computer to execute the following process: the questions include questions inquiring about at least one of the patient's psychological state, preferences, physical condition, and behavior; estimating a psychological tendency of the patient based on answers to the questions at the first timing and answers to the questions at the second timing; and inputting patient information including the estimated psychological tendency of the patient into the language model, thereby outputting a sentence indicating an intervention method for the patient.

4. The computer program according to claim 2, wherein the patient information further includes at least one of the patient's age, sex, and family structure.

5. The computer program of claim 1, which causes the computer to execute the process of: generating a prompt including the patient information and instructing the generation of the sentence; and outputting a sentence indicating an intervention method for the patient by inputting the generated prompt into the language model.

6. A computer program as claimed in any one of claims 1 to 5, for causing the computer to execute the process of: acquiring a dialogue log relating to a dialogue between a dialogue system and the patient; and estimating the patient's acceptance stage for chronic kidney disease based on the acquired dialogue log.

7. A computer program as claimed in claim 6, for causing the computer to execute the following processes: the dialogue includes questions from the dialogue system and the patient's answers to the questions; deriving a score according to the patient's answers; and estimating the acceptance stage based on the derived score.

8. An information processing method comprising: acquiring, with respect to a patient suffering from chronic kidney disease, patient information including the patient's acceptance stage for chronic kidney disease determined at a first timing and the patient's acceptance stage for chronic kidney disease determined at a second timing prior to the first timing; and inputting the acquired patient information into a language model to output a sentence indicating an intervention method for the patient.

9. An information processing device comprising at least one processor, which acquires patient information for a patient suffering from chronic kidney disease, the patient's acceptance stage for chronic kidney disease determined at a first timing and the patient's acceptance stage for chronic kidney disease determined at a second timing prior to the first timing, and outputs a sentence indicating an intervention method for the patient by inputting the acquired patient information into a language model.