Symptom comprehension support device, symptom comprehension support method, and symptom comprehension support program

Abstract

To provide a symptom comprehension support device capable of providing more appropriate support in comprehending symptoms of patients.SOLUTION: A symptom comprehension support device is provided, comprising an explanation acquisition unit for acquiring an explanation text representing symptoms of a patient explained by the patient, a summary generation unit configured to generate a summary of the explanation text by inputting the explanation text to a large language model, a medical information acquisition unit for acquiring medical information of the patient, a symptom prediction unit configured to predict candidate symptoms of the patient based on the summary and the medical information, and an output unit for outputting the summary and the predicted candidate symptoms.SELECTED DRAWING: Figure 1

Description

[Technical Field]

[0001] The present disclosure relates to a symptom understanding assistance device, a symptom understanding assistance method, and a symptom understanding assistance program. [Background technology]

[0002] Technologies for assisting diagnosis are known. One example of the technology for assisting diagnosis is the technology described in Patent Document 1. Patent Document 1 discloses an information processing device that acquires patient medical information including at least one of patient information about a patient who has undergone a medical interview and interview information related to the answers to the interview, extracts at least one piece of information based on the medical information from an information group including at least treatment information related to treatments and medication information related to medications associated with each piece of medical information, and outputs medical-related information related to the extracted information and the medical information to another information processing device. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Publication No. 2022-142234 Summary of the Invention [Problem to be solved by the invention]

[0004] However, during medical examinations, there are cases where the patient's verbal explanation is lengthy and not to the point, or where the patient is an infant or the like and is unable to accurately explain his or her subjective symptoms. In such cases where it is difficult to accurately grasp the content of the patient's verbal explanation, the technology described in Patent Document 1 poses a problem in that a medical professional such as a doctor diagnosing the patient cannot properly diagnose the patient.

[0005] The present disclosure has been made in view of the above problems, and an exemplary purpose thereof is to provide a technology that can more appropriately assist patients in understanding their symptoms. [Means for solving the problem]

[0006] A symptom understanding assistance device according to an exemplary aspect of the present disclosure includes an explanation acquisition means for acquiring an explanatory text in which a patient describes his or her symptoms, a summary generation means for using a language model to input the explanatory text and generate a summary of the explanatory text, a medical information acquisition means for acquiring medical information of the patient, a symptom prediction means for predicting possible symptoms of the patient based on the summary text and the medical information, and an output means for outputting the summary text and the predicted possible symptoms.

[0007] A symptom understanding assistance method according to an exemplary aspect of the present disclosure includes an explanation acquisition process in which at least one processor acquires an explanatory text in which a patient describes his or her symptoms; a summary generation process in which the at least one processor uses a language model to input the explanatory text and generate a summary text of the explanatory text; a medical information acquisition process in which the at least one processor acquires medical information of the patient; a symptom prediction process in which the at least one processor predicts candidate symptoms of the patient based on the summary text and the medical information; and an output process in which the at least one processor outputs the summary text and the predicted candidate symptoms.

[0008] A symptom understanding assistance program according to an exemplary aspect of the present disclosure is a symptom understanding assistance program that causes a computer to function as a symptom understanding assistance device, and causes the computer to function as an explanation acquisition means that acquires an explanatory text in which a patient describes his or her symptoms, a summary generation means that uses a language model to input the explanatory text and generate a summary text of the explanatory text, a medical information acquisition means that acquires medical information of the patient, a symptom prediction means that predicts possible symptoms of the patient based on the summary text and the medical information, and an output means that outputs the summary text and the predicted possible symptoms. [Effects of the Invention]

[0009] According to an exemplary aspect of the present disclosure, an exemplary effect is achieved in that a technology can be provided that more appropriately supports patients in understanding their symptoms. [Brief explanation of the drawings]

[0010] [Figure 1] 1 is a block diagram showing a configuration of a symptom understanding assistance device according to the present disclosure. [Figure 2] 1 is a flow chart showing the flow of a symptom understanding support method according to the present disclosure. [Figure 3] 1 is a block diagram illustrating a configuration of an information processing device according to the present disclosure. [Figure 4] FIG. 2 is a diagram illustrating a functional configuration of a control unit according to the present disclosure. [Figure 5] 10A and 10B are diagrams illustrating specific examples of information output by an output control unit according to the present disclosure. [Figure 6] 1 is a flow diagram showing an example of the flow of a symptom understanding support method according to the present disclosure. [Figure 7] 1 is a block diagram illustrating a configuration of a computer that functions as a symptom understanding assistance device or an information processing device according to the present disclosure. DETAILED DESCRIPTION OF THE INVENTION

[0011] The following are examples of embodiments of the present invention. However, the present invention is not limited to the exemplary embodiments shown below, and various modifications are possible within the scope of the claims. For example, embodiments obtained by appropriately combining the technologies (part or all of the products or methods) employed in the exemplary embodiments shown below may also be included in the scope of the present invention. Furthermore, embodiments obtained by appropriately omitting some of the technologies employed in the exemplary embodiments shown below may also be included in the scope of the present invention. Furthermore, the effects mentioned in the exemplary embodiments shown below are examples of effects expected in the exemplary embodiments, and do not define the scope of the present invention. In other words, embodiments that do not exhibit the effects mentioned in the exemplary embodiments shown below may also be included in the scope of the present invention.

[0012] First Exemplary Embodiment A first exemplary embodiment, which is an example of an embodiment of the present invention, will be described in detail with reference to the drawings. This exemplary embodiment is a basic form for each of the exemplary embodiments described below. Note that the scope of application of each technique employed in this exemplary embodiment is not limited to this exemplary embodiment. That is, each technique employed in this exemplary embodiment can also be employed in other exemplary embodiments included in the present disclosure, to the extent that no particular technical obstacles arise. Furthermore, each technique shown in the drawings referenced to explain this exemplary embodiment can also be employed in other exemplary embodiments included in the present disclosure, to the extent that no particular technical obstacles arise.

[0013] (Configuration of the symptom understanding support device) The configuration of the symptom understanding support device 1 will be described with reference to FIG. 1. FIG. 1 is a block diagram showing the configuration of the symptom understanding support device 1. As shown in FIG. 1, the symptom understanding support device 1 includes an explanation acquisition unit 11, a summary generation unit 12, a medical information acquisition unit 13, a symptom prediction unit 14, and an output unit 15. The explanation acquisition unit 11 acquires an explanatory text in which a patient explains his or her symptoms. The summary generation unit 12A uses a language model to generate a summary text of the explanatory text, taking the explanatory text as input. The medical information acquisition unit 13 acquires medical information of the patient. The symptom prediction unit 14 predicts candidate symptoms of the patient based on the summary text and the medical information. The output unit 15 outputs the summary text and the predicted candidate symptoms.

[0014] (Effects of the symptom understanding support device) As described above, the symptom understanding support device 1 includes an explanation acquisition unit 11 that acquires an explanatory text in which a patient explains his or her symptoms, a summary generation unit 12 that uses a language model to input the explanatory text and generate a summary of the explanatory text, a medical information acquisition unit that acquires medical information about the patient, a symptom prediction unit that predicts candidate symptoms for the patient based on the summary text and the medical information, and an output unit 15 that outputs the summary text and the predicted candidate symptoms. Therefore, the symptom understanding support device 1 has the effect of being able to more appropriately support the patient's understanding of their symptoms.

[0015] (Flow of symptom understanding support method) The flow of the symptom understanding support method S1 will be described with reference to FIG. 2. FIG. 2 is a flow diagram showing the flow of the symptom understanding support method S1. As shown in FIG. 2, the symptom understanding support method S1 includes an explanation acquisition process S11, a summary generation process S12, a medical information acquisition process S13, a symptom prediction process S14, and an output process S15. In the explanation acquisition process S11, at least one processor acquires an explanatory text in which the patient explains his or her symptoms. In the summary generation process S12, the at least one processor uses a language model to input the explanatory text and generate a summary text of the explanatory text. In the medical information acquisition process S13, the at least one processor acquires medical information of the patient. In the symptom prediction process S14, the at least one processor predicts candidate symptoms of the patient based on the summary text and the medical information. In the output process S15, the at least one processor outputs the summary text and the predicted candidate symptoms.

[0016] (Effects of symptom understanding support methods) As described above, the symptom understanding support method S1 includes an explanation acquisition process S11 in which at least one processor acquires an explanatory text from a patient describing his or her symptoms, a summary generation process S12 in which the at least one processor uses a language model to input the explanatory text and generate a summary of the explanatory text, a medical information acquisition process S13 in which the at least one processor acquires medical information about the patient, a symptom prediction process in which the at least one processor predicts candidate symptoms for the patient based on the summary text and the medical information, and an output process in which the at least one processor outputs the summary text and the predicted candidate symptoms. Therefore, the symptom understanding support method S1 has the effect of more appropriately supporting understanding of a patient's symptoms.

[0017] Second Exemplary Embodiment A second exemplary embodiment, which is one example of an embodiment of the present invention, will be described in detail with reference to the drawings. Components having the same functions as those described in the above exemplary embodiment will be assigned the same reference numerals, and their description will be omitted as appropriate. The scope of application of each technology employed in this exemplary embodiment is not limited to this exemplary embodiment. That is, each technology employed in this exemplary embodiment can also be employed in other exemplary embodiments included in the present disclosure, to the extent that no particular technical hindrance occurs. Furthermore, each technology shown in each drawing referenced to explain this exemplary embodiment can also be employed in other exemplary embodiments included in the present disclosure, to the extent that no particular technical hindrance occurs.

[0018] (Configuration of information processing device) The information processing device 1A is a device that outputs information to assist a patient in understanding their symptoms. The information processing device 1A is an example of a symptom understanding assistance device according to the present disclosure. The configuration of the information processing device 1A will be described with reference to FIG. 3. FIG. 3 is a block diagram showing the configuration of the information processing device 1A. The information processing device 1A includes a control unit 10A, a storage unit 20A, a communication unit 30A, an input unit 40A, and an output unit 50A.

[0019] (Communications Department) The communication unit 30A communicates with devices external to the information processing device 1A via a communication line. While the specific configuration of the communication line does not limit the present exemplary embodiment, examples of the communication line include a wireless LAN (Local Area Network), a wired LAN, a WAN (Wide Area Network), a public line network, a mobile data communication network, or a combination thereof. The communication unit 30A transmits data supplied from the control unit 10A to other devices, and supplies data received from other devices to the control unit 10A.

[0020] (Input section) The input unit 40A is configured to receive input to the information processing device 1A, and includes, for example, input devices such as a keyboard, a mouse, a touch panel, a camera, a microphone, etc. The input unit 40A may also be configured to receive data from the input devices via an interface such as a USB (Universal Serial Bus).

[0021] (output section) The output unit 50A is a component for performing output from the information processing device 1A, and includes, for example, output devices such as a display, a printer, a touch panel, a speaker, etc. The output unit 50A may also be configured to include, for example, an interface such as a USB, and to output data to the output device via the interface.

[0022] (Storage part) The storage unit 20A stores various types of information referenced by the control unit 10A. Examples of such information include medical information 201, explanatory text 202, summary text 203, and symptom candidates 204.

[0023] The medical information 201 is information related to the patient's medical care. Examples of the medical information 201 include chart information. The medical information 201 includes, for example, at least one of the patient's personal information, examination findings, and medical history information. The patient's personal information is the patient's personal information and includes, for example, information indicating the patient's age, gender, smoking amount, etc. The patient's examination findings information is information indicating findings by a medical professional such as a doctor and includes, for example, information obtained by the medical professional through a medical interview or visual examination. The information obtained through a medical interview or visual examination may be, for example, a sentence such as "There is pain when pressing the abdomen." The patient's medical history information is information related to the patient's medical history and includes, for example, information indicating the patient's medical history, family medical history, and smoking amount, etc. The medical information 201 may also include information indicating the measurement results of the patient's vital signs. The information indicating the measurement results of the vital signs may be, for example, information indicating "37.8°C / heart rate 90 / respiratory rate 30."

[0024] The medical information 201 may also include diagnostic images of patients. Examples of diagnostic images include at least one of X-ray images, endoscopic images, pathological images, MRI images, and CT images. The storage unit 20A stores medical information 201 for each of a plurality of patients.

[0025] The explanatory text 202 is text that represents the content of the patient's explanation of his or her symptoms. The explanatory text 202 may be, for example, text that represents the content of the patient's verbal explanation of his or her symptoms, or may be text that represents the content of the patient's symptoms written in a medical questionnaire or the like. When the patient verbally describes his or her symptoms, for example, the explanation acquisition unit 11A, which will be described later, performs a process of converting the patient's voice into text. The explanatory text 202 is, for example, a sentence such as, "I feel tired and my stomach hurts in the middle. I feel like I'm going to vomit and have a persistent fever..."

[0026] The summary text 203 is text generated by the summary generation unit 12A, which will be described later. The summary text 203 represents the content that summarizes the explanatory text 202. For example, the summary text 203 is a sentence such as "Feeling fatigued and having pain around the pit of the stomach. Nausea and slight fever."

[0027] The symptom candidate 204 is information indicating a symptom of a patient predicted by a symptom prediction unit 14A, which will be described later. The symptom candidate 204 is, for example, information such as "appendicitis / acute gastritis."

[0028] (Control unit) FIG. 4 is a diagram showing the functional configuration of the control unit 10A. The control unit 10A includes an explanation acquisition unit 11A, a summary generation unit 12A, a medical information acquisition unit 13A, a symptom prediction unit 14A, and an output control unit 15A. The explanation acquisition unit 11A is an example of an explanation acquisition means according to the present disclosure. The summary generation unit 12A is an example of a summary generation means according to the present disclosure. The medical information acquisition unit 13A is an example of a medical information acquisition means according to the present disclosure. The symptom prediction unit 14A is an example of a symptom prediction means according to the present disclosure. The output control unit 15A is an example of an output means according to the present disclosure.

[0029] (Explanation acquisition section) The explanation acquisition unit 11A acquires explanatory text 202 in which the patient explains his or her symptoms, and supplies the acquired explanatory text 202 to the summary generation unit 12A. As an example, the explanation acquisition unit 11A may acquire the explanatory text 202 by reading it from a storage location (which may be a storage device within the information processing device 1A or a storage device external to the information processing device 1A) designated by the user of the information processing device 1A. Alternatively, the explanation acquisition unit 11A may acquire the explanatory text 202 by receiving it from another device via the communication unit 30A. Alternatively, the explanation acquisition unit 11A may acquire the explanatory text 202 input to the input unit 40A.

[0030] The explanation acquisition unit 11A may also acquire voice data representing the voice collected during the examination of the patient, and convert the acquired voice data into text data.

[0031] (Summary generator) The summary generation unit 12A uses a large-scale language model M1 to generate a summary of an explanatory text 202 as an input. The large-scale language model M1 is an example of a language model according to the present disclosure. The large-scale language model M1 may be stored in a storage unit 20A of the information processing device 1A, or may be stored in a device other than the information processing device 1A. Note that the large-scale language model M1 being stored in the storage unit 20A means that parameters defining the large-scale language model M1 are stored in the storage unit 20A.

[0032] The large-scale language model M1 is a language model generated by machine learning and composed of an artificial neural network with many parameters. Examples of the large-scale language model M1 include, but are not limited to, generative AI such as ChatGPT (Chat Generative Pre-trained Transformer) and GPT-4 (Generative Pre-trained Transformer 4), or a generative AI fine-tuned using medical data.

[0033] The input information input by the summary generation unit 12A to the large-scale language model M1 includes explanatory text 202. The input information may also include information (e.g., text) instructing the generation of a summary. The output information output from the large-scale language model M1 includes summary text 203, which is a summary of the explanatory text 202.

[0034] When the large-scale language model M1 is stored in a device other than the information processing device 1A, the summary generation unit 12A, for example, inputs the explanatory text 202 into the large-scale language model M1 by transmitting the explanatory text 202 to the device storing the large-scale language model M1 via the communication unit 30A. In this case, the summary generation unit 12A receives information output by the large-scale language model M1 from the device via the communication unit 30A.

[0035] (Medical Information Acquisition Department) The medical information acquisition unit 13A acquires medical information 201 of a patient. In the example of FIG. 4, the medical information acquisition unit 13A acquires the medical information 201 including information obtained by interview and visual examination, information indicating a medical history, and information indicating a vital sign. For example, the medical information acquisition unit 13A may acquire the medical information 201 by reading the medical information 201 from a storage destination (which may be a storage device within the information processing device 1A or a storage device external to the information processing device 1A) designated by the user of the information processing device 1A. Alternatively, the medical information acquisition unit 13A may acquire the medical information 201 by receiving the medical information 201 from another device via the communication unit 30A. Alternatively, the medical information acquisition unit 13A may acquire the medical information 201 input to the input unit 40A.

[0036] (Symptom Prediction Department) The symptom prediction unit 14A predicts candidate symptoms of the patient based on the summary text 203 and the medical information 201. The candidate symptoms are used, for example, in decision-making regarding the diagnosis of the patient.

[0037] As an example, the symptom prediction unit 14A predicts symptom candidates based on the output obtained by inputting the summary text 203 and the medical information 201 into a prediction model M2. The prediction model M2 is a trained model generated by machine learning. Examples of the prediction model M2 include, but are not limited to, trained models generated by supervised learning using techniques such as neural networks, or generation AIs such as ChatGPT and GPT-4, or generation AIs fine-tuned with medical data. Furthermore, the prediction model M2 may be the same model as the large-scale language model M1.

[0038] The prediction model M2 may be stored in the storage unit 20A of the information processing device 1A, or may be stored in a device other than the information processing device 1A. Note that the prediction model M2 being stored in the storage unit 20A means that parameters defining the prediction model M2 are stored in the storage unit 20A.

[0039] The input information input by the symptom prediction unit 14A to the prediction model M2 includes a summary text 203 and medical information 201. The output information output from the prediction model M2 is information indicating the prediction result of the patient's symptoms (also referred to as "symptom candidate"). The information indicating the prediction result is, for example, information indicating "appendicitis / acute gastritis."

[0040] When the prediction model M2 is stored in a device other than the information processing device 1A, the symptom prediction unit 14A, for example, inputs the summary text 203 and the medical information 201 to the prediction model M2 by transmitting the summary text 203 and the medical information 201 to the device storing the prediction model M2 via the communication unit 30A. In this case, the symptom prediction unit 14A receives information output by the prediction model M2 from the above device via the communication unit 30A.

[0041] (Output control section) The output control unit 15A outputs output information 205 including summary sentence 203 and symptom candidate 204. As an example, the output control unit 15A may output the output information 205 by writing it to a storage destination (which may be a storage device within the information processing device 1A or a storage device external to the information processing device 1A) designated by the user of the information processing device 1A. Furthermore, the output control unit 15A may transmit the output information 205 via the communication unit 30A, or may output the output information 205 to an output device such as a display.

[0042] 5 is a diagram showing a specific example of output information 205 output by the output control unit 15A. As an example, the output control unit 15A may cause the display device to display the output information 205 shown in FIG. 5. In this case, the screen displayed on the display device includes a summary text 203 and symptom candidates 204. The screen also includes an explanatory text 202 and medical information 201, which are input to the information processing device 1A. As shown in FIG. 5, the output control unit 15A may output the explanatory text 202 and medical information 201 together with the summary text 203 and symptom candidates 204.

[0043] In the example of FIG. 5 , the output information 205 includes explanatory text 202 of the oral description, "I feel tired and have pain in the middle of my stomach. I continue to feel like I'm going to vomit and have a fever." The output information 205 also includes medical information 201, including information obtained by medical interview or visual examination, "There is pain when I press on my abdomen," and vital sign information, "37.8°C / heart rate 90 / respiratory rate 30." The output information 205 also includes summary text 203 of the oral description, "I feel fatigued and have pain in the pit of my stomach. I have nausea and a slight fever." The output information 205 also includes predicted symptom candidate 204, "appendicitis / acute gastritis."

[0044] (Flow of symptom understanding support method) Fig. 6 is a flowchart showing an example of the flow of a symptom understanding support method S1A executed by the information processing device 1 A. The steps included in the flowchart of Fig. 6 may be executed in parallel or in a different order.

[0045] In step S101, the explanation acquisition unit 11A acquires the explanatory text 202. In step S102, the summary generation unit 12A generates a summary text 203 of the explanatory text 202 using the large-scale language model M1. In step S103, the medical information acquisition unit 13A acquires the medical information 201. In step S104, the symptom prediction unit 14A predicts candidate symptoms of the patient by inputting the summary text 203 and the medical information 201 into the prediction model M2. In step S105, the output control unit 15A outputs the summary text 203 and the candidate symptoms predicted in step S104.

[0046] (Effects of information processing devices) As described above, the information processing device 1A predicts the patient's symptoms using the summary text 203, which is a summary of the explanatory text 202 in which the patient explains his or her symptoms, in addition to the patient's medical information 201. As a result, even if the patient's explanation is lengthy and off-point, for example, the information processing device 1A can more appropriately predict the patient's symptoms, thereby more appropriately supporting the patient in understanding their symptoms.

[0047] Furthermore, the information processing device 1A employs a configuration in which the medical information 201 includes at least one of the patient's personal information, the patient's medical findings, and the patient's medical history information. Therefore, the information processing device 1A can more appropriately predict the patient's symptoms by using at least one of the patient's personal information, the patient's medical findings, and the patient's medical history information.

[0048] Furthermore, the information processing device 1A employs a configuration in which the explanation acquisition unit 11A converts the voice collected during the patient's examination into text data. Therefore, the information processing device 1A can more appropriately predict the patient's symptoms simply by examining the patient. In other words, the patient does not need to perform any complicated tasks other than receiving the examination.

[0049] Furthermore, the information processing device 1A employs a configuration in which the symptom prediction unit 14A predicts candidate symptoms of a patient based on the output obtained by inputting the summary text 203 and the medical information 201 into a prediction model M2 generated by machine learning. Therefore, the information processing device 1A can more appropriately predict the symptoms of a patient by using the prediction model M2 generated by machine learning.

[0050] Furthermore, the information processing device 1A employs a configuration in which the medical information 201 includes a diagnostic image of the patient. By using the diagnostic image of the patient, the symptoms of the patient can be predicted more appropriately.

[0051] Furthermore, the information processing device 1A employs a configuration in which the symptom candidate 204 is information used for decision-making regarding the diagnosis of a patient, thereby enabling medical professionals and others diagnosing patients to make more appropriate decisions regarding the diagnosis.

[0052] [Software implementation example] Some or all of the functions of the symptom understanding support device 1 and the information processing device 1A (hereinafter also referred to as "the above-mentioned devices") may be realized by hardware such as an integrated circuit (IC chip), or may be realized by software.

[0053] In the latter case, each of the above devices is realized by, for example, a computer that executes instructions of a program, which is software that realizes each function. An example of such a computer (hereinafter referred to as computer C) is shown in Figure 7. Figure 7 is a block diagram showing the hardware configuration of computer C that functions as each of the above devices.

[0054] The computer C includes at least one processor C1 and at least one memory C2. The memory C2 stores a program P for causing the computer C to operate as each of the above-mentioned devices. In the computer C, the processor C1 reads and executes the program P from the memory C2, thereby realizing the functions of each of the above-mentioned devices.

[0055] The processor C1 may be, for example, a central processing unit (CPU), a graphic processing unit (GPU), a digital signal processor (DSP), a micro processing unit (MPU), a floating point number processing unit (FPU), a physics processing unit (PPU), a tensor processing unit (TPU), a quantum processor, a microcontroller, or a combination thereof. The memory C2 may be, for example, a flash memory, a hard disk drive (HDD), a solid state drive (SSD), or a combination thereof.

[0056] The computer C may further include a RAM (Random Access Memory) for expanding the program P during execution and for temporarily storing various data. The computer C may also include a communication interface for transmitting and receiving data to and from other devices. The computer C may also include an input / output interface for connecting input / output devices such as a keyboard, mouse, display, and printer.

[0057] Furthermore, the program P can be recorded on a non-transitory tangible recording medium M that can be read by the computer C. Such a recording medium M can be, for example, a tape, a disk, a card, a semiconductor memory, or a programmable logic circuit. The computer C can acquire the program P via such a recording medium M. The program P can also be transmitted via a transmission medium. Such a transmission medium can be, for example, a communication network or broadcast waves. The computer C can also acquire the program P via such a transmission medium.

[0058] Furthermore, the functions of each of the devices may be realized by a single processor provided in a single computer, by multiple processors provided in a single computer working in cooperation, or by multiple processors provided in each of multiple computers working in cooperation. Furthermore, the programs for causing each of the devices to realize the functions may be stored in a single memory provided in a single computer, or may be distributed and stored in multiple memories provided in a single computer, or may be distributed and stored in multiple memories provided in each of multiple computers.

[0059] [Appendix A] This disclosure includes the techniques described in the following appendices. However, the present invention is not limited to the techniques described in the following appendices, and various modifications are possible within the scope of the claims.

[0060] (Appendix A1) An explanation acquisition means for acquiring an explanation text in which a patient explains his or her symptoms; a summary generation means for generating a summary of the explanatory text by inputting the explanatory text using a large-scale language model; a medical information acquisition means for acquiring medical information of the patient; a symptom prediction means for predicting candidate symptoms of the patient based on the summary text and the medical information; an output means for outputting the summary sentence and the predicted symptom candidate; A symptom understanding support device comprising:

[0061] (Appendix A2) The medical information includes at least one of personal information of the patient, medical examination findings information of the patient, and medical history information of the patient. 1. A symptom understanding assistance device as described in Appendix A1.

[0062] (Appendix A3) the explanation acquisition means converts the voice collected during the patient interview into text data. A symptom understanding assistance device according to appendix A1 or A2.

[0063] (Appendix A4) the symptom prediction means predicts the symptom candidate based on an output obtained by inputting the summary sentence and the medical information into a trained model generated by machine learning. 10. A symptom understanding assistance device according to any one of appendices A1 to A3.

[0064] (Appendix A5) the medical information includes a diagnostic target image of the patient; 10. A symptom understanding assistance device according to any one of appendices A1 to A4.

[0065] (Appendix A6) The candidate symptoms are information used in decision-making regarding the patient's diagnosis. 10. A symptom understanding assistance device according to any one of appendices A1 to A5.

[0066] [Appendix B] This disclosure includes the techniques described in the following appendices. However, the present invention is not limited to the techniques described in the following appendices, and various modifications are possible within the scope of the claims.

[0067] (Appendix B1) an explanation acquisition process in which at least one processor acquires an explanation sentence in which the patient describes his or her symptoms; a summary generation process in which the at least one processor uses a large-scale language model to input the explanatory text and generate a summary of the explanatory text; a medical information acquisition process, in which the at least one processor acquires medical information of the patient; a symptom prediction process in which the at least one processor predicts candidate symptoms of the patient based on the summary sentence and the medical information; an output process in which the at least one processor outputs the summary sentence and the predicted symptom candidate; A method for supporting symptom understanding, including:

[0068] (Appendix B2) The medical information includes at least one of personal information of the patient, medical examination findings information of the patient, and medical history information of the patient. A symptom understanding assistance method as described in Appendix B1.

[0069] (Appendix B3) In the explanation acquisition process, the at least one processor converts the voice collected during the patient interview into text data. A symptom understanding support method as described in Appendix B1 or B2.

[0070] (Appendix B4) In the symptom prediction process, the at least one processor predicts the symptom candidate based on an output obtained by inputting the summary sentence and the medical information into a trained model generated by machine learning. A symptom understanding support method according to any one of appendices B1 to B3.

[0071] (Appendix B5) the medical information includes a diagnostic target image of the patient; A symptom understanding support method according to any one of appendices B1 to B4.

[0072] (Appendix B6) The candidate symptoms are information used in decision-making regarding the patient's diagnosis. A symptom understanding assistance method according to any one of appendices B1 to B5.

[0073] [Appendix C] This disclosure includes the techniques described in the following appendices. However, the present invention is not limited to the techniques described in the following appendices, and various modifications are possible within the scope of the claims.

[0074] (Appendix C1) A program for causing a computer to function as a symptom understanding assistance device, the program comprising: An explanation acquisition means for acquiring an explanation text in which a patient explains his or her symptoms; a summary generation means for generating a summary of the explanatory text by inputting the explanatory text using a large-scale language model; a medical information acquisition means for acquiring medical information of the patient; a symptom prediction means for predicting candidate symptoms of the patient based on the summary text and the medical information; an output means for outputting the summary sentence and the predicted symptom candidate; A symptom understanding support program to function as a

[0075] (Appendix C2) The medical information includes at least one of personal information of the patient, medical examination findings information of the patient, and medical history information of the patient. Symptom understanding support program described in Appendix C1.

[0076] (Appendix C3) the explanation acquisition means converts the voice collected during the patient interview into text data. A symptom understanding support program described in Appendix C1 or C2.

[0077] (Appendix C4) the symptom prediction means predicts the symptom candidate based on an output obtained by inputting the summary sentence and the medical information into a trained model generated by machine learning. A symptom understanding support program as set forth in any one of Appendices C1 to C3.

[0078] (Appendix C5) the medical information includes a diagnostic target image of the patient; A symptom understanding support program as set forth in any one of Appendices C1 to C4.

[0079] (Appendix C6) The candidate symptoms are information used in decision-making regarding the patient's diagnosis. A symptom understanding support program as set forth in any one of Appendices C1 to C5.

[0080] [Appendix D] This disclosure includes the techniques described in the following appendices. However, the present invention is not limited to the techniques described in the following appendices, and various modifications are possible within the scope of the claims.

[0081] (Appendix D1) at least one processor, An explanation acquisition process for acquiring an explanation text in which a patient describes his or her symptoms; a summary generation process for generating a summary of the explanatory text using a large-scale language model as an input; a medical information acquisition process for acquiring medical information of the patient; a symptom prediction process for predicting candidate symptoms of the patient based on the summary text and the medical information; an output process for outputting the summary sentence and the predicted symptom candidate; A symptom understanding support device that performs the following.

[0082] The symptom understanding assistance device may further include a memory, and the memory may store a program for causing the at least one processor to execute each of the processes.

[0083] (Appendix D2) The medical information includes at least one of personal information of the patient, medical examination findings information of the patient, and medical history information of the patient. 10. A symptom understanding assistance device according to claim D1.

[0084] (Appendix D3) In the explanation acquisition process, the at least one processor converts the voice collected during the patient interview into text data. A symptom understanding assistance device according to appendix D1 or D2.

[0085] (Appendix D4) In the symptom prediction process, the at least one processor predicts the symptom candidate based on an output obtained by inputting the summary sentence and the medical information into a trained model generated by machine learning. A symptom understanding assistance device according to any one of appendices D1 to D3.

[0086] (Appendix D5) the medical information includes a diagnostic target image of the patient; A symptom understanding assistance device according to any one of appendices D1 to D4.

[0087] (Appendix D6) The candidate symptoms are information used in decision-making regarding the patient's diagnosis. A symptom understanding assistance device according to any one of appendices D1 to D5.

[0088] [Appendix E] This disclosure includes the techniques described in the following appendices. However, the present invention is not limited to the techniques described in the following appendices, and various modifications are possible within the scope of the claims.

[0089] (Appendix E1) A program for causing a computer to function as a symptom understanding support device, the program comprising: An explanation acquisition process for acquiring an explanation text in which a patient describes his or her symptoms; a summary generation process for generating a summary of the explanatory text using a large-scale language model as an input; a medical information acquisition process for acquiring medical information of the patient; a symptom prediction process for predicting candidate symptoms of the patient based on the summary text and the medical information; an output process for outputting the summary sentence and the predicted symptom candidate; A non-transitory recording medium on which a symptom understanding support program for executing the symptom understanding support program is recorded. [Explanation of symbols]

[0090] 1 Symptom understanding support device 1A Information processing equipment 10A Control unit 11, 11A Explanation Acquisition Section 12, 12A Summary generator 13, 13A Medical Information Acquisition Department 14, 14A Symptom Prediction Section 15, 50A output section 15A Output Control Unit

Claims

1. An explanation acquisition means for acquiring an explanation text in which a patient explains his or her symptoms; a summary generation means for generating a summary of the explanatory text by inputting the explanatory text using a large-scale language model; a medical information acquisition means for acquiring medical information of the patient; a symptom prediction means for predicting candidate symptoms of the patient based on the summary text and the medical information; an output means for outputting the summary sentence and the predicted symptom candidate; A symptom understanding support device comprising:

2. The medical information includes at least one of personal information of the patient, medical examination findings information of the patient, and medical history information of the patient. The symptom understanding support device according to claim 1 .

3. the explanation acquisition means converts the voice collected during the examination of the patient into text data. The symptom understanding support device according to claim 1 or 2.

4. the symptom prediction means predicts the symptom candidate based on an output obtained by inputting the summary sentence and the medical information into a trained model generated by machine learning. The symptom understanding support device according to claim 1 or 2.

5. the medical information includes a diagnostic target image of the patient; The symptom understanding support device according to claim 1 or 2.

6. The candidate symptoms are information used in decision-making regarding the patient's diagnosis. The symptom understanding support device according to claim 1 or 2.

7. an explanation acquisition process in which at least one processor acquires an explanation sentence in which the patient describes his or her symptoms; a summary generation process in which the at least one processor uses a large-scale language model to input the explanatory text and generate a summary of the explanatory text; a medical information acquisition process, in which the at least one processor acquires medical information of the patient; a symptom prediction process in which the at least one processor predicts candidate symptoms of the patient based on the summary sentence and the medical information; an output process in which the at least one processor outputs the summary sentence and the predicted symptom candidate; A method for supporting symptom understanding, including:

8. A symptom understanding support program for causing a computer to function as a symptom understanding support device, the computer comprising: An explanation acquisition means for acquiring an explanation text in which a patient explains his or her symptoms; a summary generation means for generating a summary of the explanatory text by inputting the explanatory text using a large-scale language model; a medical information acquisition means for acquiring medical information of the patient; a symptom prediction means for predicting candidate symptoms of the patient based on the summary text and the medical information; an output means for outputting the summary sentence and the predicted symptom candidate; A symptom understanding support program to function as a

Images