Patient support device and patient support method

Abstract

To provide a patient support device and a patient support method that enable appropriate self-care for side effects associated with cancer treatment.SOLUTION: A patient support device (management server) comprises: an acquisition unit (acquisition module) that acquires cancer treatment information of a target patient; a side effect prediction unit (side effect prediction module) that predicts side effects and their occurrence timing on the basis of the acquired cancer treatment information; a coping method acquisition unit (individual countermeasure acquisition module) that acquires coping methods corresponding to the predicted side effects; and an output unit (output module) that outputs information regarding the side effects and coping methods in association with the occurrence timing of the side effects. The acquisition unit acquires, as the cancer treatment information, information regarding the cancer type, anticancer drug, and treatment start date. The side effect prediction unit calculates an occurrence timing at which the probability of occurrence of a side effect exceeds a first reference, with the treatment start date as a reference on the basis of occurrence probability basic information indicating the probability of occurrence of a side effect for each elapsed day from the start of administration of the anticancer drug for the cancer type.SELECTED DRAWING: Figure 2

Description

[Technical Field]

[0001] The present invention relates to a patient support device and a patient support method. [Background technology]

[0002] JP 2006-158490 A (Patent Document 1) is a background technology in this technical field. This publication states that "a cancer pain management system 10 includes a pain relief target value input unit 12 for inputting a pain relief target value indicating a goal for pain relief from cancer pain, a medical record database 18 for storing a ladder indicating stages of narcotic potency of drugs administered to the patient, a patient condition input unit 14 for inputting the patient's condition including subjective symptoms, a drug management unit 24 for determining whether the pain relief target value inputted in the pain relief target value input unit 12 has been achieved based on the patient's subjective symptoms inputted in the patient condition input unit 14, and for selecting a drug to be administered to the patient from a ladder one stage more narcotic than the ladder stored in the medical record database 18 in response to a determination that the pain relief target value has not been achieved, and an output unit 26 for outputting information on the drug selected by the drug management unit 24" (see Abstract). [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Application Laid-Open No. 2006-158490 Summary of the Invention [Problem to be solved by the invention]

[0004] The technology in Patent Document 1 is said to be able to address patient pain early and improve the rate of pain relief. However, side effects of cancer treatment are not limited to pain. Furthermore, because the content of cancer treatment varies from cancer patient to cancer patient, cancer patients face the challenge of being unable to take appropriate self-care measures based solely on general information about side effects associated with cancer treatment that can be collected from the Internet, etc.

[0005] Therefore, this technology provides a new mechanism for appropriate self-care against side effects associated with cancer treatment. [Means for solving the problem]

[0006] In order to solve the above problems, for example, the configurations described in the claims are adopted. The present application includes multiple means for solving the above-mentioned problems, and one example is a patient support device that includes an acquisition unit that acquires cancer treatment information for a target patient, a side effect prediction unit that predicts side effects and the timing of their occurrence based on the acquired cancer treatment information, a countermeasure acquisition unit that acquires countermeasures for the predicted side effects, and an output unit that outputs information regarding the side effects and the countermeasures in association with the timing of the occurrence of the side effects. [Effects of the Invention]

[0007] According to the present invention, a new mechanism for appropriate self-care against side effects associated with cancer treatment can be provided. Problems, configurations, and effects other than those described above will become apparent from the following description of the embodiments. [Brief explanation of the drawings]

[0008] [Figure 1] FIG. 1 is an example of an overall configuration diagram of a patient support system 1. [Figure 2] FIG. 2 shows an example of the hardware configuration of the management server 101. [Figure 3] FIG. 3 shows an example of the hardware configuration of the patient terminal 102. [Figure 4] FIG. 4 shows an example of the hardware configuration of the expert terminal 103. [Figure 5] FIG. 5 is an example of patient information 500. [Figure 6] FIG. 6 is an example of basic occurrence probability information 600. [Figure 7] FIG. 7 is an example of treatment correction information 700. [Figure 8] FIG. 8 is an example of the handling information 800. [Figure 9] FIG. 9 is an example of the priority handling information 900. [Figure 10] FIG. 10 is an example of symptom information 1000. [Figure 11] FIG. 11 is an example of specialist training information 1100. [Figure 12] FIG. 12 is an example of a cancer patient support flow 1200. [Figure 13] FIG. 13 is an example of a flow 1300 for predicting a side effect. [Figure 14] FIG. 14 shows an example of a treatment method correction flow 1400. [Figure 15] FIG. 15 shows an example of a subjective symptom correction flow 1500. [Figure 16] FIG. 16 shows an example of an individual measure proposal flow 1600. [Figure 17] FIG. 17 is an example of a patient terminal screen 1700. [Figure 18] FIG. 18 is an example of a graph 1800 showing the probability of occurrence of a side effect. [Figure 19] FIG. 19 is another example of a graph 1900 showing the probability of occurrence of a side effect. [Figure 20] FIG. 20 is another example of a graph 2000 showing the probability of occurrence of a side effect. [Figure 21] FIG. 21 is another example of a graph 2100 showing the probability of occurrence of a side effect. [Figure 22] FIG. 22 is an example of a subjective symptom input display 2200. [Figure 23] FIG. 23 is another example of a patient terminal screen 2300. [Figure 24] FIG. 24 shows another example of the health information management screen 2400. [Figure 25] FIG. 25 is an example of an expert terminal screen 2500. [Figure 26] FIG. 26 is another example of an expert terminal screen 2600. DETAILED DESCRIPTION OF THE INVENTION

[0009] The patient support system, patient support method, and program related to this technology are described below with reference to the drawings as appropriate. When cancer patients are diagnosed with cancer and undergo treatment, they may have anxiety and worries not only about the disease and treatment, but also about living their daily lives while dealing with side effects. This technology predicts side effects specific to cancer treatment for cancer patients and when they will occur, and provides this information to cancer patients by correlating it with information on how to deal with the side effects, for example.

[0010] This patient support system allows cancer patients to easily obtain information on more appropriate side effects and coping methods for their cancer treatment, thereby improving their quality of life (QOL), particularly by reducing mental and physical hurdles and burdens.

[0011] Hereinafter, the present technology will be described using as an example a case where an online patient support service is provided in a patient support system according to one embodiment, and cancer patients who use the service are supported.

[0012] [Patient Support System] FIG. 1 is an example of an overall configuration diagram of a patient support system 1 according to an embodiment. The patient support system 1 is configured to include one or more management servers 101, one or more patient terminals 102, and one or more expert terminals 103. The one or more expert terminals 103 are not essential elements, but are additional elements that can be provided.

[0013] One or more patient terminals 102 and one or more specialist terminals 103 are each configured to be connectable to one or more management servers 101 via a network. The network may be wired or wireless, and each terminal can send and receive information to and from each other via the network.

[0014] The patient terminal 102 may be provided separately from the management server 101, or may be provided integrally with the management server 101. The expert terminal 103 may be provided separately from the management server 101, or may be provided integrally with the management server 101.

[0015] The management server 101, patient terminal 102, and expert terminal 103 (hereinafter, the patient terminal 102 and the expert terminal 103 may be simply referred to as "terminals") in the patient support system 1 may each be, for example, a portable terminal (mobile terminal) such as a smartphone, tablet, mobile phone, or personal digital assistant (PDA), or a wearable terminal such as glasses (including goggles), wristwatch, or clothing. Furthermore, the management server 101 and the terminal may each be a stationary or portable computer, or a server located on the cloud or a network.

[0016] Furthermore, from the viewpoint of functionality, each of the management server 101 and the terminal may be a VR (Virtual Reality) terminal, an AR (Augmented Reality) terminal, or an MR (Mixed Reality) terminal. Alternatively, each of the management server 101 and the terminal may be a combination of these. For example, a combination of one smartphone and one wearable terminal may logically function as one management server 101 or terminal. Each of the management servers 101 or terminals may be an information processing terminal other than these.

[0017] The management server 101 or terminal of the patient support system 1 may optionally include a processor that executes an operating system, applications, programs, etc.; a primary storage device such as RAM (Random Access Memory); a secondary storage device such as an IC card, hard disk drive, SSD (Solid State Drive), or flash memory; a communication control unit such as a network card, wireless communication module, or mobile communication module; an input device that detects motion by capturing images from a touch panel, keyboard, mouse, audio input device, motion controller, or camera; and an output device such as a monitor, display, printer, audio output device, or oscillator. The input device may include sensors such as a GPS, gyro sensor, or acceleration sensor. The output device may be a device or terminal that transmits information to be output to an external monitor, display, printer, or device.

[0018] The main memory stores various programs and applications (software modules), and the processor executes these programs and applications to realize each functional element of the overall system. Each module may be implemented by one or more programs or applications. Each module may also be implemented by an independent program or application, or as a subprogram or function within a single integrated program or application.

[0019] Furthermore, each of these modules may be implemented as hardware by integrating circuits or employing a microcomputer (hardware module).

[0020] Furthermore, each module may be implemented by a single processor or multiple processors. Furthermore, each module may be provided on a single management server or terminal, or may be provided separately on two or more management servers or terminals interconnected via a network. Furthermore, some modules may be implemented in a different country from the other modules.

[0021] In this specification, each module is described as a subject that performs processing, but in reality, processing is performed by a processor executing various programs, applications, and the like.

[0022] The auxiliary storage device stores various databases (DB). A "database" is a set of data that has been organized and collected so that it can accommodate any data manipulation (e.g., extraction, addition, deletion, overwriting, etc.) from a processor or an external computer. The auxiliary storage device is a functional element (storage unit) that stores one or more sets of data.

[0023] The implementation method of the database is not limited, and may be, for example, a database management system, spreadsheet software, or text files such as XML or JSON. Some or all of this information may be stored in a relational database or a non-relational database. The database may be provided independently while being connectable to a processor or the like.

[0024] [Administration Server] FIG. 2 illustrates an example of the hardware configuration of the management server 101. The management server 101 is an element that manages this patient support system 1. The management server 101 is typically a device that is managed by an administrator who manages and operates this patient support system 1. The management server 101 is configured, for example, by a computer server or the like that is deployed on a cloud.

[0025] The management server 101 includes a main storage device 201 and an auxiliary storage device 202. The management server 101 also includes a processor 203, an input device 204, an output device 205, and a communication control unit 206 as described above.

[0026] The main memory device 201 stores programs and applications such as a management module 211, an acquisition module 212, a side effect prediction module 213, a countermeasure acquisition module 214, an individual measure acquisition module 215, an output module 216, a counseling module 217, and a specialist education module 218. Each functional element of the management server 101 is realized by the processor 203 executing these programs and applications stored in the main memory device 201.

[0027] Furthermore, the implementation method of each module provided in the main memory device 201 is not limited to this embodiment, and each module may be realized in a form in which multiple servers or cloud applications cooperate with each other.

[0028] The auxiliary storage device 202 stores information necessary for the operation of the patient support system 1. The auxiliary storage device 202 stores, for example, patient information 500, basic occurrence probability information 600, treatment correction information 700, countermeasure information 800, priority countermeasure information 900, subjective symptom information 1000, specialist training information 1100, side effect information 210, health information 220, and counseling information 230.

[0029] The details of this information will be described later. Note that the implementation method of each piece of information stored in the auxiliary storage device 202 is not limited to this embodiment, and each piece of information may be distributed and allocated to multiple database servers or cloud applications.

[0030] Each functional element of the management server 101 will be briefly described. The management module 211 manages the operations of the patient terminal 102 and the specialist terminal 103. The management module 211 cooperates with, for example, the patient terminal execution module 311 and the patient side counseling module 312 of the patient terminal 102 to control the basic operations for executing the patient support service on the patient terminal 102.

[0031] The management module 211, for example, works in cooperation with the patient terminal execution module 311 and the patient side counseling module 312 of the patient terminal 102 to output (display) a login screen for connecting to the patient support service and a patient terminal screen, which will be described later, on an output device 305, such as a display, of the patient terminal 102.

[0032] The management module 211, for example, cooperates with the expert terminal execution module 411 and the expert terminal counseling module 412 of the expert terminal 103 to control the basic operations for executing the patient support service on the expert terminal 103. For example, the management module 211 cooperates with the expert terminal execution module 411 of the expert terminal 103 to output (display) a login screen for connecting to the patient support service, an expert terminal screen (described later), and the like, on the output device 405 such as a display of the expert terminal 103.

[0033] The acquisition module 212 acquires information from the patient terminal 102 and the expert terminal 103. The management module 211, for example, cooperates with the patient terminal execution module 311 and patient side counseling module 312 of the patient terminal 102 to acquire input information input from the patient terminal 102. The management module 211, for example, cooperates with the expert terminal execution module 411 and expert terminal counseling module 412 of the expert terminal 103 to acquire input information input from the expert terminal 103. The acquisition module 212 outputs (records) the acquired information to the auxiliary storage device 202.

[0034] The side effect prediction module 213 predicts side effects. The side effect prediction module 213 predicts side effects and their occurrence times based on, for example, cancer treatment information in the patient information 500. The side effect prediction module 213 may be configured to generate an occurrence probability curve based on, for example, basic occurrence probability information 600, which will be described later. Prediction of side effects and their occurrence times will be described later.

[0035] The countermeasure acquisition module 214 acquires countermeasures for side effects. For example, the countermeasure acquisition module 214 acquires countermeasures for side effects that are predicted to occur for a patient who is a support target. The acquisition of countermeasures will be described later.

[0036] The individual measure acquisition module 215 acquires individual measures corresponding to side effects. The individual measure acquisition module 215 acquires information on individual measures indicating more specific measures based on the countermeasures. The acquisition of individual measures will be described later.

[0037] The output module 216 outputs information about side effects and how to deal with them. For example, the output module 216 outputs information about side effects and how to deal with them in association with the time when the side effects occurred. The output of side effects and how to deal with them will be described later.

[0038] The counseling module 217 manages the counseling service performed between the patient terminal 102 and the expert terminal 103. For example, the counseling module 217 cooperates with the patient-side counseling module 312 of the patient terminal 102 and the expert terminal counseling module 412 of the expert terminal 103 to control operations for the counseling service performed between the patient terminal 102 and the expert terminal 103.

[0039] The expert training module 218 manages training for experts in the expert terminal 103. The expert training module 218 outputs training content to the expert terminal 103, for example, in cooperation with the expert learning module 413 of the expert terminal 103.

[0040] [Patient device] FIG. 3 shows an example of the hardware configuration of the patient terminal 102. The patient terminal 102 is a terminal used by a user (typically a patient, in this embodiment, a cancer patient) who uses the patient support service provided by the management server 101. The patient terminal 102 is configured, for example, by a terminal such as a mobile information terminal such as a smartphone or tablet, a notebook PC, or a desktop PC.

[0041] The patient terminal 102 includes a main memory device 301 and an auxiliary memory device 302. The patient terminal 102 also includes a processor 303, an input device 304, an output device 305, a camera 306, and a communication control unit 307 as described above.

[0042] The main memory device 301 stores programs and applications such as a patient terminal execution module 311 and a patient side counseling module 312, and the processor 303 executes these programs and applications to realize each functional element of the patient terminal 102.

[0043] The patient terminal execution module 311 controls the basic operations of the patient terminal 102. For example, the patient terminal execution module 311 cooperates with the management module 211 of the management server 101 to control the basic operations for utilizing the patient support services provided by the management server 101.

[0044] The patient-side counseling module 312 manages the counseling services provided between the patient terminal 102 and the expert terminal 103. The patient-side counseling module 312 cooperates with, for example, the counseling module 217 of the management server 101 and the expert terminal counseling module 412 of the expert terminal 103, and controls operations to output (display) a counseling screen on the patient terminal 102 and to execute web counseling held between the patient terminal 102 and the expert terminal 103.

[0045] The auxiliary storage device 302 stores information necessary for the operation of the patient terminal 102. The auxiliary storage device 302 stores, for example, patient information 500, symptom information 1000, side effect information 210, health information 220, and counseling information 230. This information may be some or all of the information related to the operation of the patient terminal 102 among the patient information 500, symptom information 1000, side effect information 210, health information 220, and counseling information 230 stored in the auxiliary storage device 202 of the management server 101.

[0046] [Expert Terminal] FIG. 4 shows an example of the hardware configuration of the expert terminal 103. The expert terminal 103 is a terminal used by an expert who provides counseling to cancer patients in patient support services. The expert terminal 103 may be, for example, a terminal used by a service provider who provides patient support services to cancer patients.

[0047] The experts typically include medical professionals (for example, doctors, nurses, pharmacists, clinical laboratory technicians, radiological technologists, nutritionists (including, for example, registered dietitians and registered dietitians specializing in cancer pathological nutrition), and office staff). In this embodiment, the experts are registered dietitians. The expert terminal 103 is configured by a terminal such as a smartphone, tablet, laptop PC, or desktop PC.

[0048] The expert terminal 103 includes a main memory device 401 and an auxiliary memory device 402. The expert terminal 103 also includes a processor 403, an input device 404, an output device 405, a camera 406, and a communication control unit 407 as described above.

[0049] The main memory device 401 stores programs and applications such as an expert terminal execution module 411, an expert terminal counseling module 412, and an expert learning module 413, and the processor 403 executes these programs and applications to realize each functional element of the expert terminal 103.

[0050] The expert terminal execution module 411 manages the basic operations of the expert terminal 103. The expert terminal execution module 411, for example, works in cooperation with the management module 211 of the management server 101 to control the basic operations of the expert terminal 103 in the patient support service provided by the management server 101.

[0051] The expert terminal counseling module 412 manages counseling services provided between the expert terminal 103 and the patient terminal 102. The expert terminal counseling module 412, for example, works in conjunction with the counseling module 217 of the management server 101 and the patient side counseling module 312 of the patient terminal 102 to output (display) an expert terminal screen (described later) on the expert terminal 103 and control operations for executing web counseling held between the expert terminal 103 and the patient terminal 102.

[0052] The expert learning module 413 manages education for experts in the expert terminal 103. The expert learning module 413 outputs educational content to the output device 405, such as a display, of the expert terminal 103, based on instructions from an expert (typically a registered dietitian) using the expert terminal. The expert learning module 413 outputs educational content in cooperation with the expert education module 218 of the management server 101, for example.

[0053] The auxiliary storage device 402 stores information necessary for the operation of the expert terminal 103. The auxiliary storage device 402 stores, for example, patient information 500, symptom information 1000, specialist training information 1100, side effect information 210, health information 220, and counseling information 230. This information may be part or all of the information related to patient support at the expert terminal 103, among the patient information 500, symptom information 1000, specialist training information 1100, side effect information 210, health information 220, and counseling information 230 stored in the management server 101.

[0054] 5 to 11 show examples of various types of information stored in the auxiliary storage device 202 of the management server 101. FIG. 5 is an example of patient information 500. The patient information 500 is information about cancer patients (users) who use the patient support services provided by the management server 101.

[0055] The patient information 500 includes, for example, patient identification information for identifying the patient, cancer treatment information, etc. In the patient information 500, for example, values ​​such as those shown as sample values ​​520 are entered for item names 510. The contents indicated by the sample values ​​520 are written in a summary 530 column.

[0056] Examples of patient identification information include patient ID, patient display ID, name, etc. Examples of cancer treatment information include cancer type, treatment details, and whether or not a consent form is present. Although not limited thereto, cancer types may be classified according to the organ-specific cancer classification in the "Cancer Treatment Guidelines" of the Japanese Society of Clinical Oncology, including, for example, esophageal cancer, gastric cancer, colon cancer, gastrointestinal stromal tumor (GIST), adult brain tumor, pediatric brain tumor, breast cancer, etc.

[0057] Treatment can be broadly divided into, for example, chemotherapy (including, for example, postoperative adjuvant chemotherapy), surgery (including, for example, endoscopic resection), and palliative care. The information about chemotherapy may include, for example, the anticancer drug used and the start date of treatment. The information about chemotherapy may include, for example, the course of treatment and the planned start date. The information about chemotherapy may include, for example, information in accordance with the cancer chemotherapy protocol prepared for each type of cancer.

[0058] Furthermore, the information about the surgery (hereinafter sometimes simply referred to as "procedure method") may be, for example, one or a combination of two or more of the date of the procedure, the extent of resection, the resection method, or the extent of lymph node dissection. Examples of the procedure method include total gastrectomy, gastrectomy, laparoscopic gastrectomy, gastrectomy with lymph node dissection, and proximal gastrectomy. The procedure method may also be, for example, a surgical procedure in accordance with the treatment guidelines for each cancer set by each organ-specific cancer society.

[0059] The consent form is an agreement regarding the explanation of using this patient support service. For example, the consent form indicates that the patient agrees to receiving predictions about when side effects of their cancer will occur and suggestions on how to deal with them.

[0060] FIG. 6 is an example of basic occurrence probability information 600. The basic information 600 on incidence probability indicates the incidence probability 640 of a side effect 620 for each number of days 630 elapsed since the start of treatment. The basic information 600 on incidence probability can be prepared for each type of cancer or each combination 610 of a cancer type and an anticancer drug, for example.

[0061] The occurrence probability basic information 600 may include information regarding a first criterion and a second criterion regarding the occurrence probability. The first criterion represents an occurrence probability that serves as an index for predicting when a side effect will manifest as a symptom, and may be, for example, a value of 50%. The second criterion represents an occurrence probability that serves as an index for predicting a predetermined time before a side effect will manifest as a symptom, and may be, for example, a value lower than the first criterion (for example, 45%). The second criterion may be set to represent, for example, an appropriate time to take some kind of preventive action before a side effect occurs.

[0062] The occurrence probability 640 may be, for example, normalized to reflect the difference in occurrence probability between side effects, but is not limited to this. Note that the occurrence probability 640 in Figure 6 is a sample value and may not necessarily reflect the actual occurrence probability of side effects.

[0063] The basic information on occurrence probability 600 can be created based on the relationship between cancer type or combination of cancer type and anticancer drug 610, number of days elapsed 630, and occurred side effects 620, which are collected by, for example, medical institutions, pharmaceutical companies, research institutions, academic societies, etc. Furthermore, the basic information on occurrence probability 600 may be updated with newer information at any time based on data acquired from, for example, medical institutions, pharmaceutical companies, research institutions, academic societies, cancer patients (including, for example, users), etc.

[0064] FIG. 18 is an example of a graph 1800 showing the probability of occurrence of a side effect. For example, when the horizontal axis represents the number of days elapsed and the vertical axis represents the probability of side effects, the basic information 600 on occurrence probability may be stored as an occurrence probability curve showing the probability of side effects occurring for each side effect as shown in Fig. 18. The probability of side effects occurring will be described later.

[0065] FIG. 7 is an example of treatment correction information 700. The treatment correction information 700 is information for correcting the occurrence probability of a side effect for each treatment method. The treatment correction information 700 is, for example, a correction coefficient for correcting the occurrence probability in the occurrence probability basic information 600, which is determined based on the relationship between the treatment method and the side effect. Although not limited to this, for example, the occurrence probability of a predetermined side effect in the occurrence probability basic information 600 can be multiplied by the correction coefficient for the corresponding side effect depending on the treatment method, thereby correcting the occurrence probability of the side effect to a more appropriate value.

[0066] FIG. 8 is an example of the handling information 800. Countermeasure information 800 is information indicating countermeasures 820 for each side effect 810. Side effects 810 may be prepared, for example, by cancer type or treatment content. Side effects 810 may be prepared, for example, by chemotherapy, treatment method, or a combination thereof. For example, side effects 810 may be prepared for each combination of two or more of cancer type, anticancer agent, and treatment method.

[0067] For example, for the side effect of "loss of appetite," a distinction may be made between loss of appetite caused by chemotherapy and loss of appetite caused by gastrointestinal resection, and appropriate measures may be prepared separately for each. Note that the measures for loss of appetite caused by chemotherapy and loss of appetite caused by gastrointestinal resection may, for example, partially overlap.

[0068] The countermeasure information 800 may be, for example, countermeasures from the viewpoint of diet (nutrition), exercise, activity, mental state, etc. Countermeasures related to diet are, for example, information indicating how to eat, what to eat, how much to eat, how to cook, etc. to deal with side effects. Exercise-related coping methods include, for example, information on rehabilitation exercises to deal with side effects, daily activities, and the like.

[0069] The measures for activities are, for example, information indicating precautions and ideas for activities that take side effects into consideration. The coping methods for the mental state are, for example, information indicating a way to change one's mood to cope with side effects, advice, etc. In this embodiment, the present technology will be described in detail using an example in which coping methods for diet are presented.

[0070] In the countermeasure information 800, the countermeasure 820 may be information that outlines the countermeasure for the side effect 810. For example, countermeasures 820 for the side effect 810 "loss of appetite due to chemotherapy" may include "small, frequent meals" and "easily digestible meals." One or more countermeasures 820 can be associated with one side effect 810.

[0071] Although not limited to this, the countermeasure 820 may be associated with a detailed countermeasure 830, which is information indicating the content of a more specific countermeasure. As an example, the detailed countermeasure 830 for the countermeasure 820 "eat small amounts frequently" may be "make efforts to maximize the number of meals possible," "eat frequently at times and cycles when you feel best," etc. One or more detailed countermeasures 830 may be associated with one countermeasure 820. Furthermore, the detailed countermeasures 830 associated with different countermeasures 820 may have some or all of the same features.

[0072] Furthermore, the detailed countermeasures 830 may be associated with individual countermeasures 840, which are information indicating the content of more specific countermeasures. As an example, individual countermeasures 840 for the detailed countermeasure 830 "ways to increase the number of meals possible" may include "small cup noodles," "ochazuke," "small portions of frozen meals," "convenience store prepared foods," etc. One or more individual countermeasures 840 can be associated with one detailed countermeasure 830. Furthermore, the individual countermeasures 840 associated with different detailed countermeasures 830 may have some or all of the same features in common.

[0073] FIG. 9 is an example of the priority handling information 900. The priority action information 900 is information for assigning a priority to each of a plurality of individual actions 910 in accordance with the patient's subjective symptoms. For example, the priority action information 900 defines a priority point 930 in accordance with the subjective symptom 920 for each of the individual actions 910. When a patient has any of the subjective symptoms 920, for example, a priority is determined for each individual action 910 based on the priority point 930 stored in the column of the corresponding subjective symptom 920. A method for determining the priority will be described later.

[0074] FIG. 10 is an example of symptom information 1000. The symptom information 1000 is information indicating the subjective symptoms of a target patient. The symptom information 1000 includes, for example, a date and time 1010, a type of side effect 1020, and a degree 1030. For example, when information regarding the type 1020 and the degree 1030 of a side effect is transmitted from the patient terminal 102 to the management server 101, the acquisition module 212 associates the information regarding the type 1020 of the side effect and its degree 1030 with the information regarding the acquired date and time 1010 and stores the information as the symptom information 1000.

[0075] FIG. 11 is an example of specialist training information 1100. The specialist training information 1100 is information about educational content prepared for experts to study. The specialist training information 1100 includes information such as a content ID and a data URL, and values ​​such as those shown in the sample value 1120 are entered for each field name 1110. The content indicated by the sample value 1120 is also written in the summary 1130 column.

[0076] The educational content is content that provides knowledge, theories, information, etc. for professionals to use in counseling various cancer patients. The educational content can be in various forms, such as textbooks, slides, videos, etc.

[0077] The data URL is information indicating the storage location of the data for each educational content, such as the URL of a storage folder that stores the various data that make up the learning content for each unit.

[0078] The side effect information 210 is information about side effects calculated (predicted) by the side effect prediction module 213, and is stored, for example, linked to patient identification information for identifying a patient. The side effect information 210 may include, for example, information about the timing of occurrence, including the predicted date of onset and date of disappearance of a side effect. The side effect information 210 may include, for example, information about a supplemental side effect occurrence probability graph for each patient and a corrected supplemental side effect occurrence probability graph.

[0079] Health information 220 is information related to the health management of a patient, and may include, for example, reference health management information and health management information acquired from the patient. Examples of reference health management information include information on a healthy weight, target calorie intake, target nutritional intake, etc., for each attribute of the patient, such as gender, age, and physique. The health management information acquired from the patient is stored linked to patient identification information for identifying the patient, and may include, for example, information on the patient's weight and diet (ingested nutritional value), as well as information on the date and time this information was acquired. The counseling information 230 is information relating to counseling between a patient and a specialist, and is stored in association with, for example, patient identification information for identifying the patient, a counseling ID for identifying each counseling session, etc. The counseling information 230 may include, for example, information such as a counseling ID, reservation date and time information, session date and time information, a patient ID, a specialist ID, and a counseling memo.

[0080] The above contents of the various information 210 to 230 and 500 to 1100 are examples, and the various information 500 to 1100 may include information other than the above examples.

[0081] [Patient support method] A patient support method according to the present technology will be described based on an operation example of the patient support system 1. Below, the present technology will be described using as an example a case where a cancer patient executes an application program for using the patient support service on the patient terminal 102 and accesses the management server 101 to use the patient support service.

[0082] <Side effects and how to deal with them> FIG. 12 is an example of a cancer patient support flow 1200. The patient support method according to the present technology acquires cancer treatment information (step S1210), predicts side effects and their occurrence times (step S1220), acquires countermeasures for the predicted side effects (step S1230), and outputs information regarding the side effects and countermeasures (step S1240).

[0083] The management module 211 of the management server 101, for example, works in cooperation with the patient terminal execution module 311 of the patient terminal 102 to display (output) an initial registration screen on the output device 305, such as a display, of the patient terminal 102, and accepts input of patient information by the cancer patient. The patient information includes, for example, the name and cancer treatment information (e.g., type of cancer, treatment details).

[0084] The patient terminal execution module 311 of the patient terminal 102 transmits the patient information input by the cancer patient to the management server 101. The acquisition module 212 of the management server 101 acquires the patient information and stores it in the auxiliary storage device 202 as patient information 500.

[0085] Although the management server 101 and the patient terminal 102 (or the expert terminal 103) operate in cooperation with each other, for the sake of simplicity, the following description will mainly focus on the operation of the management server 101, and will omit a description of the operation of the patient terminal 102 (or the expert terminal 103) that it cooperates with.

[0086] FIG. 17 is an example of a patient terminal screen 1700. The management module 211 of the management server 101 displays (outputs) a patient terminal screen 1700 on, for example, the output device 305 of the patient terminal 102. The management module 211 displays, for example, a treatment calendar field 1710, a cancer type display field 1720, a treatment method display field 1730, a chemotherapy type display field 1740, and a side effect / countermeasure display field 1750 on the patient terminal screen 1700. The patient terminal screen 1700 can be a so-called dashboard, in which various pieces of patient support information are displayed together on a single screen.

[0087] The management module 211 displays, for example, the number of days elapsed from the start of treatment to the present, the number of current treatment courses, the number of days from the present until the next medication treatment, the number of next treatment courses, etc. in the treatment calendar field 1710. For example, the management module 211 can calculate this information based on the patient information 500. Based on the patient information 500, the management module 211 displays the cancer type, treatment method, and type of chemotherapy in a cancer type display field 1720, a treatment method display field 1730, and a chemotherapy type display field 1740, respectively.

[0088] The side effect prediction module 213, the countermeasure acquisition module 214, and the output module 216 work together to output information about side effects and countermeasures in the side effect / countermeasure display column 1750. The output of side effects and countermeasures will be described below.

[0089] (Getting side effects) First, the side effect prediction module 213 predicts side effects and their occurrence times. FIG. 13 is an example of a flow 1300 for predicting a side effect. In the side effect prediction flow 1300, information on the type of cancer, anticancer drug, and treatment start date is obtained as cancer treatment information (step S1310), and based on the basic occurrence probability information 600, the time of side effect occurrence is calculated using the treatment start date as the reference (step S1320), and the time of side effect occurrence is output (step S1330).

[0090] Specifically, the side effect prediction module 213 acquires information on the type of cancer, anticancer drug, and treatment start date as cancer treatment information from the patient information 500 (step S1310). Note that if the patient is not undergoing chemotherapy, the side effect prediction module 213 may not acquire information on the anticancer drug, or may acquire information indicating that the anticancer drug is "none."

[0091] Then, the side effect prediction module 213 calculates the time of occurrence of the side effect based on the occurrence probability basic information 600, using the treatment start date as a reference (step S1320). In one embodiment, the side effect prediction module 213 generates an occurrence probability curve based on the occurrence probability basic information 600. As described above, the side effect occurrence probability graph 1800 in Fig. 18 is a graphical representation of the occurrence probability basic information 600. As described above, the occurrence probability basic information 600 indicates the occurrence probability of a side effect for each cancer type for each number of days elapsed since the start of administration of an anticancer drug.

[0092] The side effect occurrence probability graph 1800 shows, for example, an occurrence probability curve 1810 for "sudden nausea and vomiting" as a side effect, an occurrence probability curve 1820 for "persistent nausea and vomiting, loss of appetite" as a side effect, an occurrence probability curve 1830 for "stomatitis" as a side effect, and an occurrence probability curve 1840 for "diarrhea" as a side effect. In the occurrence probability graph 1800, a case where the occurrence probability is a first standard R1 (e.g., an occurrence probability of 50%) is indicated by a dashed dotted line. The side effect prediction module 213 may be configured to generate information (which may be, for example, approximate formula information, information for graph drawing, image information, etc.) relating to these occurrence probability curves 1810, 1820, 1830, 1840, etc., and store the information in the occurrence probability basic information 600 (which may be, for example, the side effect information 210). The side effect prediction module 213 may be configured to provide a countermeasure column for inputting a countermeasure, which will be described later, for each side effect below the occurrence probability curves 1810, 1820, 1830, and 1840. In this case, each combination of a side effect and a corresponding target method column (in FIG. 18, an arrow as part of the target method column) may be displayed in a different color, pattern, or background so that the combination of the side effect and the corresponding target method column can be easily identified.

[0093] The side effect prediction module 213 (which may be the output module 216) may, for example, generate a side effect occurrence probability graph 1800 and display it on the patient terminal screen 1700. In this case, the side effect prediction module 213 displays an occurrence probability curve for each predicted side effect and the first criterion R1 in the side effect occurrence probability graph 1800. In addition, below the occurrence probability curves 1810, 1820, 1830, and 1840, a countermeasure column in which a countermeasure corresponding to each side effect is entered is displayed.

[0094] In the occurrence probability curves 1810-1840 of each side effect, when the occurrence probability is higher than the first criterion R1, it can be predicted that this is the time when the side effect will appear as a symptom. Furthermore, among the intersections of the occurrence probability curves 1810-1840 of each side effect and the first criterion R1, the points with a relatively early number of days elapsed indicate the date when the side effect will appear, and the points with a relatively late number of days elapsed indicate the date when the side effect will disappear. In the case of the occurrence probability graph 1800, it is shown that it is possible to predict that the side effects that will occur in this order from the start of administration of the anticancer drug are "sudden nausea and vomiting," "persistent nausea and vomiting, loss of appetite," "stomatitis," and "diarrhea."

[0095] The side effect prediction module 213 calculates, based on such occurrence probability basic information 600, the occurrence time when the occurrence probability of a side effect is higher than the first standard R1, using the treatment start date as a reference. The side effect prediction module 213 calculates the predicted occurrence date, disappearance date, and occurrence time of a side effect, for example, based on the number of days elapsed from the treatment start date as a reference. The side effect prediction module 213 outputs (stores) the calculation results to, for example, the side effect information 210 (step S1330).

[0096] (Correction based on treatment method) The manifestation of side effects may vary depending on the treatment method, etc. FIG. 14 shows an example of a treatment method correction flow 1400. In the treatment method correction flow 1400, information on the treatment method is obtained as cancer treatment information (step S1410), a correction coefficient corresponding to the treatment method is obtained (step S1420), and the occurrence probability for each number of elapsed days is corrected using the correction coefficient (step S1430).

[0097] The side effect prediction module 213 acquires information on the treatment method as cancer treatment information from the patient information 500 (step S1410). Note that if the patient has not undergone surgical treatment, the side effect prediction module 213 may not execute the treatment method correction flow 1400, or may acquire information indicating that the treatment method is "none."

[0098] Then, the side effect prediction module 213 acquires a correction coefficient corresponding to the treatment method based on the treatment correction information 700 (step S1320). For example, when a patient has undergone "total gastrectomy", the side effect prediction module 213 acquires correction coefficients such as a correction coefficient of "12" for the side effect "nausea and vomiting", a correction coefficient of "2" for the side effect "loss of appetite", and a correction coefficient of "1" for the side effect "stomatitis".

[0099] Next, the side effect prediction module 213 corrects the occurrence probability for each elapsed day using the acquired correction coefficient (step S1430). Specifically, for example, the side effect prediction module 213 corrects the occurrence probability curve by multiplying the occurrence probability curve of each side effect by the corresponding correction coefficient.

[0100] FIG. 19 is another example of a graph 1900 showing the probability of occurrence of a side effect. The occurrence probability graph 1900 shows the occurrence probability curve 1910 of "sudden nausea and vomiting" and the occurrence probability curve 1920 of "persistent nausea and vomiting, loss of appetite" and the occurrence probability curve 1940 of "diarrhea" when the occurrence probability curves 1810 to 1840 are multiplied by the corresponding correction coefficients.

[0101] The occurrence probability curve 1910 of "sudden nausea and vomiting" has an occurrence probability 12 times higher than that of the occurrence probability curve 1810 (shown by the dotted line) in FIG. 18, for example. The occurrence probability curve 1920 of "persistent nausea and vomiting, loss of appetite" has an occurrence probability 2 times higher than that of the occurrence probability curve 1820 (shown by the dotted line) in FIG. 18, for example. The occurrence probability curve 1940 of "diarrhea" has an occurrence probability 1.2 times higher than that of the occurrence probability curve 1840 (shown by the dotted line) in FIG. 18, for example. Because the correction coefficient for "stomatitis" is "1", the occurrence probability curve 1930 of "stomatitis" has the same shape as the occurrence probability curve 1830 of "stomatitis" in the occurrence probability graph 1800. The position of the first criterion R1 remains unchanged.

[0102] The side effect prediction module 213 may, for example, display a corrected side effect occurrence probability graph 1900 on the patient terminal screen 1700. In this case, the side effect prediction module 213 displays corrected occurrence probability curves 1910 to 1940 for each predicted side effect on the side effect occurrence probability graph 1900. The side effect prediction module 213 may also store information related to the generated corrected side effect occurrence probability graph 1900 in the side effect information 210 (which may be the basic occurrence probability information 600).

[0103] In the side effect occurrence probability graph 1900, the corrected occurrence probability curves 1910-1940 also change how they intersect with the first standard R1. If the occurrence probability is higher than the first standard R1 in the corrected side effect occurrence probability curves 1910-1940, the side effect prediction module 213 predicts the time when the side effect will appear as a symptom. Furthermore, among the intersections between each side effect occurrence probability curve 1910-1940 and the first standard R1, the point with a relatively early number of days elapsed is predicted to be the date when the side effect will occur, and the point with a relatively late number of days elapsed is predicted to be the date when the side effect will disappear.

[0104] The side effect prediction module 213 calculates the predicted onset date, disappearance date, and onset time of a side effect based on, for example, the number of days elapsed from the treatment start date. The side effect prediction module 213 outputs (stores) the calculated results to, for example, the side effect information 210.

[0105] (Correction based on subjective symptoms) Furthermore, the manifestation of side effects may vary depending on the characteristics of each individual patient. FIG. 15 shows another example of a subjective symptom correction flow 1500. In the symptom correction flow 1500, information about the subjective symptoms of the target patient is acquired (step S1510), and the occurrence probability for each number of elapsed days is corrected based on the information about the subjective symptoms (step S1520).

[0106] FIG. 22 is an example of a subjective symptom input display 2200. The management module 211 outputs a subjective symptom input display 2200 relating to side effects to the patient terminal 102. The management module 211 displays, for example, an expected side effect item 2210 and a side effect level selection field 2220 in the subjective symptom input display 2200. The side effect level selection field 2220 displays, for example, five circles for each side effect item 2210, and the severity of the side effect can be expressed in six levels from level 0 (for example, no subjective symptoms) to 5 (for example, very severe).

[0107] If the patient terminal 102 is a touch panel output device 205 such as a smartphone, the level selection field 2220 is configured so that the user can input the level of the side effect by tracing (sliding a finger) five circles from the right the number of which corresponds to the degree of the side effect. Note that the subjective symptom input display 2200 may be configured so that subjective symptoms related to side effects other than expected side effects can be input.

[0108] The acquisition module 212 receives input of subjective symptoms of side effects from the patient terminal 102, and stores the input in the symptom information 1000 of the auxiliary storage device 202 in association with information on the date and time of reception. The side effect prediction module 213 corrects the occurrence probability for each number of elapsed days as necessary based on the symptom information 1000. The correction method may be, for example, the following method.

[0109] (1) Horizontal shift Specifically, for example, if subjective symptoms of a side effect appear on a day different from the predicted onset date, the side effect prediction module 213 shifts the occurrence probability curve of the side effect horizontally so that the intersection with the first criterion R1 on the side with a shorter number of elapsed days (i.e., the intersection representing the onset date) coincides with the day on which the subjective symptoms appeared. If the day on which the subjective symptoms appeared is earlier than the predicted onset date, the side effect prediction module 213 shifts the occurrence probability curve of the side effect in the direction of shortening the number of elapsed days. If the day on which the subjective symptoms appeared is later than the predicted onset date, the side effect prediction module 213 shifts the occurrence probability curve of the side effect in the direction of lengthening the number of elapsed days.

[0110] 20 is another example of a side effect occurrence probability graph 2000. In the occurrence probability graph 2000, for example, since the side effect "stomatitis" appeared several days (e.g., three days) earlier than the predicted onset date, the side effect prediction module 213 shifts the stomatitis occurrence probability curve 2030 by three days in the direction of shortening the number of elapsed days so that the predicted onset date coincides with the date on which the subjective symptoms appeared. In this case, for example, the disappearance date of the stomatitis is also shifted in the direction of shortening the number of elapsed days from the initially predicted disappearance date.

[0111] (2) Period adjustment Specifically, for example, if subjective symptoms of a side effect appear on a day different from the predicted onset date, the side effect prediction module 213 expands or contracts the side effect occurrence probability curve along the number of days that have passed, so that the intersection point between the side effect occurrence probability curve and the first criterion R1 on the side with the shorter number of days (i.e., the intersection point representing the onset date) coincides with the day on which the subjective symptoms appeared, and the intersection point on the side with the longer number of days that have passed (i.e., the intersection point representing the disappearance date) does not change.

[0112] If the day on which subjective symptoms appeared is earlier than the predicted onset date, the side effect prediction module 213 expands the occurrence probability curve of the side effect in the direction of the number of elapsed days so that the intersection representing the onset date coincides with the day on which the subjective symptoms appeared and the intersection representing the disappearance date remains unchanged.If the day on which subjective symptoms appeared is later than the predicted onset date, the side effect prediction module 213 contracts the occurrence probability curve of the side effect in the direction of the number of elapsed days so that the intersection representing the onset date coincides with the day on which the subjective symptoms appeared and the intersection representing the disappearance date remains unchanged.

[0113] (3) Up / down shift Specifically, for example, if subjective symptoms of a side effect appear on a day different from the predicted onset date, the side effect prediction module 213 shifts the occurrence probability curve of the side effect up or down so that the intersection with the first criterion R1 on the side with the shorter number of days elapsed (i.e., the intersection representing the onset date) coincides with the day on which the subjective symptoms appeared.

[0114] If the day on which subjective symptoms appear is earlier than the predicted onset date, the side effect prediction module 213 shifts the occurrence probability curve of the side effect upward. If the day on which subjective symptoms appear is later than the predicted onset date, the side effect prediction module 213 shifts the occurrence probability curve of the side effect downward. In this case, for example, the disappearance date of stomatitis is also shifted in a direction that makes the number of elapsed days longer or shorter than the initially predicted disappearance date.

[0115] (4) Period adjustment Specifically, for example, if subjective symptoms of a side effect appear on a day different from the predicted onset date, the side effect prediction module 213 expands or contracts the side effect occurrence probability curve in the vertical direction so that the intersection point between the side effect occurrence probability curve and the first criterion R1 on the side with the shorter number of days elapsed (i.e., the intersection point representing the onset date) coincides with the day on which the subjective symptoms appeared, and the intersection point on the side with the longer number of days elapsed (i.e., the intersection point representing the disappearance date) does not change.

[0116] If the day on which the subjective symptoms appeared is earlier than the predicted onset date, the side effect prediction module 213 extends the occurrence probability curve of the side effect upward so that the intersection representing the onset date coincides with the day on which the subjective symptoms appeared and the intersection representing the disappearance date remains unchanged.If the day on which the subjective symptoms appeared is later than the predicted onset date, the side effect prediction module 213 contracts the occurrence probability curve of the side effect downward so that the intersection representing the onset date coincides with the day on which the subjective symptoms appeared and the intersection representing the disappearance date remains unchanged.

[0117] (5) Other The side effect prediction module 213 can correct the probability of occurrence of a side effect for each number of elapsed days by arbitrarily combining the above (1) to (4). The side effect prediction module 213 may be configured to correct the occurrence probability for each number of days in advance, for example, by arbitrarily combining the above (1) to (4) in response to information regarding the degree of variability in the manifestation of side effects depending on the type of cancer, the type of treatment, and the type of side effect.

[0118] Furthermore, the side effect prediction module 213 may be configured to correct the occurrence probability for each number of elapsed days in accordance with the severity of the side effect, for example. The side effect prediction module 213 may be configured to make a correction so that the occurrence probability for each number of elapsed days becomes relatively higher when the severity of the side effect is high, and to make a correction so that the occurrence probability for each number of elapsed days becomes relatively lower when the severity of the side effect is low, for example.

[0119] In another aspect, the side effect prediction module 213 may be configured to predict side effects and their occurrence times using a side effect prediction model. For example, if information indicating the occurrence probability 640 of a side effect 620 for each number of days 630 elapsed since the start of treatment can be acquired as the occurrence probability basic information 600, in association with information on the type of cancer and the type of anticancer drug, and additionally, information on the treatment content, the side effect prediction model can be adjusted by having the machine learning model perform machine learning according to a predetermined model learning program.

[0120] The side effect prediction model is, for example, a parameterized composite function that combines multiple functions. The parameterized composite function is defined by a combination of multiple adjustable functions and parameters. When the side effect prediction model is generated using a forward propagation type multilayer network, the parameterized composite function can be defined, for example, as a combination of linear relationships between each layer using a weighting matrix, nonlinear relationships (or linear relationships) using activation functions in each layer, and biases. The weighting matrix and bias are parameters in the multilayer network. In a parameterized composite function, the form of the function changes depending on how the parameters are selected. In a multilayer network, by appropriately setting the constituent parameters, it is possible to define a function that can output desirable results from the output layer.

[0121] The side effect prediction model according to this embodiment may be any composite function with parameters that satisfies the above requirements, for example, a multi-layer neural network model (hereinafter referred to as a "multi-layer network"). A side effect prediction model using a multi-layer network has an input layer, an output layer, and at least one intermediate layer or hidden layer provided between the input layer and the output layer. As the multi-layer network according to this embodiment, for example, a deep neural network (DNN), which is a multi-layer neural network that is the subject of deep learning, can be used. As the DNN, for example, a convolution neural network (CNN) that targets images may be used as a part thereof.

[0122] The above-described treatment method correction flow 1400 and subjective symptom correction flow 1500 are not essential steps, and can be additionally performed.

[0123] (Getting solutions) Next, the countermeasure acquisition module 214 acquires a countermeasure corresponding to the side effect (step S1230). The countermeasure acquisition module 214 acquires information on a countermeasure 820 corresponding to the side effect 810, for example, based on the countermeasure information 800. For example, the countermeasure acquisition module 214 can acquire countermeasures such as "small, frequent meals" or "easy-to-digest meals" for the side effect "loss of appetite due to chemotherapy" based on the countermeasure information 800.

[0124] (Output of side effects and solutions) The output module 216 displays the information on the side effects and countermeasures acquired by the side effect prediction module 213 and the countermeasure acquisition module 214, for example, in a side effect / countermeasure display field 1750 on the patient terminal screen 1700 shown in Fig. 17. The output module 216 displays the information on the side effects and countermeasures in the side effect / countermeasure display field 1750, for example, before the side effect occurs (for example, a predetermined length of time before). This allows the management server 101 to provide the patient with the details of the side effect and countermeasures before the side effect occurs.

[0125] The output module 216 may be configured, for example, in the side effect / treatment display field 1750 of the patient terminal screen 1700, to display the side effects of the day and the treatment methods therefor during a specified time period (e.g., from midnight to 5pm), and to display the side effects of the next day and the treatment methods therefor during other specified time periods (e.g., from 5pm to midnight).

[0126] FIG. 23 is another example of a patient terminal screen 2300. The management module 211 of the management server 101 displays, for example, a patient terminal screen 2300 on the output device 305 of the patient terminal 102. On the patient terminal screen 2300, the management module 211 displays, for example, a health management column 2310, a health prediction column 2320, a treatment calendar column 2330, an individual countermeasure column 2340, and the like.

[0127] The output module 216 may display the information about side effects and countermeasures acquired by the side effect prediction module 213 and the countermeasure acquisition module 214, for example, in a treatment calendar field 2330. The output module 216 may, for example, display a calendar for the month including the current day in the treatment calendar field 2330, and display information within this calendar indicating, for example, the treatment start date and each side effect and its occurrence time.

[0128] In the treatment calendar field 2330, the output module 216 indicates the time of occurrence of side effects by displaying them in a band. The output module 216 also indicates the time of occurrence of side effects by type using different colors. In the treatment calendar field 2330, the output module 216 displays information about side effects and how to deal with them, for example, from before the time of occurrence of the side effects. In addition, the output module 216 can display information about side effects and how to deal with them, for example, during and after the time of occurrence of the side effects, as a side effect history, in the treatment calendar field 2330.

[0129] The output module 216 displays, for example, a representative image (e.g., an icon) of the individual measure for the current day in the individual measure field 2340. The output module 216 may be configured to display detailed information of the individual measure when a representative image of the individual measure is selected by the user. Furthermore, the output module 216 may be configured to display, in the individual measure field 2340, a representative image of the individual measure for the selected day when a day other than the current day is selected in the treatment calendar field 2330.

[0130] The output module 216 may be configured to, for example, cooperate with another calendar application that the user most frequently uses to display information indicating the treatment start date, each side effect, and its occurrence time on a calendar in the other calendar application. The output module 216 may also be configured to output the information indicating the treatment start date, each side effect, and its occurrence time as file information in ICS format.

[0131] <Individual measures output> FIG. 16 shows an example of an individual measure proposal flow 1600. In the individual measure proposal flow 1600, individual measures corresponding to the coping method are acquired (step S1610), information on subjective symptoms is acquired (step S1620), and the priority of each individual measure is calculated based on priority handling information indicating the relationship between the individual measures and the subjective symptoms (step S1630).

[0132] In the individual measure proposal flow 1600, questions related to the individual measures prepared for each coping method are output to the patient terminal (step S1640), answers to the questions from the target patient are acquired (step S1650), and the priority of each individual measure is calculated based on the answers from the target patient (step S1660).Then, individual measures with a priority higher than a predetermined standard are output (step S1670).

[0133] The individual measure proposal flow 1600 is not a required step and can be performed additionally. In the individual measure proposal flow 1600, the order in which steps S1620 to S1630 and steps S1640 to S1660 are performed is not particularly limited. Furthermore, only one of steps S1620 to S1630 and steps S1640 to S1660 may be performed.

[0134] (Acquisition of individual measures) 8, the individual measure acquisition module 215 can acquire the detailed measures 830 and the individual measures 840 associated with the measures 820 based on the measure information 800 (step S1610). The output module 216 displays, for example, an icon or button representing the measures 820 and / or the detailed measures 830 for each side effect in the individual measure column 2340 on the patient terminal screen 2300. The output module 216 may be configured to display, for example, the detailed measures 830 and / or the individual measures 840 associated with the measures 820 and / or the detailed measures 830 when this icon or button is selected.

[0135] More specifically, the individual measure acquisition module 215 acquires, for example, information on the detailed measure "ways to increase the number of meals possible" in association with the measure "eat small amounts frequently" based on the countermeasure information 800. The individual measure acquisition module 215 acquires, for example, information on the individual measures such as "small cup noodles," "ochazuke," "small portions of frozen food," "prepared meals at convenience stores," "sushi," "chocolate," "cereal," and "nutritional supplement jelly" in association with the detailed measure "ways to increase the number of meals possible" (see FIG. 9).

[0136] These detailed coping methods and individual measures can be useful information for cancer patients. However, there are cases where the amount of information is too much, or the individual measures are not necessarily appropriate depending on the individual condition of the cancer patient.

[0137] Therefore, the individual measure acquisition module 215 acquires information about subjective symptoms from the symptom information 1000 (step S1620). Then, the individual measure acquisition module 215 calculates the priority of each individual measure based on the priority handling information 900 (see FIG. 9) indicating the relationship between the individual measures and the subjective symptoms (step S1630).

[0138] 22 from the subjective symptom information 1000. Specifically, the individual measure acquisition module 215 acquires, for example, information on subjective symptoms and their severity, such as those shown in Fig. 22. Specifically, the individual measure acquisition module 215 acquires, for example, information on "taste disorder: level 1," "nausea: level 2," "stomatitis: level 5," and "constipation: level 2" as subjective symptoms. Then, the individual measure acquisition module 215 calculates the priority of each individual measure based on the information on the subjective symptoms and the priority response information 900.

[0139] The calculation of the priority of each individual measure by the individual measure acquisition module 215 can be performed according to the following formula, for example. Priority of individual measures = Σ (priority points for each subjective symptom of individual measures) × (level of each subjective symptom)

[0140] The priority of each individual measure calculated in this way is as follows: The larger the value, the higher the priority. Small instant noodles: -12 Ochazuke: -5 Small frozen meals: 4 Convenience store prepared foods: 0 Sushi: -2 Chocolate: 5 Serial: -11 Nutritional Supplement Jelly: 17

[0141] On the other hand, changes in the physical and mental health of each cancer patient tend to be unstable and do not necessarily correspond to subjective symptoms of side effects. Therefore, the individual measure acquisition module 215 outputs, for example, questions related to the individual measures prepared for each coping method to the patient terminal (step S1640). The individual measure acquisition module 215 outputs, for example, the following question related to the individual measures: "Among these, is there a food you like? (Multiple choices allowed)" and the options "A: Rice ball, B: Cup noodles, C: Sushi, D: Cereal, E: Chocolate, F: Other" to the patient terminal 102.

[0142] Furthermore, the individual measure acquisition module 215 acquires answers to the above questions from the patient terminal 102. For example, the individual measure acquisition module 215 acquires an answer such as "A: rice ball, B: instant noodles, E: chocolate" (step S1650). The individual measure acquisition module 215 calculates the priority of each individual measure based on the answer from the patient (step S1660). For example, the individual measures "rice ball," "instant noodles," and "chocolate" are calculated to have high priorities (for example, +10), and the priorities of the other individual measures are calculated to be low (for example, -10).

[0143] Then, the individual measure acquisition module 215 outputs an individual measure whose priority is higher than a predetermined standard based on the priority measure information 900 and the priority measure based on the response from the patient (step S1670). The individual measure acquisition module 215 calculates a final priority by, for example, adding the priority measure based on the priority measure information 900 and the priority measure based on the response from the patient.

[0144] As a result, the individual measure acquisition module 215 stores, for example, a predetermined number (for example, two) of individual measures, "rice ball" and "chocolate," in descending order of priority, as individual measures whose priorities satisfy a predetermined standard.

[0145] The criteria for determining the priority in step S1670 may be various. For example, by prioritizing a more direct response from the patient, the individual measure acquisition module 215 may determine that, of the individual measures "rice ball," "cup noodles," and "chocolate" included in the response acquired from the patient terminal 102, the remaining "rice ball" and "chocolate" are individual measures whose priority meets a predetermined standard, excluding cup noodles, ochazuke, sushi, and cereal, which have low priorities (e.g., negative values) of individual measures based on the priority handling information 900.

[0146] Alternatively, for example, by prioritizing a more direct response from the patient, the individual measure acquisition module 215 may determine that of the individual measures "rice ball," "cup noodles," and "chocolate" included in the response acquired from the patient terminal 102, excluding cup noodles and cereal, which have low priorities as individual measures based on the priority handling information 900 (for example, priority is in a predetermined order from the bottom (for example, up to second place)), the remaining "rice ball" and "chocolate" are individual measures whose priorities meet a predetermined standard.

[0147] The output module 216 may output the individual measures acquired in this way as countermeasures to the patient terminal 102 (step S1240). This configuration is preferable because the contents of the individual measures are narrowed down to more appropriate ones and presented, so the patient does not have to worry about which individual measure to select.

[0148] <Action and effect> In the above embodiment, the management server 101 (an example of a patient support device) includes an acquisition module 212 (an example of an acquisition unit) that acquires cancer treatment information for a target patient, a side effect prediction module 213 (an example of a side effect prediction unit) that predicts side effects and the timing of their occurrence based on the acquired cancer treatment information, an individual countermeasure acquisition module 215 (an example of a countermeasure acquisition unit) that acquires countermeasures for the predicted side effects, and an output module 216 (an example of an output unit) that outputs information regarding the side effects and countermeasures in association with the timing of the side effect occurrence.

[0149] This configuration allows cancer patients to easily receive information about side effects and how to deal with them, which vary greatly depending on the type of cancer treatment. The number of cancer patients in Japan is increasing by approximately one million each year, and the number of cancer patients who continue outpatient treatment while working is also increasing. As a result, the burden of patient care on medical professionals involved in cancer treatment is increasing, and the reality is that side effect prevention and dietary control for patients receiving treatment at home is left to the patients themselves or their families.

[0150] This technology allows patients to learn when side effects will occur and how to deal with them, based on their individual cancer treatment, without being restricted by time or location. This allows cancer patients to prepare for and take measures against side effects in advance. For example, even if a cancer patient is fighting the disease alone, this can alleviate their anxiety. Ultimately, this can contribute to improving patients' quality of life.

[0151] Furthermore, by being able to predict side effects and when they will occur, it is possible to predict when patients will recover from the effects of these side effects. This allows cancer patients to plan their future schedules and schedules while taking into account changes in their physical condition. As a result, cancer patients can lead more fulfilling lives while reducing their psychological burden.

[0152] In the above configuration, the acquisition module 212 acquires information on the type of cancer, anticancer drug, and treatment start date as cancer treatment information. The side effect prediction module 213 calculates the occurrence time when the occurrence probability of a side effect is higher than a first standard, using the treatment start date as a reference, based on basic occurrence probability information that indicates the occurrence probability of a side effect for each cancer type for each number of days elapsed since the start of anticancer drug administration. With this configuration, side effects that differ depending on the type of cancer and anticancer drug and their occurrence time can be predicted more accurately and simply, even without specialized knowledge.

[0153] In the above configuration, the acquisition module 212 acquires information about treatment methods as cancer treatment information. The side effect prediction module 213 corrects the occurrence probability for each elapsed day indicated by the occurrence probability basic information based on the acquired information about treatment methods. This configuration makes it possible to more accurately predict not only differences in side effects caused by differences in chemotherapy, but also differences in side effects caused by differences in surgical treatments.

[0154] In the above configuration, the acquisition module 212 further acquires information about the subjective symptoms of the subject patient. The side effect prediction module 213 corrects the occurrence probability for each elapsed day indicated by the occurrence probability basic information 600 based on the acquired information about the subjective symptoms. With this configuration, even if the prediction based on the occurrence probability basic information 600 is incorrect, the prediction of the type and occurrence time of the side effect can be corrected to match the actual timing and symptoms of the side effect experienced by the patient. This allows for more accurate subsequent predictions, even for side effects that vary greatly from person to person.

[0155] In the above configuration, the acquisition module 212 further acquires information on subjective symptoms of the target patient. The system further includes an individual measure acquisition module 215 (an example of an individual measure acquisition unit) that calculates a priority for each individual measure corresponding to a coping method based on the acquired information on the subjective symptoms and outputs the calculated individual measure with the highest priority.

[0156] This configuration makes it possible to propose individualized measures that are more suited to the subjective symptoms of cancer patients, thereby supporting patients in taking appropriate self-care measures against side effects of cancer treatment, which vary greatly from person to person.

[0157] The above configuration further includes an individual measure acquisition module 215 (an example of an individual measure acquisition unit) that outputs a question to the patient terminal 102 (an example of a terminal device used by the target patient) asking about the target patient's preferences for each individual measure corresponding to the coping method, calculates a priority for each individual measure based on the response from the target patient, and outputs individual measures whose calculated priority is higher than a predetermined standard.

[0158] According to this configuration, among the side effects of cancer treatment, nausea, taste disorders, etc. vary greatly from person to person, and weight loss can lead to a decline in physical strength, which can be a serious and significant issue for patients. Therefore, by applying this configuration to, for example, proposing individual dietary measures, it is possible to intervene more appropriately in symptom alleviation and nutritional management at the patient's home.

[0159] <Variation 1> In the above embodiment, for example, in the side effect occurrence probability graph 1800 in Fig. 18, only the first criterion R1 is used as the evaluation criterion for the occurrence probability. However, the present technology is not limited to this example, and for example, two or more criteria may be used as the evaluation criterion for the occurrence probability.

[0160] FIG. 21 is another example of a graph 2100 showing the probability of occurrence of a side effect. The side effect prediction module 213 displays, for example, a side effect occurrence probability graph 2100 on, for example, the patient terminal screen 1700. The side effect prediction module 213 displays a first criterion R1 and a second criterion R2 in addition to occurrence probability curves 2110-2140 for each predicted side effect in the side effect occurrence probability graph 2100. In the side effect occurrence probability graph 2100, the side effect prediction module 213 indicates, with dashed dotted lines, cases where the occurrence probability is the first criterion R1 and cases where the occurrence probability is the second criterion R2 that is lower than the first criterion R1.

[0161] The side effect prediction module 213 indicates, for example, a first criterion R1 as an occurrence probability that would result in a side effect appearing as a symptom if the occurrence probability were higher in the occurrence probability curves 2110 to 2140. The side effect prediction module 213 also indicates, for example, a second criterion R2 as an occurrence probability that would result in a suitable timing for taking some kind of prevention before the side effect occurs if the occurrence probability were higher in the occurrence probability curves 2110 to 2140.

[0162] The side effect prediction module 213 further calculates, based on the occurrence probability basic information 600, a prevention period, which is a period when the occurrence probability of the side effect is higher than the second standard R2 and equal to or lower than the first standard R1 and which precedes the occurrence of the side effect, using the treatment start date as a reference. For example, the side effect prediction module 213 determines that, among the periods between the intersections of the occurrence probability curve 2130 for the side effect "stomatitis" and the second standard R2, a period before the occurrence of the side effect is an appropriate period for carrying out a countermeasure (for example, "advance oral care") to prevent the side effect "stomatitis."

[0163] The side effect prediction module 213 calculates the start date and time of the prevention period for the side effect "stomatitis" based on, for example, the treatment start date. The output module 216 can further output, for example, information on the side effect and how to deal with it (i.e., how to prevent it) in association with the calculated prevention period. This makes it possible to provide the patient with information on the most appropriate prevention period.

[0164] <Additional configuration 1> The acquisition module 212 can acquire information about the patient's weight from, for example, the patient terminal 102. The acquisition module 212 can acquire information about the patient's weight from, for example, a weight scale (not shown) that can communicate with the patient terminal 102 via the patient terminal 102. The acquired information about the weight is stored in the health information 220, for example, in association with weight measurement date and time information.

[0165] The acquisition module 212 can also acquire information about the patient's diet from, for example, the patient terminal 102. The acquisition module 212 is configured to acquire information about the patient's diet, for example, as text information or image information, and acquire information about the calories and nutritional value of the patient's diet using a nutritional value database, a large-scale language model (LLM), an AI image analysis model (none of which are shown), etc. The acquired information about the intake calories and nutritional value is stored in the health information 220, for example, in association with date and time information about the meal.

[0166] The nutritional value database may, for example, store text data representing meal details in association with calorie information and nutritional value information for the meal, although this is not limited to this. The acquisition module 212 can acquire information relating to the calorie value and nutritional value (e.g., the content of the five major nutrients) of the meal, which is associated with the text data representing the meal details, based on the nutritional value database.

[0167] The large-scale language model (LLM) is a learning model that is trained to take, for example, but not limited to, text data representing meal contents as input data and output calorie values ​​associated with the meal contents. The acquisition module 212 can input text data representing meal contents to the large-scale language model and acquire information on the calorie values ​​and nutritional values ​​of the meal as output data.

[0168] Furthermore, the AI ​​image analysis model is a learning model that is trained to use, for example, image data representing meal contents as input data and output data representing calorie values ​​associated with the meal contents, although this is not limited to this. The AI ​​image analysis model may be configured to output the name of the dish corresponding to the meal contents and nutritional value (e.g., the content of the five major nutrients) in addition to the calorie value. By inputting image data representing the meal contents into this AI image analysis model, the acquisition module 212 can acquire, for example, information regarding the calorie value and nutritional value of the meal as output data.

[0169] The output module 216, for example, constantly displays graphs showing the transitions of the patient's weight information and calorie intake information in the health management section 2310 (see FIG. 23 ) of the patient terminal screen 2300. The output module 216, for example, displays graphs showing the transitions of the weight information and calorie intake information of other patients with similar attributes (gender, age, type of cancer, etc.) to the subject patient in the health management section 2310, for example, as "senior patient data." The output module 216 displays this "senior patient data," for example, based on health information 220 acquired from other patients. The output module 216 may output the "senior patient data" based on the health information 220 of patients with good prognosis. The output module 216 may output information within a predetermined range from the average value (e.g., the average value ±20%) based on the health information 220 as the "senior patient data." The output module 216 may, for example, display the transitions of the weight information and calorie intake information as normalized values ​​using the treatment start date as a reference (e.g., "100").

[0170] This allows the patient to understand, for example, whether their weight change is within an appropriate range or whether they should take action. Also, if weight loss is something that requires attention, for example, the patient can take measures themselves.

[0171] 24 is another example of the health information management screen 2400. The output module 216 displays the health information management screen 2400 on, for example, the patient terminal 102. On the health information management screen 2400, the output module 216 displays, for example, calorie intake information 2410, weight information 2420, dietary information 2430, nutritional value information 2440, etc.

[0172] The output module 216 displays the target calorie intake and the actual calorie intake (obtained value) for that day, for example, as overlapping bars of different colors, as calorie intake information 2410. The greater the ratio of the overlap length of the bar representing the target calorie intake to the bar representing the actual calorie intake, the closer the actual calorie intake is to the calorie intake goal.

[0173] The output module 216 displays the weight information for that day 2420 alongside the calorie intake. By displaying the weight and calorie intake side by side, the patient can easily understand the correlation between their calorie intake and their weight.

[0174] The output module 216 displays images of the meals that the patient ate that day as dietary information 2430. This configuration reduces the burden on the patient while allowing them to create a dietary record and increases their motivation to eat.

[0175] The output module 216 displays information on the calories and nutritional value of the meals ingested by the patient that day as nutritional value information 2440. For example, the output module 216 displays bar graph display frames in the nutritional value information 2440 that are longer than the target values ​​by a predetermined percentage (e.g., 10%) for each calorie and nutritional value. Each time the output module 216 acquires information about a meal ingested by the patient that day, the output module 216 displays the calories and nutritional value ingested by the patient based on that meal, superimposed within the respective bar graph display frames. In addition to the intake value of the calorie or nutritional value, the output module 216 displays the target value and the "relationship" between the target value and the intake value in text near the bar graph display frames.

[0176] The output module 216 can display the relationship between the target value and the intake value in a variety of ways. For example, when the intake value is less than the target value, the output module 216 displays the difference between the target value and the intake value in a form such as "XX g remaining" to encourage intake of the calories or nutritional value. For example, for a nutrient (e.g., dietary fiber) whose inadequate intake is particularly undesirable for the patient, the output module 216 displays the difference between the target value and the intake value in a form that more actively encourages the intake of that nutrient, such as "Deficient XX g." For example, if the intake reaches or exceeds a target value for calories or a nutrient value (e.g., protein) within a range that is acceptable for the patient to consume in excess, the output module 216 outputs a positive indication (e.g., "Achieved") instead of the difference, indicating that the intake is good. For example, when the intake value of calories or nutrients (e.g., carbohydrates) that are undesirable for the patient to consume in excess exceeds the target value, the output module 216 outputs a display indicating that the intake of the calories or nutrients should be suppressed, such as "over XX g," showing the difference between the target value and the intake value. This configuration allows patients to easily understand the nutritional balance of their meals, and can use this information as a reference for determining nutritionally balanced meals.

[0177] <Additional configuration 2> The counseling module 217 of the management server 101 is configured to enable remote counseling over the web between the patient terminal 102 and the expert terminal 103. The patient-side counseling module 312 of the patient terminal 102 and the expert terminal counseling module 412 of the expert terminal 103 are configured to enable remote counseling over the web via the counseling module 217 of the management server 101. Information related to counseling is stored, for example, in counseling information 230.

[0178] Fig. 25 is an example of an expert terminal screen 2500. Fig. 26 is another example of an expert terminal screen 2600. The management module 211 of the management server 101 outputs the expert terminal screen 2500 or the expert terminal screen 2600 to the output device 405 such as a display of the expert terminal 103.

[0179] The management module 211 displays, for example, patient information 500 of the target patient and side effect occurrence probability graphs 1800, 1900 on the specialist terminal screen 2500. The management module 211 may also display, for example, a treatment calendar field 2330 on the specialist terminal screen 2500. The management module 211 outputs, for example, symptom information 1000 of the target patient and health information 220 (e.g., information on diet, weight transition, calorie intake, and nutritional value) on the specialist terminal screen 2600. The occurrence probability graphs 1800, 1900, treatment calendar field 2330, symptom information 1000, and health information 220 output by the management module 211 may have the same configuration as those displayed to the patient on the patient terminal screen 2300 and health information management screen 2400, for example.

[0180] With this configuration, a registered dietitian or other specialist can specifically understand the patient's living conditions outside of the hospital, and can intervene appropriately after understanding and sharing the patient's symptoms and nutritional status. As a result, the efficiency of patient treatment can be improved and the psychological burden on the patient and their family can be reduced.

[0181] Furthermore, even when patients are experiencing a decline in their physical strength, they can receive counseling from a registered dietitian or other specialist, with the physical burden reduced. Even when patients' physical strength is declining, being able to easily receive appropriate advice from a registered dietitian can be extremely beneficial in improving the quality of their daily lives without imposing a burden on them.

[0182] <Additional configuration 3> The management server 101 is configured to be able to output educational content to the expert terminal 103. For example, when an instruction to output educational content from a registered dietitian is received from the expert terminal 103, the expert education module 218 of the management server 101 is configured to output the corresponding educational content to the expert terminal 103.

[0183] The specialist education module 218 may be configured to, for example, output recommendation information recommending predetermined educational content to the specialist terminal 103. For example, the specialist education module 218 may take into consideration the attributes of a cancer patient who is the target of counseling by a registered dietitian using the specialist terminal 103, and output, as recommendation information, educational content that teaches counseling techniques for patients similar to the target patient.

[0184] Furthermore, the specialist education module 218 may output recommendation information that recommends educational content that has been viewed frequently. This configuration can improve the counseling skills of registered dietitians and eliminate variations in counseling skills.

[0185] The present invention is not limited to the above-described embodiments and includes various modifications. For example, the above-described embodiments have been described in detail to clearly explain the present invention, and the present invention is not necessarily limited to those including all of the described configurations. Furthermore, it is possible to replace part of the configuration of one embodiment with the configuration of another embodiment, or to add the configuration of another embodiment to the configuration of one embodiment. Furthermore, it is possible to add, delete, or replace part of the configuration of each embodiment with other configurations.

[0186] Furthermore, the above-described configurations, functions, processing units, processing means, etc. may be partially or entirely implemented in hardware, for example, by designing them as integrated circuits. The above-described configurations, functions, etc. may also be implemented in software, with a processor interpreting and executing a program that implements each function. Information such as the programs, tables, and files that implement each function can be stored in a memory, a recording device such as a hard disk or SSD (Solid State Drive), or a recording medium such as an IC card, SD card, or DVD.

[0187] In addition, the control lines and information lines shown are those that are considered necessary for the explanation, and do not necessarily show all the control lines and information lines in the product. In reality, it can be assumed that almost all components are interconnected. The above-described embodiments disclose at least the configurations described in the claims.

[0188] The present disclosure also encompasses configurations including at least one of the following (1) to (9) alone, or any two or more of them in combination. (1) an acquisition unit that acquires cancer treatment information of a target patient; a side effect prediction unit that predicts side effects and their occurrence time based on the acquired cancer treatment information; a countermeasure acquisition unit that acquires a countermeasure corresponding to the predicted side effect; an output unit that outputs information about the side effect and the countermeasure in association with the occurrence time of the side effect; A patient support device comprising: (2) the acquiring unit acquires, as the cancer treatment information, information regarding a type of cancer, an anticancer drug, and a treatment start date; the side effect prediction unit calculates, based on basic occurrence probability information indicating the occurrence probability of the side effect for each number of days elapsed since the start of administration of the anticancer drug for the cancer type, an occurrence time at which the occurrence probability of the side effect is higher than a first standard, using the treatment start date as a standard; The patient support device according to (1) above. (3) the acquisition unit acquires information on a treatment method as the cancer treatment information, The side effect prediction unit corrects the occurrence probability for each elapsed day indicated by the occurrence probability basic information based on the acquired information on the treatment method. The patient support device according to (2) above. (4) The acquisition unit further acquires information regarding subjective symptoms of the target patient, The side effect prediction unit corrects the occurrence probability for each elapsed day indicated by the occurrence probability basic information based on the acquired information on the subjective symptoms. The patient support device according to (2) above. (5) the side effect prediction unit further calculates, based on the basic information on occurrence probability, a preventive period, which is a period when the occurrence probability of the side effect is higher than a second standard and equal to or lower than the first standard and which precedes the occurrence period, using the treatment start date as a reference; the output unit further outputs information about the side effect and the countermeasure in association with the prevention timing. The patient support device according to (2) above. (6) The acquisition unit further acquires information regarding subjective symptoms of the target patient, An individual measure acquisition unit, an individual measure acquisition unit that calculates a priority for each individual measure corresponding to the coping method based on the acquired information on the subjective symptoms and outputs the calculated individual measure with a high priority; The patient support device according to any one of (1) to (5) above. (7) An individual measure acquisition unit, outputting a question to a terminal device used by the target patient asking about the target patient's preferences for each individual measure corresponding to the countermeasure; Calculating a priority for each individual measure based on the response from the target patient, and outputting an individual measure whose calculated priority is higher than a predetermined standard. Further comprising an individual countermeasure acquisition unit; The patient support device according to any one of (1) to (6) above. (8) 1. A computer-implemented method for patient assistance, comprising: Obtain cancer treatment information for target patients, predicting side effects and their occurrence timing based on the acquired cancer treatment information; Obtaining a countermeasure for the predicted side effect; outputting information about the side effect and the countermeasure in association with the time of occurrence of the side effect; Patient support methods. (9) A program for causing a computer to carry out each step of the patient support method described in (8) above. [Explanation of symbols]

[0189] 1...Patient support system, 101...Management server, 102...Patient terminal, 103...Expert terminal, 211...Management module, 212...Acquisition module, 213...Side effect prediction module, 214...Countermeasure acquisition module, 215...Individual measure acquisition module, 216...Output module, 217...Counseling module, 218...Expert education module, 311...Patient terminal execution module, 312...Patient side counseling module, 411...Expert terminal execution module, 412...Expert side counseling module, 413...Expert learning module

Claims

1. an acquisition unit that acquires cancer treatment information of a target patient; a side effect prediction unit that predicts side effects and their occurrence time based on the acquired cancer treatment information; a countermeasure acquisition unit that acquires a countermeasure corresponding to the predicted side effect; an output unit that outputs information about the side effect and the countermeasure in association with the occurrence time of the side effect; A patient support device comprising:

2. the acquiring unit acquires, as the cancer treatment information, information regarding a type of cancer, an anticancer drug, and a treatment start date; the side effect prediction unit calculates, based on basic occurrence probability information indicating the occurrence probability of the side effect for each number of days elapsed since the start of administration of the anticancer drug for the cancer type, an occurrence time at which the occurrence probability of the side effect is higher than a first standard, using the treatment start date as a standard; 10. The patient support device of claim 1.

3. the acquisition unit acquires information on a treatment method as the cancer treatment information, The side effect prediction unit corrects the occurrence probability for each elapsed day indicated by the occurrence probability basic information based on the acquired information on the treatment method.

3. The patient support device of claim 2.

4. The acquisition unit further acquires information regarding subjective symptoms of the target patient, The side effect prediction unit corrects the occurrence probability for each elapsed day indicated by the occurrence probability basic information based on the acquired information on the subjective symptoms.

3. The patient support device of claim 2.

5. the side effect prediction unit further calculates, based on the basic information on occurrence probability, a preventive period, which is a period when the occurrence probability of the side effect is higher than a second standard and equal to or lower than the first standard and which precedes the occurrence period, using the treatment start date as a reference; the output unit further outputs information about the side effect and the countermeasure in association with the prevention timing.

3. The patient support device of claim 2.

6. The acquisition unit further acquires information regarding subjective symptoms of the target patient, An individual measure acquisition unit, an individual measure acquisition unit that calculates a priority for each individual measure corresponding to the coping method based on the acquired information on the subjective symptoms and outputs the calculated individual measure with a high priority; 10. The patient support device of claim 1.

7. An individual measure acquisition unit, outputting a question to a terminal device used by the target patient asking about the target patient's preferences for each individual measure corresponding to the countermeasure; Calculating a priority for each individual measure based on the response from the target patient, and outputting an individual measure whose calculated priority is higher than a predetermined standard. Further comprising an individual countermeasure acquisition unit; 10. The patient support device of claim 1.

8. 1. A computer-implemented method for patient assistance, comprising: Obtain cancer treatment information for target patients, predicting side effects and their occurrence timing based on the acquired cancer treatment information; Obtaining a countermeasure for the predicted side effect; outputting information about the side effect and the countermeasure in association with the time of occurrence of the side effect; Patient support methods.

9. A program for causing a computer to carry out each step of the patient support method according to claim 8.

Images