Proposal system, proposal program, and proposal method

Abstract

To provide a novel technology capable of proposing reliable patient-specific rehabilitation plans.SOLUTION: A proposal system that proposes rehabilitation plans for a patient includes a specification part. The specification part inputs patient information and a plurality of combinations extracted from the rehabilitation plans into a pre-trained learning model, obtains the degree of improvement for the patient for each combination, and identifies candidate combinations of the rehabilitation plans on the basis of the obtained improvement degree.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

[0002] In recent years, efforts have been made to extend the period during which people can remain healthy and independent without becoming ill or needing care (so-called healthy life expectancy). One of these efforts is the enhancement of rehabilitation. In this case, it is preferable that appropriate rehabilitation be implemented for each patient. An example of a technology that proposes such rehabilitation is proposed in, for example, Patent Document 1.

[0003] Patent document 1 discloses that by comparing a normal state at a first time in the past with a normal state at a second time (e.g., the present) that is later than the first time and is based on user-related information, a progression from the normal state at the first time to an abnormality of a predetermined level or more is detected as an abnormal state, and a task is provided to suppress the detected progression. [Prior art documents] [Patent documents]

[0004] [Patent Document 1] Patent Publication No. 2018-12071 Summary of the Invention [Problem to be solved by the invention]

[0005] However, although the invention described in Patent Document 1 can provide tasks based on information about the user (patient), it cannot guarantee the reliability of the provided tasks (rehabilitation content).

[0006] In view of the above circumstances, an object of the present invention is to provide a novel technique that can propose reliable rehabilitation content suitable for a patient. [Means for solving the problem]

[0007] In order to solve the above problems, the present invention provides a proposal system that proposes rehabilitation content to be performed by a patient, the proposal system including an identification unit that inputs patient information and multiple combinations extracted from multiple rehabilitation content to a proposal means, obtains the patient's degree of improvement for each combination, and identifies candidate combinations of rehabilitation content based on the obtained degree of improvement.

[0008] In a preferred embodiment of the present invention, the proposal system further includes a learning unit, wherein the proposal means is a learning model, and the learning unit learns the learning model using patient information, the combination of rehabilitation content, and the degree of improvement as training data.

[0009] With this configuration, multiple combinations of rehabilitation content can be input to the proposing means, and multiple output results can be obtained, thereby enabling accurate identification of rehabilitation content candidates according to the patient's degree of improvement. This makes it possible to identify rehabilitation content candidates that improve the patient's prognosis, thereby ensuring the reliability of the rehabilitation content.

[0010] In a preferred embodiment of the present invention, the proposal system further includes a learning unit that extracts the combinations based on the number of times the rehabilitation content has been performed, and learns the learning model using the patient information and the extracted combinations as training data.

[0011] This configuration can prevent rehabilitation that is not often performed from being identified as a candidate, thereby reducing the computational load on the learning model.

[0012] The proposal system further includes a display processing unit, which displays a screen on which candidates for rehabilitation content for the patient can be specified, and which displays the candidates for rehabilitation content and the evaluation of the rehabilitation content received from the patient side by side, and the identification unit identifies the rehabilitation content for the patient based on the specification of the candidate rehabilitation content.

[0013] This configuration allows medical professionals to specify rehabilitation content while checking the patient's evaluation on the screen where they specify the rehabilitation content to be provided to the patient, thereby enabling more appropriate rehabilitation to be provided to the patient.

[0014] In a preferred embodiment of the present invention, the proposal system further includes an evaluation receiving unit that receives an evaluation of the rehabilitation content from the patient and registers the evaluation in association with the patient and the rehabilitation items performed by the patient, and the identification unit identifies candidate rehabilitation content for the patient based on the evaluation.

[0015] With this configuration, it is possible to identify candidate rehabilitation contents based on the patient's evaluation of the rehabilitation, and to provide rehabilitation contents that reflect the patient's wishes. [Effects of the Invention]

[0016] The present invention can provide a novel technique that can propose reliable rehabilitation content suitable for a patient. [Brief explanation of the drawings]

[0017] [Figure 1] 1 is a block diagram showing a configuration of a system according to the present invention; [Figure 2] FIG. 1 is a hardware configuration diagram of a system according to the present invention. [Figure 3] FIG. 1 is a functional block diagram according to an embodiment of the present invention. [Figure 4] 1 is an example of a processing flowchart according to an embodiment of the present invention. [Figure 5] 10 is an example of a screen displayed on a medical staff terminal device according to an embodiment of the present invention. [Figure 6] 10 is an example of a screen displayed on a patient terminal device according to an embodiment of the present invention. DETAILED DESCRIPTION OF THE INVENTION

[0018] The present invention will be described in more detail below with reference to the accompanying drawings, in which preferred embodiments are shown, but which may be embodied in many different forms and are not limited to the embodiments set forth herein.

[0019] For example, although the configuration, operation, etc. of the proposed system are described in this embodiment, similar effects can be achieved by the executed method, device, computer program, etc. Furthermore, the program may be stored on a recording medium. By using this recording medium, the program can be installed on a computer, for example, thereby configuring the proposed device and proposed system. Here, the recording medium storing the program may be a non-transitory recording medium, such as a CD-ROM.

[0020] <1. Overview of the present invention> The present invention relates to a system that proposes rehabilitation content suitable for each patient diagnosed as needing rehabilitation (hereinafter abbreviated as "rehabilitation") to a doctor. The present invention proposes rehabilitation content to a doctor using a proposal means that estimates, based on the results of rehabilitation performed on the patient, how much prognosis will be improved by implementing what type of rehabilitation content for what type of patient.

[0021] In this embodiment, the suggestion means uses a learning model that predicts the degree of improvement in prognosis using patient information, rehabilitation content, and the degree of improvement in prognosis due to the implemented rehabilitation content as training data. Alternatively, the suggestion means may use a correspondence table that associates patient information and rehabilitation content with the degree of improvement in prognosis.

[0022] Furthermore, the present invention improves the prognosis of patients by providing rehabilitation videos to the patients as rehabilitation content. In this embodiment, the rehabilitation videos include mandatory videos that must be provided to patients and individually suggested videos that are suggested to each patient by a suggestion means.

[0023] <1.1. System configuration of the present invention> Fig. 1 is a block diagram showing the configuration of the system of the present invention. As shown in Fig. 1, the proposed system 0 includes a proposed device 1, a patient terminal device 3, a medical staff terminal device 4, and a hospital database 5, and is configured to be able to communicate via a communication network NW. The communication network NW in the present invention is an IP (Internet Protocol) network, but there is no restriction on the type of communication protocol, and there is also no restriction on the type or scale of the network.

[0024] A general-purpose server computer or a personal computer can be used as the proposed device 1. A smartphone, a tablet terminal, a personal computer, a wearable device, or the like can be used as the patient terminal device 3 and the medical staff terminal device 4. The proposed device 1 may also be configured with multiple computers that are capable of sending and receiving information via a communication network NW or another network.

[0025] The hospital database 5 registers patient information and examination reservation information.

[0026] The patient information is information about patients who have undergone rehabilitation testing. The patient information includes a patient ID that uniquely identifies the patient, basic patient information, and patient test information. The basic patient information is information known before the patient's rehabilitation testing, and includes the patient's name, gender, age, and height. The patient test information is information obtained from the patient's rehabilitation testing results, and includes the WBI (Weight Bearing Index), KL classification (Kellegren-Lawrence classification), 2STEP value indicating the value obtained by dividing two strides (cm) by height, Locomo 25 total indicating the total score of Locomo 25, Locomo Score (Standing Test) indicating the locomo score obtained as a result of the Standing Test, Locomo Score (2-Step Test) indicating the locomo score obtained as a result of the 2-Step Test, Locomo Score (Locomo 25) indicating the locomo score obtained as a result of the Locomo 25, Locomo Score indicating the total locomo score of each test, and Locomo Score (Number of hits) indicating the number of tests that resulted in a diagnosis of locomo score. The patient information may be stored in a database 2, which will be described later.

[0027] The examination reservation information is information about reservations for rehabilitation examinations. As the examination reservation information, an examination reservation ID that uniquely identifies the examination reservation information, a patient ID, a scheduled examination date, a doctor in charge of the examination, etc. are registered.

[0028] <1.2. Hardware Configuration> 2 is a hardware configuration diagram of the proposed system 0. As shown in FIG. 2(a), the server 10 (proposed device 1) includes a processing unit 101, a storage unit 102, and a communication unit 103.

[0029] The processing unit 101 has one or more processors such as a CPU capable of executing an instruction set, and controls the overall operation and processing of the proposed device 1 by executing the proposed program according to the present invention, an OS, and other applications. The storage unit 102 has a volatile memory such as a RAM capable of storing an instruction set, and a non-volatile recording medium such as an HDD or SSD capable of recording an OS and a generation program according to the present invention. The communication unit 103 has a communication interface device with the communication network NW, and controls communication with the communication network NW to input and output information.

[0030] As shown in FIG. 2(b), the terminal device 9 (patient terminal device 3 and medical staff terminal device 4) includes a processing unit 91, a storage unit 92, a communication unit 93, an input unit 94, and an output unit 95.

[0031] The processing unit 91 has one or more processors, such as a CPU, that can execute an instruction set, and controls the overall operation and processing of the terminal device 9 by executing a proposed device usage program, an OS, and other applications for using the proposed device 1. The storage unit 92 has a volatile memory such as a RAM capable of storing an instruction set, and a non-volatile recording medium such as an HDD or SSD capable of recording an OS, a program for using the proposed device, and the like. The communication unit 93 has a communication interface device for connecting to a network, and controls communication with the communication network NW to input and output information. The input unit 94 has an input device capable of input processing, such as a keyboard or a touch panel. The output unit 95 has a display device capable of display processing, such as a display.

[0032] <1.3. System Functional Configuration> Fig. 3 is a functional block diagram of the proposal device 1 in embodiment 1. As shown in Fig. 3, the proposal device 1 includes a registration unit 11, an identification unit 12, a learning unit 13, an evaluation receiving unit 14, a display processing unit 15, and a database 2. This is information processing performed by software (stored in a storage unit 102) specifically realized by hardware (a processing unit 101).

[0033] Note that some or all of the functional components (units) of the proposed device 1 may be provided in the client, i.e., the patient terminal device 3 and / or the medical staff terminal device 4. For example, the patient terminal device 3 may include a registration unit 11, an evaluation reception unit 14, a display processing unit 15, etc.; the medical staff terminal device 4 may include a registration unit 11, an identification unit 12, a learning unit 13, a display processing unit 15, etc., and the proposed device 1 may be a cloud storage that records and manages various data such as patient rehabilitation information, which will be described later. In this embodiment, the proposed system 0 is used via the patient terminal device 3 and the medical staff terminal device 4 that have executed the proposed device utilization program; however, the proposed device 1 may also be configured by installing the proposed program of the present invention in the medical staff terminal device 4.

[0034] <1.4.Database 2> The database 2 includes a rehabilitation video database 21 and a training database 22. The rehabilitation video database 21 stores individually proposed video information and required video information. The training database 22 stores patient rehabilitation information as information used for training the learning model. Note that the patient rehabilitation information may be stored in a database different from the training database 22 as information for managing information related to patient rehabilitation.

[0035] <1.4.1. Individually proposed video information> The individually proposed video information is information about individually proposed videos proposed to medical professionals. The individually proposed video information includes an individually proposed video ID that uniquely identifies the proposed video, a video title, a video type, and an individually proposed video, and is registered in association with a rehabilitation item. Here, the video type can be information indicating the area where rehabilitation is performed, etc. In this embodiment, one individually proposed video is registered in association with one rehabilitation item, but multiple individually proposed videos may also be registered in association with one rehabilitation item.

[0036] <1.4.2. Required Video Information> The mandatory video information is information about mandatory videos that must be displayed to patients undergoing rehabilitation. The mandatory video information includes a mandatory video ID that uniquely identifies the mandatory video, a video title, a video type, and a mandatory video. Here, the video type may be the same as the video type of the individually proposed video information, or a different type may be registered. The mandatory video information may be registered in association with patient examination information.

[0037] <1.4.3. Patient Rehabilitation Information> The patient rehabilitation information is information related to the rehabilitation performed by the patient. The patient rehabilitation information includes a patient rehabilitation ID that uniquely identifies the patient rehabilitation information, a patient ID, rehabilitation content, rehabilitation evaluation, and a video viewing log. In this embodiment, the rehabilitation content includes the rehabilitation items performed by the patient, but the rehabilitation videos viewed by the patient (required videos and individually suggested videos) may also be registered. The video viewing log includes the video viewing date and viewing status (not viewed, dropped out, or viewed). The rehabilitation evaluation includes whether or not the rehabilitation was successfully performed, and an evaluation level. Examples of evaluation levels that can be used include appropriate, room for change, and inappropriate. In this embodiment, the evaluation level is a three-level evaluation, but may also be a two-level evaluation, or four or more levels.

[0038] <1.5. Registration Section 11> The registration unit 11 registers various information in a database. The registration unit 11 accepts patient information and examination reservation information and registers them in the hospital database 5. The registration unit 11 also accepts patient rehabilitation information and registers it in the learning database 22.

[0039] <1.6. Specific part 12> The identification unit 12 identifies candidate rehabilitation contents to be proposed to the patient. The identification unit 12 inputs patient information and a combination of multiple rehabilitation contents extracted from multiple rehabilitation contents into the learning model, acquires the degree of improvement of the patient for each combination, and identifies candidate combinations of rehabilitation contents based on the acquired degree of improvement.

[0040] In this embodiment, the identification unit 12 uses a combination of rehabilitation items as a combination of rehabilitation contents to be input into the learning model to identify candidate rehabilitation videos corresponding to the rehabilitation items as candidate rehabilitation contents. On the other hand, the identification unit 12 may use a combination of rehabilitation items as a combination of rehabilitation contents to be input into the learning model to identify candidate rehabilitation items as candidate rehabilitation contents. Furthermore, the identification unit 12 may use a combination of rehabilitation videos as a combination of rehabilitation contents to be input into the learning model to identify candidate rehabilitation videos as candidate rehabilitation contents.

[0041] <1.7. Learning Section 13> The learning unit 13 learns a learning model. The learning unit 13 learns the learning model using patient information, combinations of rehabilitation contents, and degrees of improvement as training data. In this embodiment, the learning unit 13 uses rehabilitation items as rehabilitation contents and learns the learning model using patient information, combinations of rehabilitation items, and degrees of improvement as training data. Specifically, the learning unit 13 learns the learning model using, as training data, multiple data sets in which degrees of improvement indicating two values, improved (1) or worsened (0), are set for combinations of patient information and rehabilitation items.

[0042] In this embodiment, the degree of improvement is set as a binary value, but it may also be set as a multi-level numerical value (for example, an integer value from 1 to 5).

[0043] In a preferred embodiment of the present invention, the learning unit 13 extracts combinations based on the number of times each rehabilitation content has been performed, and uses patient information and the extracted combinations as training data to train a learning model. Specifically, the learning unit 13 tallyes the number of times each rehabilitation item has been performed as rehabilitation content based on the patient rehabilitation test information of multiple patients, extracts a predetermined number of rehabilitation items from the rehabilitation items in ascending order of the number of times performed, and trains a learning model. Alternatively, the learning unit 13 may extract rehabilitation items that have been performed a predetermined number of times or more from the rehabilitation items and train a learning model.

[0044] The learning unit 13 may extract a combination based on the number of times a rehabilitation video has been viewed as rehabilitation content.

[0045] Furthermore, in this embodiment, the learning unit 13 has learned a learning model that uses a combination including multiple rehabilitation contents to predict the degree of improvement for the combination, but it may also learn a learning model that predicts the degree of improvement for one rehabilitation content.

[0046] <1.8. Evaluation Reception Section 14> The evaluation receiving unit 14 receives an evaluation of each rehabilitation content from the patient. The evaluation receiving unit 14 receives a rehabilitation evaluation of the individual proposed video as a rehabilitation content from the patient, and registers patient rehabilitation information of the patient in which the individual proposed video and the rehabilitation evaluation are associated with each other.

[0047] The evaluation receiving unit 14 may receive a rehabilitation evaluation for each rehabilitation item from the patient.

[0048] <1.9. Display Processing Unit 15> The display processing unit 15 performs display processing of various screens and causes the display processing results to be displayed on the patient terminal device 3 and the medical staff terminal device 4. Specific screens will be described later.

[0049] In this embodiment, the display process refers to a process in which the display processing unit 15 executes a process of generating information required for display, and transmits the generated information to the terminal device 9, thereby causing the terminal device 9 to display the generated information. On the other hand, in the case where the display processing unit 15 is provided in the terminal device 9 (in the case of a stand-alone type), the display process may be a process in which the display processing unit 15 executes a process of generating required information, and transmits the generated information to the output unit 95 of the terminal device 9, thereby causing the output unit 95 to display the generated information.

[0050] <2. Processing flowchart of the proposed method> The proposed method using the proposed system 0 will be described with reference to Fig. 4. Fig. 4 is a sequence diagram showing the process in which the proposed system 0 registers patient information of a patient undergoing rehabilitation for the first time, identifies rehabilitation content to be proposed to the patient, and registers patient rehabilitation information. The process related to the proposed method in this embodiment can be broadly divided into patient registration process (A), pre-rehabilitation process (B), and rehabilitation process (C).

[0051] <2.1. Patient Registration Process (A)> In the patient registration process (A), a patient who visits a hospital to undergo a rehabilitation examination downloads the application of the present invention, and a process of registering basic patient information, which is part of the patient information, is executed.

[0052] <2.1.1. Issuance of patient ID> First, in steps SA1 to SA3 (hereinafter, "step SXX" will be simply written as "SXX"), the registration unit 11 issues a patient ID.

[0053] In this embodiment, the patient terminal device 3 acquires a hospital ID by reading a two-dimensional code (a barcode or a QR code (registered trademark)) installed in the hospital (SA1). Then, the registration unit 11 receives a request for issuing a patient ID including the hospital ID from the patient terminal device 3 (SA2), and issues the patient ID (SA3).

[0054] <2.1.2. Registering basic patient information> In SA4 to SA8, the registration unit 11 accepts basic patient information and registers the basic patient information in a database.

[0055] In this embodiment, the registration unit 11 transmits a request to receive basic patient information to the patient terminal device 3 (SA4). The patient terminal device 3 then displays a screen for inputting basic patient information and receives the patient's name, sex, age, and height as basic patient information from the patient (SA5). The registration unit 11 then receives the basic patient information input in SA5 (SA6), and transmits the issued patient ID and the received basic patient information to the hospital database 5 based on the hospital ID acquired in SA2 (SA7), and registers the basic patient information (SA8).

[0056] In this embodiment, the registration unit 11 registers information in an external database (hospital database 5), but may also register information in an internal database (database 2).

[0057] <2.2. Pre-rehabilitation treatment (B)> In the rehabilitation pre-processing (B), a process is executed to identify rehabilitation content suitable for the patient using patient examination information, which is the result of rehabilitation examinations performed on the patient, and basic patient information.

[0058] <2.2.1. Identifying rehabilitation video candidates> In SB1 to SB4, candidates for rehabilitation content to be provided to the patient are identified. In the following explanation, a combination of rehabilitation items is identified as rehabilitation content based on the degree of improvement in prognosis, and candidates for individually suggested videos corresponding to the combination are identified.

[0059] First, in SB1, the medical staff terminal device 4 acquires patient examination information. In this embodiment, the medical staff terminal device 4 receives the following patient examination information from the medical staff: WBI and KL classification, 2STEP value of rehabilitation examination results, locomotive syndrome 25 total, locomotive syndrome degree (standing test), locomotive syndrome degree (2-step test), locomotive syndrome degree (locomotive syndrome 25), locomotive syndrome degree, and locomotive syndrome degree (number of hits). The medical staff terminal device 4 may also acquire patient examination information input by the patient at the patient terminal device 3.

[0060] At SB2, the medical staff terminal device 4 accepts the designation of the required video. In this embodiment, the medical staff terminal device 4 displays the video type of the required video and the patient examination information side by side among the rehabilitation videos to be provided to the patient.

[0061] 5(a) is an example of a screen displayed on the medical staff terminal device 4 for accepting the designation of required videos to be provided to a patient. In the illustrated example, a video type (in the illustrated example, "rehabilitation part selection") is displayed so that it can be selected and input, and required videos corresponding to the selected video type are displayed so that they can be viewed. The medical staff terminal device 4 then accepts the designation of required videos by accepting the selection input of the video type of the required videos from the medical staff.

[0062] In a preferred embodiment of the present invention, essential videos are designated based on patient examination information and registered in association with a patient ID. Specifically, the registration unit 11 inputs the patient examination information acquired in SB1 to a suggestion means that estimates the optimal essential video based on the patient examination information, thereby identifying essential videos, and registers the essential videos in association with the patient ID of the patient examination information. The suggestion means for estimating the optimal required video may be a correspondence table that associates patient examination information with required videos, or may be a learning model that learns using patient examination information and required videos as training data.

[0063] Then, in SB3 to SB4, the identification unit 12 identifies candidates for individually suggested videos to be proposed to the patient. In this embodiment, when the identification unit 12 receives the patient examination information acquired by the medical staff terminal device 4 in SB1 (SB3), the identification unit 12 inputs the patient examination information into a learning model to identify candidates for individually suggested videos as rehabilitation content (SB4).

[0064] Specifically, the identification unit 12 randomly extracts a plurality of combinations of rehabilitation items from a plurality of rehabilitation items. That is, combinations including the same items may be extracted. The identification unit 12 inputs the extracted combinations into a learning model to obtain a plurality of degrees of improvement in prognosis corresponding to each combination.

[0065] Then, based on the acquired degree of improvement, the identification unit 12 identifies the combination of rehabilitation items with the highest degree of improvement, and identifies the individual proposed video corresponding to each rehabilitation item included in the combination as a candidate for the individual proposed video to be provided to the patient. Specifically, when there are multiple combinations including the same item among the extracted combinations of rehabilitation items, the identification unit 12 acquires the average value of the degrees of improvement of those combinations as the degree of improvement of the combination including the same item.

[0066] In a preferred embodiment of the present invention, the identification unit 12 extracts a combination of rehabilitation items based on a predetermined condition. In this embodiment, the identification unit 12 extracts a combination of rehabilitation items from the rehabilitation items used in training the learning model as the predetermined condition. Specifically, the identification unit 12 extracts a combination of rehabilitation items from among the rehabilitation items that have been frequently performed. In this embodiment, the identification unit 12 extracts a combination of rehabilitation items from 32 rehabilitation items in descending order of the number of times they have been performed.

[0067] In addition, the identifying unit 12 extracts a combination of rehabilitation items based on patient information as a predetermined condition. Specifically, a combination of rehabilitation items is associated with the result of a rehabilitation test, and the identifying unit 12 extracts a combination of rehabilitation items according to the patient test information of the patient information.

[0068] In addition, the identification unit 12 extracts a combination of rehabilitation items based on a correspondence table showing the linkage of rehabilitation items as a predetermined condition. Specifically, the identification unit 12 identifies rehabilitation items linked in the correspondence table as a combination to be extracted, and extracts the combination.

[0069] In another preferred embodiment, the identification unit 12 extracts combinations of rehabilitation items a predetermined number of times or more. In this embodiment, the identification unit 12 extracts combinations of rehabilitation items 100 times or more.

[0070] In a more preferred embodiment, the identification unit 12 determines the predetermined number of times based on the patient examination information and extracts a combination of rehabilitation items. Specifically, the identification unit 12 determines the predetermined number of times based on the values ​​of the locomotive syndrome degree, locomotive syndrome degree (number of hits), locomotive syndrome degree (2-step test), locomotive syndrome degree (locomotive syndrome 25), and / or locomotive syndrome degree (standing up test) in the patient examination information and extracts a combination of rehabilitation items. This means that the more severe the locomotive syndrome, the more appropriate rehabilitation items need to be provided to patients, and by increasing the number of trials depending on the locomotive syndrome level, more accurate results can be obtained.

[0071] The identification unit 12 may input multiple combinations randomly extracted from multiple rehabilitation items into the learning model and obtain the patient's degree of improvement for each combination. Alternatively, the identification unit 12 may input one rehabilitation item into the learning model, obtain the degree of improvement for each rehabilitation item, and identify individually proposed videos corresponding to a predetermined number of rehabilitation items in ascending order of improvement degree as candidates for individually proposed videos to be provided to the patient. In this case, if there are multiple degrees of improvement for the same rehabilitation item, the identification unit 12 obtains the average value of these degrees of improvement as the degree of improvement for that rehabilitation item. The identification unit 12 may also input one rehabilitation item and a combination of rehabilitation items into the learning model.

[0072] In this embodiment, the identifying unit 12 inputs the basic patient information and the patient examination information of the patient information into the learning model to obtain the degree of improvement from the learning model. On the other hand, the identifying unit 12 may input only the basic patient information into the learning model to obtain the degree of improvement, or may input only the patient examination information into the learning model to obtain the degree of improvement.

[0073] <2.2.2. Registration of individual proposed videos> Next, in SB5 to SB9, the required videos and individually suggested videos are registered in the database 2 as rehabilitation videos to be provided to the patient.

[0074] First, the medical staff terminal device 4 receives the candidates for the individually proposed video identified by the identification unit 12 (SB5), and accepts from the medical staff a designation of the individually proposed video to be provided to the patient (SB6). In this embodiment, the medical staff terminal device 4 displays the candidates for the individually proposed video identified in SB4 side by side on the same screen so that selection can be input.

[0075] 5(b) is an example of a screen display for accepting the designation of an individual suggested video to be provided to a patient, which is displayed on the medical staff terminal device 4. In the illustrated example, the individual suggested videos corresponding to the rehabilitation items identified in SB4 and included in the combination with the greatest degree of improvement are displayed side by side.

[0076] In a preferred embodiment of the present invention, the degree of improvement acquired in SB4 is displayed in association with the individually suggested moving image.

[0077] In the illustrated example, the individual suggested videos corresponding to the rehabilitation items included in the combination identified in SB4 and having the greatest degree of improvement are displayed. Alternatively, a predetermined number of combinations may be displayed in ascending order of the degree of improvement, and by receiving a selection input of a combination, the individual suggested video included in the selected combination may be designated as the individual suggested video to be provided to the patient.

[0078] Also, Fig. 5(c) is an example of a screen displayed on the medical staff terminal device 4 for changing the individually suggested video provided to the patient. In the illustrated example, when the "Change" button on the screen of Fig. 5(b) is pressed, the screen of Fig. 5(c) is displayed, and multiple individually suggested videos that are candidates for change are displayed based on the suggested video information stored in the database 2.

[0079] In a preferred embodiment of the present invention, suggested individual videos that are candidates for change are displayed based on the patient examination information acquired in SB1. In another preferred embodiment, suggested individual videos that are candidates for change are displayed based on the video type of the required video selected and input in SB2. This allows individual suggested videos to be displayed as change candidates based on the patient's test results and the video type of required videos provided to the patient, making it possible to streamline medical professionals' video change work.

[0080] Then, the specifying unit 12 specifies the individual proposed video to be provided to the patient by receiving a selection input of the individual proposed video from the medical staff from among the displayed individual proposed videos.

[0081] In SB7 to SB9, the registration unit 11 registers the rehabilitation video in the database.

[0082] The registration unit 11 receives the individually suggested videos designated in SB6, the required videos designated in SB2, and the patient ID of the patient examination information acquired in SB1 (SB7).Then, the registration unit 11 transmits the patient ID, the required videos, and the individually suggested videos to the database 2 (SB8), and registers the patient rehabilitation information in the database 2, in which the patient ID is associated with the rehabilitation videos designated by the medical professional (the required videos and individually suggested videos) (SB9).

[0083] In this embodiment, the registration unit 11 registers the individually suggested video in an internal database (database 2), but it may also register the individually suggested video in an external database (hospital database 5).

[0084] <2.3. Rehabilitation Treatment (C)> In the rehabilitation process (C), when a patient undergoes rehabilitation testing and undergoes rehabilitation after the test, the rehabilitation video registered in the pre-rehabilitation process (B) is displayed, and a rehabilitation evaluation is received from the patient.

[0085] <2.3.1. Display of individual suggested videos> In SC1 to SC4, the rehabilitation video registered in SB9 is displayed on the patient terminal device 3.

[0086] First, the patient terminal device 3 receives a request to display rehabilitation videos from a patient (SC1), and transmits the request, including the patient ID, to the display processing unit 15 (SC2). The display processing unit 15 processes and displays the rehabilitation videos (essential videos and individually suggested videos) linked to the patient ID. The display processing unit 15 then transmits the display processing results to the patient terminal device 3 (SC3), and displays the rehabilitation videos (SC4).

[0087] 6(a) and (b) are display examples of a screen displaying rehabilitation videos displayed on the patient terminal device 3. FIG. 6(a) displays a uniform rehabilitation video that all patients should watch. In this embodiment, the uniform rehabilitation video is a video related to ADL (activities of daily living), and in the illustrated example, a video related to a pathological condition and a video related to pain mechanisms are displayed, but the types of videos are not limited to this. Then, when the display processing unit 15 determines that these uniform rehabilitation videos have been viewed, it performs display processing of FIG. 6(b).

[0088] Fig. 6(b) is an example of a screen displaying rehabilitation videos registered in rehabilitation pre-processing (B). Fig. 6(b) displays the required videos and individually suggested videos (in the illustrated example, "Knee Exercise A" to "Knee Exercise C") identified in rehabilitation pre-processing (B). Then, by receiving a selection input from the patient for these rehabilitation videos, the display processing unit 15 displays the contents of the rehabilitation videos, and the registration unit 11 registers a video viewing log of the rehabilitation videos.

[0089] <2.3.2. Rehabilitation evaluation registration> In SC5 to SC8, the evaluation receiving unit 14 receives rehabilitation evaluations for each rehabilitation video from patients who have viewed the video, and registers patient rehabilitation information that links the patient ID, rehabilitation video, and rehabilitation evaluation.

[0090] At SC5, the patient terminal device 3 receives a rehabilitation evaluation for the rehabilitation video from the patient. Figures 6(c) and 6(d) are examples of screens displayed on the patient terminal device 3 for receiving a rehabilitation evaluation after viewing each rehabilitation video.

[0091] Fig. 6(c) displays the evaluation level, allowing selection and input of whether to implement (implementable or not implementable). When "Done" (implementable) in Fig. 6(c) is selected and input, Fig. 6(d) is displayed, and selection and input of appropriate (in the illustrated example, "no pain"), room for change (in the illustrated example, "slight pain"), and inappropriate (in the illustrated example, "painful and unpleasant") is accepted.

[0092] Then, the evaluation receiving unit 14 receives the rehabilitation evaluation and the patient ID received in SC5 (SC6), transmits the rehabilitation evaluation and the patient ID to the database 2 (SC7), and registers the patient rehabilitation information linked to the patient ID, rehabilitation video, and rehabilitation evaluation in the database 2 (SC8). Note that the evaluation receiving unit 14 may also register the patient rehabilitation information in the hospital database 5.

[0093] As described above, by executing the processes SA1 to SC8, it is possible to propose optimal rehabilitation videos to medical professionals according to the results of the patient's rehabilitation examination. This also makes it possible to provide the patient with the best rehabilitation content that takes into account the medical professionals' knowledge. This allows medical professionals to more easily decide on rehabilitation content, reducing their workload.

[0094] <3. Treatment for rehabilitation sessions from the second session onwards> When implementing rehabilitation for the second time or later, the patient rehabilitation information can be used to make it easier for medical professionals to decide on the rehabilitation content.

[0095] Specifically, the display processing unit 15 displays the rehabilitation evaluation (whether or not the rehabilitation was performed and / or the evaluation level) in association with the rehabilitation video based on the patient rehabilitation information on the screen (Figure 5) displayed on the medical staff terminal device 4 (not shown).

[0096] In a preferred embodiment, the identification unit 12 extracts a combination of rehabilitation items based on a rehabilitation evaluation of a patient and identifies candidates for individually suggested videos to be provided to the patient. Specifically, the identification unit 12 extracts rehabilitation items so as not to include rehabilitation items whose implementation status in the rehabilitation evaluation of the patient's rehabilitation information is "not implemented" or whose evaluation level is "inappropriate." The identification unit 12 then obtains the degree of improvement for each combination of the extracted rehabilitation items from the learning model and identifies candidates for individually suggested videos based on the degree of improvement.

[0097] In a preferred embodiment, if the rehabilitation evaluation for a required video includes "could not be performed," "room for change," or "painful and undesirable," a notification unit (not shown) notifies the medical professional of this.

[0098] In a preferred embodiment, when multiple individually proposed videos are linked to one rehabilitation item, candidates for the individually proposed video are identified based on the patient's video viewing log. Specifically, the identification unit 12 identifies a combination of rehabilitation items with the highest degree of improvement based on multiple degrees of improvement obtained using a learning model. Then, of the multiple individually proposed videos corresponding to each of the rehabilitation items included in the combination, the individually proposed video with a viewing status of "viewed" in the video viewing log is identified as the individually proposed video to be provided to the patient.

[0099] In a preferred embodiment, when multiple individual suggested videos are linked to one rehabilitation item, candidates for the individual suggested video may be identified based on the patient's rehabilitation evaluation. Specifically, the identification unit 12 identifies a combination of rehabilitation items based on multiple degrees of improvement, and identifies an individual suggested video with an evaluation level of "appropriate" from among multiple individual suggested videos corresponding to each rehabilitation item included in the combination as the individual suggested video to be provided to the patient.

[0100] As described above, when proposing rehabilitation content from the second session onwards, medical professionals can use the results of previous rehabilitation sessions to more efficiently provide patients with the most appropriate rehabilitation videos.

[0101] In a preferred embodiment of the present invention, the patient may be notified based on the examination reservation information, rehabilitation evaluation, and video viewing log. Specifically, if there is a rehabilitation video for which the video viewing log and rehabilitation evaluation have not been registered within a predetermined period before the scheduled examination date in the examination reservation information, a notifying unit (not shown) notifies the patient that the rehabilitation video will be viewed.

[0102] In a preferred embodiment, if the patient stops watching a rehabilitation video midway, the rehabilitation evaluation may be input as "unfeasible" or "inappropriate." Specifically, the registration unit 11 identifies a rehabilitation video that the patient stopped watching midway based on the video viewing log, and registers patient rehabilitation information in which the rehabilitation evaluation is set to "unfeasible" or "inappropriate" in association with the rehabilitation video. [Explanation of symbols]

[0103] 0: Proposed system 1: Proposed device 2: Database 3: Patient terminal device 4: Medical staff terminal equipment 10: Server 101: Processing section 102: Storage section 103: Communications Department 9: Terminal device 91: Processing section 92: Storage section 93: Communications Department 94: Input section 95: Output section 11: Registration Department 12: Specific part 13: Learning Department 14: Evaluation Reception Department 15: Display processing section 21: Rehabilitation video database 22: Learning database NW: Communication network

Claims

1. A proposal system that proposes rehabilitation content to be performed by a patient, The proposal system includes an identification unit, The identification unit inputs patient information and a plurality of combinations extracted from a plurality of rehabilitation contents to the suggestion unit, acquires a degree of improvement of the patient for each of the combinations, and identifies candidate combinations of the rehabilitation contents based on the acquired degree of improvement. Suggestion system.

2. The proposed system further comprises a learning unit, The suggestion means is a learning model, The learning unit learns the learning model using patient information, the combination of the rehabilitation content, and the degree of improvement as training data. The recommendation system of claim 1 .

3. The proposal system further includes a learning unit, The learning unit extracts the combinations based on the number of times the rehabilitation content has been performed, and learns the learning model using the patient information and the extracted combinations as training data. The proposal system of claim 2 .

4. The proposal system further includes a display processing unit, the display processing unit displays a screen on which candidates for rehabilitation content for the patient can be designated, the screen displaying the candidates for rehabilitation content and an evaluation of the rehabilitation content received from the patient side by side; The specifying unit specifies the rehabilitation content for the patient based on the designation of the rehabilitation content candidates. The recommendation system of claim 1 .

5. The proposal system further includes an evaluation receiving unit, the evaluation receiving unit receives an evaluation of the rehabilitation content from the patient, and registers the evaluation in association with the patient and the rehabilitation item performed by the patient; The identification unit identifies the rehabilitation content candidates for the patient based on the evaluation. The recommendation system of claim 1 .

6. A proposal program that proposes rehabilitation content to be implemented by a patient, the proposal program causes a computer to function as a specific unit, The identification unit inputs patient information and a plurality of combinations extracted from a plurality of rehabilitation contents to the suggestion unit, acquires a degree of improvement of the patient for each of the combinations, and identifies candidate combinations of the rehabilitation contents based on the acquired degree of improvement. Proposed program.

7. A method for proposing rehabilitation content to be performed by a patient, The computer A process of inputting patient information and a plurality of combinations extracted from a plurality of rehabilitation contents to a suggestion means, acquiring the degree of improvement of the patient for each of the combinations, and identifying candidate combinations of the rehabilitation contents based on the acquired degree of improvement. A proposed method for performing

Images