Consensus building support system, device and program

Abstract

To easily get to know selection of the determination about the diagnosis and / or nursing care of a plurality of users.SOLUTION: A consent formation support system of an embodiment includes a storage unit, a determination unit, an index calculation unit, and a display unit. The storage unit stores a database for recording the state of a first user and the actions of the first user and a second user. The determination unit determines whether the main body of an action is the first user or the second user. The index calculation unit calculates a first state evaluation index showing the evaluation of the state by the first user on the basis of the state of the first user and the action of the first user, and calculates a second state evaluation index showing the evaluation of the state by the second user on the basis of the state of the first user and the action of the second user. The display unit displays the first state evaluation index and / or the second state evaluation index.SELECTED DRAWING: Figure 2

Description

[Technical Field]

[0001] The embodiments disclosed in this specification and the drawings relate to a consensus building support system, an apparatus, and a program. [Background technology]

[0002] In order for patients to understand their illness, be satisfied with the treatment plan, and continue to participate in treatment, shared decision-making, in which doctors and patients share the decision-making process, rationale, and results, is important. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Special Publication No. 2017-519303 Summary of the Invention [Problem to be solved by the invention]

[0004] The system described in Patent Document 1 has patients answer questions, and based on the answers, estimates the patient's preferences, the reasons for those preferences, and the patient's understanding of the disease. However, this method requires a lot of effort from the patient to answer the questions. In addition, it cannot measure whether the doctor understands the patient, resulting in one-way shared decision-making.

[0005] One of the problems to be solved by the embodiments disclosed in this specification and the drawings is to easily grasp the decision-making preferences of multiple users regarding medical treatment and / or care. However, the problems to be solved by the embodiments disclosed in this specification and the drawings are not limited to the above problem. Problems corresponding to the effects of each configuration shown in the embodiments described below can also be positioned as other problems. [Means for solving the problem]

[0006] A consensus building support system according to an embodiment includes a storage unit, a discrimination unit, an index calculation unit, and a display unit. The storage unit stores a database that records a state of a first user and actions of the first user and a second user. The discrimination unit determines whether the subject of the action is the first user or the second user. The index calculation unit calculates a first state evaluation index representing an evaluation of the state by the first user based on the state of the first user and actions related to the first user, and calculates a second state evaluation index representing an evaluation of the state by the second user based on the state of the first user and actions related to the second user. The display unit displays the first state evaluation index and / or the second state evaluation index. [Brief explanation of the drawings]

[0007] [Figure 1] FIG. 1 is a diagram illustrating an example of the configuration of a consensus building support system according to the first embodiment. [Figure 2] FIG. 2 is a diagram illustrating an example of the configuration of the consensus building support device according to the first embodiment. [Figure 3] FIG. 3 is a diagram illustrating an example of a process of supporting consensus building by the consensus building support device. [Figure 4] FIG. 4 is a diagram showing an example of an execution record of a designated order. [Figure 5] FIG. 5 is a diagram showing an example of a nursing record. [Figure 6] FIG. 6 is a diagram illustrating an example of a state and a combined action. [Figure 7] FIG. 7 is a diagram illustrating an example of a subject for each combined action. [Figure 8] FIG. 8 is a diagram showing the relationship between the state s(t), state s(t+1), and action adr(t) related to the doctor in FIG. [Figure 9] FIG. 9 is a diagram showing the relationship between the state s(t), state s(t+1), and action apt(t) related to the patient in FIG. [Figure 10] FIG. 10 is a diagram showing an example of a display screen of a patient condition evaluation index map and a doctor condition evaluation index map. [Figure 11] FIG. 11 is a diagram showing an example of a display screen of a patient condition evaluation index map and a doctor condition evaluation index map. [Figure 12] FIG. 12 is a diagram showing an example of a display screen showing the time transition of the state combination corresponding to the maximum value of the state evaluation index. [Figure 13] FIG. 13 is a diagram illustrating an example of the configuration of a consensus building support device according to the second embodiment. [Figure 14] FIG. 14 is a diagram showing an example of a display screen of a graph showing the transition over time of the difference value between the patient condition evaluation index and the doctor condition evaluation index. [Figure 15] FIG. 15 is a diagram showing an example of a display window of the recommended candidate actions. [Figure 16] FIG. 16 is a diagram showing an example of a display window of the calculation basis of the recommended candidate actions. [Figure 17] FIG. 17 is a diagram illustrating an example of a route peripheral area of ​​a patient's optimal action route and a route peripheral area of ​​a doctor's optimal action route. [Figure 18] FIG. 18 is a diagram illustrating past action paths and future action paths in a state space. DETAILED DESCRIPTION OF THE INVENTION

[0008] Hereinafter, embodiments of a consensus building support system, an apparatus, and a program will be described in detail with reference to the drawings.

[0009] (First embodiment) Fig. 1 is a diagram showing an example of the configuration of a consensus building support system 1 according to the first embodiment. As shown in Fig. 1, the consensus building support system 1 is a computer network having a consensus building support device 2 and a medical / nursing record storage device 3 that are communicably connected to each other via a network.

[0010] The consensus building support device 2 is a computer that supports consensus building regarding medical treatment and / or nursing care among multiple users. More specifically, the consensus building support device 2 acquires medical records and / or nursing care records from the medical treatment / nursing care record storage device 3, generates support information for consensus building based on the acquired medical records and / or nursing care records, and displays the generated support information. Users according to this embodiment include patients, the patient's family, medical professionals and nursing care workers in charge of the patient, etc. Medical professionals according to this embodiment include doctors, pharmacists, nurses, etc. Nursing care workers according to this embodiment include nursing care staff, certified care workers, certified social workers, care managers, etc.

[0011] The medical / care record storage device 3 is a computer that stores a database of medical records and / or care records related to various patients. The medical records according to this embodiment are records of the series of patient conditions and the series of user (patient, family, caregiver, etc.) actions in response to the conditions, which are generated during the course of medical treatment for the patient. The care records according to this embodiment are records of the series of patient conditions and the series of user (patient, family, caregiver, etc.) actions in response to the conditions, which are generated during the course of care.

[0012] 2 is a diagram illustrating an example of the configuration of the consensus building support device 2 according to the first embodiment. As illustrated in FIG. 2, the consensus building support device 2 includes a processing circuit 21, a storage device 22, an input device 23, a communication device 24, and a display device 25.

[0013] The processing circuit 21 has processors such as a CPU (Central Processing Unit) and a GPU (Graphics Processing Unit). The processing circuit 21 executes a consensus building support program to realize an acquisition function 211, a discrimination function 212, a state evaluation index calculation function 213, a display control function 214, and the like. Note that each of the functions 211 to 214 is not limited to being realized by a single processing circuit. A processing circuit may be configured by combining multiple independent processors, and each processor may execute a program to realize each of the functions 211 to 214. Furthermore, each of the functions 211 to 214 may be a modularized program that constitutes the consensus building support program, or may be an individual program. These programs are stored in the storage device 22.

[0014] By implementing the acquisition function 211, the processing circuit 21 acquires various information. For example, the processing circuit 21 acquires the status of the first user and the actions of the first user and the second user from the database of the medical / nursing record storage device 3. The first user is the user to be processed and refers to the subject of the status. Typically, the first user is a patient. The second user is a user other than the user to be processed, specifically, a family member of the patient, a medical professional, or a nursing professional. In other words, the second user is a person with whom an agreement is formed with the first user.

[0015] By implementing the determination function 212, the processing circuit 21 determines whether the subject of the behavior acquired by the acquisition function 211 is the first user or the second user.

[0016] By implementing the state evaluation index calculation function 213, the processing circuitry 21 calculates a first state evaluation index representing an evaluation of the state by a first user based on the state of the first user and actions related to the first user. Also, the processing circuitry 21 calculates a second state evaluation index representing an evaluation of the state by a second user based on the state of the first user and actions related to a second user. The first state evaluation index and the second state evaluation index are examples of support information for consensus building.

[0017] By implementing the display control function 214, the processing circuitry 21 displays various information on the display device 25. For example, the processing circuitry 21 displays the first condition evaluation index and / or the second condition evaluation index on the display device 25.

[0018] The storage device 22 is a read-only memory (ROM), a random access memory (RAM), a hard disk drive (HDD), a solid state drive (SSD), an integrated circuit storage device, or the like that stores various types of information. In addition to the above storage devices, the storage device 22 may also be a drive device that reads and writes various types of information from portable storage media such as a compact disc (CD), a digital versatile disc (DVD), or a flash memory, or a semiconductor memory element. The storage device 22 may also be located in another computer connected via a network.

[0019] The input device 23 receives various input operations from an operator, converts the received input operations into electrical signals, and outputs the electrical signals to the processing circuit 21. Specifically, the input device 23 is connected to input devices such as a mouse, a keyboard, a trackball, a switch, a button, a joystick, a touchpad, and a touch panel display. The input device 23 outputs electrical signals corresponding to the input operations to the input device to the processing circuit 21. The input device 23 may also be an input device provided in another computer connected via a network or the like.

[0020] The communication device 24 is an interface for transmitting and receiving various information to and from other computers, such as the medical / nursing record storage device 3 included in the consensus building support system 1.

[0021] The display device 25 displays various information in accordance with the display control function 214 of the processing circuit 21. For example, a liquid crystal display (LCD), a cathode ray tube (CRT) display, an organic electroluminescence display (OLED), a plasma display, or any other display may be used as appropriate as the display device 25. A projector may also be used as the display device 25.

[0022] An example of the operation of the consensus building support device 2 according to the first embodiment will be described below. In the following description, it is assumed that the first user is a patient and the second user is a doctor. It is assumed that the medical / care record storage device 3 holds an electronic medical record database that records medical records. Electronic medical records are also called electronic charts. The consensus building support device 2 performs consensus building support to support shared decision-making between a patient and a doctor.

[0023] Fig. 3 is a diagram showing an example of a process of supporting consensus building by the consensus building support device 2. As shown in Fig. 3, the processing circuit 21, by implementing the acquisition function 211, acquires behavior and condition data related to the patient to be processed from the medical record database (step S1).

[0024] A "state" refers to a state of a patient in the course of medical treatment. An "action" refers to an action taken by either or both of the patient and the doctor in response to a certain "state" of the patient. In other words, a "state" can be defined as something that changes and is observable depending on the "action." A "state" can be anything, including vital data, test results, medical expenses, subjective symptoms, treatment effects, costs, and side effects. The state to be acquired in step S1 can be any of these types, and the number can be any number as long as it is one or more. The type of state acquired in step S1 may be determined in advance manually or automatically. In the following example, the state types are assumed to be two: the presence or absence of edema and the SpO2 value. The patient's state in this case is determined by the combination of the presence or absence of edema and the SpO2 value. This combination is called a state combination.

[0025] The medical record database includes nursing records and implementation records of instruction orders. Implementation records generally contain a chronological record of the actions taken by doctors and other medical professionals in response to instruction orders. Nursing records generally contain a chronological record of the patient's condition and the actions taken in response to that condition. The actions recorded in nursing records may be actions taken by the patient or by medical professionals such as doctors and nurses.

[0026] FIG. 4 is a diagram showing an example of an implementation record of an instruction order. FIG. 5 is a diagram showing an example of a nursing record. As shown in FIG. 4, the implementation record records the date and the content of the implementation record using letters and numbers. Specifically, the implementation record in FIG. 4 records the actions of the doctor using free words. As shown in FIG. 5, the nursing record records the date and the content of the nursing record using letters and numbers. Specifically, the nursing record in FIG. 5 records SOAP descriptions. Note that "S" records subjective information about the patient, "O" records objective information about the patient's condition, "A" records evaluations, and "P" records actions by medical professionals such as doctors.

[0027] In step S1, the processing circuit 21, for example, acquires action and status data from the implementation records of instruction orders and nursing records using natural language processing. A certain status and the action taken for that status form one combination. The action and status are acquired in association with a numerical value representing the date and time. It is also preferable that the action and status are acquired in association with an identifier representing the source of acquisition. At the time of step S1, the subject of the "action" does not need to be identified.

[0028] The method of acquiring behavior and condition data is not limited to natural language processing. As another example, an identifier (ID) for identifying the content of each item, such as an instruction order or an execution order, in the medical record database may be assigned, and behavior and condition data may be acquired by introducing the identifier. For example, an item corresponding to identifier "1" may be provided in the instruction order or execution order, and the presence or absence of edema, which is a "condition," may be recorded in that item. In step S1, when acquiring the presence or absence of edema, the processing circuitry 21 searches for the item with identifier "1" and acquires the presence or absence of edema from that item.

[0029] FIG. 6 is a diagram showing an example of a state and a combined action. Note that "combined action" means an action by either or both of the patient and the doctor. As shown in FIG. 6, a combination of a state and a combined action is obtained for each time (step) t. A state is a combination of the presence or absence of edema and an SpO2 value. The presence or absence of edema is represented by a categorical value. For example, "0" represents "no edema" and "1" represents "present edema." The presence or absence of edema may be converted into a categorical value by the processing circuit 21. SpO2 is represented by a continuous value, which is the measurement value itself. SpO2 may also be converted into a categorical value according to the level of the measurement value. The combined action is represented by a character string. The combined action may also be converted into a categorical value. For example, "medication A taken" may be converted into "0001," "medication A not taken" may be converted into "0002," etc.

[0030] After step S1 is performed, the processing circuit 21 determines the subject of each action by implementing the determination function 212 (step S2).

[0031] 7 is a diagram showing an example of the subject of each combined action. As shown in FIG. 7, for each combined action, the subject is determined from among the patient, the doctor, or both the patient and the doctor. The subject is determined automatically based on the source of the combined action or the content of the combined action.

[0032] An example of a method for determining the subject of a combined action based on the source of the combined action is as follows: If the combined action is obtained from an instruction order, the processing circuitry 21 may determine that the subject of the combined action is a doctor; if the combined action is obtained from an implementation order, the processing circuitry 21 may determine that the subject of the combined action is a patient. As another method, if the combined action is obtained from "P" in SOAP, the processing circuitry 21 may determine that the subject of the combined action is a doctor; if the combined action is obtained from "S" in SOAP, the processing circuitry 21 may determine that the subject of the combined action is a patient. As another example, the processing circuitry 21 may determine the subject of the combined action by rule-based processing using an order ID. More specifically, if the combined action is obtained from a specified item included in an order, the processing circuitry 21 determines whether the subject of the combined action is a doctor or a patient according to the identifier assigned to the specified item.

[0033] In the case of a determination method based on natural language processing, the processing circuitry 21 performs natural language processing on a character string including characters describing the combined action to determine whether the subject of the combined action is a doctor or a patient. The character string includes not only the characters describing the combined action, but also characters describing or inferring the subject of the combined action. Typically, natural language processing is performed on a character string describing the processing date in the electronic medical record.

[0034] When step S2 is performed, the processing circuit 21 calculates a state evaluation index based on the state and action for each actor by implementing the state evaluation index calculation function 213 (step S3). The state sequence in this embodiment follows a Markov decision process. In this case, in step S3, the processing circuit 21 calculates, as an example, the state s(t) of the step to be processed and the state s(t+1) of the next step of the step to be processed, and the patient's action a between the state s(t) of the step to be processed and the state s(t+1) of the next step. pt (t) and the patient condition evaluation index r pt Similarly, the processing circuit 21 calculates the state s(t) of the step to be processed and the state s(t+1) of the next step, and the doctor's action a between the state s(t) of the step to be processed and the state s(t+1) of the next step. dr (t) and the inverse reinforcement learning based on dr Calculate.

[0035] FIG. 8 shows the state s(t), state s(t+1) and action a related to the doctor in FIG. dr 9 is a diagram showing the relationship between the state s(t), state s(t+1) and action a(t) related to the patient in FIG. pt (t). The state associated with the doctor's behavior and the state associated with the patient's behavior are the same as the patient's state. pt (t),r dr (t) is action a pt (t),a dr (t) is calculated for the step t. For example, as shown in FIG. 8, at t=0, the action a dr Since (0) exists, the condition evaluation index r dr is calculated, but at t=1, action a dr Since (1) does not exist, the condition evaluation index r dr Similarly, as shown in Figure 9, for example, at t=0, the action a pt Since (0) exists, the condition evaluation index r pt is calculated, but at t=3, action a pt Since (3) does not exist, the condition evaluation index r ptis not calculated.

[0036] Typically, the condition evaluation index r pt ,r dr is the reward R in inverse reinforcement learning pt (s),R dr (s). For example, the reward R pt (s),R dr (s) is the state s i Optimal action in a * If is known from past knowledge, etc., the optimal action a * The optimal action is calculated using a linear programming method or the like that uses the difference between the reward in and the expected reward. If the optimal action is unknown, it is calculated using the past policy and Maximum Entropy inverse reinforcement learning or the like. At this time, the processing circuit 21 calculates the optimal action by using the action a pt (t) and Action a dr (t) may be converted from a character string describing the content of the action to a category value. The character string describing the content of the action and the category value may be associated in advance in a table or the like, and the processing circuit 21 may use the table to convert the character string describing the content of the action into a category value.

[0037] As another example, the state evaluation index r is used as the optimal policy π(s) in an imitation learning algorithm using inverse reinforcement learning such as GAIL (Generative Adversarial Imitation Learning). pt ,r dr As another example, the reward R pt (s,a),R dr (s, a) and the action value function Q pt (s),Q dr (s), state value function V pt (s),V dr (s) as the condition evaluation index r pt ,r dr may be calculated.

[0038] When step S3 is performed, the processing circuitry 21 displays the condition evaluation index calculated in step S3 by implementing the display control function 214 (step S4). In step S4, the processing circuitry 21 displays the condition evaluation index related to the patient and / or the condition evaluation index related to the doctor on the display device 25. As an example, the processing circuitry 21 displays a map of the condition evaluation index related to the patient and a map of the condition evaluation index related to the doctor (hereinafter referred to as condition evaluation index map).

[0039] Generally speaking, a state is represented by a time series of a combination of a plurality of state values ​​corresponding to a plurality of state types, respectively. For example, as shown in Figures 6 and 7, when there are two state types, the presence or absence of edema and SpO2, the state is represented by a time series of a combination of a category value of the presence or absence of edema and an SpO2 value. The patient state evaluation index and the physician state evaluation index have one value for each state combination at each time in the time series of state combinations. The state evaluation index map represents the distribution of the patient state evaluation index and / or the physician state evaluation index in a state space defined by a plurality of state types.

[0040] FIG. 10 is a diagram showing an example of a display screen I1 displaying a patient condition evaluation index map I11 and a doctor condition evaluation index map I12. In FIG. 10, the patient's name is "Patient Taro" and the doctor's name is "Doctor Ichiro." As shown in FIG. 10, the patient condition evaluation index map I11 and the doctor condition evaluation index map I12 are displayed side by side on the display screen I1. The condition evaluation index maps I11 and I12 represent the distribution of condition evaluation indexes in a state space defined by a first state (presence or absence of edema) and a second state (SpO2). One pixel on the condition evaluation index maps I11 and I12 corresponds to one state combination. In the condition evaluation index maps I11 and I12, the categorical value (or discrete value) of the presence or absence of edema is represented on the horizontal axis, and the distribution of continuous values ​​of SpO2 (for example, numerical values ​​from 0 to 100) is represented on the vertical axis. In the condition evaluation index maps I11 and I12, a condition evaluation index value is assigned to each combination of the presence or absence of edema and the continuous value of SpO22. The condition evaluation index value is specified numerically or on an ordinal scale. A color value corresponding to the condition evaluation index value is assigned to each pixel of the ice body evaluation index. Each pixel is displayed in a color corresponding to the color value assigned to that pixel. The correspondence between the condition evaluation index value and the color value is determined by a color table I13. It is recommended that the color table I13 also be displayed in order to understand the correspondence between the condition evaluation index value and the color value.

[0041] By displaying the condition evaluation index maps I11 and I12, the observer can visually grasp the distribution of the condition evaluation indexes for each patient and doctor. This allows the observer to quantitatively grasp the desirability and value of each condition combination for each patient and doctor. Furthermore, by displaying the condition evaluation index map I11 and the condition evaluation index map I12 side by side, the observer can easily and effortlessly grasp the differences in desirability and value for each condition combination.

[0042] In the above display example, there are two condition types: the presence or absence of edema and SpO2. However, the processing circuitry 21 may similarly display condition evaluation indexes when there are three or more condition types. When there are three or more condition types, the processing circuitry 21 may display a condition evaluation index map related to the patient and / or a condition evaluation index map related to the doctor on a specified plane formed by one or two condition types specified by the operator from among the three or more condition types.

[0043] As an example, if the condition types are the presence or absence of edema, SpO2, treatment effects such as BNP (Brain Natriuretic Peptide), and medical costs, the condition evaluation index is defined in a four-dimensional state space. Since it is difficult to directly display the distribution of the condition evaluation index in the four-dimensional state space, the operator specifies one or two condition types to be displayed via the input device 23. The processing circuit 21 sets a specified plane formed by the specified one or two condition types in the state space and displays the distribution of the condition evaluation index on the specified plane. In other words, the condition evaluation index map I11, etc., shown in Figures 10 and 11 can also be expressed as the distribution of the condition evaluation index on a specified plane formed by the presence or absence of edema and SpO2. In this case, any value may be specified for the condition types other than the condition type to be displayed. In the above specific example, if the condition types to be displayed are the presence or absence of edema and SpO2, the BNP value and the medical cost value must be set to define the specified plane. The values ​​of BNP and medical expenses may be specified as arbitrary values ​​via the input device 23, for example, or may be set automatically according to a predetermined algorithm.

[0044] When step S4 is performed, the consensus building support according to the first embodiment ends.

[0045] The method of displaying the patient condition evaluation index and the doctor condition evaluation index is not limited to the above, and various modifications and applications are possible.

[0046] Fig. 11 is a diagram showing an example of a display screen I2 of a patient condition evaluation index map I21 and a doctor condition evaluation index map I22. The patient condition evaluation index map I21 is similar to the patient condition evaluation index map I11 shown in Fig. 10, the doctor condition evaluation index map I22 is similar to the doctor condition evaluation index map I12 shown in Fig. 10, and the color table I23 is similar to the color table I23 shown in Fig. 10.

[0047] As shown in FIG. 11 , the processing circuitry 21 highlights the condition combination I211 corresponding to the maximum value of the patient condition evaluation index in the patient condition evaluation index map I21 and the condition combination I221 corresponding to the maximum value of the physician condition evaluation index in the physician condition evaluation index map I22. The highlighting method may be to highlight the areas corresponding to the condition combination I211 and the condition combination I221 in color, or by flashing or surrounding them with a frame. It is not necessary to always highlight both the condition combination I211 and the condition combination I221; either the condition combination I211 or the condition combination I221 may be highlighted. By highlighting the condition combination I211 and / or the condition combination I221, the observer can easily identify the condition combination that requires attention. The highlighted area may be an area corresponding to a condition evaluation index value equal to or greater than a threshold, rather than the area corresponding to the maximum value of the condition evaluation index. The threshold may be set to any value via the input device 23 or the like.

[0048] 11, the processing circuit 21 may display text information I24 for the condition combination I211 and text information I25 for the condition combination I221. For example, the text information I24 and the text information I25 may display "edema = none" and "SpO2 = 95." This makes it possible to understand the actual meaning of the condition combination I211 and / or the condition combination I221.

[0049] As another example, processing circuitry 21 may display a physician condition evaluation index in a first specific state in which the patient condition evaluation index takes a predetermined value. As another example, processing circuitry 21 may display a patient condition evaluation index in a second specific state in which the physician condition evaluation index takes a predetermined value. The predetermined value may be set to any statistical value such as a maximum or minimum value, or may be set to the sum of condition evaluation index values ​​that are greater than or equal to a threshold value or less than a threshold value.

[0050] As another example, the processing circuitry 21 may display a diagram showing the time transition of the condition combination I211 corresponding to a predetermined value of the patient condition evaluation index in the patient condition evaluation index map I21 and / or the condition combination I221 corresponding to a predetermined value of the doctor condition evaluation index in the doctor condition evaluation index map I22. The predetermined value may be set to any statistical value such as a maximum value or a minimum value, or may be set to the sum of the condition evaluation index values ​​equal to or greater than a threshold value or equal to or less than a threshold value.

[0051] FIG. 12 is a diagram showing an example of a display screen I3 showing the time progression of a condition combination corresponding to the maximum value of a condition evaluation index. As shown in FIG. 12, the display screen I3 displays a graph I31 showing the time progression of a condition combination corresponding to the maximum value of a patient condition evaluation index. The vertical axis of the graph I31 represents the presence or absence of edema and SpO2, and the horizontal axis represents time (steps). The graph I31 plots the condition combination that takes the maximum value of the patient's condition evaluation index at each time (for example, date). This makes it possible to understand the time progression of the condition combination focusing on the maximum value. Note that the time progression of the condition combination corresponding to the maximum value of the physician condition evaluation index can also be displayed in a similar manner. Furthermore, the time progression of the condition combination corresponding to the maximum value of the patient condition evaluation index and the time progression of the condition combination corresponding to the maximum value of the physician condition evaluation index may both be displayed side by side.

[0052] As described above, the consensus building support system 1 according to the first embodiment includes a medical treatment / nursing record storage device 3 and a consensus building support device 2. The medical treatment / nursing record storage device 3 stores a database that records the state of a first user and the actions of the first user and a second user. The consensus building support device 2 determines whether the subject of the action is the first user or the second user. Based on the state of the first user and the actions related to the first user, the consensus building support device 2 calculates a first state evaluation index that represents the first user's evaluation of the state, and based on the state of the first user and the actions related to the second user, calculates a second state evaluation index that represents the second user's evaluation of the state. The consensus building support device 2 displays the first state evaluation index and / or the second state evaluation index.

[0053] According to the above configuration, a condition evaluation index representing the first user's and second user's evaluations of the first user's condition can be calculated without any effort on the part of the first user, etc. Furthermore, by displaying the condition evaluation index of the first user and / or the second user, an observer can quantitatively grasp the first user's and / or second user's evaluations of the first user's condition. This enables two-way sharing of decision-making between patients and doctors. As a result, it becomes possible to easily grasp the preferences of multiple users regarding medical decision-making.

[0054] In the above description, the first user and the second user are a patient and a doctor, respectively. However, this embodiment is not limited to this, and the first user and the second user may be the same person.

[0055] As an example, the first and second users may be the same patient undergoing long-term treatment for a chronic illness, and past and present behaviors can be compared to identify changes in preferences over time.

[0056] As another example, the first user and the second user may be the same doctor. By comparing past and present behaviors of the same doctor, it is possible to clarify changes in preferences over time. By clarifying changes in preferences, it becomes possible to ensure consistency in treatment. It is also possible to confirm whether treatment has been changed in accordance with changes in guidelines (for example, whether the treatment has reverted to the treatment prescribed in the guidelines before the change).

[0057] As another example, the first user and the second user may be different doctors. By comparing the behavior of the first doctor and the second doctor, it is possible to clarify the differences in their preferences for behavior. For example, if the attending physician is changed due to a transfer or other reason, it is possible to confirm whether the treatment is being carried out according to the same policy between the predecessor and successor. Furthermore, by applying this system to the first doctor and the second doctor who work at different hospitals, it is possible to confirm whether the treatment is being carried out according to the same policy at the different hospitals.

[0058] (Second embodiment) Next, a consensus building support system, an apparatus, and a program according to a second embodiment will be described. In the following description, components having substantially the same functions as those in the first embodiment will be given the same reference numerals, and will be described only when necessary.

[0059] 13 is a diagram illustrating an example of the configuration of the consensus building support apparatus 2 according to the second embodiment. As illustrated in FIG. 13, the processing circuitry 21 of the consensus building support apparatus 2 realizes an acquisition function 211, a determination function 212, a state evaluation index calculation function 213, and a display control function 214, as well as a recommended behavior calculation function 215.

[0060] By implementing the display control function 214, the processing circuitry 21 displays the difference between the state evaluation index of the first user and the state evaluation index of the second user. By implementing the recommended action calculation function 215, the processing circuitry 21 calculates candidates for recommended actions to reduce the difference between the state evaluation index of the first user and the state evaluation index of the second user for a state combination in which the difference is equal to or greater than a threshold. The calculated candidates are displayed on the display device 25 or the like by implementing the display control function 214.

[0061] An example of the operation of the consensus building support device 2 according to the second embodiment will be described below. In the following description, as in the description of the example of the operation in the first embodiment, it is assumed that the first user is a patient and the second user is a doctor. It is assumed that the medical / care record storage device 3 holds an electronic medical record database that records medical records.

[0062] The processing circuitry 21 according to the second embodiment displays a difference value between the patient condition evaluation index and the doctor condition evaluation index. There are various ways of displaying the difference value. For example, the processing circuitry 21 may display a difference map showing the distribution of the difference values ​​between the patient condition evaluation index and the doctor condition evaluation index for each condition combination. The difference value may be the absolute value of the difference between the patient condition evaluation index and the doctor condition evaluation index, or the subtraction value of the doctor condition evaluation index from the patient condition evaluation index, or the subtraction value of the patient condition evaluation index from the doctor condition evaluation index. As another example, the processing circuitry 21 may display a difference value between the patient condition evaluation index and the doctor condition evaluation index in a first specific condition in which the patient condition evaluation index takes a predetermined value. Alternatively, the processing circuitry 21 may display a difference value between the patient condition evaluation index and the doctor condition evaluation index in a second specific condition in which the doctor condition evaluation index takes a predetermined value. The predetermined value may be set to any statistical value, such as a maximum value or a minimum value, or may be set to the sum of the condition evaluation index values ​​that are greater than or equal to a threshold value or less than a threshold value.

[0063] As another example of displaying the difference value, the processing circuitry 21 may display a graph showing the time progression of the difference value between the patient condition evaluation index and the doctor condition evaluation index.

[0064] FIG. 14 is a diagram showing an example of a display screen I4 of a graph I41 representing the transition over time of the difference value between the patient condition evaluation index and the doctor condition evaluation index. As shown in FIG. 14, the display screen I4 displays a graph I41 in which the vertical axis represents the difference value and the horizontal axis represents time (date and time). The difference value may be the absolute value of the difference between the patient condition evaluation index and the doctor condition evaluation index, or may be the subtraction value of the doctor condition evaluation index from the patient condition evaluation index, or may be the subtraction value of the patient condition evaluation index from the doctor condition evaluation index. By displaying the difference value, the observer can know the deviation between the patient condition evaluation index and the doctor condition evaluation index. By displaying the transition over time of the difference value, the observer can know the transition over time of the deviation between the patient condition evaluation index and the doctor condition evaluation index.

[0065] As shown in Fig. 14, a graph I41 displays a threshold value Th for the difference value. The threshold value Th may be set based on any standard, but as an example, it is set at the boundary between an acceptable difference value and an unacceptable difference value. The processing circuit 21 highlights difference values ​​equal to or greater than the threshold value Th with a frame line I42 or the like. This makes it possible to draw the viewer's attention to difference values ​​equal to or greater than the threshold value Th.

[0066] As shown in FIG. 14, a display recommended action button I43 and a display calculation basis button I44 are displayed on the display screen I4. When the display recommended action button I43 is pressed, the processing circuit 21 realizes the recommended action calculation function 215 to calculate candidates for recommended actions to reduce difference values ​​equal to or greater than the threshold Th. When there are two or more difference values ​​equal to or greater than the threshold Th, the difference value to be calculated may be designated via the input device 23 or the like. Furthermore, the user for whom the candidate recommended actions are to be calculated can be selected from patients and / or doctors via the input device 23 or the like. The calculated candidates for recommended actions are displayed by the processing circuit 21.

[0067] There are various methods for calculating the recommended candidate actions. As an example, the processing circuit 21 calculates the recommended candidate actions by reinforcement learning based on the state and the state evaluation index. Specifically, first, various historical data on patients and doctors obtained in the past is recorded in the medical / nursing record storage device 3. Elements of the patient historical data include a combination of the patient's state at a certain step, the patient's behavior in response to that state, a patient state evaluation index for that state, and the patient's state at the next step observed as a result of that behavior. Elements of the doctor historical data include a combination of the patient's state at a certain step, the doctor's behavior in response to that state, a doctor state evaluation index for that state, and the patient's state at the next step observed as a result of that behavior.

[0068] The processing circuitry 21 inputs the patient's condition at the step to be processed and the difference value of the state evaluation index of the calculation target user from the patient and doctor history data, and generates a trained model that outputs recommended candidate actions for the calculation target user that reduce the difference value. The trained model is stored in the storage device 22. The processing circuitry 21 inputs the patient's condition at the step to be processed and the difference value of the state evaluation index of the calculation target user into the trained model, and calculates recommended candidate actions. Alternatively, the processing circuitry 21 may identify the patient's behavior path (optimal behavior path) with the highest state evaluation index (reward) for the patient based on the history data, and calculate the patient's behavior at the step to be processed from the optimal behavior path as the recommended candidate action.

[0069] The history data may be not only data on conditions, actions, and condition evaluation indices relating to patients and doctors that have actually been obtained, but also data on conditions, actions, and condition evaluation indices that have been generated in a simulated manner.

[0070] Fig. 15 is a diagram showing an example of a display window I5 of recommended candidate actions. The display window I5 is displayed, for example, superimposed on the display screen I4 of the difference values ​​of the state assessment index shown in Fig. 14. The display window I5 includes a display field I51, in which a character string representing the content of the recommended action is displayed. In Fig. 15, as an example, "moderate exercise" is displayed as a recommended candidate action for the patient on "February 1st" shown in Fig. 14.

[0071] When the calculation basis display button I44 shown in FIG. 14 is pressed, the processing circuit 21 displays the calculation basis of the recommended candidate actions.

[0072] Fig. 16 is a diagram showing an example of a display window I6 of the calculation basis for recommended candidate actions. As shown in Fig. 16, the display window I6 is displayed, for example, superimposed on the display screen I4 of the difference value of the state evaluation index shown in Fig. 14. The display window I6 displays, as calculation candidates, the state combinations and actions on the date corresponding to the difference value to be calculated. For example, when a recommended candidate action for a patient on February 1st is displayed, it is preferable to display the state combination and patient action on February 1st, which is the step to be calculated, and the state combination and patient action on February 2nd, which is the next step.

[0073] In the above example, the difference between the patient condition evaluation index and the doctor condition evaluation index is the sum of the difference between the patient condition evaluation index and the doctor condition evaluation index for all state combinations, i.e., the entire state space. However, the method for calculating the difference is not limited to this, and various methods are possible.

[0074] As an example, the processing circuitry 21 may calculate the difference value between the patient condition evaluation index and the doctor condition evaluation index by limiting the area to a partial area of ​​the state space. More specifically, the processing circuitry 21 may calculate the difference value between the patient condition evaluation index and the doctor condition evaluation index by limiting the area to a peripheral area of ​​each user's optimal behavior route (hereinafter referred to as a route peripheral area).

[0075] FIG. 17 illustrates an example of a path peripheral region I74 of the patient's optimal behavior path I72 and a path peripheral region I84 of the doctor's optimal behavior path I82. The left diagram of FIG. 17 schematically illustrates the path peripheral region I74 of the patient's optimal behavior path I72 in the state space I7, and the right diagram of FIG. 17 schematically illustrates the path peripheral region I84 of the doctor's optimal behavior path I82 in the state space I8. As shown in FIG. 17, the state spaces I7 and I8 are assumed to be two-dimensional state spaces represented by states S1 and S2. As shown in the left diagram of FIG. 17, an optimal behavior path I72 for the patient is determined, connecting the initial state I71 and the final state I73 in the state space I7. The optimal behavior path I72 refers to the path taken by the patient's behavior in the state space I7 that maximizes the reward. Similarly, as shown in the right diagram of FIG. 17, an optimal behavior path I82 for the doctor is determined, connecting the initial state I81 and the final state I83 in the state space I8. The optimal behavioral path I82 is the path that the doctor follows in the state space I8 to maximize the reward. The optimal behavioral paths I72 and I82 are expanded by a predetermined distance to form the path surrounding areas I74 and I84. This predetermined distance can be set to any value.

[0076] The processing circuit 21 calculates a first sum of the state evaluation indexes of all state combinations included in the route peripheral area I74 and a second sum of the state evaluation indexes of all state combinations included in the route peripheral area I84, and calculates the difference between the first sum and the second sum as the state evaluation index difference value. More specifically, the processing circuit 21 calculates the state evaluation index difference value by subtracting the first sum from the second sum or by subtracting the second sum from the first sum. The calculated state evaluation index difference value is displayed on the display device 25 by the processing circuit 21. At this time, the processing circuit 21 may display the state evaluation index difference value together with the optimal action routes I72 and I82, the route peripheral areas I74 and I84, and the state spaces I7 and I8 shown in FIG. 17. This allows the observer to understand the basis of the state evaluation index difference value.

[0077] As another example, processing circuitry 21 may map route surrounding area I74 onto state space I8 and calculate, as the state evaluation index difference value, the difference between the sum of the state evaluation indexes of all state combinations included in this mapping area and the first sum. Similarly, processing circuitry 21 may map route surrounding area I84 onto state space I7 and calculate, as the state evaluation index difference value, the difference between the sum of the state evaluation indexes of all state combinations included in this mapping area and the second sum.

[0078] In the above description, the difference between the total values ​​of the condition evaluation indexes is calculated as the condition evaluation index difference value, but the difference between the average values ​​of the condition evaluation indexes may also be calculated as the condition evaluation index difference value.

[0079] As another example, if the current state has not reached the final state, the processing circuitry 21 may calculate a state evaluation index difference value for each of the past action path and the future action path.

[0080] FIG. 18 is a diagram illustrating a past behavior path I92 and a future behavior path I94 in the state space I9. The past behavior path I92 and the future behavior path I94 may be either a patient's behavior path or a doctor's behavior path. The past behavior path I92 is a behavior path actually taken by the user from the initial state I91 to the current state I93. The future behavior path I94 is an optimal behavior path that can be taken from the current state I93 to the final state I95. The future behavior path I94 may be calculated by reinforcement learning based on the past behavior path I92, each state from the initial state I91 to the current state I93, and a state evaluation index.

[0081] As an example, the processing circuit 21 calculates the sum of the state evaluation indexes of the state combinations over the past behavior path I92 and the sum of the state evaluation indexes of the state combinations over the future behavior path I94, and displays the sum for the past behavior path I92 and the sum for the future behavior path I94. In this case, the processing circuit 21 may display the past behavior path I92 and the future behavior path I94 together with the sum for the past behavior path I92 and the sum for the future behavior path I94, as shown in Fig. 18. Note that the processing circuit 21 may display either the sum for the past behavior path I92 or the sum for the future behavior path I94.

[0082] As another example, the processing circuitry 21 may identify a region in the patient state space where the condition evaluation index takes a predetermined value, map the region onto the doctor state space, and calculate, as the condition evaluation index difference value, a difference between the value of the condition evaluation index in this mapped region (doctor state evaluation index value) and the predetermined value of the patient state evaluation index. The predetermined value may be set to the maximum value of the condition evaluation index or to a value equal to or greater than a threshold. Similarly, the processing circuitry 21 may identify a region in the doctor state space where the condition evaluation index takes a predetermined value, map the region onto the patient state space, and calculate, as the condition evaluation index difference value, a difference between the value of the condition evaluation index in this mapped region (patient state evaluation index value) and the predetermined value of the doctor state evaluation index. The region where the condition evaluation index takes a predetermined value is not limited to a region that coincides with a state combination where the condition evaluation index takes a predetermined value, but may also be a region of a predetermined size, such as 3 × 3 or 5 × 5, that includes a state combination where the condition evaluation index takes a predetermined value.

[0083] As another example, the processing circuitry 21 may calculate the difference value of the condition evaluation index by limiting it to the behavioral paths of various patients. Specifically, the processing circuitry 21 acquires multiple behavioral paths for multiple past patients from history data, and identifies a representative behavioral path (hereinafter referred to as a representative path) of multiple past patients based on the acquired multiple behavioral paths. The representative path may be set, for example, to a path through which a threshold or more behavioral paths pass. Then, the processing circuitry 21 calculates the difference value between the patient condition evaluation index and the doctor condition evaluation index across the representative paths included in the state space. By limiting it to the representative path, it becomes possible to compare the patient condition evaluation index and the doctor condition evaluation index using a uniform behavioral path that is not dependent on individual patients, etc.

[0084] According to at least one of the embodiments described above, it is possible to easily grasp the decision-making preferences of multiple users regarding medical treatment and / or care.

[0085] The term "processor" used in the above description refers to a circuit such as a CPU, a GPU, an application specific integrated circuit (ASIC), a programmable logic device (e.g., a simple programmable logic device (SPLD), a complex programmable logic device (CPLD), and a field programmable gate array (FPGA)). A processor realizes its functions by reading and executing a program stored in a memory circuit. Note that instead of storing a program in a memory circuit, a program may be directly embedded in the processor circuit. In this case, the processor realizes its functions by reading and executing the program embedded in the circuit. Furthermore, instead of executing a program, a function corresponding to the program may be realized by combining logic circuits. Note that each processor in this embodiment is not limited to being configured as a single circuit, but may be configured as a single processor by combining multiple independent circuits to realize its function. Furthermore, multiple components in FIGS. 1, 2, and 13 may be integrated into a single processor to realize its function.

[0086] Although several embodiments have been described, these embodiments are presented as examples and are not intended to limit the scope of the invention. These embodiments can be implemented in various other forms, and various omissions, substitutions, modifications, and combinations of embodiments can be made without departing from the spirit of the invention. These embodiments and their modifications are included within the scope and spirit of the invention, as well as within the scope of the invention and its equivalents as defined in the claims. [Explanation of symbols]

[0087] 1. Consensus Building Support System 2 Consensus building support device 3. Nursing / care record storage device 21 Processing circuit 22 Storage device 23 Input Devices 24. Communications equipment 25 Display equipment 211 Acquisition Function 212 Discrimination Function 213 Condition evaluation index calculation function 214 Display Control Function 215 Recommended Action Calculation Function

Claims

1. a storage unit that stores a database that records a state of a first user and actions taken by the first user and a second user in response to the state; a determination unit that determines whether the subject of the behavior is the first user or the second user; an index calculation unit that calculates a first state evaluation index representing an evaluation of the state by the first user based on the state of the first user and an action related to the first user, and calculates a second state evaluation index representing an evaluation of the state by the second user based on the state of the first user and an action related to the second user; a display unit that displays the first condition evaluation index and / or the second condition evaluation index; A consensus building support system equipped with the above.

2. The consensus building support system of claim 1, wherein the discrimination unit determines that the subject of the action is the second user, a doctor, when the action is obtained from an instruction order, and determines that the subject of the action is the first user, a patient, when the action is obtained from an implementation order.

3. The consensus building support system of claim 1, wherein the discrimination unit determines that the subject of the action is the second user, a doctor, when the action is obtained from P of SOAP, and determines that the subject of the action is the first user, a patient, when the action is obtained from S of SOAP.

4. The consensus building support system of claim 1, wherein when the behavior is obtained from a specified item included in an order, the discrimination unit determines whether the subject of the behavior is the second user, a doctor, or the first user, a patient, according to an identifier assigned to the specified item.

5. The consensus building support system of claim 1, wherein the discrimination unit performs natural language processing on a character string including characters describing the behavior to determine whether the subject of the behavior is the second user, a doctor, or the first user, a patient.

6. The state is included in a sequence of states that follow a Markov decision process; The index calculation unit calculating the first state evaluation index by inverse reinforcement learning based on a state of a step to be processed and a state of a step subsequent to the step to be processed in the state sequence, and an action of the first user between the state of the step to be processed and the state of the step subsequent to the step; calculating the second state evaluation index by inverse reinforcement learning based on the state of the processing step, the state of the next step, and the behavior of the second user between the state of the processing step and the state of the next step; The consensus building support system according to claim 1.

7. the state includes a time series of combinations of a plurality of state values ​​respectively corresponding to a plurality of state types; the first state evaluation index and the second state evaluation index have one value for the combination for each time in the time series; The consensus building support system according to claim 1.

8. The consensus building support system according to claim 7 , wherein the display unit displays a distribution of the first state evaluation index and / or the second state evaluation index in a state space defined by the plurality of state types.

9. The consensus building support system of claim 8, wherein the display unit displays the distribution of the first state evaluation index and / or the second state evaluation index in a specified plane formed by one or two state types specified by an operator from among the plurality of state types when the plurality of state types is three or more.

10. The consensus building support system of claim 8, wherein the display unit emphasizes in the distribution a first specific state in which the first state evaluation index takes a predetermined value and / or a second specific state in which the second state evaluation index takes a predetermined value.

11. The consensus building support system according to claim 10 , wherein the display unit displays a diagram showing a time progression of the first specific state and / or the second specific state.

12. The consensus building support system according to claim 1 , wherein the display unit displays a difference value between the first state evaluation index and the second state evaluation index.

13. The consensus building support system according to claim 12 , wherein the display unit displays a graph showing a time transition of a difference value between the first state evaluation index and the second state evaluation index.

14. The consensus building support system according to claim 13 , wherein, when the difference value is equal to or greater than a threshold, the display unit highlights, on the graph, a time corresponding to a value equal to or greater than the threshold.

15. A storage unit further comprising: a storage unit for storing historical data of another first user and historical data of another second user obtained in the past, wherein the historical data of the other first user includes a combination of the state of the other first user in one step, the behavior of the other first user with respect to that state, a first state evaluation index with respect to that state, and the state of the other first user in the next step observed as a result of that behavior; and a storage unit for the historical data of the other second user including a combination of the state of the other first user in one step, the behavior of the other second user with respect to that state, a second state evaluation index with respect to that state, and the state of the other first user in the next step observed as a result of that behavior. a candidate calculation unit that identifies a path of an action having the highest state assessment index for the first user based on history data of the other first user and history data of the other second user, and calculates a behavior of the first user at a processing target step in the identified path as a candidate of a recommended action for reducing the difference value; The display unit displays the candidates. The consensus building support system according to claim 12.

16. The consensus building support system according to claim 14 , wherein the display unit displays the behavior of the first user and / or the behavior of the second user corresponding to a time corresponding to a value equal to or greater than the threshold value.

17. The display unit displaying the second condition evaluation index in a first specific condition in which the first condition evaluation index takes a predetermined value; displaying a difference value between the first condition evaluation index and the second condition evaluation index in the first specific condition; Displaying the first condition evaluation index in a second specific state in which the second condition evaluation index takes a predetermined value; or displaying a difference value between the first condition evaluation index and the second condition evaluation index in the second specific condition; The consensus building support system according to claim 1.

18. the first user is a patient; the second user is a family member, a medical professional, and / or a caregiver of the patient; The consensus building support system according to claim 1.

19. A computer comprising: an acquisition unit that acquires, from a database, a state of a first user and actions taken by the first user and a second user in response to the state; a determination unit that determines whether the subject of the behavior is the first user or the second user; an index calculation unit that calculates a first state evaluation index representing an evaluation of the state by the first user based on the state of the first user and an action related to the first user, and calculates a second state evaluation index representing an evaluation of the state by the second user based on the state of the first user and an action related to the second user; a display unit that displays the first condition evaluation index and / or the second condition evaluation index on a display device; A consensus building support device comprising:

20. On the computer, a function of acquiring from a database the state of a first user and the actions taken by the first user and the second user in response to the state; a function of determining whether the subject of the action is the first user or the second user; a function of calculating a first state evaluation index representing an evaluation of the state by the first user based on the state of the first user and actions related to the first user, and calculating a second state evaluation index representing an evaluation of the state by the second user based on the state of the first user and actions related to the second user; a function of displaying the first condition evaluation index and / or the second condition evaluation index on a display device; A consensus-building support program that makes this a reality.

Images