Medical support device

Abstract

To avoid review of a medical treatment policy while reducing a burden associated with decision making.SOLUTION: A medical examination support device according to the present embodiment comprises: a prediction unit; and a presentation unit. The prediction unit predicts a will of a patient or an object person being a related person associated with the patient and a will of a medical doctor who determines a medical treatment policy of the object person, for the medical treatment policy of illness of the patient. The presentation unit presents information based on a result predicted by the prediction unit to at least one of the medical doctor and the object person.SELECTED DRAWING: Figure 1

Description

[Technical Field]

[0001] The embodiments disclosed in the present specification and drawings relate to a medical assistance device. [Background technology]

[0002] As medical treatments become more sophisticated, there are an increasing number of situations in which decision-making by a multidisciplinary team (MDT) is recommended. For example, when a patient has valvular heart disease, the MDT is increasingly making decisions about the patient's treatment plan, such as whether to perform surgery or catheterization as an advanced treatment. Meanwhile, shared decision-making, which considers the patient's wishes when deciding on a treatment plan, is becoming increasingly important. The patient's wishes are determined, for example, through discussion between the patient and their doctor.

[0003] However, because MDT members do not necessarily have direct contact with the patient, there are cases where the patient's wishes do not coincide with those of the MDT. In such cases, the treatment plan will need to be reconsidered. [Prior art documents] [Patent documents]

[0004] [Patent Document 1] Special Publication No. 2015-534161 Summary of the Invention [Problem to be solved by the invention]

[0005] One of the problems that the embodiments disclosed in this specification and the drawings aim to solve is to avoid reconsideration of treatment plans while reducing the burden of decision-making. However, the problems 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] The medical support device according to this embodiment includes a prediction unit and a presentation unit. The prediction unit predicts the intention of the patient or a subject related to the patient regarding a treatment policy for the patient's disease, and the intention of a doctor who will decide the treatment policy for the subject. The presentation unit presents information based on the results predicted by the prediction unit to at least one of the doctor and the subject. [Brief explanation of the drawings]

[0007] [Figure 1] FIG. 1 is a diagram showing an example of the configuration of a medical assistance system including a medical assistance device according to the first embodiment. [Figure 2] FIG. 2 is a flowchart showing the procedure of processing by the medical assistance device according to the first embodiment. [Figure 3A] FIG. 3A is a diagram for explaining processing by the medical support device according to the first embodiment. [Figure 3B] FIG. 3B is a diagram for explaining the processing by the medical support device according to the first embodiment. [Figure 4] FIG. 4 shows an example of the MDT and a screen presented to the patient's doctor. [Figure 5] FIG. 5 shows an example of the processing information. [Figure 6] FIG. 6 shows an example of the MDT and a screen presented to the patient's doctor. [Figure 7] FIG. 7 is a diagram for explaining the processing performed by the medical support device according to the second embodiment. [Figure 8] FIG. 8 is a diagram for explaining the processing performed by the medical support device according to the second embodiment. [Figure 9] FIG. 9 is a diagram for explaining the processing performed by the medical support device according to the second embodiment. [Figure 10] FIG. 10 is a diagram for explaining the processing performed by the medical support device according to the third embodiment. [Figure 11] FIG. 11 is a diagram showing an example of a screen presented to the MDT and the patient's doctor when two processes to be performed by the MDT are selected. [Figure 12A] FIG. 12A is a diagram for explaining processing by the medical support device according to the fourth embodiment. [Figure 12B] FIG. 12B is a diagram for explaining the processing by the medical support device according to the fourth embodiment. [Figure 13A] FIG. 13A is a diagram for explaining the processing performed by the medical support device in the modified example. [Figure 13B] FIG. 13B is a diagram for explaining the processing performed by the medical support device in the modified example. DETAILED DESCRIPTION OF THE INVENTION

[0008] Hereinafter, an embodiment of a medical assistance device will be described in detail with reference to the accompanying drawings. Note that the following description will be given taking a medical assistance system including the medical assistance device as an example.

[0009] (First embodiment) 1 is a diagram showing an example of the configuration of a medical support system 1 including a medical support device 100 according to the first embodiment. The medical support system shown in FIG. 1 includes the medical support device 100 and terminals 10 and 20. The medical support device 100 communicates with the terminals 10 and 20.

[0010] For example, the terminals 10 and 20 include a PC (Personal Computer), a tablet PC, a PDA (Personal Digital Assistant), a mobile terminal, and the like.

[0011] The terminal 10 is provided, for example, in the patient's regular hospital and is used by the patient's doctor.

[0012] The terminal 20 is used, for example, by a multidisciplinary team (hereinafter referred to as MDT) belonging to the patient's family hospital or a highly specialized hospital other than the family hospital. The MDT is an example of a first doctor, and the patient's doctor is an example of a second doctor.

[0013] The medical assistance device 100 includes a communication interface 110, a memory circuitry 120, and a processing circuitry 130. The communication interface 110 is connected to the processing circuitry 130 and controls the transmission and communication of various data between the medical assistance device 100 and the terminals 10 and 20.

[0014] The memory circuitry 120 is connected to the processing circuitry 130 and stores various data. For example, the memory circuitry 120 is realized by a semiconductor memory element such as RAM or flash memory, a hard disk, an optical disk, or the like. The memory circuitry 120 is an example of a means for realizing a memory unit. Furthermore, the memory circuitry 120 does not have to be built into the medical assistance device 100 as long as the medical assistance device 100 can access it over a network.

[0015] The memory circuitry 120 stores multiple pieces of patient information from electronic medical records, etc., created for multiple patients. Each piece of patient information includes basic information and medical data for the patient. The basic information includes identification information for identifying the patient, name, date of birth, sex, blood type, height, weight, etc. The medical data includes information such as numerical values ​​(measurements) and medical records, as well as information indicating the date and time of recording. For example, medical data includes prescription data, nursing record data, etc. Prescription data is medical data related to prescriptions. Nursing record data is medical data related to nursing records.

[0016] The data and information stored in the memory circuitry 120 and used in the embodiment will be described later.

[0017] The processing circuitry 130 controls the components of the medical assistance device 100. For example, the processing circuitry 130 executes a control function 131 and a presentation function 132 as shown in FIG. 1 . Here, for example, the processing functions executed by the control function 131 and the presentation function 132, which are components of the processing circuitry 130, are recorded in the storage circuitry 120 in the form of programs executable by a computer. The processing circuitry 130 is a processor that reads each program from the storage circuitry 120 and executes it to realize the function corresponding to each program. In other words, the processing circuitry 130 in a state in which each program has been read has each function shown in the processing circuitry 130 in FIG. 1 .

[0018] A display application (program) is implemented in the medical assistance device 100, and the display application can be read by the terminals 10 and 20. For example, an operator of the terminals 10 and 20 can use the display application read by the terminal to display display data transmitted from the medical assistance device 100 on the display of the terminal. The control function 131 is an example of a prediction unit. The presentation function 132 is an example of a presentation unit.

[0019] The term "processor" used in the above description refers to a circuit such as a central processing unit (CPU), a graphics processing unit (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)). If the processor is a CPU, for example, the processor realizes its function by reading and executing a program stored in the memory circuit 120. On the other hand, if the processor is an ASIC, for example, the program is directly embedded in the processor circuit instead of storing the program in the memory circuit 120. 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 FIG. 1 may be integrated into a single processor to realize its function.

[0020] The above has described the overall configuration of the medical assistance system including the medical assistance device 100 according to the first embodiment. With this configuration, the medical assistance device 100 reduces the burden of decision-making and avoids reconsideration of treatment plans.

[0021] As medical treatments become more sophisticated, there are an increasing number of situations in which decision-making by a specialized multidisciplinary team (MDT) is recommended. For example, if a patient has valvular heart disease, the MDT is increasingly making decisions about the treatment plan for the patient's disease, such as whether to perform surgery or catheterization as an advanced treatment.

[0022] On the other hand, the importance of shared decision-making, which takes into account the patient's wishes when deciding on a treatment plan, is increasing. The patient's wishes are determined, for example, through discussion between the patient and the patient's doctor.

[0023] However, because MDT members do not necessarily have direct contact with the patient, there are cases where the patient's wishes do not coincide with those of the MDT. For this reason, when the patient's wishes do not coincide with those of the MDT, the treatment plan will be reconsidered. For example, suppose that after a discussion with the patient's doctor, the patient wishes to have surgery. Then, after discussion with the MDT, the decision is made to use medication instead of surgery. In this case, the treatment plan will be reconsidered.

[0024] Furthermore, reconsidering the treatment plan places a burden on the patient, the patient's physician, and the MDT in terms of decision-making. For example, if the patient is not convinced when the patient's physician explains the treatment plan decided by the MDT, the treatment plan will have to be discussed again, which places a burden on the patient. As a result of the second discussion, for example, the patient may now wish to undergo catheterization. In this case, the decision will have to be discussed again with the MDT, which will also place a burden on the MDT. Therefore, it is necessary to avoid reconsidering the treatment plan so that the burden of decision-making is not placed on the patient or the MDT.

[0025] Therefore, the medical assistance device 100 according to the first embodiment performs the following processing. First, in the medical assistance device 100 according to the first embodiment, the control function 131 predicts the intentions of the patient and the MDT, which determines the treatment plan for the patient's disease. The presentation function 132 presents information based on the results predicted by the control function 131 to the MDT and the doctor in charge, who confirms the patient's intentions.

[0026] The following describes each function of the control function 131 and the presentation function 132 with reference to Figures 2 to 6. Figure 2 is a flowchart showing the procedure of processing by the medical support device 100 according to the first embodiment.

[0027] 2 is a step in which the processing circuitry 130 calls up a program corresponding to the control function 131 from the storage circuitry 120 and executes the program. In step S101, the control function 131 executes a prediction process. Specifically, the control function 131 predicts the intention of patient P and the intention of the MDT that determines the treatment policy for the patient P regarding the disease of the patient P.

[0028] In this embodiment, for example, the memory circuitry 120 stores, in addition to the plurality of pieces of patient information described above, first information related to decisions made by patient P or a patient group G with the same attributes as patient P. Specifically, the first information is information related to the tendency of treatment plans desired by patient P. For example, if the disease is valvular disease, the first information is information indicating whether patient group G desired treatment such as surgery, catheter treatment, or medication, or whether they desired no treatment. This first information is acquired by extracting past information about patient P and patient history information of at least one patient with the same attributes as patient P from patient history information in which attribute information such as disease information, age, generation, sex, family structure, and place of residence of each patient is associated with decision-making information related to decisions made by various patients in the past. Note that which attribute information, other than disease information, to use in determining patient group G is a parameter that can be set by the user of the medical support device 100.

[0029] Furthermore, the memory circuitry 120 stores second information related to decisions made by the MDT or a group of doctors with the same attributes as the MDT. Specifically, the second information is information related to the tendency of treatment policies proposed by specialists such as the MDT, and, for example, if patient P's disease is valvular disease, the second information is information indicating whether the specialist proposed treatment such as surgery, catheter treatment, or medication, or whether they proposed no treatment. Note that, if there is insufficient information related to past decisions made by the MDT in charge of patient P, the second information is obtained from information related to decisions made by another MDT in the hospital to which the MDT belongs regarding the same disease as patient P's disease.

[0030] The control function 131 predicts the intention of the patient P and the intention of the MDT regarding the treatment policy for the patient P's disease based on the first information and the second information stored in the memory circuitry 120.

[0031] Here, the control function 131 derives the agreement probability that the MDT and the patient P will agree on each of the multiple treatment plans for the disease, based on the patient P's preference for each of the multiple treatment plans for the disease obtained from the first information and the MDT's preference for each of the multiple treatment plans for the disease obtained from the second information. The agreement probability is calculated using the following formula (1).

[0032]

number

[0033] In the examples shown in Figures 3A and 3B, the probability that the MDT will select "surgery (SAVR)", "catheterization (TAVI)", "medication", and "no treatment" is expressed as p1 D , p2 D , p3 D , p4 D The probability that patient P chooses "SAVR", "TAVI", "medication", or "no treatment" is expressed as p1 P , p2 P , p3 P , p4 P In equation (1), i represents an integer between 1 and 4. The probability p i D can be obtained by statistically processing the second information described above. Alternatively, the MDT preference and probability p i D is obtained by inputting the second information described above into the trained model obtained by machine learning. Also, the probability p i P can be obtained by statistically processing the first information described above. Alternatively, the preference of patient P and the probability p i D is obtained by inputting the first information described above into a trained model obtained by machine learning.

[0034] For example, probability p1 D , p2 D , p3 D , p4 D are "0.2", "0.2", "0.6", and "0.1", respectively, and the probability p1 P , p2 P , p3 P , p4 P are "0.3", "0.5", "0.2", and "0.1", respectively. In this case, the value of the agreement probability that the MDT and patient P will agree is "0.29 (29%)" according to formula (1). The value of the agreement probability derived by the control function 131 is reflected by the presentation process described below.

[0035] The control function 131 may predict the will of the patient P and the will of the MDT by excluding treatment plans that are inappropriate for the patient P. For example, if the medication used for the medication treatment of a disease is incompatible with the medication that the patient P is taking for an underlying disease that the patient P has, the control function 131 excludes the medication treatment. For example, if surgery is difficult for the patient P due to reasons such as children, the control function 131 excludes surgery. In this case, the control function 131 predicts the will of the patient P and the will of the MDT by excluding treatment plans that are inappropriate for the patient P from among the treatment plans that the MDT may select from the first information.

[0036] 2 is a step in which the processing circuitry 130 calls up a program corresponding to the presentation function 132 from the storage circuitry 120 and executes the program. In step S102, the presentation function 132 executes a presentation process. Specifically, the presentation function 132 presents information based on the results predicted by the prediction function 131 on the display of the terminal 20 of the MDT and the display of the terminal 10 of the doctor in charge of the patient P.

[0037] FIG. 4 shows an example of a screen presented to the MDT and the doctor in charge of patient P. For example, when the control function 131 makes predictions for multiple patients P, the presentation function 132 displays a list of information based on the results of the predictions made by the control function 131 for each of the multiple patients P on the terminals 10 and 20. As shown in FIG. 4, the screen displays the patient ID and patient name, which are identification information for identifying the patient P, information regarding the decision-making of the patient P and the MDT, and the collision risk. Here, the results predicted by the control function 131 are displayed in the lower left corner of the column displaying the information regarding the decision-making. Furthermore, if the column displaying the information regarding the decision-making is blank, it means the state before the decision-making. The collision risk is information regarding the degree of agreement between the intentions of patient P predicted by the control function 131 and the intentions of the MDT. In other words, the presentation function 132 presents the collision risk as information corresponding to the value of the agreement probability derived by the control function 131.

[0038] For example, for patient P with patient ID "000001," the predicted results of patient P's intention and the predicted results of MDT's intention are "TAVI." In this case, since patient P's intention and MDT's intention match, when the MDT and patient P make a decision, there is a high possibility that they will agree on the treatment policy.

[0039] On the other hand, for patient P with patient ID "000002," the predicted result of patient P's intention is "SAVR," and the predicted result of MDT's intention is "TAVI." In this case, since patient P's intention and MDT's intention do not match, it is unlikely that MDT and patient P will agree on the treatment policy. In this case, a mark representing the first collision risk is displayed on the screen in association with patient ID "000002." For example, if the agreement probability derived by control function 131 is equal to or less than the first threshold, a mark representing the first collision risk (a circle mark shown in FIG. 4) is displayed.

[0040] Furthermore, for patient P with patient ID "000004," the predicted result of patient P's intention is "medication," and the predicted result of MDT's intention is "TAVI." In this case, since patient P's intention and MDT's intention do not match, the possibility that the MDT and patient P will agree on the treatment policy is low. In this case, a mark representing a second collision risk is displayed on the screen in association with patient ID "000004." For example, if the value of the agreement probability derived by the control function 131 (e.g., "0.29 (29%)") is equal to or less than a second threshold value that is lower than the first threshold value, a mark representing the second collision risk (a triangular mark shown in FIG. 4) is displayed. The second collision risk indicates that the probability of reaching an agreement is lower than the first collision risk.

[0041] Here, if the intentions of patient P predicted by control function 131 do not match the intentions of the MDT, the presentation function 132 presents recommended processing to be carried out by at least one of the MDT and patient P's doctor based on the processing information described below.

[0042] For example, the memory circuitry 120 stores processing information that indicates the procedure of processing from when the control function 131 predicts the intentions of the MDT and the patient P until the MDT and the patient P agree on a treatment plan. Fig. 5 shows an example of the processing information.

[0043] 5, for example, the control function 131 predicts the intention of the MDT and the intention of patient P (step S201). Here, if the prediction results of the control function 131 match (step S201-Yes), the intention of patient P is understood (step S203) as a recommended procedure to be performed by the doctor in charge of patient P. If patient P is satisfied with the treatment plan proposed by the MDT in step S203 and the understanding of the intention is consistent (step S204-Yes), a treatment plan is decided as a recommended procedure to be performed by the MDT (step S206). On the other hand, if patient P is not satisfied with the treatment plan proposed by the MDT in step S203 and the understanding of the intention is inconsistent (step S204-No), additional explanation is provided to patient P as a recommended procedure to be performed by the doctor in charge of patient P (step S205), and then step S206 is performed. Then, as a recommended process to be carried out by the doctor in charge of patient P, consensus building with patient P is carried out (step S211), and if patient P agrees with the treatment plan decided by the MDT in step S206 (step S212-Yes), the treatment plan is finalized. Note that if the MDT and patient P do not agree (step S212-No), the process returns to step S206, and the MDT decides on a treatment plan again.

[0044] Furthermore, if the prediction results of the control function 131 do not match (step S202—No), alternative treatments are considered as recommended processing to be performed by the MDT (step S207), and then patient P's wishes are understood as recommended processing to be performed by the patient P's doctor (step S208). Specifically, the doctor presents the alternatives proposed by the MDT in step S207 to the patient P and understands the patient P's wishes. If the patient is satisfied with the MDT's alternatives in step S208 and the understanding of wishes is consistent (step S209—Yes), steps S211 and S212 are performed. If the patient is not satisfied with the MDT's alternatives in step S208 and the understanding of wishes is inconsistent (step S209—No), additional explanation is provided to the patient P as recommended processing to be performed by the patient P's doctor (step S210), and then steps S211 and S212 are performed.

[0045] Here, the recommended treatment to be performed by the doctor in charge of patient P is updated as first information, and the recommended treatment to be performed by the MDT is updated as second information. Fig. 6 shows an example of a screen presented to the MDT and the doctor in charge of patient P. As shown in Fig. 6, the screen also displays a recommended action. Here, the recommended action is displayed when the intention of patient P predicted by the control function 131 does not match the intention of the MDT, and is information representing a recommended treatment to be performed by at least one of the MDT and the doctor in charge of patient P.

[0046] The presentation function 132 displays the recommended process together with information based on the result predicted by the control function 131. Here, the presentation function 132 updates the display on the screen. For example, when the presentation function 132 receives information indicating that the currently presented recommended process has been executed, the presentation function 132 presents the next recommended process based on the process information.

[0047] Specifically, for patient P with patient ID "000002," the predicted result of patient P's intention, "SAVR," and the predicted result of MDT's intention, "TAVI," do not match, so, for example, the process "Consider alternatives" in step S207 is recommended. In this case, the screen displays, in association with patient ID "000002," a recommended action "MDT Consider alternatives," which indicates the consideration of treatment alternatives, as the recommended process to be performed by the MDT.

[0048] Furthermore, for patient P with patient ID "000004," the predicted result of patient P's intention, "medication," and the predicted result of MDT's intention, "TAVI," do not match, so the process "consider alternatives" in step S207 and the process "understand intentions" in step S208 are recommended and executed. Then, because patient P with patient ID "000004" is satisfied with the MDT's alternative, the process "additional explanation" in step S210 is recommended and executed, and then the process "consensus building" in step S211 is recommended. In this case, the screen further displays, in association with patient ID "000004," information regarding the MDT's decision-making, "TAVI," and also displays a recommended action, "attending physician consensus building," representing consensus building for patient P, as a recommended action to be performed by patient P's physician.

[0049] On the other hand, for patient P with patient ID "000001", the predicted result of patient P's intention "TAVI" and the predicted result of MDT's intention "TAVI" match, so for example, the process "understand intention" in step S203, the process "decide policy" in step S206, and the process "build consensus" in step S211 are recommended and executed in that order to finalize the treatment plan. In this case, the screen further displays, in association with patient ID "000001", information regarding patient P's decision-making "TAVI" and information regarding MDT's decision-making "TAVI", as well as the recommended action "confirm" indicating the finalization of the treatment plan.

[0050] Furthermore, for patient P with patient ID "000003", the predicted result of patient P's intention "SAVR" and the predicted result of MDT's intention "SAVR" match, so for example, the process "understand intention" in step S203 is recommended. In this case, the screen displays, in association with patient ID "000003", a recommended action "understand intention of attending physician" that indicates understanding of patient P's intention as the recommended process to be carried out by patient P's attending physician.

[0051] Furthermore, for patient P with patient ID "000005", the predicted result of patient P's intention "SAVR" and the predicted result of MDT's intention "SAVR" match, so for example, after the process "understand intention" in step S203 is recommended and executed, the process "decide policy" in step S206 is recommended. In this case, the screen displays the recommended action "MDT policy decision", which indicates a treatment policy decision, as the recommended process to be performed by the MDT, in association with patient ID "000005".

[0052] For patient P with patient ID "000006," the predicted result of patient P's intention, "SAVR," and the predicted result of MDT's intention, "SAVR," match, but patient P is not convinced by the treatment plan proposed by the MDT, and there is a mismatch in understanding of intentions. Therefore, for example, the process of "additional explanation" in step S205 is recommended. In this case, the screen displays, in association with patient ID "000006," a recommended action representing additional explanation to patient P, "attending physician additional explanation," as a recommended process to be carried out by patient P's attending physician.

[0053] As described above, in the medical support device 100 according to the first embodiment, the control function 131 predicts the intentions of patient P and the intentions of the MDT, which determines the treatment plan for the patient P's disease, and the presentation function 132 presents information based on the results predicted by the control function 131 to the MDT and the doctor in charge who confirms the patient P's intentions, thereby avoiding reconsideration of the treatment plan. Therefore, in the medical support device 100 according to the first embodiment, the MDT can provide treatment according to a treatment plan that the patient P agrees with. Furthermore, in the medical support device 100 according to the first embodiment, the doctor in charge of patient P can avoid having to discuss the treatment plan again with the patient P or having to discuss it again with the MDT, thereby reducing the burden of decision-making.

[0054] When displaying a list, the presentation function 132 may display the patients P in order of divergence of their intentions. For example, when displaying a list, the presentation function 132 changes the order in which the patients P are displayed depending on the degree of agreement between the intentions of the patients P predicted by the control function 131 and the intentions of the MDT. In the example shown in Fig. 4, when priority is given to displaying marks indicating collision risk, information about the patients P with patient IDs "000004", "000006", and "000002" is displayed with priority.

[0055] Furthermore, when displaying a list, the presentation function 132 may display the patients P in descending order of urgency of treatment. For example, when displaying a list, the presentation function 132 changes the order in which the patients P are displayed according to the urgency of the treatment plan that the control function 131 predicts from the first information is likely to be selected by the MDT.

[0056] Furthermore, the presentation function 132 updates the display of recommended actions as part of the screen display update, but it may also update the display of collision risk in addition to the recommended actions. For example, for patient P with patient ID "000002," the collision risk was displayed, but the agreement probability for the alternative determined by the MDT may be calculated again, and if the agreement probability becomes greater than a first threshold, the collision risk may not be displayed. This allows the attending physician to understand that the collision risk has been significantly reduced and to understand patient P's intentions.

[0057] (Second embodiment) The medical support device 100 according to the second embodiment determines the order in which to present the processes performed by the MDT and the processes performed by the doctor in charge of the patient P, based on the agreement probability. That is, the presentation function 132 presents the recommended order of processes as information according to the value of the agreement probability derived by the control function 131.

[0058] Specifically, in step S101, the control function 131 derives a first probability that the MDT and the patient P will agree when a decision is made from the MDT, and a second probability that the MDT and the patient P will agree when a decision is made from the patient P, based on the patient P's preferences and tolerance ranges for each of a plurality of treatment plans for the disease obtained from the first information and the MDT's preferences and tolerance ranges for each of a plurality of treatment plans for the disease obtained from the second information. In step S102, the presentation function 132 determines the order in which to present the processes to be performed by the MDT and the processes to be performed by the doctor in charge of the patient P, based on the first probability and the second probability.

[0059] In the example shown in FIG. 7, the probability of preference and tolerance range is not considered, and the preference considers whether to select or not, and the tolerance range considers whether it is acceptable or not. For example, the probability (p i D ya p i P ) is equal to or greater than the threshold A, the options are indicated by a circle in FIG. 7, indicating that they are selectable.i D ya p i P ) is equal to or greater than threshold B, the options are shaded in FIG. 7 to indicate that they are acceptable. Threshold A is a threshold set for determining whether or not a selection is possible, and threshold B is a threshold set for determining whether an option is acceptable or unacceptable. The control function 131 calculates the agreement probability that the MDT and patient P will agree when a decision is made from the MDT, and the agreement probability that the MDT and patient P will agree when a decision is made from patient P. The agreement probability is calculated using the following formula (2).

[0060]

number

[0061] In the example shown in Figure 7, MDT can accept two of the four options, "SAVR," "TAVI," "medication," and "no treatment," so the number of options included in the MDT's acceptable range is "2." Also, patient P can accept three of the four options, "SAVR," "TAVI," "medication," and "no treatment," so the number of options included in patient P's acceptable range is "3."

[0062] Here, when the decision is made from the MDT, there is only one option, "TAVI," that is within the acceptable range of both the MDT and patient P. Therefore, the value of the agreement probability that the MDT and patient P will agree when the decision is made from the MDT is "0.5 (50%)" according to formula (2). This agreement probability is an example of a first probability. Furthermore, when the decision is made from patient P, there is only one option, "TAVI," that is within the acceptable range of both the MDT and patient P in the numerator of formula (2). Therefore, the value of the agreement probability that the MDT and patient P will agree when the decision is made from patient P is "0.33 (33%)" according to formula (2). This agreement probability is an example of a second probability.

[0063] In this case, the presentation function 132 determines, based on the first probability and the second probability, that the process performed by the MDT and the process performed by the doctor in charge of patient P should be presented in order to prioritize the process performed by the MDT, and presents on the displays of the terminals 10 and 20 that it is better to prioritize the process performed by the MDT. Specifically, since there is a higher probability of agreement if patient P makes a decision after the MDT has made a decision, for example, the presentation function 132 presents the process "consider alternatives" in step S207 as the recommended process, as shown in the flowchart of FIG.

[0064] In the example shown in FIG. 8, the preference takes into account the probability of selection, and the tolerance takes into account whether it is acceptable or not. Here, for example, the probability (p i D ya p i P ) is equal to or greater than the threshold, the options are shaded in FIG. 8 to indicate that they are acceptable. The control function 131 determines the agreement probability p D , and the agreement probability p , where the MDT and patient P agree when a decision is made by patient P. P Calculate the consensus probability p D , p P are calculated by the following formulas (3) and (4), respectively.

[0065]

number

[0066]

number

[0067] In the example shown in Fig. 8, probability is taken into consideration in the preference. For example, it is assumed that the MDT can accept the options "SAVR" and "TAVI" out of four options "SAVR", "TAVI", "medication", and "no treatment", and that the patient P can accept the options "TAVI", "medication", and "no treatment" out of the options "SAVR", "TAVI", "medication", and "no treatment". In the example shown in Fig. 8, similarly to the first embodiment, the probability that the MDT will select the options "SAVR", "TAVI", "medication", and "no treatment" is respectively expressed as p1 D , p2 D , p3 D , p4 D The probability that patient P chooses the options "SAVR", "TAVI", "medication", and "no treatment" is expressed as p1 P , p2 P , p3 P , p4 P It is expressed as follows.

[0068] For example, probability p1 D , p2 D , p3 D , p4 D are "0.4", "0.4", "0.1", and "0.1", respectively, and the probability p1 P , p2 P , p3 P , p4 P are respectively "0.1", "0.6", "0.2", and "0.1". In addition, in equations (3) and (4), the threshold value a for the tolerance range is "0.2". In this case, the agreement probability p D The value of p D =0.4×0+0.4×1+0.1×1+0.1×0=0.5(50%). The agreement probability p D is an example of the first probability. In addition, the agreement probability p P The value of p P = 0.1 × 1 + 0.6 × 1 + 0.2 × 0 + 0.1 × 0 = 0.7 (70%). The agreement probability p P is an example of the second probability.

[0069] In this case, the presentation function 132 determines, based on the first probability and the second probability, the order in which to present the processing performed by the MDT and the processing performed by the patient P's doctor, to prioritize the processing performed by the patient P's doctor, and presents on the display of the terminals 10 and 20 a message that the processing performed by the patient P's doctor should be prioritized. Specifically, since there is a higher probability that the patient P will agree to a decision made by the MDT after making a decision, for example, unlike the flowchart in Figure 5, if the prediction results do not match, the presentation function 132 first presents, as a recommended process, "understanding intentions," in which the doctor in charge presents the MDT's proposal to the patient in step S203 to confirm their intentions. If there is still a mismatch, the presentation function 132 presents "consider alternatives," which recommends the processing in step S207.

[0070] In the example shown in Fig. 9, the preference takes into account the probability of selection, and the tolerance takes into account the probability of acceptance. The control function 131 calculates the agreement probability p D , and the agreement probability p , where the MDT and patient P agree when a decision is made by patient P. P Calculate the consensus probability p D , p P are calculated by the following formulas (5) and (6), respectively.

[0071]

number

[0072]

number

[0073] In the example shown in Fig. 9, probabilities are considered for preferences and tolerance ranges. For example, in the example shown in Fig. 9, as in Fig. 8, it is assumed that the MDT can accept the options "SAVR" and "TAVI" out of the four options "SAVR", "TAVI", "medication", and "no treatment", and that the patient P can accept the options "TAVI" and "medication" out of the four options "SAVR", "TAVI", "medication", and "no treatment". Also, in the example shown in Fig. 9, as in the first embodiment, the probabilities that the MDT will select the options "SAVR", "TAVI", "medication", and "no treatment" are respectively set as p1 D , p2 D , p3 D , p4 D The probability that patient P chooses the options "SAVR", "TAVI", "medication", and "no treatment" is expressed as p1 P , p2 P , p3 P , p4 P In the example shown in Figure 9, the probability that MDT can accept the options "SAVR", "TAVI", "medication", and "no treatment" is expressed as q1 D , q2 D , q3 D , q4 D The probability that patient P can accept the options "SAVR", "TAVI", "medication", and "no treatment" is expressed as q1 P , q2 P , q3 P , q4 P The probability p i D and probability q for the tolerance range i D can be obtained by statistically processing the second information described above. Alternatively, the MDT preference and probability p i D is obtained by inputting the second information described above into the trained model obtained by machine learning. Also, the probability p i P and probability q for the tolerance range i P can be obtained by statistically processing the first information described above. Alternatively, the preference of patient P and the probability p i Dis obtained by inputting the first information described above into a trained model obtained by machine learning.

[0074] For example, probability p1 D , p2 D , p3 D , p4 D are respectively "0.4", "0.4", "0.1", and "0.1", and the probability q1 D , q2 D , q3 D , q4 D are "0.7", "0.8", "0.4", and "0.2", respectively. Probability p1 P , p2 P , p3 P , p4 P are respectively "0.1", "0.6", "0.2", and "0.1", and the probability q1 P , q2 P , q3 P , q4 P are respectively "0.3", "0.9", "0.6", and "0.1". Then, the agreement probability p D The value of p D = 0.4 × 0.3 + 0.4 × 0.9 + 0.1 × 0.6 + 0.1 × 0.6 = 0.6 (60%). The agreement probability p D is an example of the first probability. In addition, the agreement probability p P The value of p P = 0.1 × 0.7 + 0.6 × 0.8 + 0.2 × 0.4 + 0.1 × 0.2 = 0.65 (65%). The agreement probability p P is an example of the second probability.

[0075] In this case, the presentation function 132 determines, based on the first probability and the second probability, that the process performed by the MDT and the process performed by the doctor in charge of patient P should be presented in order to give priority to the process performed by the doctor in charge of patient P, and presents on the displays of the terminals 10 and 20 that it is better to give priority to the process performed by the doctor in charge of patient P. Specifically, the presentation function 132 performs the process described in the example shown in FIG.

[0076] (Third embodiment) In the medical support device 100 according to the third embodiment, the order in which the processes to be performed by the MDT and the processes to be performed by the doctor in charge of the patient P are presented is determined based on the agreement probability for each number of selections made from multiple treatment plans for the disease.

[0077] In the example shown in FIG. 10, the preference takes into account the probability of selection, and the tolerance takes into account whether it is acceptable or not. Here, for example, the probability (p i D ya p i P ) is equal to or greater than the threshold, the options are shaded in FIG. 10 to indicate that they are acceptable. The control function 131 calculates the agreement probability p D , and the agreement probability p that the MDT and patient P agree when two decisions are selected from patient P. P Calculate the consensus probability p D , p P are calculated by the following formulas (7) and (8), respectively.

[0078]

number

[0079]

number

[0080] In the example shown in FIG. 10, the number of choices is further considered when a conflict is expected (when the agreement probability is low). For example, it is assumed that the MDT can accept the option "SAVR" out of four options "SAVR", "TAVI", "medication", and "no treatment", and that the patient P can accept the option "medication" out of four options "SAVR", "TAVI", "medication", and "no treatment". Furthermore, in the example shown in FIG. 10, as in the first embodiment, the probabilities that the MDT will select the options "SAVR", "TAVI", "medication", and "no treatment" are respectively set as p1 D , p2D , p3 D , p4 D The probability that patient P chooses the options "SAVR", "TAVI", "medication", and "no treatment" is expressed as p1 P , p2 P , p3 P , p4 P It is expressed as follows.

[0081] For example, probability p1 D , p2 D , p3 D , p4 D are "0.5", "0.3", "0.1", and "0.1", respectively, and the probability p1 P , p2 P , p3 P , p4 P are respectively "0.3", "0.1", "0.5", and "0.1". Here, when the control function 131 uses the above-mentioned formulas (3) and (4), the agreement probability p D is "0.1", and the agreement probability p P Therefore, since the agreement probability is low, for example, the control function 131 sets the agreement probability p D , and the agreement probability p that the MDT and patient P agree when two decisions are selected from patient P. P Calculate.

[0082] In Equations (7) and (8), a is set to 0.4. Therefore, the agreement probability p D The value of p D =0.5×(0.1 / (1-0.5))×1)+0.3×(0.1 / (1-0.3))×1+0.1×1+0.1×(0.1 / (1-0.1))×1)=0.254 (25.4%). D is an example of the first probability. Also, the agreement probability pP The value of p P =0.3×1+0.1×(0.3 / (1-0.1))×1)+0.1×(0.3 / (1-0.1))×1+0.5×(0.3 / (1-0.5))×1)+0.1×(0.3 / (1-0.1))×1)=0.667(66.7%). The agreement probability p P is an example of the second probability.

[0083] In this case, based on the first probability and the second probability for each selection number, the presentation function 132 determines the order in which to present the processing performed by the MDT and the processing performed by the doctor in charge of patient P, giving priority to the processing performed by the doctor in charge of patient P, and presents on the display of terminals 10 and 20 that it is better to give priority to the processing performed by the doctor in charge of patient P.

[0084] For example, Fig. 11 shows an example of a screen presented to the MDT and the doctor in charge of patient P when two processes to be performed by the MDT are selected. In the example shown in Fig. 11, for patient P with patient ID "000002", the predicted result of patient P's intention "SAVR" and the predicted result of MDT's intention "TAVI" do not match, so the process of step S207, for example, is recommended. In this case, the screen displays a recommended action "MDT Alternative Consideration (2)" that indicates the proposal of two alternative treatments as the recommended process to be performed by the MDT, in association with patient ID "000002".

[0085] (Fourth embodiment) In the medical support device 100 according to the fourth embodiment, as shown in FIGS. 12A and 12B, the probability of selection is taken into consideration for the preference, and the conditional selection probability is used as the acceptable probability for the tolerance range.

[0086] In this case, the control function 131 determines the agreement probability p D , and the agreement probability p , where the MDT and patient P agree when a decision is made by patient P. P Calculate the consensus probability p D , p Pare calculated by the following formulas (9) and (10), respectively.

[0087]

number

[0088]

number

[0089] In the examples shown in Figures 12A and 12B, the tolerance range is predicted using conditional probability. In the examples shown in Figures 12A and 12B, "Treatment A," "Treatment B," and "Treatment C" correspond to the above-mentioned "SAVR," "TAVI," and "medication," respectively. For example, the probability p D (i) are respectively "0.1", "0.2", and "0.7". Also, before the presentation, the probability that patient P will select "Treatment A", "Treatment B", or "Treatment C" is p P (i) is "0.3", "0.6", and "0.1" respectively.

[0090] In addition, the conditional choice probability p i D (j) is the probability that the MDT can accept "Treatment A," "Treatment B," and "Treatment C," which are set to "0.6," "0.1," and "0.3," respectively. Also, the conditional choice probability p i D (j) is the probability that the MDT can accept "Treatment A," "Treatment B," and "Treatment C," and is set to "0.2," "0.2," and "0.6," respectively. Also, the conditional choice probability p i D(j) is the probability that "Treatment A," "Treatment B," and "Treatment C" are acceptable to the MDT, and are set to "0.2," "0.0," and "0.8," respectively.

[0091] Furthermore, the conditional choice probability p for patient P to choose "Treatment A," "Treatment B," or "Treatment C" after "Treatment A" is presented by the MDT is i P (j) is the probability that patient P can accept "Treatment A," "Treatment B," and "Treatment C," and is set to "0.2," "0.6," and "0.2," respectively. Also, the conditional choice probability p i P (j) is the probability that patient P can accept "Treatment A," "Treatment B," and "Treatment C," and is set to "0.2," "0.8," and "0.0," respectively. In addition, the conditional choice probability p i P (j) represents the probability that patient P can tolerate "Treatment A," "Treatment B," and "Treatment C," and is set to "0.4," "0.6," and "0.0," respectively.

[0092] In addition, in equations (9) and (10), i represents an integer from 1 to 3, and i = 1, 2, and 3 correspond to "treatment A," "treatment B," and "treatment C," respectively. The conditional selection probability p D (i), p i D (j) can be obtained by statistically processing the second information mentioned above. Alternatively, the conditional selection probability p D (i), p i D (j) is obtained by inputting the second information described above into the trained model obtained by machine learning. Also, the conditional selection probability p P (i), p i P (j) can be obtained by statistically processing the first information described above. Alternatively, the conditional selection probability p P (i), p i P(j) is obtained by inputting the first information described above into a trained model obtained by machine learning.

[0093] Therefore, the probability of agreement between the MDT and patient P when a decision is made from the MDT is p D The value of p D = 0.1 × 0.2 + 0.2 × 0.8 + 0.7 × 0.0 = 0.18 (18%). The agreement probability p D is an example of the first probability. In addition, the agreement probability p P The value of p P = 0.3 × 0.6 + 0.6 × 0.2 + 0.1 × 0.8 = 0.38 (38%). The agreement probability p P is an example of the second probability. In Figures 12A and 12B, the conditional selection probabilities used in equations (9) and (10) are indicated by shading.

[0094] In this case, the presentation function 132 determines, based on the first probability and the second probability, that the process performed by the MDT and the process performed by the doctor in charge of patient P should be presented in order to give priority to the process performed by the doctor in charge of patient P, and presents on the displays of the terminals 10 and 20 that it is better to give priority to the process performed by the doctor in charge of patient P. Specifically, the presentation function 132 performs the process described in the example shown in FIG.

[0095] In addition, in the medical support device 100 according to the fourth embodiment, as in the third embodiment, the order in which the processing performed by the MDT and the processing performed by the doctor in charge of patient P are presented may be determined based on the agreement probability for each number of selections from multiple treatment plans for the disease.

[0096] In this case, the control function 131 determines the agreement probability p D , and the agreement probability p that the MDT and patient P agree when two decisions are selected from patient P. P Calculate the consensus probability p D , p Pare calculated by the following formulas (11) and (12), respectively.

[0097]

number

[0098]

number

[0099] 12A and 12B, if a collision is expected (if the agreement probability is low), the number of selections may be further considered. When the number of selections is further considered, all conditional selection probabilities are used regardless of whether or not the selections are shaded in FIGS. 12A and 12B.

[0100] Therefore, the probability of agreement between the MDT and patient P when two decisions are selected from the MDT is p D The value of p D =0.1×(0.2 / (1-0.1))×(0.2+0.2)+0.1×(0.7 / (1-0.1))×(0.2+0.4)+ =0.4(40%). The agreement probability p D is an example of the first probability. Also, the agreement probability p P The value of p P =0.3×(0.6 / (1-0.3))×(0.6+0.1)+0.3×(0.1 / (1-0.3))×(0.6+0.2)+ =0.585(58.5%). The agreement probability p P is an example of the second probability. In this case, based on the first probability and the second probability, the presentation function 132 determines that the priority should be given to the process performed by the doctor in charge of patient P as the order of presentation of the process performed by the MDT and the process performed by the doctor in charge of patient P, and presents on the displays of the terminals 10 and 20 that it is better to give priority to the process performed by the doctor in charge of patient P.

[0101] (Other embodiments) Up to this point, the first to fourth embodiments have been described, but the present invention may be implemented in various different forms other than the above-described first to fourth embodiments.

[0102] For example, as described above, the decision-making of patient P and the decision-making of the MDT are made in different places and at different times. Therefore, as a variation of this embodiment, the control function 131 may predict the intentions of two of at least three or more decision makers, including the MDT and patient P, and the presentation function 132 may present the predicted results of the two.

[0103] In this case, the control function 131 predicts the intentions of the patient P or a subject who is related to the patient P, and the intentions of the MDT that determines the treatment policy for the patient P, regarding the treatment policy for the patient P's disease, and the presentation function 132 presents information based on the results predicted by the control function 131 to the MDT and the subject. Here, examples of related persons include the patient P's relatives, and examples of the patient P's relatives include the patient P's father, mother, brothers, sisters, grandparents, spouse, children, etc. For example, the patient P's intentions may be the result of consultation with the patient's doctor or the result of consultation with the patient P's relatives, and these results are included to be the patient P's intentions.

[0104] For example, as shown in FIG. 13A, in process A, the control function 131 selects three individuals, namely, the MDT, patient P, and patient P's mother, from among the MDT, patient P, and patient P's relatives. Next, in process B, the control function 131 selects two individuals, namely, the MDT and patient P, from among the three individuals, namely, the MDT, patient P, and patient P's mother. Next, in process C, the control function 131 predicts the intentions of both the MDT and patient P, and the presentation function 132 presents information based on the results of the prediction by the control function 131 to both the MDT and patient P. Then, the MDT and patient P agree on the treatment policy.

[0105] 13B, in process A, the control function 131 selects two parties, the MDT and patient P's spouse, from among the MDT, patient P, and patient P's relatives. Next, in process B, the control function 131 predicts the MDT's intention, and in process C, it predicts the intention of patient P's spouse as patient P's intention, and the presentation function 132 presents information based on the results predicted by the control function 131 to the MDT and patient P's spouse. Then, the MDT and patient P's spouse agree on the treatment policy.

[0106] Here, in a modified example, when predictions are presented by two different parties, the number of treatment plans to be selected may be changed, as in the third and fourth embodiments.

[0107] Furthermore, as a modification of this embodiment, the presentation function 132 may present information based on the results predicted by the control function 131 only to the MDT.

[0108] For example, when information based on the results predicted by the control function 131 is presented on the display of the MDT's terminal 20, the MDT communicates the information directly to the patient P, or the MDT communicates the information to the patient P via the patient's doctor, as communication between the MDT and the patient P. Specifically, the screen displayed on the display of the MDT's terminal 20 displays a recommended action, "The doctor in charge will understand the patient's wishes," associated with the patient's patient ID as a recommended process to be carried out by the MDT. In this case, the MDT communicates information based on the results predicted by the control function 131 to the patient in charge, and the doctor in charge, who has received the information, meets with the patient P to understand the patient P's wishes.

[0109] For example, as a modified example of this embodiment, the presentation function 132 may present information based on the results predicted by the control function 131 only to the above-mentioned target person, without the intervention of the doctor in charge of the patient P. Specifically, the presentation function 132 presents information based on the results predicted by the control function 131 only to the patient P or related persons related to the patient P (relatives of the patient P).

[0110] For example, when information based on the results predicted by the control function 131 is presented on the display of the patient P's terminal, the MDT and patient P communicate on the system. Specifically, the screen displayed on the display of the patient P's terminal displays a recommended action "understand intention" in association with the patient's patient ID as a recommended process to be performed by the patient P. Here, when the patient P inputs the intention of the patient P using the patient P's terminal, the presentation function 132 presents the next recommended process to the MDT. Specifically, the screen displayed on the display of the MDT's terminal 20 displays a recommended action "MDT policy decision," which indicates a treatment policy decision, in association with the patient's patient ID as a recommended process to be performed by the MDT. The MDT then decides on a treatment policy.

[0111] In this way, in the medical support device 100 of the modified example, whether the information based on the prediction results of the control function 131 is presented only to the MDT or only to the subject, reconsideration of the treatment plan can be avoided by communicating between the MDT and the patient P. Therefore, even in the medical support device 100 of the modified example, the MDT can provide treatment according to a treatment plan that satisfies the patient P. Furthermore, in the medical support device 100 of the modified example, repeated discussions at the MDT can be avoided, thereby reducing the burden on decision-making.

[0112] Furthermore, in the first embodiment, the presentation function 132 presents the collision risk as information regarding the degree of agreement between the will of the patient P predicted by the control function 131 and the will of the MDT, but this is not limited to this. For example, in a modified example of this embodiment, the presentation function 132 may present the collision risk as information regarding the degree of agreement between the will of the subject (patient P or an associated person related to the patient P) predicted by the control function 131 and the will of the MDT.

[0113] Furthermore, in the first embodiment, the control function 131 predicts the will of the patient P and the will of the MDT based on first information regarding the decision-making made by the patient P (information regarding the trend of the treatment plan desired by the patient P) and second information regarding the decision-making made by the MDT (information regarding the trend of the treatment plan proposed by a specialist such as the MDT), but is not limited to this. For example, in a modification of this embodiment, the control function 131 may predict the will of the subject (patient P or a related person related to the patient P) and the will of the MDT based on first information regarding the decision-making made by the subject (patient P or a related person related to the patient P) and second information regarding the decision-making made by the MDT.

[0114] Furthermore, in the first embodiment, the control function 131 derives an agreement probability that the MDT and the patient P will agree on each of the multiple treatment plans for the disease based on the patient P's preference for each of the multiple treatment plans for the disease obtained from the first information and the MDT's preference for each of the multiple treatment plans for the disease obtained from the second information, and the presentation function 132 presents information corresponding to the value of the agreement probability derived by the control function 131, but is not limited to this. For example, in a modified example of this embodiment, the control function 131 may derive an agreement probability that the MDT and the subject will agree on each of the multiple treatment plans for the disease based on the subject's (patient P or a related person related to the patient P) preference for each of the multiple treatment plans for the disease obtained from the first information and the MDT's preference for each of the multiple treatment plans for the disease obtained from the second information, and the presentation function 132 may present information corresponding to the value of the agreement probability derived by the control function 131.

[0115] Furthermore, in the first embodiment, when the control function 131 makes predictions for multiple patients P, the presentation function 132 displays a list of information based on the results predicted by the control function 131 for each of the multiple patients P, but is not limited to this. For example, in a modified example of this embodiment, when the control function 131 makes predictions for multiple subjects, the presentation function 132 may display a list of information based on the results predicted by the control function 131 for each of the multiple subjects (patient P or associated persons related to the patient P).

[0116] Furthermore, in the first embodiment, when displaying a list, the presentation function 132 changes the order of the patient P to be displayed depending on the degree of agreement between the intention of the patient P predicted by the control function 131 and the intention of the MDT, but is not limited to this. For example, in a modified example of this embodiment, when displaying a list, the presentation function 132 may change the order of the subjects to be displayed depending on the degree of agreement between the intention of the subject (patient P or a related person related to the patient P) predicted by the control function 131 and the intention of the MDT.

[0117] Furthermore, in the first embodiment, when displaying a list, the presentation function 132 changes the order of the patients P to be displayed according to the urgency of the treatment plan that the control function 131 predicts from the first information that the MDT is likely to select, but is not limited to this. For example, in a modified example of this embodiment, when displaying a list, the presentation function 132 may change the order of the subjects (patients P or associated persons related to the patient P) to be displayed according to the urgency of the treatment plan that the control function 131 predicts from the first information that the MDT is likely to select.

[0118] Furthermore, in the first embodiment, the control function 131 predicts the intention of the patient P and the intention of the MDT by excluding a treatment plan that is inappropriate for the patient P from among the treatment plans that the MDT may select from the first information, but is not limited to this. For example, in a modified example of this embodiment, the control function 131 may predict the intention of the subject (patient P or a related person related to the patient P) by excluding a treatment plan that is inappropriate for the subject (patient P or a related person related to the patient P) from among the treatment plans that the MDT may select from the first information.

[0119] Furthermore, in the first embodiment, the memory circuitry 120 stores processing information indicating the procedure of processing from when the control function 131 predicts the intentions of the MDT and the patient P until the MDT and the patient P agree on a treatment plan, and when the intentions of the MDT predicted by the control function 131 do not match the intentions of the patient P, the presentation function 132 presents recommended processing to be performed by at least one of the MDT and the doctor in charge of the patient P based on the processing information. Here, the presentation function 132 displays the recommended processing together with information based on the results predicted by the control function 131. Furthermore, when the presentation function 132 receives information indicating that the currently presented recommended processing has been executed, it presents the next recommended processing based on the processing information. However, this is not limited to this. For example, in a modified example of this embodiment, the memory circuitry 120 stores processing information representing the processing steps from when the control function 131 predicts the intentions of the MDT and the subject (patient P or a related person related to the patient P) to when the MDT and the subject agree on a treatment plan, and the presentation function 132 may present recommended processing to be carried out by at least one of the MDT and the doctor in charge of patient P based on the processing information if the intentions of the MDT predicted by the control function 131 do not match the intentions of the subject.

[0120] Furthermore, in the second and fourth embodiments, the control function 131 derives a first probability (agreement probability) that the MDT and the patient P will agree when a decision is made from the MDT, and a second probability (agreement probability) that the MDT and the patient P will agree when a decision is made from the patient P, based on the patient P's preference and tolerance range for each of a plurality of treatment plans for the disease obtained from the first information and the MDT's preference and tolerance range for each of a plurality of treatment plans for the disease obtained from the second information, and the presentation function 132 determines the order in which to present the processing to be performed by the MDT and the processing to be performed by the doctor in charge of the patient P, based on the first probability and the second probability. However, the present invention is not limited to this. For example, in a modified example of this embodiment, the control function 131 derives a first probability (agreement probability) that the MDT and the subject will agree when a decision is made from the MDT, and a second probability (agreement probability) that the MDT and the subject will agree when a decision is made from the subject, based on the preferences and tolerance range of the subject (patient P or a related person related to the patient P) for each of multiple treatment plans for the disease obtained from the first information, and the preferences and tolerance range of the MDT for each of multiple treatment plans for the disease obtained from the second information, and the presentation function 132 may determine the order in which to present the processing performed by the MDT and the processing performed by the doctor in charge of patient P, based on the first probability and the second probability.

[0121] Furthermore, in the third and fourth embodiments, the control function 131 derives a first probability and a second probability for each number of selections selected from a plurality of treatment plans for a disease, and the presentation function 132 determines, based on the first probability and the second probability for each number of selections, the order in which the number of treatment plans selected by the MDT and patient P, the processing performed by the MDT, and the processing performed by the doctor in charge of patient P are presented, but is not limited to this. For example, in a modified example of this embodiment, the control function 131 may derive a first probability and a second probability for each number of selections selected from a plurality of treatment plans for a disease, and the presentation function 132 may determine, based on the first probability and the second probability for each number of selections, the order in which the number of treatment plans selected by the MDT and the subject (patient P or a related person related to patient P) are presented, the processing performed by the MDT, and the processing performed by the doctor in charge of patient P are presented.

[0122] Note that the components of each device illustrated in the present embodiment are functional concepts and do not necessarily have to be physically configured as illustrated. In other words, the specific form of distribution and integration of each device is not limited to that illustrated, and all or part of them can be functionally or physically distributed and integrated in any unit depending on various loads, usage conditions, etc. Furthermore, all or any part of the processing functions performed by each device can be realized by a CPU and a program analyzed and executed by the CPU, or can be realized as hardware using wired logic.

[0123] The method described in this embodiment can be realized by executing a prepared program on a computer such as a personal computer or a workstation. This program can be distributed via a network such as the Internet. This program can also be recorded on a non-transitory computer-readable recording medium such as a hard disk, flexible disk (FD), CD-ROM, MO, or DVD, and executed by being read from the recording medium by a computer.

[0124] According to at least one of the embodiments described above, it is possible to reduce the burden of decision-making and avoid having to reconsider the treatment plan.

[0125] 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]

[0126] 100 Medical support equipment 131 Control Functions 132 Prompt Function

Claims

1. A prediction unit that predicts the intention of a prediction target patient and the intention of a prediction target doctor who is a doctor who decides the treatment policy for a target disease that the prediction target patient has; a presentation unit that presents information based on the result of the prediction by the prediction unit to at least one of the patient to be predicted, a person related to the patient to be predicted, and the doctor to be predicted; Equipped with The prediction unit obtaining first information on decision-making regarding the target disease made by the prediction target patient or a patient with the same attributes as the prediction target patient from information on trends in treatment plans desired by patients for each disease; obtaining second information on decision-making regarding a disease made by the prediction target doctor or a doctor with the same attributes as the prediction target doctor from information on trends in treatment policies proposed by doctors for each disease; predicting the intention of the prediction target patient and the intention of the prediction target doctor based on the first information and the second information; Medical support equipment.

2. The presentation unit presents information regarding the degree of agreement between the intention of the patient to be predicted predicted by the prediction unit and the intention of the doctor to be predicted. The medical support device according to claim 1.

3. The prediction unit derives an agreement probability that the prediction target doctor and the prediction target patient will agree on each of a plurality of treatment plans for the disease based on a preference of the prediction target patient for each of a plurality of treatment plans for the disease obtained from the first information and a preference of the prediction target doctor for each of a plurality of treatment plans for the disease obtained from the second information, The presentation unit presents information according to the value of the agreement probability derived by the prediction unit. The medical support device according to claim 1.

4. When the prediction unit performs prediction for a plurality of the prediction target patients, the presentation unit displays a list of information based on the results of prediction by the prediction unit for each of the plurality of prediction target patients. The medical support device according to any one of claims 1 to 3.

5. When performing the list display, the presenting unit changes the order of the prediction target patients to be displayed according to a degree of agreement between the intention of the prediction target patient predicted by the prediction unit and the intention of the prediction target doctor. The medical support device according to claim 4.

6. When performing the list display, the presenting unit changes the order of the prediction target patients to be displayed according to the urgency of the treatment plan that the prediction unit predicts from the first information as being highly likely to be selected by the prediction target doctor. The medical support device according to claim 4.

7. The prediction unit performs the prediction by excluding a treatment plan that is inappropriate for the patient to be predicted from among treatment plans that the doctor to be predicted may select based on the first information. The medical support device according to any one of claims 1 to 6.

8. The presentation unit further presents information based on the result of the prediction by the prediction unit to a doctor in charge of the patient to be predicted. The medical support device according to any one of claims 1 to 7.

9. Further provided is a storage unit that stores processing information representing a processing procedure from when the prediction unit predicts the intention of the prediction target doctor and the intention of the prediction target patient to when the prediction target doctor and the prediction target patient agree on a treatment policy, the presentation unit presents, based on the processing information, a recommended process to be performed by at least one of the doctor to be predicted and the doctor in charge of the patient to be predicted, when the intention of the doctor to be predicted predicted by the prediction unit does not match the intention of the patient to be predicted. The medical support device according to any one of claims 1 to 8.

10. the presentation unit displays the recommended process together with information based on the result predicted by the prediction unit. The medical support device according to claim 9.

11. When the presentation unit receives information indicating that the currently presented recommended process has been executed, the presentation unit presents the next recommended process based on the process information. The medical support device according to claim 9 or 10.

12. the prediction unit derives a first probability that the prediction target doctor and the prediction target patient will agree when a decision is made from the prediction target doctor, and a second probability that the prediction target doctor and the prediction target patient will agree when a decision is made from the prediction target patient, based on the preferences and tolerance ranges of the prediction target patient for each of a plurality of treatment plans for the disease obtained from the first information and the preferences and tolerance ranges of the prediction target doctor for each of a plurality of treatment plans for the disease obtained from the second information; the presentation unit determines an order in which to present the process performed by the doctor who is the prediction target and the process performed by the doctor in charge of the patient who is the prediction target, based on the first probability and the second probability. The medical support device according to any one of claims 1, 3 and 7.

13. the prediction unit derives the first probability and the second probability for each selection number selected from a plurality of treatment policies for the disease; the presentation unit determines an order in which to present the number of treatment plans selected by the doctor to be predicted and the patient to be predicted, the processes to be performed by the doctor to be predicted, and the processes to be performed by the attending doctor, based on the first probability and the second probability for each of the selection numbers. The medical support device according to claim 12.

Images