Display method, information processing device, and display program

Abstract

In this display method, when one user among a plurality of users has been selected, a computer executes a process for acquiring route information and an index value related to the user from a storage unit, and displaying, on the basis of the acquired route information, the index value of the user and a path in which the route of the user is emphasized on a screen.

Description

Display method, information processing device, and display program

[0001] The present invention relates to a display method, an information processing device, and a display program.

[0002] One type of workflow is the policy flow graph, which diagrams the process of assigning policy target objects, such as users, to services to achieve the policy's objectives in various fields such as medical care, nursing care, and administration.

[0003] As one technology for supporting the evaluation of such measures, the following health care data analysis system has been proposed. For example, the health care data analysis system calculates vector information from nationwide (first population) health care data, and generates model information (prediction model) from this vector information and the vector information of health care data on measures implemented in a specific region (second population) and measures implemented in that region. By applying health care data from another region (third population) to this model information, it becomes possible to predict the effects of measures implemented in a specific region (second population) when implemented in another region (third population), thereby supporting the creation of new health care (medical care, medical checkups, or nursing care) measures.

[0004] Japanese Patent Application Laid-Open No. 2021-089523

[0005] However, conventional technologies such as the above-mentioned health insurance data analysis system only predict the overall effect of a policy, and therefore are not necessarily effective in verifying the effectiveness of the policy.

[0006] In other words, the service route to which a user is assigned in the policy flow graph changes depending on the conditional branching, and is not necessarily the same. For example, in the case of a policy in the medical field, the combination of individual medical institutions that collaborate as a patient moves from the acute phase through the recovery phase and back home depends on which medical institution the patient is assigned to based on the conditional branching of each medical function in the policy flow graph. As such, even if the overall effectiveness of the policy is presented, it is difficult to verify the effectiveness of the policy for a specific user, even though differences will appear in the combination of medical institutions that collaborate as the user changes.

[0007] In one aspect, the present invention aims to provide a display method, an information processing device, and a display program that can improve the visibility of service routes.

[0008] In one embodiment of the display method, when one user is selected from a plurality of users, the computer executes a process of obtaining an index value and route information for the user from a memory unit, and based on the obtained route information, displaying on the screen a path that highlights the user's route and the user's index value.

[0009] According to one embodiment, it is possible to improve the visibility of service routes.

[0010] FIG. 1 is a block diagram showing an example of the functional configuration of a server device. FIG. 2 is a diagram illustrating an example of a flow graph of a policy. FIG. 3 is a diagram illustrating a specific example of a flow graph of a policy. FIG. 4 is a diagram illustrating an example of medical institution list data. FIG. 5 is a diagram illustrating a detailed example of a medical institution list. FIG. 6 is a diagram (1) showing an example of a care pathway display. FIG. 7 is a diagram (2) showing an example of a care pathway display. FIG. 8 is a diagram (3) showing an example of a care pathway display. FIG. 9 is a diagram showing an example of a length of hospitalization graph. FIG. 10 is a diagram showing an example of a bed occupancy rate graph. FIG. 11 is a diagram showing an example of a care path selection screen. FIG. 12 is a diagram showing an example of a care path selection screen. FIG. 13 is a diagram (4) showing an example of a care pathway display. FIG. 14 is a diagram showing an example of a radar chart. FIG. 15 is a diagram (5) showing an example of a care pathway display. FIG. 16 is a diagram (6) showing an example of a care pathway display. FIG. 17 is a diagram showing an example of a radar chart. FIG. 18 is a diagram (7) showing an example of a care pathway display. Fig. 19 is a diagram showing an example of a radar chart. Fig. 20 is a schematic diagram showing an example of a care path prediction model. Fig. 21 is a schematic diagram showing an example of an index value prediction model. Fig. 22 is a diagram (8) showing an example of a care pathway display. Fig. 23 is a diagram showing an example of a radar chart. Fig. 24 is a flowchart showing the steps of a generation process. Fig. 25 is a flowchart showing the steps of a calculation process. Fig. 26 is a diagram showing an example of a hardware configuration.

[0011] Hereinafter, a description will be given of a display method, an information processing device, and a display program (hereinafter referred to as "embodiments") according to the present application with reference to the accompanying drawings. Each embodiment merely illustrates examples and aspects, and does not limit the range of values, functions, or usage scenarios. Each embodiment can be adaptively combined within a range that does not cause inconsistencies in the processing content.

[0012] <First Embodiment> <System Configuration> Fig. 1 is a block diagram showing an example of the functional configuration of a server device 10. The server device 10 shown in Fig. 1 provides a data-based platform that enables sharing, cross-referencing, and updating of policy flow data.

[0013] For example, the server device 10 can provide the functions of the data infrastructure platform as a cloud service by executing PaaS (Platform as a Service) type middleware or SaaS (Software as a Service) type applications.

[0014] As shown in Fig. 1, the server device 10 can be communicatively connected to a client terminal 30 via a network NW. For example, the network NW may be any type of communication network, whether wired or wireless, such as the Internet or a local area network (LAN). Note that Fig. 1 shows an example in which one client terminal 30 is connected to one server device 10, but any number of client terminals 30 may be connected.

[0015] The client terminal 30 is a terminal device that receives the above-mentioned data infrastructure. For example, the client terminal 30 may be used by a policy planner, such as a local government or an insurer, as an example of a party involved in implementing a policy. Furthermore, the client terminal 30 may be used by a medical institution such as a clinic or hospital as an example of a provider of a service specified in the policy, or by residents as an example of a beneficiary of the service. Note that the client terminal 30 may be realized by any computer, such as a personal computer, a smartphone, a tablet terminal, or a wearable terminal, as an example.

[0016] <Flow Graph of Policy> An example of a flow graph of the above policy is shown in Figure 2. Figure 2 is a diagram illustrating an example of a flow graph of a policy. Z1, Z2, Z3, and Z4 in Figure 2 indicate, for example, services that an administrator provides to a user. These may also be referred to as "service implementation components." Specific examples of services include, in the medical field, "interventions" to which the target object of the policy, such as a resident, is assigned, such as undergoing a health checkup or being examined by a specialist, as well as "no intervention" such as follow-up observation, but are not limited to policies in the medical field.

[0017] H1 and H2 indicate, for example, conditional branches including conditions. These may also be referred to as "conditional branch components." Specific examples of conditions, in the medical field, include an estimated glomerular filtration rate (eGFR) below a threshold, a hemoglobin A1c value (HbA1c) below a threshold, and a urinary protein value equal to or greater than a threshold, but are not limited to conditions in the medical field.

[0018] Z1, Z2, Z3, Z4, H1, and H2 may each be referred to as a "component." From the perspective of graph data, such a "component" may correspond to an example of a "node." Furthermore, the connection between nodes may correspond to an example of an "edge," including a "directed edge."

[0019] In this embodiment, policy planning in the medical field will be described as an example, but the present invention is not limited to this. The above-described embodiment may be used for various policy planning such as work with conditional branching, tests, and questionnaires. In this case, the same effects as those of the above-described embodiment can be obtained.

[0020] Figure 3 shows a specific example of a policy flow graph. As shown in Figure 3, a policy is modeled as a workflow consisting of a combination of components such as conditional branching and service implementation. Then, the number of people receiving each service is output from a model that has been trained by accumulating information and parameters on the flow of people based on the actual values ​​when each conditional branching component is used.

[0021] In the example shown in FIG. 3 , the number of people N=1000 is input at S0. At S1, component #1 as service execution component A is set to "health check." At S2, component #2 as conditional branch component B is set to "eGFR<α." If "eGFR<α" is not satisfied (see the NO route at S2), it is determined that "no intervention" by a specialist is required for the citizen, as shown at S5.

[0022] On the other hand, if "eGFR<α" is satisfied (see the YES route at S2), then component #3 as conditional branch component C is set to "HbA1c<β" as shown at S3. If "HbA1c<β" is satisfied (see the YES route at S3), then component #4 as conditional branch component D is set to "nephrologist" as shown at S6, and it is determined that the citizen requires intervention by a "nephrologist." On the other hand, if "HbA1c<β" is not satisfied (see the NO route at S3), then it is determined that the citizen requires intervention by a "diabetes specialist" as shown at S7.

[0023] In the example shown in Figure 3, the number of people who will flow through part #1, part #2, part #3, and part #4 in that order is predicted, as indicated by the arrows. For example, in the policy flow graph shown in Figure 3, the results of assigning the number of people N = 1000 to interventions Z2 to Z4 are as follows: 50 people are assigned to intervention Z2. 150 people are assigned to intervention Z3. Furthermore, 800 people are assigned to intervention Z4.

[0024] Hereinafter, the flow graphs of measures exemplified in FIG. 2 and FIG. 3 may be abbreviated as "measure flow."

[0025] <Data Infrastructure> In the above data infrastructure, policy flows may be shared in any framework. As just one example, the above data infrastructure allows policy flows to be shared among organizations around the world, for example, public organizations such as local governments.

[0026] A planner can refer to templates of existing plans from around the world collected in the data base via the client terminal 30. For example, the planner can update the original plan by incorporating all or part of an existing plan similar to the original plan from the templates collected in the data base.

[0027] Thus, when drafting a policy, it is important to consider whether similar policies have been implemented in the past, from the perspective of administrative (political) ease of implementation. For this reason, it is becoming increasingly important to compare the flow graph of the proposed policy with the flow graph of existing policies that serve as reference.

[0028] <Configuration of Server Device 10> Fig. 1 shows a schematic diagram of blocks related to the data infrastructure of the server device 10. As shown in Fig. 1, the server device 10 has a communication control unit 11, a storage unit 13, and a control unit 15. Note that Fig. 1 only shows a selection of functional units related to the data infrastructure, and the server device 10 may also be provided with functional units other than those shown.

[0029] The communication control unit 11 is a functional unit that controls communication with other devices such as the client terminal 30. As just one example, the communication control unit 11 can be realized by a network interface card such as a LAN card. In one aspect, the communication control unit 11 receives various requests from the client terminal 30 and outputs responses to the requests to the client terminal 30.

[0030] The storage unit 13 is a functional unit that stores various types of data. As just one example, the storage unit 13 is realized by internal, external, or auxiliary storage of the server device 10. For example, the storage unit 13 stores a medical database (DB) 13A and a policy DB 13B. The medical DB 13A and the policy DB will be described together with the scenes in which the medical DB 13A and the policy DB are referenced, created, or registered.

[0031] The control unit 15 is a functional unit that performs overall control of the server device 10. For example, the control unit 15 can be realized by a hardware processor. Alternatively, the control unit 15 can be realized by hardwired logic. As shown in FIG. 1 , the control unit 15 includes a receiving unit 15A, a generating unit 15B, a calculating unit 15C, and a display unit 15D.

[0032] The reception unit 15A is a processing unit that receives various requests from the client terminal 30. In one aspect, the reception unit 15A can receive a request to display a care pathway from the client terminal 30. The term "care pathway" used here refers to a path that indicates the route through medical institutions when multiple users use medical services corresponding to each medical function.

[0033] When receiving such a display request, the reception unit 15A can accept a specification of the data range to be used in generating the care pathway. Examples of items related to the data range include "patient's residential area," "period," "disease," and "hospital." Examples of "patient's residential area" include a primary medical area, such as a municipality, a secondary medical area, or a tertiary medical area, which is a collection of multiple municipalities. Examples of "period" include one or more fiscal years or years, two start and end points, or either a start or end point and a duration. Examples of "disease" include any disease, such as acute myocardial infarction or cerebral infarction. Examples of "hospital" include the name and identification information of individual medical institutions. While the example above illustrates a user-defined data range, this does not necessarily have to be user-defined; the data range may be system-defined.

[0034] The generator 15B is a processing unit that generates the above-mentioned care pathway using the medical DB 13A. The medical DB 13A can store any collection of medical data. For example, the medical data may be medical checkups, medical insurance claims, electronic medical records, etc. Furthermore, the medical DB 13A may be realized by DPC (Diagnosis Procedure Combination) data, a database of medical insurance claim information and specific medical checkup information, known as the National DateBase (NDB), a National Health Insurance database, known as the KDB, etc.

[0035] The following is merely an example in which medical DB 13A is realized by DPC data, but as mentioned above, this does not prevent it from being realized by other databases such as NDB, KDB, or DBs used by electronic medical record systems.

[0036] As an example, the generation unit 15B extracts, from the medical data stored in the medical DB 13A, medical data that corresponds to the data range for which the specification has been accepted by the acceptance unit 15A. For example, the generation unit 15B extracts, from the medical data stored in the medical DB 13A, medical data that satisfies the AND condition for the specifications of the items "patient's residential area," "period," "disease," and "hospital."

[0037] Next, the generation unit 15B executes the following process a number of times corresponding to the number I of patients included in the medical data corresponding to the above data range. At this time, since different personal IDs (IDentifications) may be assigned to the same user in the DPC data at different hospitals, the generation unit 15B can identify multiple personal IDs for one user as the same person. Such identification can be achieved by comparing values ​​of personal information items, such as place of residence, gender, and date of birth, included in the DPC data.

[0038] That is, the generation unit 15B lists the medical institutions from which the i-th patient will use medical services corresponding to each medical function, such as highly acute, acute, recovery, or maintenance. Hereinafter, a list of medical institutions by medical function may be referred to as a "medical institution list." When generating such a list of medical institutions, the medical functions are identified from the medical treatment history included in the medical data of the i-th patient. At this time, since one hospital may provide medical services corresponding to multiple medical functions, each element of the medical institution included in the medical institution list is identified by a combination of medical function and hospital. Then, the generation unit 15B sorts the medical institutions included in the medical institution list in chronological order.

[0039] FIG. 4 is a diagram showing an example of medical institution list data. FIG. 4 shows medical institution list data including a list of I medical institutions. As shown in FIG. 4, the medical institution list data may be data in which a number identifying the medical institution list, a patient ID identifying the patient, and a medical institution list are associated with each other. For example, FIG. 4 shows excerpts of the medical institution lists for patient ID "0001" and patient ID "0002." Of these, the details of the medical institution list for patient ID "0001" are as shown in FIG. 5.

[0040] FIG. 5 is a diagram showing a detailed example of a medical institution list. As shown in FIG. 5, the medical institution list may be data in which, for each medical institution, items such as the start date and time of admission (visit) when medical services begin, the end date and time of admission (visit) when medical services end, costs, and other information are associated. For example, in the example of the entry in the first line, it can be determined that a patient identified by patient ID "0001" received medical services corresponding to a highly acute phase at Hospital B on January 15, 2015. Furthermore, in the example of the entry in the second line, it can be determined that a patient identified by patient ID "0001" received medical services corresponding to an acute phase at Hospital B and was hospitalized at Hospital B from January 15, 2015 to January 21, 2015.

[0041] After such a list of medical institutions has been generated, the generation unit 15B performs the following process for each of the J medical institutions included in the medical institution list for the i-th patient. Specifically, the generation unit 15B determines whether a node corresponding to the j-th medical institution among the J medical institutions included in the medical institution list for the i-th patient has not yet been generated on the care pathway being generated. If a node corresponding to the j-th medical institution has not yet been generated, the generation unit 15B adds a node corresponding to the j-th medical institution to the care pathway being generated. When adding a new node in this way, the generation unit 15B can sort the medical institutions by medical function on the care pathway. As an example, if the medical function classifications are sorted row-wise, the generation unit 15B can place medical institutions corresponding to the same medical function in the same column.

[0042] The generation unit 15B then determines whether an edge has not yet been generated between the jth medical institution node and the j-1th medical institution node in the care pathway being generated. At this time, if an edge has not yet been generated between the jth medical institution node and the j-1th medical institution node, the generation unit 15B adds an edge between the jth medical institution node and the j-1th medical institution node. Furthermore, the generation unit 15B increments the number of paths of the edge connecting the jth medical institution node and the j-1th medical institution node, i.e., the number of patients, by one.

[0043] In this way, a care path for the i-th patient is generated by attempting to add nodes and edges for each of the J medical institutions included in the medical institution list for the i-th patient. Furthermore, a care path for the medical institution list generated for each I patient is generated, thereby generating a care pathway that combines the care paths for I patients.

[0044] The calculation unit 15C is a processing unit that calculates index values ​​for any evaluation item, such as the length of hospital stay (number of hospitalization days), bed occupancy rate, BI (Barthel Index) score difference, resource usage rate, and medical expenses.

[0045] As an example, the calculation unit 15C calculates an index value for each of K evaluation items in the smallest unit corresponding to the evaluation item. That is, the calculation unit 15C calculates an index value for the mth smallest unit related to the kth evaluation item.

[0046] Among the above evaluation items, the length of hospital stay, BI score difference, and medical expenses can have unique index values ​​for each medical institution and patient. Therefore, the smallest unit is the combination of a "node" of a medical institution included in the care pathway and a "patient" passing through the node of the medical institution. For example, in the case of the length of hospital stay, the list of medical institutions for the patient to be calculated from the list of I medical institutions is targeted, and the difference between the start date and time of admission and the end date and time of admission for the medical institution to be calculated from the list of medical institutions for that patient is calculated as the length of hospital stay. In the case of the BI score difference, the difference between the BI score at the start date and time of admission and the BI score at the end date and time of admission is calculated as the BI score difference. Furthermore, in the case of medical expenses, the list of medical institutions for the patient to be calculated from the list of I medical institutions is targeted, and the costs for the medical institution to be calculated from the list of medical institutions for that patient is calculated as the medical expenses.

[0047] Furthermore, among the above evaluation items, bed occupancy and resource utilization can have unique index values ​​for each medical institution, so the smallest unit is the "node" of the medical institution included in the care pathway. For example, in the case of bed occupancy, the calculation is performed by dividing the aggregate value of patients receiving medical services from the medical institution for each interval into which the care pathway data range is divided, such as "day," "week," or "month," by the number of beds owned by the medical institution. In the case of resource utilization, the calculation is performed by dividing the aggregate value of patients receiving medical services from the medical institution for each interval by the number of medical personnel affiliated with or working at the medical institution. The "medical personnel" mentioned here can be classified as doctors only, nurses only, or both doctors and nurses.

[0048] After calculating the index value for the smallest unit in this way, the calculation unit 15C calculates the index value for the entire care pathway for the kth evaluation item. For example, the calculation unit 15C calculates a statistical value, such as the average, median, maximum, or minimum value, of the index values ​​calculated for each combination of "medical institution" and "patient" or for each smallest unit of "medical institution."

[0049] The display unit 15D is a processing unit that displays various information for the client terminal 30. In one aspect, the display unit 15D can cause the client terminal 30 to display the care pathway generated by the generation unit 15B.

[0050] FIG. 6 is a diagram (1) showing an example of a care pathway display. FIG. 6 illustrates a screen 200, intended for use by policy planners, that includes a care pathway G10 that combines care paths for 100 emergency transport patients. Displaying such a care pathway G10 visualizes the state of collaboration among medical functions. For example, care pathway G10 allows users to understand that Hospitals A, B, and C independently provide highly acute and acute care. Furthermore, it can be seen that Hospitals B and C collaborate with Hospital D in providing care from the acute phase to the early recovery phase. Furthermore, it can be seen that Hospital A collaborates with Hospitals D and E in providing care from the early recovery phase to the late recovery phase. Furthermore, it can be seen that Hospital E collaborates with Hospital F, and Hospital D collaborates with Hospitals F through I in providing care from the late recovery phase to the maintenance phase.

[0051] FIG. 7 is a diagram (2) showing an example of a care pathway display. FIG. 7 also illustrates a screen 210, as a display for policy planners, including a care pathway G11 that combines care paths for 100 emergency transport patients. As shown in FIG. 7 , the care pathway G11 plots the number of patients passing through each edge included in the care pathway G11, compared to the care pathway G10 shown in FIG. 6 . Furthermore, compared to the care pathway G10 shown in FIG. 6 , the care pathway G11 displays each edge in a thickness corresponding to the number of patients passing through the edge. Furthermore, the care pathway G11 plots the resources at each node included in the care pathway G11, such as the number of physicians. By displaying such a care pathway G11, the balance of supply and demand at each medical institution can be visualized.

[0052] Furthermore, the display unit 15D can also display the index values ​​of the evaluation items calculated by the calculation unit 15C in association with the medical institutions included in the care pathway generated by the generation unit 15B. In this case, the display unit 15D can associate and display the index values ​​of the evaluation items for all medical institutions included in the care pathway, or it can narrow down the display to evaluation items whose index values ​​satisfy specific conditions and associate and display the index values ​​of the evaluation items.

[0053] Figure 8 is a diagram (3) showing an example of a care pathway display. Figure 8 also illustrates a screen 220 for planners, including a care pathway G12 that combines care paths for 100 patients who received emergency transport. As shown in Figure 8, care pathway G12 differs from care pathway G11 shown in Figure 7 in that medical institutions that meet condition 1—that is, the number of patients whose hospital stay exceeds the first threshold Th1 is equal to or greater than the second threshold Th2—are highlighted. The first threshold Th1, which is compared with the hospital stay, can be set based on, for example, statistical values, such as the mean, median, or standard deviation, of the length of hospital stay for patients receiving medical services for the same disease at the same medical institution. For example, in care pathway G12, an alert 221 is associated with the node "Hospital C Providing Advanced Acute Care." Displaying this alert 221 can visualize the occurrence of patient delays (prolonged hospitalization).

[0054] For example, when an operation is received for alert 221 of node "Hospital C for Advanced Acute Care" in care pathway G12, a graph of the number of days of hospitalization (see Figure 9) for node "Hospital C for Advanced Acute Care" can be displayed.

[0055] FIG. 9 is a diagram showing an example of a length of stay graph. The vertical axis of the graph shown in FIG. 9 corresponds to patient ID, and the horizontal axis of the graph corresponds to the number of days of stay (days). As shown in FIG. 9, in the length of stay graph, plots of the number of days of stay of patients receiving medical services at Hospital C providing advanced acute care whose length of stay exceeds a first threshold are highlighted by being filled in black. This display of the length of stay graph makes it possible to identify patients who are causing overstay (prolonged hospitalization) at the node "Hospital C providing advanced acute care" and the number of days of their stay.

[0056] 7, the care pathway G12 shown in FIG. 8 differs from the care pathway G11 shown in FIG. 7 in that medical institutions that satisfy condition 2, that is, that the bed occupancy rate exceeds the third threshold value Th3, are highlighted. For example, in the care pathway G12, an alert 222 is associated with the node "Hospital E for Convalescent Care." When an operation on such alert 222 is received, a bed occupancy rate graph (see FIG. 10) for the node "Hospital E for Convalescent Care" can be displayed.

[0057] FIG. 10 is a diagram showing an example of a bed occupancy rate graph. The vertical axis of the graph shown in FIG. 10 corresponds to the bed occupancy rate, and the horizontal axis of the graph corresponds to the date. As shown in FIG. 10, the bed occupancy rate graph displays the trend of the bed occupancy rate calculated by the calculation unit 15C for each interval, for example, for each "day," i.e., time-series data. By displaying such a bed occupancy rate graph, it is possible to grasp the time when the bed occupancy rate at the node "Hospital E for Late-Stage Convalescent Care" reaches the third threshold value Th3.

[0058] In another aspect, the display unit 15D can superimpose and display a care path related to a specific user on the care pathway generated by the generation unit 15B. In this case, the display unit 15D can accept the designation of a specific user via the care path selection screens exemplified in Figures 11 and 12. Note that the care path selection screens shown in Figures 11 and 12 can be displayed either after the care pathway is displayed or when a request to display the care pathway is received.

[0059] 11 and 12 are diagrams illustrating examples of care path selection screens. As shown in FIG. 11, the care path selection screen 230 displays a pull-down menu as an example of a GUI (Graphical User Interface) for specifying the medical institution responsible for each medical function. For example, in the example shown in FIG. 11, care paths for the highly acute phase "Hospital C," the acute phase "Hospital C," the early convalescence phase "Hospital D," the late convalescence phase "Hospital D," and the maintenance phase "Hospital G" are selected. When the confirm button is pressed after a care path has been selected in this manner, a patient list L1 is displayed, as shown in FIG. 12, listing patients corresponding to the care paths shown in FIG. 11. By accepting a patient selection from among the patients included in this patient list L1, a care path for a specific user can be selected. For example, when a patient with patient ID "AAA" is selected from among the patients included in the patient list L1, a screen 240 including a care pathway G13 shown in FIG. 13 is displayed.

[0060] FIG. 13 is a diagram (4) showing an example of a care pathway display. FIG. 13 also illustrates a screen 240, intended for a planner, including a care pathway G13 that combines care paths for 100 patients who were transported by ambulance. As shown in FIG. 13, compared to the care pathway G11 shown in FIG. 7, the care pathway G13 for patient ID "AAA" is displayed with a superimposed thick solid arrow. That is, the care path for patient ID "AAA" includes the nodes "Hospital C for Advanced Acute Care," "Hospital C for Acute Care," "Hospital D for Early Convalescent Care," "Hospital D for Early Convalescent Care," and "Hospital G for Maintenance Care." Furthermore, the care path for patient ID "AAA" is associated with the overall hospital stay (N days), the overall medical expenses (M), and "no readmission" for the care path.

[0061] Furthermore, the care pathway G13 shown in Figure 13 can display the statistical index values ​​of each evaluation item for the entire policy flow (care pathway G13) in association with the index values ​​of each evaluation item for a specific user, for example, patient ID "AAA."

[0062] FIG. 14 shows an example of a radar chart. This chart plots statistical index values ​​for five evaluation items for the entire policy flow (care pathway G13), as well as five evaluation items for patient ID "AAA." The statistical index values ​​for each evaluation item for the entire policy flow can be obtained by calculating the statistical values, such as the average, of the overall index values ​​for the care paths of 100 individual patients (in this example, 1 name). By displaying the radar chart for the entire policy flow and the radar chart for a specific user, relative index values ​​can be evaluated between the entire policy flow and the care path of a specific user. For example, if a specific user's care path is superior to the entire policy flow, a draft policy for retaining that care path can be created during medical reorganization. Furthermore, if a specific user's care path is inferior to the entire policy flow, a draft policy for removing that care path can be created during medical reorganization.

[0063] In addition to the specific user, the display unit 15D can also superimpose and display a specified care path among the care pathways generated by the generation unit 15B. For example, the display unit 15D can superimpose and display a care path selected via the care path selection screen 230 shown in FIG. 11 on the care pathway generated by the generation unit 15B.

[0064] FIG. 15 is a diagram (5) showing an example of a care pathway display. FIG. 13 also illustrates a screen 250, intended for use by policy planners, including a care pathway G14 that combines care paths for 100 patients transported by ambulance. As shown in FIG. 15, care pathway G14 is similar to care pathway G13 shown in FIG. 13 in that a specified care path, such as a thick solid arrow in the figure, is superimposed. That is, care paths for the nodes "Hospital C for Advanced Acute Care," "Hospital C for Acute Care," "Hospital D for Early Convalescent Care," "Hospital D for Early Convalescent Care," and "Hospital G for Maintenance Care," are displayed. Meanwhile, care pathway G14 differs from care pathway G13 shown in FIG. 13 in that, instead of the care path for patient ID "AAA," the care path for group X of x patients belonging to the care path is superimposed. Furthermore, the care path for group X of x patients is displayed in association with the average length of hospital stay for the entire care path for group X ("N days"), the average medical costs for the entire care path ("M"), and the average number of readmissions ("none").

[0065] Furthermore, the care pathway G14 shown in Figure 15 can display the statistical index values ​​of each evaluation item for the entire policy flow (care pathway G14) in association with the statistical index values ​​of each evaluation item for the user group of group X.

[0066] For example, a radar chart plotting statistical index values ​​for five evaluation items for the entire policy flow (care pathway G14) and a radar chart plotting statistical index values ​​for five evaluation items for the user group of Group X can be displayed. Of these, the statistical index values ​​for each evaluation item for the entire policy flow can be obtained by calculating the statistical values, e.g., average values, of the index values ​​for the entire care path for I individual patients (100 patients in this example), for each evaluation item. Meanwhile, the statistical index values ​​for each evaluation item for the user group of Group X can be obtained by calculating the statistical values, e.g., average values, of the index values ​​for the user group of Group X belonging to the care paths of the nodes "Hospital C for Advanced Acute Care," "Hospital C for Acute Care," "Hospital D for Early Convalescence Care," "Hospital D for Early Convalescence Care," and "Hospital G for Maintenance Care," for each evaluation item. By displaying the radar chart for the entire policy flow and the radar chart for Group X belonging to a specific care path, it is possible to consider whether it is appropriate to increase the number of members in Group X.

[0067] As a further aspect, the display unit 15D can associate and display a specific policy flow among the policy flows included in the policy DB 13B with a care pathway generated from a data range corresponding to the specific policy flow. In this case, the display unit 15D can display nodes corresponding to the same medical function between the policy flow and the care pathway in a common display format, such as a common color or common hatching. Furthermore, the display unit 15D can display nodes of medical institutions included in the care pathway in association with the location of the medical institution on a map.

[0068] Figure 16 is a diagram (6) showing an example of a care pathway display. As an example, Figure 16 displays a screen 260 including a policy flow before medical reorganization and a care pathway generated using a data range corresponding to the pre-medical reorganization. Furthermore, Figure 16 displays a care pathway for patients with acute myocardial infarction as an example of a disease. Furthermore, Figure 16 displays a care pathway in which Hospital A and Hospital B are specified as an example of a data range.

[0069] As shown in FIG. 16 , between the policy flows and care pathways before the medical reorganization, the nodes "Hospital A for Advanced Acute Care" and "Hospital B for Advanced Acute Care" are displayed with common hatching, i.e., light dotted hatching in the figure. Furthermore, between the policy flows and care pathways before the medical reorganization, the nodes "Hospital A for Acute Care" and "Hospital B for Acute Care" are displayed with common hatching, i.e., dark dotted hatching in the figure. Furthermore, between the policy flows and care pathways before the medical reorganization, the nodes "Hospital A for Convalescent Care" and "Hospital B for Convalescent Care" are displayed with common hatching, i.e., diagonal hatching that slopes upward to the right in the figure. Furthermore, between the policy flows and care pathways before the medical reorganization, the node "Hospital B for Chronic Care" is displayed with common hatching, i.e., vertical hatching in the figure.

[0070] 16, the nodes "Hospital A for Advanced Acute Care," "Hospital A for Acute Care," and "Hospital A for Convalescent Care" are placed in association with the icon of the location of Hospital A on the map. Furthermore, in the care pathway shown in FIG. 16, the nodes "Hospital B for Advanced Acute Care," "Hospital B for Acute Care," "Hospital B for Convalescent Care," and "Hospital B for Chronic Care" are placed in association with the icon of the location of Hospital B on the map.

[0071] In addition, the care pathway shown in Figure 16 displays the care path of a specific user, "Mr. A," superimposed on it, and also displays a graph of the number of days of hospitalization associated with the edge where congestion is occurring.

[0072] Here, the care pathway shown in Figure 16 can display the statistical index values ​​of each evaluation item for the entire policy flow in association with the index values ​​of each evaluation item for specific hospitals, for example, "Hospital A" and "Hospital B."

[0073] FIG. 17 is a diagram illustrating an example of a radar chart. FIG. 17 shows a radar chart plotting statistical index values ​​for five evaluation items for the entire policy flow before medical reorganization, a radar chart plotting statistical index values ​​for five evaluation items for Hospital A, and a radar chart plotting statistical index values ​​for five evaluation items for Hospital B. For Hospital A and Hospital B, radar charts plotting statistical index values ​​for the five evaluation items for each medical function in the "acute phase" and "recovery phase" may be displayed. By displaying these radar charts, the statistical index values ​​for each evaluation item can be compared for the same medical functions between Hospital A and Hospital B, and this can be used as information for deciding whether to retain the medical function of the hospital with a higher evaluation in the evaluation items that are important to the policy planner in the medical reorganization, or whether to eliminate the medical function of the hospital with a lower evaluation in the evaluation items that are important to the policy planner in the medical reorganization.

[0074] Figure 18 is a diagram (7) showing an example of a care pathway display. As an example, Figure 18 displays a screen 270 including a policy flow after medical reorganization and a care pathway generated within a data range corresponding to the medical reorganization. Furthermore, Figure 18 displays a care pathway for patients with acute myocardial infarction as an example of a disease. Furthermore, Figure 18 displays a care pathway in which Hospital A and Hospital B are specified as an example of a data range.

[0075] The policy flow after medical reorganization shown in Figure 18 differs from the policy flow before medical reorganization shown in Figure 16 in that the nodes "Hospital B for Advanced Acute Care" and "Hospital B for Acute Care" have been abolished, and the node "Hospital A for Convalescent Care" has also been abolished.

[0076] As shown in Figure 18, between the policy flows and care pathways after medical reorganization, the node "Hospital A providing advanced acute care" is displayed with common hatching, i.e., light dotted hatching in the figure. Furthermore, between the policy flows and care pathways after medical reorganization, the node "Hospital A providing acute care" is displayed with common hatching, i.e., dark dotted hatching in the figure. Furthermore, between the policy flows and care pathways after medical reorganization, the node "Hospital B providing convalescent care" is displayed with common hatching, i.e., diagonal hatching that slopes upward to the right in the figure. Furthermore, between the policy flows and care pathways after medical reorganization, the node "Hospital B providing chronic care" is displayed with common hatching, i.e., vertical hatching in the figure.

[0077] In addition, in the care pathway shown in Figure 18, the nodes "Hospital A for Advanced Acute Care" and "Hospital A for Acute Care" are placed in association with the icon of the location of Hospital A on the map. Furthermore, in the care pathway shown in Figure 18, the nodes "Hospital B for Convalescent Care" and "Hospital B for Chronic Care" are placed in association with the icon of the location of Hospital B on the map. In addition, the care pathway of a specific user "Mr. A" is superimposed on the care pathway shown in Figure 18.

[0078] Here, the care pathway shown in Figure 18 can display the statistical index values ​​of each evaluation item for the entire policy flow before and after medical reorganization, in association with the index values ​​of each evaluation item for specific hospitals, such as "Hospital A" and "Hospital B," before and after medical reorganization.

[0079] FIG. 19 is a diagram illustrating an example of a radar chart. FIG. 19 shows a radar chart plotting statistical index values ​​for five evaluation items for the entire policy flow before and after medical reorganization, a radar chart plotting statistical index values ​​for five evaluation items for Hospital A before and after medical reorganization, and a radar chart plotting statistical index values ​​for five evaluation items for Hospital B before and after medical reorganization. For Hospitals A and B, radar charts plotting statistical index values ​​for the five evaluation items before and after medical reorganization may be displayed for the medical functions remaining after medical reorganization. By displaying these radar charts, it is possible to grasp the improvement trends for each evaluation item, i.e., the results of medical reorganization, such as an increase in the BI score difference for the entire policy flow and Hospitals A and B, an increase in bed occupancy rate within an acceptable range, and a decrease in hospital stay days after medical reorganization.

[0080] As a further aspect, the display unit 15D can predict an individual's care path based on the individual's attributes or personal information, and display the predicted individual's care path superimposed on the care pathway.

[0081] FIG. 20 is a schematic diagram showing an example of a care path prediction model. As shown in FIG. 20 , a machine learning model m1 is used to predict an individual's care path. For example, the machine learning model m1 may be implemented using a neural network, a support vector machine, gradient boosting, or the like. To train this machine learning model m1, a dataset TR11 can be used, which includes training data that associates attribute information such as part of an individual's address, age, and gender, or personal information such as an individual's address, age, gender, health check results, family doctor, and medical history with the correct label of the care path.

[0082] For example, in the training phase, the machine learning model m1 can be trained using any machine learning algorithm, such as deep learning, with at least one of the individual's attribute information and personal information as the explanatory variable and the label as the objective variable of the machine learning model m1, thereby obtaining a trained machine learning model M1.

[0083] In the prediction phase, at least one of the individual's attribute information or personal information is input to the machine learning model M1. The machine learning model M1, to which the individual's attribute information or personal information has been input, outputs the individual's care path. Furthermore, by generating the machine learning model M1 for each disease, it is possible to predict the care path for any disease.

[0084] Note that Figure 20 illustrates examples of individual attribute information and personal information as input to the machine learning model M1, but it is also possible to input additional information, such as part of a care path, such as an end point.

[0085] In addition, the display unit 15D can predict an individual's index value based on the individual's attributes or personal information, and display the predicted individual's index value in association with a care pathway.

[0086] FIG. 21 is a schematic diagram showing an example of an index value prediction model. As shown in FIG. 21 , a machine learning model m2 is used to predict an individual's index value. For example, the machine learning model m2 may be implemented using a neural network, a support vector machine, gradient boosting, or the like. To train this machine learning model m2, a dataset TR12 can be used, which includes training data in which attribute information such as part of an individual's address, age, and gender, or personal information such as an individual's address, age, gender, health check results, family doctor, and medical history, and correct answer labels for index values ​​of specific evaluation items are associated.

[0087] For example, in the training phase, the machine learning model m2 can be trained using any machine learning algorithm, such as deep learning, with at least one of the individual's attribute information and personal information as the explanatory variable and the label as the objective variable of the machine learning model m2, thereby obtaining a trained machine learning model M2.

[0088] In the prediction phase, at least one of the individual's attribute information or personal information is input to the machine learning model M2. The machine learning model M2, to which the individual's attribute information or personal information has been input, outputs a prediction index value for the individual. Furthermore, by generating the machine learning model M2 for each disease and each evaluation item, it is possible to predict a care path for any disease.

[0089] Figure 22 is a diagram (8) showing an example of a care pathway display. Figure 18 shows, as an example only, a screen 280 including a policy flow before medical reorganization and a care pathway generated using a data range corresponding to the pre-medical reorganization. Furthermore, Figure 18 displays a care pathway for patients with acute myocardial infarction as an example of a disease. Furthermore, Figure 16 displays a care pathway in which Hospital A and Hospital B are specified as an example of a data range.

[0090] The care pathway shown in Figure 22 differs from the care pathway shown in Figure 16 in that the care pathway for individual "Mr. B" predicted by the care path prediction model shown in Figure 20 is superimposed. Furthermore, the care pathway shown in Figure 22 can display the statistical index values ​​of each evaluation item for the entire policy flow in association with the predicted index values ​​of each evaluation item for a specific individual "Mr. B."

[0091] 23 is a diagram showing an example of a radar chart. This diagram shows a radar chart plotting statistical index values ​​for five evaluation items for the entire policy flow before medical reorganization, and a radar chart plotting predicted index values ​​for five evaluation items for an individual named "Mr. B." By displaying these radar charts, each index (radar chart graph) for Mr. B's care pathway on the map can be compared with the overall data, allowing comparisons of Mr. B's evaluation items, such as his length of hospital stay, which tends to be longer than the overall data.

[0092] <Processing Flow> Next, a processing flow of the server device 10 according to this embodiment will be described. Here, (1) generation processing and (2) calculation processing executed by the server device 10 will be described.

[0093] (1) Generation Process Fig. 24 is a flowchart showing the steps of the generation process. As shown in Fig. 24, when the reception unit 15A receives a care pathway display request (step S101), the generation unit 15B executes the following process. That is, the generation unit 15B extracts medical data corresponding to the data range specified in the display request from the medical data stored in the medical DB 13A (step S102).

[0094] Next, the generation unit 15B executes loop processing 1, which repeats the processing from step S103 to step S109 below a number of times corresponding to the number I of patients included in the medical data corresponding to the above data range.

[0095] That is, the generation unit 15B generates a list of medical institutions when the i-th patient uses a medical service corresponding to each medical function, such as a highly acute phase, an acute phase, a recovery phase, a maintenance phase, etc. (Step S103). Then, the generation unit 15B sorts the medical institutions included in the list of medical institutions for the i-th patient obtained by the listing in Step S103 in chronological order (Step S104).

[0096] Then, the generation unit 15B executes loop processing 2, which repeats the processing from step S105 to step S109 described below a number of times corresponding to the number J of medical institutions included in the medical institution list of the i-th patient.

[0097] That is, the generation unit 15B determines whether a node corresponding to the jth medical institution among the J medical institutions included in the medical institution list of the i-th patient has not yet been generated on the care pathway being generated (step S105).

[0098] If a node corresponding to the jth medical institution has not been generated (Yes in step S105), the generating unit 15B adds a node corresponding to the jth medical institution to the care pathway being generated (step S106).

[0099] Thereafter, the generating unit 15B determines whether an edge has not yet been generated between the node of the jth medical institution and the node of the j-1th medical institution in the care pathway being generated (step S107).

[0100] At this time, if an edge has not been generated between the node of the jth medical institution and the node of the j-1th medical institution (Yes in step S107), the generation unit 15B adds an edge between the node of the jth medical institution and the node of the j-1th medical institution (step S108).Furthermore, the generation unit 15B increments the number of paths of the edge connecting the node of the jth medical institution and the node of the j-1th medical institution, i.e., the number of patients, by one (step S109).

[0101] A care path for the i-th patient is generated by repeating this loop process 2. Furthermore, a care pathway in which care paths for I patients are combined is generated by repeating loop process 1.

[0102] (2) Calculation Process FIG. 25 is a flowchart showing the procedure of the calculation process. As shown in FIG. 25, the calculation unit 15C executes loop process 1, which repeats the process of step S301 and the process of step S302 described below a number of times corresponding to the number K of evaluation items. Furthermore, the calculation unit 15C executes loop process 2, which repeats the process of step S301 described below for the smallest unit corresponding to the kth evaluation item. That is, the calculation unit 15C calculates the mth smallest unit index value for the kth evaluation item (step S301). By repeating this loop process 2, M smallest unit index values ​​for the kth evaluation item are calculated. Then, the calculation unit 15C calculates the index value of the entire care pathway for the kth evaluation item by calculating a statistical value, such as the average value, of the M smallest unit index values ​​for the kth evaluation item (step S302). Then, by repeating loop process 1, M smallest unit index values ​​for each of the K evaluation items and the index value of the entire care pathway are calculated.

[0103] As described above, the server device 10 according to the present embodiment generates and displays a pathway indicating the route to medical institutions when multiple users use medical services corresponding to each medical function. Therefore, the server device 10 according to the present embodiment can improve the visibility of the service route, for example, the coordination status of medical functions.

[0104] Furthermore, the server device 10 according to this embodiment displays a care pathway, which indicates the route taken by multiple users through medical institutions when using medical services corresponding to each medical function, superimposed on the care path and index values ​​of a specific individual. Therefore, the server device 10 according to this embodiment can verify the effectiveness of measures for a specific user.

[0105] Furthermore, the server device 10 according to this embodiment displays medical institutions that correspond to the same medical functions in the policy flow and care pathway in a common display format, and displays the medical institutions included in the care pathway in association with their locations on a map. Therefore, the server device 10 according to this embodiment can improve the readability of the policy flow.

[0106] Although the embodiments relating to the disclosed device have been described above, the present invention may be embodied in various different forms other than the above-described embodiments. Therefore, other embodiments included in the present invention will be described below.

[0107] <Distribution and Integration> Furthermore, the components of each device shown in the figure do not necessarily have to be physically configured as shown. In other words, the specific form of distribution and integration of each device is not limited to that shown in the figure, and all or part of the devices can be functionally or physically distributed and integrated in any unit depending on various loads, usage conditions, etc. For example, the reception unit 15A, the generation unit 15B, the calculation unit 15C, or the display unit 15D may be connected via a network as an external device to the server device 10. Furthermore, the reception unit 15A, the generation unit 15B, the calculation unit 15C, or the display unit 15D may each be included in a separate device, and the functions of the server device 10 may be realized by the devices being connected to a network and operating together.

[0108] <Hardware Configuration> The various processes described in the above embodiments can be realized by executing a prepared program on a computer such as a personal computer, a workstation, etc. Therefore, an example of a computer that executes a display program having the same functions as those in the first and second embodiments will be described below with reference to FIG.

[0109] Fig. 26 is a diagram showing an example of a hardware configuration. As shown in Fig. 26, a computer 100 has an operation unit 110a, a speaker 110b, a camera 110c, a display 120, and a communication unit 130. The computer 100 also has a CPU 150, a ROM 160, an HDD 170, and a RAM 180. These units 110 to 180 are connected via a bus 140.

[0110] 26, the HDD 170 stores a display program 170a that performs the same functions as the reception unit 15A, generation unit 15B, calculation unit 15C, and display unit 15D shown in the first embodiment. This display program 170a may be integrated or separated, similar to the components of the reception unit 15A, generation unit 15B, calculation unit 15C, and display unit 15D shown in FIG. 1. In other words, the HDD 170 does not necessarily have to store all of the data shown in the first embodiment, as long as the data used for processing is stored in the HDD 170.

[0111] Under such an environment, the CPU 150 reads the display program 170a from the HDD 170 and loads it into the RAM 180. As a result, the display program 170a functions as a display process 180a, as shown in FIG. 26 . The display process 180a loads various data read from the HDD 170 into an area of ​​the storage area of ​​the RAM 180 allocated to the display process 180a, and executes various processes using the loaded data. For example, examples of the processes executed by the display process 180a include the processes shown in FIGS. 24 and 25 . Note that the CPU 150 does not necessarily need to operate all of the processing units described in the first embodiment; it is sufficient that the processing units corresponding to the processes to be executed are virtually implemented.

[0112] The display program 170a does not necessarily have to be stored in the HDD 170 or the ROM 160 from the beginning. For example, each program may be stored on a "portable physical medium" such as a flexible disk, a so-called FD, a CD-ROM, a DVD disk, a magneto-optical disk, or an IC card that is inserted into the computer 100. The computer 100 may then retrieve and execute each program from such a portable physical medium. Alternatively, each program may be stored in another computer or server device connected to the computer 100 via a public line, the Internet, a LAN, a WAN, or the like, and the computer 100 may retrieve and execute each program from such a computer or server device.

[0113] REFERENCE SIGNS LIST 10 Server device 11 Communication control unit 13 Storage unit 13A Medical DB 13B Policy DB 15 Control unit 15A Reception unit 15B Generation unit 15C Calculation unit 15D Display unit 30 Client terminal

Claims

1. The computer When one user is selected from the plurality of users, the index value and route information related to the selected user are acquired from the storage unit; displaying a path highlighting the route of the user and an index value of the user on a screen based on the acquired route information; A display method characterized by performing a process.

2. The acquiring process further includes acquiring an average index value for all of the plurality of users; The displaying process further includes displaying the acquired average index value on the screen.

2. The display method according to claim 1, wherein the display method is a process.

3. The computer When one of the multiple routes is selected, an average index value of the group of users belonging to the selected route is obtained from the storage unit; displaying a path highlighting the route and an average index value of the user group on a screen; A display method characterized by performing a process.

4. The acquiring process further includes acquiring a total average index value for all users, The displaying process further includes displaying the acquired total average index value on the screen.

4. The display method according to claim 3, wherein the display method is a process.

5. When one user is selected from the plurality of users, the index value and route information related to the selected user are acquired from the storage unit; displaying a path highlighting the route of the user and an index value of the user on a screen based on the acquired route information; An information processing device comprising a control unit that executes processing.

6. On the computer, When one user is selected from the plurality of users, the index value and route information related to the selected user are acquired from the storage unit; displaying a path highlighting the route of the user and an index value of the user on a screen based on the acquired route information; A display program that causes a process to be executed.