JP6866708B2 - Search program, search method and search device - Google Patents

Description

The present invention relates to a search program and the like.

In a conventional medical system, information on a patient's test result is stored in a database, and a doctor refers to the information on the patient's test result to determine whether or not the patient's symptoms are worsening. For example, when a doctor determines that a patient's symptoms are worsening, he / she determines the cause of the worsening of the symptoms based on past empirical rules.

In addition, as a conventional technique for automatically determining whether or not a patient's symptoms are worsening, for a certain test item, the value at the time of the test is compared with the value before a predetermined period, and the rate of increase or decrease of the value is obtained. There is a technique for determining whether or not the symptom of a certain test item is worsening based on the above. There is also a conventional technique for determining whether or not the symptom of a certain item is worsened by simply comparing the value at the time of inspection of a certain test item with the threshold value.

Japanese Unexamined Patent Publication No. 2009-66269 Japanese Unexamined Patent Publication No. 8-235275

However, the above-mentioned conventional technique has a problem that the cause of symptom exacerbation cannot be identified from the patient's test result.

For example, since various factors influence the factors of symptomatology deterioration, it is difficult to identify the factors of symptomatology deterioration by comparing the rate of increase, the rate of decrease, and the threshold value as in the prior art.

In one aspect, it is an object of the present invention to provide a search program, a search method, and a search device capable of identifying a factor of aggravation of symptoms from a patient's test result.

In the first plan, the computer is made to perform the following processing. The computer refers to a storage unit that stores information indicating the patient's condition for each of a plurality of items. The computer generates a graph showing the patient's condition in chronological order for at least two or more items among the plurality of items for each item. When a part of the first graph displaying the patient's condition of the first item in the generated graph in chronological order is selected, the first feature of the figure of the first graph around the selected part is selected. And each second feature around the portion corresponding to the periphery of the selected portion in the plurality of graphs, which is a graph for each of the two or more items that generated the graph. The computer identifies the item corresponding to the second graph having the second feature similar to the first feature.

The cause of symptom exacerbation can be identified from the patient's test results.

FIG. 1 is a functional block diagram showing a configuration of a search device according to this embodiment. FIG. 2 is a diagram showing an example of the data structure of the inspection history table. FIG. 3 is a diagram showing an example of the data structure of the inspection result. FIG. 4 is a diagram showing an example of the data structure of the graph table. FIG. 5 is a diagram showing an example of a graph showing the numerical values of a certain inspection item in chronological order. FIG. 6 is a diagram for explaining a period specifying process. FIG. 7 is a diagram for explaining the item search process. FIG. 8 is a flowchart showing a processing procedure of the search device according to the present embodiment. FIG. 9 is a diagram showing an example of a computer hardware configuration that realizes a function similar to that of a search device.

Hereinafter, examples of the search program, search method, and search device disclosed in the present application will be described in detail with reference to the drawings. The present invention is not limited to this embodiment.

FIG. 1 is a functional block diagram showing a configuration of a search device according to this embodiment. As shown in FIG. 1, the search device 100 includes a communication unit 110, an input unit 120, a display unit 130, a storage unit 140, and a control unit 150.

The communication unit 110 is a processing unit that executes communication with an external device (not shown) via a network. The communication unit 110 corresponds to a communication device.

The input unit 120 is an input device for inputting various information to the search device 100. The input unit 120 corresponds to an input device such as a keyboard, a mouse, and a touch panel.

The display unit 130 is a display device that displays information output from the control unit 150. The display unit 130 corresponds to a display device such as a liquid crystal display or a touch panel.

The storage unit 140 has an inspection history table 141 and a graph table 142. The storage unit 140 corresponds to semiconductor memory elements such as RAM (Random Access Memory), ROM (Read Only Memory), and flash memory (Flash Memory), and storage devices such as HDD (Hard Disk Drive).

The examination history table 141 is a table that holds information on the history of examination results for each patient. FIG. 2 is a diagram showing an example of the data structure of the inspection history table. As shown in FIG. 2, the examination history table 141 has patient identification information, a patient profile, and an examination result.

The patient identification information is information that uniquely identifies the patient. The patient profile contains information about the patient's gender, age, allergies, etc. The test result is information that retains information about the test result of each patient.

FIG. 3 is a diagram showing an example of the data structure of the inspection result. As shown in FIG. 3, this inspection result has a plurality of tables that are the inspection results of each inspection item. In the example shown in FIG. 3, tables 50a, 50b, and 50c are shown as inspection results, but tables corresponding to other inspection items may be provided.

The table 50a is a table that holds the information of the inspection result of the inspection item "item A", and associates the "date" of the inspection with the "numerical value" of the inspection result. The table 50b is a table that holds the information of the inspection result of the inspection item "item B", and associates the "date" of the inspection with the "numerical value" of the inspection result. The table 50c is a table that holds information on the inspection result of the inspection item "item C", and associates the "date" of the inspection with the "numerical value" of the inspection result.

The graph table 142 is a table that holds graph information that represents the numerical values of the examination items for each patient in chronological order. FIG. 4 is a diagram showing an example of the data structure of the graph table. As shown in FIG. 4, the graph table 142 associates the patient identification information with the test items and the graph. The patient identification information is information that uniquely identifies the patient. The inspection item is information that uniquely identifies the inspection item. The graph is the information of the graph showing the numerical values of the corresponding inspection items in chronological order.

FIG. 5 is a diagram showing an example of a graph showing the numerical values of a certain inspection item in chronological order. The horizontal axis of the graph shown in FIG. 5 is the axis corresponding to time, and the vertical axis of the graph is the axis corresponding to the numerical value of a certain item. In this embodiment, as an example, the graph shown in FIG. 5 is a graph showing the numerical values of item A in chronological order.

Returning to the description of FIG. The control unit 150 includes a reception unit 151, a generation unit 152, and a search unit 153. The control unit 150 can be realized by a CPU (Central Processing Unit), an MPU (Micro Processing Unit), or the like. The control unit 150 can also be realized by hard-wired logic such as an ASIC (Application Specific Integrated Circuit) or an FPGA (Field Programmable Gate Array).

The reception unit 151 is a processing unit that receives various types of information via the communication unit 110 or the input unit 120, and updates the information stored in the storage unit 140 based on the received information. For example, when the reception unit 151 receives the patient profile and the test result associated with the patient identification information, the reception unit 151 updates the test history table 141 with the received information.

The generation unit 152 is a processing unit that generates a graph showing the values of inspection items in chronological order based on the inspection results of the inspection history table 141. The generation unit 152 generates a graph for each examination item for each patient identification information, and stores the generated graph information in the graph table 142.

For example, as shown in FIG. 3, when the inspection items include "item A, item B, item C", the generation unit 152 sets the graph of item A and the graph of item B for each patient identification information. Generate graphs for item C respectively. The generation unit 152 associates the patient identification information with the graph of item A, the graph of item B, and the graph of item C, and registers them in the graph table 142.

The search unit 153 is a processing unit that searches for items in another graph having graphic features similar to those of the graph in the same period as the period in which the patient's symptoms shown in the graph worsen. The search unit 153 may output the search result to the display unit 130 and display it, or may notify the external device via the network. The search unit 153 executes the period specifying process and the item search process in order.

FIG. 6 is a diagram for explaining a period specifying process. For example, the period specified by the search unit 153 by the period specifying process corresponds to the period in which the patient's symptom worsens. In the following description, the period during which the patient's symptoms worsen is referred to as the "target period". The search unit 153 acquires a graph corresponding to a certain item of certain patient identification information from the graph table 142. The search unit 153 may receive patient identification information and instructions for examination items from the input unit 120 or the like, and may acquire the corresponding graph from the graph table 142. Here, as an example, the case where the search unit 153 acquires the graph 60a of the item A will be described.

The search unit 153 arranges the window W on the graph 60a, and moves the window W to calculate the area of each area S surrounded by the line segment 71a of the graph 60a and the reference line 70a in the window W. Repeatedly execute while letting. The reference line 70a is a parallel line (horizontal axis) orthogonal to the vertical axis at a position where the numerical value on the vertical axis is 0. The position of the reference line 70a may be appropriately adjusted by the administrator. The search unit 153 specifies a period (target period) corresponding to the area S having a predetermined area or more.

In the example shown in FIG. 6, the search unit 153, the window _{W 1} is arranged to calculate the area of the region _S 1 to S _5, respectively. The search unit 153 shifts the position of the window W _{, arranges the window W 2,} and calculates the areas of the areas S _{6 to} S ₁₀ , respectively. The search unit 153 shifts the position of the window W _{, arranges the window W 3,} and calculates the areas of the areas S _{11 to} S ₁₅ , respectively.

Search section 153 compares the area to a predetermined area of each region S ₁ to S _15, specifies an area S made becomes equal to or higher than a predetermined area. Here, as an example, the region S _7, a predetermined area or region. The search unit 153 specifies a period from date T _{1 to date T 2 at} which the line segment of the graph constituting the _{area S 7 and the reference line 70a intersect.} That is, period is a period from the date _{T 1} to the date _{T 2.} It is assumed that the predetermined area to be compared by the search unit 153 is preset for each different inspection item.

In the above-mentioned period specifying process, the case where the area of each area S is obtained while shifting the position of the window W has been described, but the present invention is not limited to this. For example, the search unit 153 may receive the position where the window W is arranged from the input unit 120, arrange the window W at the accepted position, and execute the above process.

The search unit 153 executes the item search process after specifying the target period by executing the period specifying process. FIG. 7 is a diagram for explaining the item search process. The search unit 153 compares the characteristics of the graphic of the target period in the graph of each search item, and searches for the item of the graph having the characteristics of the graphic similar to the characteristics of the graphic of the reference graph. For example, the reference graph is a graph used in the period specifying process.

In the example shown in FIG. 7, the graph of item A is referred to as graph 60a, the graph of item B is referred to as graph 60b, the graph of item C is referred to as graph 60c, and the graph of item D is referred to as graph 60d. The reference graph is graph 60a, and the target period is periods T _{1 to} T ₂ . In the graphs 60b to 60d, the reference lines are the reference lines 70b to 70d, and the line segments of the graph are the line segments 71b to 71d, respectively.

Search section 153 for each graph 60 a to 60 d, and extracts the shape characteristics of the target period _T 1 through T _2. For example, the search unit 153 extracts values obtained by arranging the distances from the reference line corresponding to each date to the line segment of the graph in chronological order as graphic features. The search unit 153 calculates the correlation coefficient between the graphic feature of the reference graph 60a and the graphic feature of the other graphs 60b to 60d, respectively, and identifies a set of graphs having a correlation coefficient of a predetermined value or more. The search unit 153 searches for graph items that are paired with the graph 60a whose correlation coefficient is equal to or greater than the threshold value.

For example, the search unit 153 states that the correlation coefficient between the graphic feature of the graph 60a and the graphic feature of the graph 60b is equal to or greater than the threshold value, and the correlation coefficient between the graphic feature of the graph 60a and the graphic feature of the graph 60c is equal to or greater than the threshold value. To do. Further, it is assumed that the correlation coefficient between the graphic feature of the graph 60a and the graphic feature of the graph 60d is less than the threshold value. In this case, the search unit 153 uses the item B of the graph 60b and the item C of the graph 60c as the search result.

By the way, the search unit 153 may search for another patient similar to the reference patient by using the graphic feature of the reference graph. Here, a reference graph will be described as a graph 60a. Assuming that the test item of the reference graph 60a is "item A", the search unit 153 acquires the information of the graph of the test item "item A" corresponding to other patient identification information, and the period described in FIG. By performing the specific processing, the target period is specified and the graphic features of the target period are extracted.

The search unit 153 calculates the correlation coefficient between the graphic feature of the graph 60a as a reference and the graphic feature of the graph of the test item “item A” corresponding to other patient identification information. When the correlation coefficient is equal to or greater than the threshold value, the search unit 153 identifies the patient with such other patient identification information as another patient similar to the reference patient.

Next, the processing procedure of the search device 100 according to this embodiment will be described. FIG. 8 is a flowchart showing a processing procedure of the search device according to the present embodiment. As shown in FIG. 8, the generation unit 152 of the search device 100 refers to the inspection history table 141 (step S101) and generates a graph for each inspection item (step S102).

The search unit 153 of the search device 100 calculates the area of the area surrounded by the reference line and the graph included in the window while moving the window with respect to the reference graph (step S103). The search unit 153 specifies a period in which the area is equal to or greater than the threshold value as a target period (step S104).

The search unit 153 calculates the correlation coefficient between the graphic feature of the reference graph and the graphic feature of each of the other graphs (step S105). The search unit 153 identifies other graph items whose correlation coefficient is equal to or higher than the threshold value as the search result (step S106). The search unit 153 outputs the search result (step S107).

Next, the effect of the search device 100 according to this embodiment will be described. The search device 100 generates a time-series graph for each inspection item of the inspection result, and during the same period as the target period specified by the reference graph, the item of the graph having the graphic feature similar to the graphic feature of the reference graph is displayed. Search for. Therefore, the cause of symptom exacerbation can be identified from the patient's test result. For example, it can be said that the target period is the period during which the patient's symptoms worsen for one test item, and at the same time, other graph items similar to the graphic features of the reference graph are factors that affect the worsening of symptoms. It can be said that.

Since the search device 100 searches for a patient similar to the reference patient by comparing the graphic features of the graph corresponding to the same test item of each patient, the search device 100 has the same symptoms as the reference patient. The patient can be detected accurately.

Since the search device 100 identifies and uses the area surrounded by the reference line and the graph as a drawing feature, it evaluates whether or not the patient's symptom is worsening by comprehensively using the test results of each date. be able to.

The search device 100 calculates the area of the area surrounded by the reference line and the graph included in the window while moving the window, and uses the area having a predetermined area or more as a graphic feature. Therefore, it is possible to efficiently identify the period during which the patient's symptoms worsen.

Next, an example of a computer hardware configuration that realizes the same functions as the search device 100 shown in the above embodiment will be described. FIG. 9 is a diagram showing an example of a computer hardware configuration that realizes a function similar to that of a search device.

As shown in FIG. 9, the computer 200 includes a CPU 201 that executes various arithmetic processes, an input device 202 that receives data input from a user, and a display 203. Further, the computer 200 has a reading device 204 for reading a program or the like from a storage medium, and an interface device 205 for exchanging data with another computer via a network. Further, the computer 200 has a RAM 206 for temporarily storing various information and a hard disk device 207. Then, each of the devices 201 to 207 is connected to the bus 208.

The hard disk device 207 has a specific program 207a and a search program 207b. The CPU 201 reads out the specific program 207a and the search program 207b and deploys them in the RAM 206.

The specific program 207a functions as a specific process 206a. The search program 207b functions as the search process 206b. The process of the specific process 206a corresponds to the process of the specific unit 152. The process of the search process 206b corresponds to the process of the search unit 153.

The programs 207a and 207b do not necessarily have to be stored in the hard disk device 207 from the beginning. For example, each program is stored in a "portable physical medium" such as a flexible disk (FD), a CD-ROM, a DVD disk, a magneto-optical disk, or an IC card inserted into the computer 200. Then, the computer 200 may read and execute the programs 207a and 207b.

The following additional notes will be further disclosed with respect to the embodiments including each of the above embodiments.

(Appendix 1) To the computer
With reference to the storage unit that stores information indicating the patient's condition for each of multiple items,
A graph displaying the patient's condition in chronological order for at least two or more of the plurality of items is generated for each item.
When a part of the first graph displaying the patient's condition of the first item in the generated graph in chronological order is selected, the first feature of the figure of the first graph around the selected part and the first feature. Each second feature around the portion corresponding to the selected periphery in the plurality of graphs, which is a graph for each of the two or more items that generated the graph, is identified.
A search program characterized by executing a process of specifying an item corresponding to a second graph having a second feature similar to the first feature.

(Appendix 2) The generated process generates a graph showing the patient status of a certain item in chronological order for each different patient, and the specified process is the first graph of each patient. The search program according to Appendix 1, wherein the process of searching for another patient similar to a certain patient is further executed by comparing each of the features.

(Appendix 3) The process of specifying the first feature is characterized in that, with respect to the first graph of the region corresponding to the periphery of the portion, the region surrounded by the reference line and the first graph is specified as the first feature. The search program described in Appendix 1 or 2.

(Appendix 4) In the process of specifying the first feature, the area corresponding to the periphery of the portion is moved, and the process of specifying the area surrounded by the reference line and the first graph is repeatedly executed to obtain a predetermined area. The search program according to Appendix 3, wherein the above-mentioned area is specified as a first feature.

(Appendix 5) This is a search method executed by a computer.
With reference to the storage unit that stores information indicating the patient's condition for each of multiple items,
A graph displaying the patient's condition in chronological order for at least two or more of the plurality of items is generated for each item.
When a part of the first graph displaying the patient's condition of the first item in the generated graph in chronological order is selected, the first feature of the figure of the first graph around the selected part and the first feature. Each second feature around the portion corresponding to the selected periphery in the plurality of graphs, which is a graph for each of the two or more items that generated the graph, is identified.
A search method characterized by executing a process of specifying an item corresponding to a second graph having a second feature similar to the first feature.

(Appendix 6) The generated process generates a graph displaying the patient status of a certain item in chronological order for each different patient, and the specified process is the first graph of each patient. The search method according to Appendix 5, wherein the process of searching for another patient similar to a certain patient is further executed by comparing each of the features.

(Appendix 7) The process for specifying the first feature is characterized in that, for the first graph of the region corresponding to the periphery of the portion, the region surrounded by the reference line and the first graph is specified as the first feature. The search method according to Appendix 5 or 6.

(Appendix 8) In the process of specifying the first feature, the area corresponding to the periphery of the portion is moved, and the process of specifying the area surrounded by the reference line and the first graph is repeatedly executed to obtain a predetermined area. The search method according to Appendix 7, wherein the above-mentioned area is specified as a first feature.

(Appendix 9) A storage unit that stores information indicating the patient's condition for each of a plurality of items,
A generator that generates a graph displaying the patient's condition in chronological order for at least two or more of the plurality of items for each item.
When a part of the first graph displaying the patient's condition of the first item in the generated graph in chronological order is selected, the first feature of the figure of the first graph around the selected part and the first feature. Each second feature around the portion corresponding to the selected periphery in the plurality of graphs, which is a graph for each of the two or more items that generated the graph, is identified.
A search device comprising a search unit for specifying an item corresponding to a second graph having a second feature similar to the first feature.

(Appendix 10) The generation unit generates a graph displaying the patient status of a certain item in chronological order for each different patient, and the search unit generates the first feature of the first graph of each patient. 9. The search device according to Appendix 9, wherein the process of searching for another patient similar to a certain patient is further executed by comparing each of the above.

(Supplementary Note 11) The search unit specifies the region surrounded by the reference line and the first graph as the first feature of the first graph of the region corresponding to the periphery of the portion. 10. The search device according to 10.

(Appendix 12) The search unit repeatedly executes a process of moving a region corresponding to the periphery of the portion and specifying an region surrounded by the reference line and the first graph, and obtains an region having a predetermined area or more. , The search device according to Appendix 11, characterized in that it is specified as a first feature.

100 Search device 110 Communication unit 120 Input unit 130 Display unit 140 Storage unit 141 Inspection history table 142 Graph table 150 Control unit 151 Reception unit 152 Generation unit 153 Search unit

Claims (6)

By referring to the storage unit that stores information indicating the state of the patient for each item of the multiple,
A graph displaying the patient's condition in chronological order for at least two or more of the plurality of items is generated for each item.
The area around the selected part of the first graph showing the patient's condition of the first item in the generated graph in chronological order, and the area surrounded by the reference line and the first graph is as equal to or greater than a predetermined area accepts the selection in the periphery of the above portion, a first feature of the figure of the first graph near the portion selected, the graph for each of the two or more items that generated the graph Each second feature around the portion corresponding to the selected periphery of the selected portion in a plurality of graphs is identified.
A search program characterized by executing a process of specifying an item corresponding to a second graph having a second feature similar to the first feature. The generated process generates a graph showing the patient status of a certain item in chronological order for each different patient, and the specific process generates the first feature of the first graph of each patient. The search program according to claim 1, further performing a process of searching for another patient similar to a certain patient by comparison. The process of specifying the first feature is characterized in that, with respect to the first graph of the region corresponding to the periphery of the portion, the region surrounded by the reference line and the first graph is specified as the first feature. The search program according to 1 or 2. In the process of specifying the first feature, the area corresponding to the periphery of the portion is moved, and the process of specifying the area surrounded by the reference line and the first graph is repeatedly executed, and the area becomes a predetermined area or more. The search program according to claim 3, wherein the search program is specified as the first feature. It ’s a computer-run search method.
With reference to the storage unit that stores information indicating the patient's condition for each of multiple items,
A graph displaying the patient's condition in chronological order for at least two or more of the plurality of items is generated for each item.
The area around the selected part of the first graph showing the patient's condition of the first item in the generated graph in chronological order, and the area surrounded by the reference line and the first graph is as equal to or greater than a predetermined area accepts the selection in the periphery of the above portion, a first feature of the figure of the first graph near the portion selected, the graph for each of the two or more items that generated the graph Each second feature around the portion corresponding to the selected periphery of the selected portion in a plurality of graphs is identified.
A search method characterized by executing a process of specifying an item corresponding to a second graph having a second feature similar to the first feature. A storage unit that stores information indicating the patient's condition for each of multiple items,
A generator that generates a graph displaying the patient's condition in chronological order for at least two or more of the plurality of items for each item.
The area around the selected part of the first graph showing the patient's condition of the first item in the generated graph in chronological order, and the area surrounded by the reference line and the first graph is as equal to or greater than a predetermined area accepts the selection in the periphery of the above portion, a first feature of the figure of the first graph near the portion selected, the graph for each of the two or more items that generated the graph Each second feature around the portion corresponding to the selected periphery of the selected portion in a plurality of graphs is identified.
A search device comprising a search unit for specifying an item corresponding to a second graph having a second feature similar to the first feature.

Images