Document preparation support device, document preparation support method, and document preparation support program

Abstract

To provide a document preparation support device, a document preparation support method and a document preparation support program capable of effectively supporting preparation of a summary document.SOLUTION: An information processing system includes a user terminal used by a user such as a doctor or the like, and an information processing device. In an information processing device 14 being a document preparation support device, an acquisition part 70 acquires a medical document 52 with which patient information on an object patient inputted by the user and an object patient inputted by the user are associated. A derivation part 72 inputs the acquired patient information and a plurality of medical documents 52 in a determination model 56. The determination model 56 outputs the importance of an inspection item included in the plurality of medical documents 52. Thus, the derivation part 72 derives the importance of the inspection item included in the plurality of medical documents 52. An output part 74 outputs the acquired plurality of medical documents 52 and the importance of the inspection item derived by the derivation part 72.SELECTED DRAWING: Figure 9

Description

[Technical field]

[0001] The present disclosure relates to a document creation support device, a document creation support method, and a document creation support program. [Background technology]

[0002] Patent Document 1 discloses a technology for automatically searching for highly relevant medical reports from past medical reports by using words or word strings weighted according to the frequency of occurrence and importance of cases as keywords in order to automatically search for related case reports from among the text of past medical reports. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] JP 2012-141797 A Summary of the Invention [Problem to be solved by the invention]

[0004] In certain industries, summary documents are sometimes created by summarizing the contents of documents created daily after a certain period of time has passed. For example, in the medical industry, summary documents are created by summarizing the contents of documents created daily, such as medical records, at a specific time, such as when a patient is discharged from the hospital. When a user, such as a doctor, creates a summary document, it is preferable to be able to present important test items and test results from the documents created daily to the user, as this can assist in the creation of the summary document.

[0005] As a method for presenting important test items and test results, a method of outputting an alert when a test result is an abnormal value is known. However, a patient may have abnormal test results for multiple test items. In this case, an abnormal test result does not necessarily mean that the test result is important, so the user is required to determine whether the test result is important or not, even if the test result is an abnormal value. Even if the test result is a normal value, the user may be required to refer to the content or to include it in a summary document. In other words, there is room for improvement in terms of supporting the creation of a summary document by simply notifying the user that the test result is an abnormal value.

[0006] The present disclosure has been made in consideration of the above circumstances, and aims to provide a document creation support device, a document creation support method, and a document creation support program that can effectively support the creation of summary documents. [Means for solving the problem]

[0007] The document creation support device disclosed herein is a document creation support device that has at least one processor, which acquires document information associated with an inputted subject, derives the number of examination information contained in the document information for each examination item, and derives the importance of the examination item for the subject based on the derived number of examination information.

[0008] In addition, the document creation support method disclosed herein involves a processor provided in the document creation support device executing a process to obtain document information associated with the input subject, derive the number of examination information contained in the document information for each examination item, and derive the importance of the examination item for the subject based on the derived number of examination information.

[0009] In addition, the document creation support program disclosed herein is intended to cause a processor provided in the document creation support device to execute a process of acquiring document information associated with the inputted subject, deriving the number of examination information contained in the document information for each examination item, and deriving the importance of the examination item for the subject based on the derived number of examination information. Effect of the Invention

[0010] According to the present disclosure, it is possible to effectively support the creation of a summary document. [Brief description of the drawings]

[0011] [Figure 1] FIG. 1 is a block diagram illustrating an example of a configuration of an information processing system. [Diagram 2] FIG. 2 is a block diagram showing an example of a hardware configuration of a user terminal. [Diagram 3] FIG. 2 is a block diagram showing an example of a hardware configuration of an information processing device. [Figure 4] FIG. 4 is a diagram showing an example of a display screen. [Diagram 5] 10 is a block diagram showing an example of a functional configuration of an information processing device in a learning phase. FIG. [Figure 6] FIG. 13 is a diagram for explaining a prediction model. [Figure 7] FIG. 13 is a diagram for explaining a judgment model. [Figure 8] 13 is a flowchart illustrating an example of a learning process. [Figure 9] 1 is a block diagram showing an example of a functional configuration of an information processing device in an operation phase. FIG. [Figure 10] 13 is a flowchart illustrating an example of an importance derivation process. [Figure 11] FIG. 2 is a block diagram showing an example of a functional configuration of a user terminal. [Figure 12] FIG. 13 is a diagram showing an example of a created document display screen. [Figure 13] 13 is a flowchart illustrating an example of a display control process. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0012] Hereinafter, examples of embodiments for carrying out the technology of the present disclosure will be described in detail with reference to the drawings.

[0013] First, the configuration of an information processing system 10 according to the present embodiment will be described with reference to Fig. 1. As shown in Fig. 1, the information processing system 10 includes a user terminal 12 used by a user such as a doctor, and an information processing device 14. Examples of the user terminal 12 include a tablet computer and a personal computer. Examples of the information processing device 14 include a server computer and a cloud server. The information processing device 14 is an example of a document creation support device according to the disclosed technology.

[0014] The user terminal 12 and the information processing device 14 are each connected to a network, and are capable of transmitting and receiving data to and from each other.

[0015] Next, a hardware configuration of the user terminal 12 according to this embodiment will be described with reference to Fig. 2. As shown in Fig. 2, the user terminal 12 includes a CPU (Central Processing Unit) 20, a memory 21, a display 24, an input device 25, and a network I / F (Interface) 26.

[0016] The CPU 20 realizes various functions by executing programs stored in a storage unit 22, which will be described later.

[0017] The memory 21 includes a storage unit 22 and a RAM (Random Access Memory) 23. The RAM 23 is a memory for primary storage, and is, for example, a RAM such as an SRAM (Static Random Access Memory) or a DRAM (Dynamic Random Access Memory).

[0018] The storage unit 22 is a non-volatile memory, and is realized by, for example, at least one of a hard disk drive (HDD), a solid state drive (SSD), a flash memory, etc. The storage unit 22 as a storage medium stores a screen display program 30. The CPU 20 reads out the screen display program 30 from the storage unit 22, expands it in the RAM 23, and executes the expanded screen display program 30.

[0019] The screen display program 30 is a program for displaying various screens on the display 24 based on data received from the information processing device 14 via the network I / F 26. The screen display program 30 includes, for example, a web browser program.

[0020] The display 24 is a device for displaying various screens, and is, for example, a liquid crystal display or an EL (Electro Luminescence) display. The input device 25 is a device for a user to input, and is, for example, at least one of a keyboard, a mouse, a microphone for voice input, a touch pad for proximity input including contact, and a camera for gesture input. The network I / F 26 is an interface for connecting to a network. The bus 27 connects the CPU 20, the memory 21, the display 24, the input device 25, and the network I / F 26.

[0021] Next, a hardware configuration of the information processing device 14 according to the present embodiment will be described with reference to Fig. 3. As shown in Fig. 3, the information processing device 14 includes a CPU 40, a memory 41, a display 44, an input device 45, and a network I / F 46.

[0022] The CPU 40 realizes various functions by executing programs stored in a storage unit 42, which will be described later. The CPU 40 is an example of a processor according to the disclosed technology.

[0023] The memory 41 includes a storage unit 42 and a RAM 43. The RAM 43 is a memory for primary storage, and is, for example, a RAM such as an SRAM or a DRAM.

[0024] The storage unit 42 is a non-volatile memory and is realized by, for example, at least one of an HDD, an SSD, a flash memory, etc. The storage unit 42 as a storage medium stores an information processing program 50. The CPU 40 reads the information processing program 50 from the storage unit 42, loads it into the RAM 43, and executes the loaded information processing program 50.

[0025] Further, the storage unit 42 stores a plurality of medical documents 52 created by a user. The medical documents 52 are an example of document information related to the disclosed technology. The plurality of medical documents 52 are used to create a summary document. In this embodiment, an example will be described in which a user creates a summary document called a discharge summary while viewing the plurality of medical documents 52. That is, in this embodiment, an example will be described in which a patient who is being discharged from the hospital is applied as a subject for which a summary document is to be created. An example of the medical document 52 is an electronic medical record. In a learning phase described later, the medical document 52 is data for learning, and in an operation phase, it is actual data.

[0026] The medical document 52 is created for each patient, and by adding patient identification information such as a patient ID as attribute information of the medical document 52, it is possible to identify which patient the medical document 52 relates to. Note that the medical document 52 may be identified as to which patient it relates to by inputting the patient ID in a specific input field in the document or storing the medical document 52 in a folder for each patient. Similarly, the creation date of the medical document 52 is also made identifiable. The medical document 52 is not limited to an electronic medical record, and may be an image reading report and a medical fee statement called a receipt. Furthermore, the document information used to create the summary document is not limited to a medical document, and may be, for example, a research diary or other document. In this case, the user creates a research report by compiling multiple research diaries created daily. Furthermore, for example, the document information used to create the summary document may be a daily report, and the summary document may be a weekly report or monthly report that is a compilation of the daily reports.

[0027] Furthermore, the storage unit 42 stores a patient database 54 (hereinafter referred to as "patient DB 54"). The patient DB 54 stores patient identification information and patient information related to the patient in association with each other. Examples of the patient information include information about the patient himself / herself, such as the patient's gender and age, and information about the patient's hospitalization, such as the patient's hospitalization period, disease name, and test results during hospitalization.

[0028] The storage unit 42 also stores a determination model 56. The determination model 56 is obtained by machine learning in a learning phase, which will be described later. The determination model 56 will be described in detail later.

[0029] In this embodiment, a case will be described as an example in which the medical documents 52, the patient DB 54, and the determination model 56 are stored in the storage unit 42 of the information processing device 14, but the disclosed technology is not limited to this aspect. For example, at least one of the medical documents 52, the patient DB 54, and the determination model 56 may be stored in a separate data storage server, and at least one of the medical documents, the patient information, etc., and the determination result may be acquired via a network.

[0030] The display 44 is a device for displaying various screens, and is, for example, a liquid crystal display or an EL display. The input device 45 is a device for a user to input, and is, for example, at least one of a keyboard, a mouse, a microphone for voice input, a touch pad for proximity input including contact, and a camera for gesture input. The network I / F 46 is an interface for connecting to a network. The bus 47 connects the CPU 40, the memory 41, the display 44, the input device 45, and the network I / F 46.

[0031] Meanwhile, users such as doctors create medical documents 52 such as electronic medical records on a daily basis for hospitalized patients, and at specific times such as when the patient is discharged from the hospital, they create a new document called a discharge summary by consolidating multiple medical documents 52 created during the patient's hospitalization.

[0032] As shown in Figure 4, the information processing system 10 of this embodiment displays, on the display 24 of the user terminal 12, a new document creation screen 100 for creating a new document, and a created document display screen 102 that displays a medical document 52 as an example of a created document used to create the new document.

[0033] When a user creates a new summary document that consolidates multiple medical documents 52, the user must search for important test items and test results from among the multiple medical documents 52. This search takes time, and the user is unable to create the summary document efficiently. Therefore, the information processing system 10 according to this embodiment has a function of deriving the importance of test items contained in multiple medical documents 52.

[0034] Next, a functional configuration of the information processing device 14 in the learning phase will be described with reference to Fig. 5. As shown in Fig. 5, the information processing device 14 includes an acquisition unit 60, a first derivation unit 62, a second derivation unit 64, and a learning unit 66. The CPU 40 executes the information processing program 50 to function as the acquisition unit 60, the first derivation unit 62, the second derivation unit 64, and the learning unit 66.

[0035] The acquiring unit 60 acquires patient information input by the user regarding a patient (hereinafter, referred to as a "target patient") for which a new document is to be created. Specifically, the acquiring unit 60 acquires patient information associated with the identification information of the target patient input by the user from the patient DB 54. The patient information is an example of target information related to the disclosed technology.

[0036] The acquisition unit 60 also acquires medical documents 52 associated with the target patient input by the user. Specifically, the acquisition unit 60 acquires, based on the identification information of the target patient input by the user and a period for which a new document is to be created (hereinafter referred to as the "target creation period"), a plurality of medical documents 52 created within the target creation period for the target patient from the storage unit 42. The medical documents 52 created within the target creation period are an example of document information created within a specific period related to the disclosed technology. An example of the target creation period is the hospitalization period of one hospitalization of a patient. The identification information of the target patient and the target creation period are, for example, input by the user at the user terminal 12, and transmitted from the user terminal 12 to the information processing device 14. The acquisition unit 60 may acquire the hospitalization period of the target patient from the patient DB 54 as the target creation period.

[0037] The first derivation unit 62 derives the number of pieces of test information included in the medical documents 52 acquired by the acquisition unit 60 for each test item. In this embodiment, the test information includes a set of test date and time, test item, and test result. Specifically, the first derivation unit 62 derives the number of pieces of test information for each test item by comparing with dictionary data in which the names of test items are listed and counting the number of pieces of test information included in the medical documents 52 for each test item. In the dictionary data, multiple expressions may be associated with one test item. For example, multiple expressions such as "ALB", "albumin", "TP", and "A / G" may be associated with albumin, which is a test item. The dictionary data may be stored in advance in the storage unit 42 or another data storage server, or may be generated by inputting a new test item or the like by a user or acquiring the name of the test item from the test result included in the patient information. The first derivation unit 62 may compare the names of the test items included in the dictionary data by exact match or partial match. Also, for example, the first derivation unit 62 may treat a plurality of test items having a similarity of a certain value or more as the same test item and derive the number of pieces of test information for each test item. Examples of the similarity in this case include edit distance, BLEU (BiLingual Evaluation Understudy), ROUGE (Recall-Oriented Understudy for Gisting Evaluation), or BERT (Bidirectional Encoder Representations from Transformers) score.

[0038] More specifically, for example, when a plurality of medical documents 52 includes a set of test items and test results of "albumin 2.5", "albumin 2.4", and "albumin 3.0" as test information, the first derivation unit 62 derives 3 as the number of test information items corresponding to the test item "albumin". The first derivation unit 62 may derive the number of test information items for each set of test items and test results. In this case, the first derivation unit 62 derives 1 as the number of test information items corresponding to each of "albumin 2.5", "albumin 2.4", and "albumin 3.0" in the above example.

[0039] As shown in FIG. 6, the first derivation unit 62 may input the plurality of medical documents 52 acquired by the acquisition unit 60 in a state in which at least a portion of the medical documents 52 is masked, to a prediction model previously obtained by machine learning, thereby deriving the number of pieces of test information included in the plurality of medical documents 52 for each test item. This prediction model is a model in which the at least a portion of the masked medical documents 52 are input, and the test items included in the input medical documents 52 are output. The prediction model is a model obtained by machine learning using a set of the at least a portion of the masked medical documents 52 collected as learning data and the test items included in the medical documents 52. In this case, the portion masked by the first derivation unit 62 may be a portion corresponding to the test item, a portion of the test item, or a randomly selected portion. In this case, even if the plurality of medical documents 52 contain variations in the notation of the test item and typos of the test item, the number of pieces of test information is derived for the same test item.

[0040] The second derivation unit 64 derives the importance of the test item for the target patient based on the number of pieces of test information for each test item derived by the first derivation unit 62. In this embodiment, the second derivation unit 64 derives a higher importance of the test item as the number of pieces of test information for each test item increases. For example, the second derivation unit 64 sets two different thresholds and derives one of "high", "medium", and "low" as the importance of the test item by comparing the number of pieces of test information with the two thresholds. Note that the number of stages of importance is not limited to three stages, and may be two stages or four or more stages.

[0041] The second derivation unit 64 may derive the importance of the test item for the target patient based on the number of test information for each test item derived by the first derivation unit 62 and length information of the sentence including the test information. The test information included in the sentence summarized by the user is considered to be relatively important test information. Therefore, the second derivation unit 64 may derive the importance of the test item by weighting the number of test information using a weighting coefficient that is larger as the length of the sentence indicated by the length information of the sentence including the test information is shorter.

[0042] The second derivation unit 64 may derive the importance of the test item for the target patient based on the number of test information for each test item derived by the first derivation unit 62 and the number of types of test items included in the multiple medical documents 52. When the number of types of test items included in the multiple medical documents 52 is small, the performed test item is considered to be a relatively important test item. Therefore, the second derivation unit 64 may derive the importance of the test item by weighting the number of test information using a weighting coefficient that is larger as the number of types of test items included in the multiple medical documents 52 is smaller. Furthermore, compared to when the same test item is derived multiple times in the same medical document 52, when the same test item is derived multiple times in different medical documents 52, it is considered to be a relatively important item. Therefore, the second derivation unit 64 may decrease the importance as the number of test information derived to medical documents 52 with the same test item is smaller, or the number of medical documents 52 from which the test item is derived is smaller. For example, the second derivation unit 64 may derive the importance of the test item by weighting the number of test information using a weighting coefficient that is larger the smaller the number of test information derived into medical documents 52 with the same test item, or the smaller the number of medical documents 52 from which the test item is derived.

[0043] The second derivation unit 64 may also derive the similarity between sentences containing test information, and derive the importance of the test item for the target patient based on the number of test information for each test item derived by the first derivation unit 62 and the derived similarity. For example, when creating a new medical document 52, the user may copy the contents of the medical document 52 up to the previous day to the new medical document 52 and then add new contents. In this case, the test information included in the copied portion overlaps with the test information included in the medical document 52 up to the previous day, so the number of test information becomes relatively large. Therefore, the second derivation unit 64 may derive the importance of the test item by weighting the number of test information included in multiple sentences whose similarity is a certain value or more using a numerical value less than 1 as a weighting coefficient. For example, when the first derivation unit 62 derives the number of test information, the first derivation unit 62 may determine that multiple sentences whose similarity is a certain value or more are overlapping sentences, and exclude all but one of the multiple sentences. In addition, in the medical document 52, the examination items that are periodically performed may be defined as the designated description items. In this case, the examination items defined as the designated description items are described many times, but have low clinical importance. Therefore, the second derivation unit 64 may lower the importance of such examination items defined as the designated description items. For example, the second derivation unit 64 may determine whether the examination information derived in the medical document 52 is a designated description item, and when it is determined that the examination information is a designated examination item, the second derivation unit 64 may derive the importance of the examination item by weighting the number of examination information using a weighting coefficient that is smaller than the weighting coefficient when it is determined that the examination information is not a designated examination item. The designated description items may be saved as a list specified by the user, or a description item that appears more than a certain number of times or at a certain rate in a plurality of patients may be estimated as the designated description item. Note that the designated description items may be determined by any one of the medical facilities, medical departments, or doctors, and therefore a description item that appears more than a certain number of times or at a certain rate in the medical documents 52 of patients who share any one of the medical facilities, medical departments, or doctors may be estimated as the designated description item.

[0044] Further, the importance of each of the medical documents 52 may be associated with the medical document 52. In this case, the second derivation unit 64 may derive the importance of the test item for the target patient based on the number of test information for each test item derived by the first derivation unit 62 and the importance associated with the multiple medical documents 52 acquired by the acquisition unit 60. In this case, the second derivation unit 64 may derive the importance of the test item by weighting the number of test information using a weighting coefficient that is larger as the importance of the medical document 52 is higher. Note that the importance of the medical document 52 may be output based on a determination model that uses the medical document 52 as input and outputs the importance of the medical document 52, or may be determined based on a list that specifies the type information of the medical document 52 associated with the medical document 52, such as a nursing record or a doctor's chart, and the importance of each medical document 52. Note that the list that specifies the type information of the medical document 52 and the importance may be set in advance, or may be specified by the user.

[0045] In addition, when deriving the importance of a test item, the second derivation unit 64 may weight the number of test items including character information when the numerical information representing the test result of the test item is related to the character information representing the test result of the test item in a plurality of test information including the same test item. In this case, the second derivation unit 64 may weight the number of test items including character information by multiplying the number of test items including character information by a weighting coefficient greater than 1. This is because the test result is considered to be more important when the test result is expressed by character information related to numerical information, such as "CRP high value", than when the test result included in the test information is expressed by numerical information, such as "CRP 3.0", because the test result includes the user's interpretation of the test result. Examples of character information related to the numerical information of the test result include characters representing high and low values ​​of the test result, such as "high" and "low", characters representing the transition of the numerical value of the test result, such as "up" and "down", and characters representing the evaluation of the test result, such as "negative" and "benign". The text information referred to here also includes symbols such as an upward arrow symbol indicating an increase, a "+" symbol indicating a positive result, and a "-" symbol indicating a negative result.

[0046] In addition, when deriving the importance of a test item, the second derivation unit 64 may weight the number of pieces of test information if the test result included in the test information is text information and the text information represents the strength of the test result or the progress of the test result. In this case, the second derivation unit 64 may weight the number of pieces of test information including text information representing the strength of the test result or the progress of the test result by multiplying the number of pieces of test information including text information representing the strength of the test result or the progress of the test result by a weighting coefficient greater than 1. This is because, for example, when the character "strong" representing the strength of the test result is added to the character "negative" representing the test result, such as "strong negative," the test information is considered to be important because it includes the user's interpretation of the test result. In addition, for example, when the character "continued" representing the progress of the test result is added to the character "negative" representing the test result, such as "continued negative," the test information is considered to be important because it includes the user's interpretation of the test result.

[0047] As shown in FIG. 7, the learning unit 66 learns a judgment model 56, which receives the patient information and medical document 52 as input and outputs the importance of the test item, by using the patient information and medical document 52 acquired by the acquisition unit 60 and the importance of the test item derived by the second derivation unit 64 for the patient information and medical document 52 as learning data. The judgment model 56 is, for example, a neural network model, and is trained by a known algorithm such as an error backpropagation method. The input of the judgment model 56 may be either the patient information or the medical document 52. The output of the judgment model 56 may include the number of pieces of test information used when the importance of the test item is derived. The learning data of the learning unit 66 is data that indicates that the test item that appears in the summary document created based on the medical document 52 is more important than the test item that appears only in the medical document 52. For example, the learning unit 66 may use as learning data the importance determined based on the number of times or the rate of appearance of a test item that appears in the medical document 52, and then weighting it differently depending on whether or not the item appears or the number of times it appears in a summary document created based on the medical document 52.

[0048] Next, the operation of the information processing device 14 in the learning phase will be described with reference to Fig. 8. The CPU 40 executes the information processing program 50 to execute the learning process shown in Fig. 8. The learning process shown in Fig. 8 is executed, for example, when a command to start execution is input by a user.

[0049] 8, the acquisition unit 60 acquires patient information on the target patient input by the user as described above. Also, the acquisition unit 60 acquires a plurality of medical documents 52 associated with the target patient input by the user as described above. In step S12, the first derivation unit 62 derives, for each examination item, the number of examination information items included in the plurality of medical documents 52 acquired in step S10 as described above.

[0050] In step S14, the second derivation unit 64 derives the importance of the test item for the target patient based on the number of pieces of test information for each test item derived in step S12, as described above. In step S16, the learning unit 66 trains the judgment model 56 using the patient information and medical document 52 acquired in step S10 and the importance of the test item derived in step S14 for the patient information and medical document 52 as training data, as described above. When the processing of step S16 ends, the training process ends. The above training process is executed multiple times using various training data. In training the judgment model 56, the same training data may be used multiple times.

[0051] Next, a functional configuration of the information processing device 14 in the operation phase will be described with reference to Fig. 9. As shown in Fig. 9, the information processing device 14 includes an acquisition unit 70, a derivation unit 72, and an output unit 74. The CPU 40 executes the information processing program 50 to function as the acquisition unit 70, the derivation unit 72, and the output unit 74.

[0052] The acquiring unit 70 acquires patient information related to the target patient input by the user, similar to the acquiring unit 60. Also, the acquiring unit 70 acquires medical documents 52 associated with the target patient input by the user, similar to the acquiring unit 60.

[0053] The derivation unit 72 inputs the patient information and the multiple medical documents 52 acquired by the acquisition unit 70 to the determination model 56. The determination model 56 outputs the importance of the test items included in the multiple medical documents 52 input for the target patient represented by the input patient information. In this way, the derivation unit 72 derives the importance of the test items included in the multiple medical documents 52.

[0054] The output unit 74 outputs the multiple medical documents 52 acquired by the acquisition unit 70 and the importance of the test item derived by the derivation unit 72 to the user terminal 12 via the network I / F 46. The output unit 74 may output only medical documents 52 including test information in which the importance of the test item derived by the derivation unit 72 is equal to or higher than a certain level, among the multiple medical documents 52 acquired by the acquisition unit 70. The output unit 74 may further output the number of pieces of test information to the user terminal 12. In this case, the judgment model 56 is trained to further output the number of pieces of test information.

[0055] Next, the action of the information processing device 14 in the operation phase will be described with reference to Fig. 10. The CPU 40 executes the information processing program 50 to execute the importance derivation process shown in Fig. 10. The importance derivation process shown in Fig. 10 is executed, for example, when a command to start execution is input by a user.

[0056] 10, the acquisition unit 70 acquires patient information on the target patient input by the user as described above. Also, the acquisition unit 70 acquires a plurality of medical documents 52 associated with the target patient input by the user as described above.

[0057] In step S22, the derivation unit 72 derives the importance of the test item by inputting the patient information and the multiple medical documents 52 acquired in step S20 into the judgment model 56, as described above. In step S24, the output unit 74 outputs the multiple medical documents 52 acquired in step S20 and the importance of the test item derived in step S22 to the user terminal 12 via the network I / F 46. When the processing of step S24 ends, the importance derivation processing ends.

[0058] Next, a functional configuration of the user terminal 12 will be described with reference to Fig. 11. As shown in Fig. 11, the user terminal 12 includes an acquisition unit 80 and a display control unit 82. The CPU 20 executes the screen display program 30 to function as the acquisition unit 80 and the display control unit 82.

[0059] The acquiring unit 80 acquires the plurality of medical documents 52 and the importance of the examination items transmitted from the information processing device 14 via the network I / F 26.

[0060] As described above, the display control unit 82 causes the display 24 to display a new document creation screen 100 for creating a new document and a created document display screen 102 for displaying the medical document 52 used to create the new document (see FIG. 4). In this embodiment, the display control unit 82 causes at least one examination information of the examination information included in at least one of the patient information and the multiple medical documents 52 based on the multiple medical documents 52 acquired by the acquisition unit 80 and the importance of the examination items, on the created document display screen 102. The display of the examination information includes, for example, at least one of display of examination information extracted from at least one of the patient information and the medical documents 52, or display of the medical document 52 including the examination information to be displayed. In addition, the display of the examination information may include display of the medical document 52 in which the examination information to be displayed is highlighted relatively to other examination information.

[0061] For example, as shown in Fig. 12, the display control unit 82 may display test information grouped by test item on the created document display screen 102. Fig. 12 shows an example in which a button 110 for the user to select a test item, and test date and test results corresponding to the test item selected by the user are displayed on the created document display screen 102. Fig. 12 also shows an example in which albumin is selected by the user.

[0062] The display control unit 82 may display only the examination information including the examination items having a certain level of importance or higher among the examination information included in the multiple medical documents 52 on the created document display screen 102. The display control unit 82 may also display the examination information, together with the examination information, on the created document display screen 102, as well as the importance of the examination items and the number of pieces of examination information for each examination item. The display control unit 82 may also change the display mode of the examination information on the created document display screen 102 according to the importance. Examples of a method for changing the display mode in this case include a method of changing the background color or a method of changing the display color of the characters. For example, the display control unit 82 may highlight the examination information including the examination items having a relatively high importance compared to the examination information including the examination items having a relatively low importance when displaying the examination information in a table format. For example, the display control unit 82 may set the background color or the display color of the characters of the cells showing the examination information including the examination items having a relatively high importance to a color that is visually noticeable compared to the examination information including the examination items having a relatively low importance when displaying the examination information in a table format. In this case, the display control unit 82 may also set the background color or text display color of a cell indicating test information including test items with a relatively low level of importance to a color that is visually less noticeable compared to test information including test items with a relatively high level of importance.

[0063] The display control unit 82 may also display the test information in the created document display screen 102 in order of the importance of the test items. When the test information being displayed on the created document display screen 102 is selected by the user, the display control unit 82 may display the medical document 52 including the selected test information. In this case, the display control unit 82 may scroll the medical document 52 so that the test information including the test items in the medical document 52 whose importance is equal to or higher than a certain level is displayed in the created document display screen 102. In this case, a marker indicating the position of the test information including the test items in the medical document 52 whose importance is equal to or higher than a certain level may be displayed on the scroll bar.

[0064] Furthermore, the display control unit 82 may display a plurality of medical documents 52 on the created document display screen 102, and highlight test information including test items with a relatively high level of importance in the medical documents 52 relative to test information including test items with a relatively low level of importance. Furthermore, the display control unit 82 may display, on the created document display screen 102, only medical documents 52 that, among the plurality of medical documents 52, include test information including test items with a certain level of importance or higher.

[0065] Furthermore, the display control unit 82 may separately display, on the created document display screen 102, a display area for displaying test information including important test results preset for each disease, and a display area for displaying test information based on the importance derived by the information processing device 14. Furthermore, the display control unit 82 may specify, on the created document display screen 102, an examination date that is included in an examination item having an importance level of a certain degree or higher and that appears more than a threshold number of times in multiple medical documents 52. In this case, the display control unit 82 may highlight the specified examination date relative to other examination dates when displaying a transition graph of the examination results, etc.

[0066] Next, the operation of the user terminal 12 will be described with reference to Fig. 13. The CPU 20 executes the screen display program 30 to execute the display control process shown in Fig. 13. The display control process shown in Fig. 13 is executed, for example, when the user terminal 12 receives a plurality of medical documents 52 and the importance of the examination items transmitted from the information processing device 14 by the process of step S24 above.

[0067] In step S30 of Fig. 13, the acquisition unit 80 acquires the multiple medical documents 52 and the importance of the examination items transmitted from the information processing device 14 via the network I / F 26. In step S32, the display control unit 82 causes the display 24 to display a new document creation screen 100 for creating a new document and a created document display screen 102 for displaying the medical documents 52 used to create the new document. At this time, as described above, the display control unit 82 causes at least one piece of examination information included in the multiple medical documents 52 to be displayed on the created document display screen 102 based on the multiple medical documents 52 and the importance of the examination items acquired in step S30. When the process of step S32 ends, the display control process ends.

[0068] As described above, according to this embodiment, it is possible to effectively assist in creating a summary document.

[0069] In the above embodiment, the derivation unit 72 derives the importance of the test item using the judgment model 56 obtained by machine learning, but the disclosed technology is not limited to this aspect. For example, the derivation unit 72 may derive the importance of the test item on a rule basis. In this case, the derivation unit 72 may derive the number of pieces of test information for each test item in the same manner as the first derivation unit 62, and then derive the importance of the test item based on the number of pieces of test information for each test item in the same manner as the second derivation unit 64.

[0070] In addition, although the case where the first derivation unit 62 derives the number of pieces of test information included in the multiple medical documents 52 for each test item has been described, the disclosed technology is not limited to this aspect. For example, the first derivation unit 62 may derive the number of pieces of test information included in each medical document 52 for each test item for each medical document 52. In this case, when a common test item is included in each medical document 52, the first derivation unit 62 may set a representative value of the number of pieces of test information including the common test item derived for each medical document 52 as the number of pieces of test information for that test item. Examples of the representative value in this case include a maximum value, an average value, a median value, or the like.

[0071] In the above embodiment, the user terminal 12 may include at least some of the functional units included in the information processing device 14, or the information processing device 14 may include at least some of the functional units included in the user terminal 12. For example, the new document creation screen 100 may be generated by the information processing device 14 and provided to the user terminal 12 in a streaming manner. Also, each functional unit included in the user terminal 12 and the information processing device 14 may be included in a single computer.

[0072] In the above embodiment, the following various processors can be used as the hardware structure of a processing unit that executes various processes, such as each functional unit of the user terminal 12 and each functional unit of the information processing device 14. As described above, the above various processors include a CPU, which is a general-purpose processor that executes software (programs) and functions as various processing units, as well as a programmable logic device (PLD), which is a processor whose circuit configuration can be changed after manufacture, such as an FPGA (Field Programmable Gate Array), a dedicated electric circuit, which is a processor having a circuit configuration designed specifically for executing specific processes, such as an ASIC (Application Specific Integrated Circuit), etc.

[0073] A single processing unit may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, multiple processing units may be configured with a single processor.

[0074] As an example of configuring multiple processing units with one processor, first, there is a form in which one processor is configured with a combination of one or more CPUs and software, as typified by computers such as client and server, and this processor functions as multiple processing units. Second, there is a form in which a processor is used that realizes the functions of the entire system including multiple processing units with one IC (Integrated Circuit) chip, as typified by System on Chip (SoC), etc. In this way, the various processing units are configured using one or more of the above various processors as a hardware structure.

[0075] Furthermore, more specifically, the hardware structure of these various processors can be an electric circuit that combines circuit elements such as semiconductor elements.

[0076] In addition, in each of the above embodiments, the screen display program 30 is described as being stored (installed) in advance in the storage unit 22, but the present invention is not limited to this. The screen display program 30 may be provided in a form recorded on a recording medium such as a CD-ROM (Compact Disc Read Only Memory), a DVD-ROM (Digital Versatile Disc Read Only Memory), or a USB (Universal Serial Bus) memory. The screen display program 30 may also be downloaded from an external device via a network.

[0077] In the above embodiment, the information processing program 50 is stored (installed) in advance in the storage unit 42, but the present invention is not limited to this. The information processing program 50 may be provided in a form recorded on a recording medium such as a CD-ROM, a DVD-ROM, or a USB memory. The information processing program 50 may be downloaded from an external device via a network.

[0078] The following supplementary notes are further disclosed regarding the above embodiment. (Appendix 1) A document creation support device having at least one processor, The processor, Obtain document information associated with the entered subject, Derive the number of pieces of examination information included in the document information for each examination item; Derive the importance of the test item for the subject based on the number of derived test information. Document creation support device.

[0079] (Appendix 2) The processor, further acquiring subject information regarding the subject; The number of pieces of examination information included in the document information created during a specific period is derived for each examination item based on the subject information. 2. A document creation support device as described in appendix 1.

[0080] (Appendix 3) The processor, A judgment model having at least one of the subject information and the document information as an input and outputting the importance of the inspection item is trained using at least one of the acquired document information and the subject information and the importance derived for at least one of the document information and the subject information as training data. 3. A document creation support device as described in appendix 2.

[0081] (Appendix 4) The processor, A prediction model in which at least partially masked document information is input and inspection items are output, and the number of inspection items included in the obtained document information is derived by inputting the obtained document information in a state in which at least a portion of the document information is masked to a prediction model previously obtained by machine learning. 4. A document creation support device according to any one of claims 1 to 3.

[0082] (Appendix 5) The processor, The importance is derived based on the number of pieces of derived test information and length information of the sentence including the test information. 5. A document creation support device according to any one of claims 1 to 4.

[0083] (Appendix 6) The processor, The importance is derived based on the number of pieces of derived inspection information and the number of types of inspection items included in the document information. 6. A document creation support device according to any one of claims 1 to 5.

[0084] (Appendix 7) The processor, Deriving a similarity between sentences including the inspection information; The importance is derived based on the number of pieces of derived inspection information and the derived similarity. 7. A document creation support device according to any one of claims 1 to 6.

[0085] (Appendix 8) The document information is associated with a level of importance of the document information; The processor, Derive the importance of the examination item for the subject based on the number of derived examination information and the importance associated with the acquired document information. 8. A document creation support device according to any one of claims 1 to 7.

[0086] (Appendix 9) The processor, In the case where numerical information representing the test result of the test item is related to character information representing the test result of the test item in a plurality of test information including the same test item, weighting is performed on the number of the test information including the character information. 9. A document creation support device according to any one of claims 1 to 8.

[0087] (Appendix 10) The processor, When the test result included in the test information is text information and the text information indicates the strength of the test result or the progress of the test result, the number of pieces of test information is weighted. 9. A document creation support device according to any one of claims 1 to 8.

[0088] (Appendix 11) Obtain document information associated with the entered subject, Derive the number of pieces of examination information included in the document information for each examination item; Derive the importance of the test item for the subject based on the number of derived test information. A document creation support method in which processing is executed by a processor included in a document creation support device.

[0089] (Appendix 12) Obtain document information associated with the entered subject, Derive the number of pieces of examination information included in the document information for each examination item; Derive the importance of the test item for the subject based on the number of derived test information. A document creation support program for causing a processor included in the document creation support device to execute processing. [Explanation of symbols]

[0090] 10. Information Processing Systems 12 User terminal 14 Information processing equipment 20, 40 CPUs 21, 41 Memory 22, 42 Storage section 23, 43 RAM 24, 44 Display 25, 45 Input device 26, 46 Network I / F 27, 47 Bus 30 Screen display program 50 Information Processing Program 52 Medical Documents 54 Patient DB 56 Decision Model 60, 70, 80 acquisition part 62 1st derivation part 64 Second derivation part 66 Learning Department 72 Derivation part 74 Output section 82 Display control section 100 New document creation screen 102 Created document display screen 110 Button

Claims

1. A document creation support device having at least one processor, The processor, Obtain document information associated with the entered subject, Derive the number of pieces of examination information included in the document information for each examination item; Derive the importance of the test item for the subject based on the number of derived test information. Document creation support device.

2. The processor, further acquiring subject information regarding the subject; The number of pieces of examination information included in the document information created during a specific period is derived for each examination item based on the subject information.

2. The document creation support device according to claim 1.

3. The processor, A judgment model having at least one of the subject information and the document information as an input and outputting the importance of the inspection item is trained using at least one of the acquired document information and the subject information and the importance derived for at least one of the document information and the subject information as training data.

3. The document creation support device according to claim 2.

4. The processor, A prediction model in which at least partially masked document information is input and inspection items are output, and the number of inspection items included in the obtained document information is derived by inputting the obtained document information in a state in which at least a portion of the document information is masked to a prediction model previously obtained by machine learning. The document creation support device according to any one of claims 1 to 3.

5. The processor, The importance is derived based on the number of pieces of derived test information and length information of the sentence including the test information. The document creation support device according to any one of claims 1 to 3.

6. The processor, The importance is derived based on the number of pieces of derived inspection information and the number of types of inspection items included in the document information. The document creation support device according to any one of claims 1 to 3.

7. The processor, Deriving a similarity between sentences including the inspection information; The importance is derived based on the number of pieces of derived inspection information and the derived similarity. The document creation support device according to any one of claims 1 to 3.

8. The document information is associated with a level of importance of the document information; The processor, Derive the importance of the examination item for the subject based on the number of derived examination information and the importance associated with the acquired document information. The document creation support device according to any one of claims 1 to 3.

9. The processor, In the case where numerical information representing the test result of the test item is related to character information representing the test result of the test item in a plurality of test information including the same test item, weighting is performed on the number of the test information including the character information. The document creation support device according to any one of claims 1 to 3.

10. The processor, When the test result included in the test information is text information and the text information indicates the strength of the test result or the progress of the test result, the number of pieces of test information is weighted. The document creation support device according to any one of claims 1 to 3.

11. Obtain document information associated with the entered subject, Derive the number of pieces of examination information included in the document information for each examination item; Derive the importance of the test item for the subject based on the number of derived test information. A document creation support method in which processing is executed by a processor included in a document creation support device.

12. Obtain document information associated with the entered subject, Derive the number of pieces of examination information included in the document information for each examination item; Derive the importance of the test item for the subject based on the number of derived test information. A document creation support program for causing a processor included in the document creation support device to execute processing.

Images