JP2017191457A - Report creation apparatus and control method thereof - Google Patents

Abstract

PROBLEM TO BE SOLVED: To create a report more easily using an input template.SOLUTION: A medical report creation apparatus for creating a medical report structured with a plurality of items with different attributes, supports a user creating a medical report, by use of an input template having item names of detailed items to be described in each of the items and input candidates. The medical report creation apparatus searches for an input candidate from descriptions input in a medical report, by use of a search condition described in association with the detailed items in the input template, and adds the searched input candidate to the input candidate of the detailed item associated with the search condition, to be used for creation support.SELECTED DRAWING: Figure 3

Description

  The present invention relates to a report creation apparatus and a control method thereof.

  In a medical field, an interpretation report for reporting a result of image diagnosis using a medical image is created. With the digitization of X-ray imaging apparatuses and the digitization of medical images by CT (Computed Tomography), MRI (Magnetic Resonance Imaging), etc., the interpretation report has been digitized.

  The interpretation report includes description contents called findings that describe events and phenomena recognized and discovered by doctors in medical images, and description contents called diagnoses that point out suspected diseases based on the findings. Findings and diagnoses are often written in text and are therefore treated as textual information. There is a logical relationship between the findings and the description of the diagnosis, such as cause and effect based on the knowledge of the doctor. Such a relationship may be omitted for obvious reasons, or may be explicitly described in a sentence, and further, the description method varies depending on doctors. Such fluctuation of the description becomes a factor that increases the time required for the doctor who requested the radiographing / interpretation to read the contents of the interpretation report and a factor of misreading.

  In recent years, the creation of structured interpretation reports has been proposed in order to clearly express the relationship between findings, diagnosis, and medical images. In addition, it has been proposed to be able to express and describe the relationship between findings and diagnoses in a plurality of related interpretation reports. Such a structure enables the user to easily check and edit the relationship between each description such as medical images, findings, and diagnoses described or attached to single or multiple interpretation reports. It is coming. Creation of a structured interpretation report is performed by displaying the structure on the screen and inputting characters while performing operations on the structure. In order to prevent omission of necessary information, an input template is often used. Also, the input content is prepared as input candidates in the input template, and character input can be performed by selecting a desired input candidate from the input template, thereby simplifying the input operation. It is generally done.

  In Patent Document 1 and Patent Document 2, a technique using an input template is described, and an input template is searched from information such as a target part. The input template has a description content candidate for each input item, and an item can be input by selecting the input candidate. Moreover, in patent document 1, it has a function which produces | generates a text from the input content of an item unit, and it is the same for reusing the description content and clarifying the instruction | indication with respect to the same target object from the already described report. Takeover takes place so that the representation is used.

  Patent Document 3 includes an input part with a hole in a written sentence, and in the input template described in the input part, a configuration in which other input part candidates are changed according to the content selected for a certain input part Is described. A perforated hole here is a portion that needs to be entered but is not yet described. Patent Document 4 describes that the interpretation report generation system recommends the contents that the user wants to input, and guides the input contents so that input is performed from items that are effective in the diagnosis result and need to be described. ing.

JP 2012-048395 A JP 2008-146220 A JP 2002-123605 A JP 2014-061397 A

  As described in Patent Documents 1 to 4, it is a basic function of an input template to show a user an item that needs to be described and to indicate input candidates corresponding to the item. In addition, it is common practice to select or narrow down input candidates held by an input template from the contents of an interpretation report being created.

  However, in the interpretation report, in order to be able to describe the same content, there is no one that obtains input candidates for the input template from the description content in the report. In the interpretation report, the same content as the input content may be described or the same content may be described in a different form or format. As described above, there has not been proposed a technique that takes into account input support using an input template when a description format or form is changed according to the purpose of use.

  The present invention has been made in view of the above problems, and an object of the present invention is to make it easier to reuse described contents in report creation using an input template.

In order to achieve the above object, a report creation apparatus according to an aspect of the present invention has the following arrangement. That is,
A medical report creation device for creating a medical report structured by a plurality of items having different attributes,
A support means for supporting creation of a medical report by a user, using an input template that holds item names and input candidates of detailed items to be described in each of the plurality of items;
Search means for searching for input candidates from the already entered description of the medical report using a search condition described in association with a detailed item in the input template;
In order to support creation by the support means, an adding means for adding the input candidate searched by the search means to the input candidate of the detailed item associated with the search condition is provided.

  According to the present invention, in the report creation using the input template, the described content can be reused more easily.

The figure which shows the structural example of the information processing apparatus by embodiment. The figure which shows the structural example of the interpretation report production system by embodiment. The figure which shows the function structural example of the interpretation report production system of embodiment. The figure which shows the example of the screen of the medical image viewer of embodiment. The figure which shows the example of the interpretation report creation screen of embodiment. The figure which shows the other example of the interpretation report creation screen of embodiment. The flowchart which shows the interpretation report creation process of embodiment. (A) is a figure which shows the example sentence described in the interpretation report, (b) is a figure which shows the analysis result of the example sentence shown to (a). The figure which shows the example of the template for input used at the time of interpretation report preparation. The figure which shows the example of a screen of the state which added the input candidate at the time of interpretation report preparation. The flowchart which shows the addition process of the input candidate at the time of interpretation report preparation. The figure explaining an example of the process which adds the input candidate at the time of interpretation report preparation. The figure which shows the example of a screen of the state which added the input candidate at the time of interpretation report preparation from description content. The figure explaining an example of the process which adds the input candidate at the time of interpretation report preparation.

  Hereinafter, preferred embodiments of the present invention will be described in detail with reference to the accompanying drawings.

  In the embodiment, a medical report creation system for supporting creation of various medical reports will be described. The medical report creation system of this embodiment is a server / client system having a server and a client that can communicate with each other. In the following, a medical report creation system that supports creation of an interpretation report as an example of a medical report will be described. First, with reference to FIG. 1, the internal structure of the information processing apparatus which comprises the server client system of embodiment is demonstrated. FIG. 1 is a diagram showing a schematic configuration example of an information processing apparatus 100 that operates as a server or a PC client in the server / client system as shown in FIG.

  The CPU 101 implements various controls in the present embodiment by executing programs stored in the ROM 102 and the RAM 103. Also, a plurality of programs can be operated in parallel by the function of the CPU 101 itself or the function of the program. The ROM 102 stores programs and data in which the control procedure by the CPU 101 is stored. The RAM 103 stores a program to be processed by the CPU 101 and provides a work area when the CPU 101 executes various controls.

  The input device 104 provides an input operation environment for the user. Specific examples of the input device 104 include a keyboard, a mouse, and the like. However, any device such as a touch panel or a stylus pen may be used as long as it provides a user input operation environment. Moreover, you may make it receive the input by voice recognition or gesture operation. The bus 105 includes an address bus and a data bus that connect the above-described or below-described components in the information processing apparatus 100, and provides information exchange and communication functions between the components. Thereby, each structure can operate | move in cooperation.

  The external storage device 106 stores various programs and data. The external storage device 106 includes a recording medium such as a hard disk, a floppy disk, an optical disk, a magnetic disk, a magnetic tape, and a nonvolatile memory card, and a drive that drives the storage medium to record information. All or part of the programs and data stored in the external storage device 106 are called up on the RAM 103 when necessary by an instruction from a keyboard or the like or instructions from various programs.

  The network communication unit (NCU 107) communicates with an external device (not shown) via the network 210 (LAN) in FIG. Thereby, it becomes possible to share the program and data of this embodiment. The communication form of the NCU 107 includes wired communication such as RS232C, USB, IEEE1394, P1284, SCSI, modem, Ethernet, wireless communication such as Bluetooth (registered trademark), infrared communication, IEEE802.11a / b / n, etc. Anything is fine.

  The graphic processing unit (GPU 108) generates an image of display contents according to a display instruction or a calculation instruction given from the CPU 101 or the like via the bus 105, calculates a display position, and the like, and displays the generation result and the calculation result on a display device 109 to execute drawing. Further, the GPU 108 may perform calculation processing in cooperation with the CPU 101 by returning the calculation result to the CPU 101 via the bus 105. The display device 109 is configured by a liquid crystal display or the like, and displays various input operation states and calculation results corresponding to the user under the control of the CPU 101 and the GPU 108.

  A storage medium such as the ROM 102 or the RAM 103 stores a program, data, and the like that realize data management according to the present embodiment. The CPU 101 realizes various functions by reading and executing programs stored in these recording media. In addition, by supplying an external recording medium (not shown) storing programs and data according to the present embodiment to the information processing apparatus 100, the programs and data are copied from the external recording medium to the RAM 103 and used. Also good. As such an external storage medium, any recording medium such as a floppy disk, a CD-ROM, a hard disk, a memory card, and a magneto-optical disk can be used.

  The program and data used in the present embodiment may be obtained via the NCU 107. Similarly, the data created in the present embodiment may be stored not only in the ROM 102, RAM 103, and external storage device 106 but also in other devices via the NCU 107.

  The internal configuration of the information processing apparatus 100 described above is merely an example, and the present embodiment is not limited to this. Further, the internal configuration and a part thereof are not limited to so-called hardware, and may be virtually created by software. Further, not only when the internal configuration described above is used alone, but also by using a plurality of internal configurations shown in FIG. It does not matter if it is realized. In other words, in the case of multiple use, each internal configuration may be in a different location, and may be configured to cooperate with each other via a LAN or the Internet, or an internal configuration created virtually by software is included. It may be. Furthermore, the usage method may be such that the internal configuration is shared such that all or some of the systems such as a plurality of servers and PC clients are operated on the single internal configuration of FIG.

  FIG. 2 is a diagram illustrating a schematic configuration example of the entire server / client system according to the embodiment. In the embodiment, the system as shown in FIG. 2 provides a support function for performing image diagnosis using medical images such as CT and MRI performed at a medical site and creating the result as an interpretation report. . In the following, in order to simplify the explanation, creation of an interpretation report will be described, but the present invention is not limited to this. For example, even if the contents of the interpretation report are described in the electronic medical record text and managed together, it is clear that it can be realized with the same configuration as the system described below, except for the description target and management system It is.

  The requesting doctor 201 is a clinician such as internal medicine or surgery. Interpretation doctor 202 is a radiology doctor who interprets medical images such as CT and MRI. The medical engineer 203 uses the imaging device 217 such as CT or MRI to image the patient 204. The requesting doctor 201, the interpretation doctor 202, and the medical engineer 203 use their respective PC clients 211, 213, and 215 for work, and perform their work using services (server services) on various servers.

  In the embodiment, the PC clients 211, 213, and 215 are the information processing apparatus 100 described above, and are realized by, for example, a personal computer. However, the present invention is not limited to this, and the PC clients 211, 213, and 215 may be in the form of a tablet terminal, a smartphone, a mobile phone, or the like, or may be realized by a personal computer virtually created on a server. Good. Further, the PC clients 211, 213, and 215 may be realized by separate devices, or may be realized by the same device. In any form, a function of a desired service is provided to the user by operating a client application that operates in cooperation with a server / service that the user wants to use on the PC client.

  The PC clients 211, 213, and 215 are connected to the network 210 via the NCU 107 and communicate with servers that provide various services. When using the server service, the PC clients 211, 213, and 215 operate a client application corresponding to the service. In FIG. 2, PC clients 211, 213, and 215 operate client applications 212, 214, and 216, respectively. The client applications 212, 214, and 216 may be installed in advance in the external storage device 106 or the ROM 102, for example, or may be downloaded from each server or server service via the NCU 107 and the network 210.

  The client applications 212, 214, and 216 are executed by the CPU 101 of each PC client, communicate with each server and service via the NCU 107 and the network 210, and provide the service to the user in cooperation with each server. Further, the client applications 212, 214, and 216 transmit user operation instructions and operation intentions obtained by using the input device 104 to the server service through communication via the NCU 107. In addition, the client applications 212, 214, and 216 communicate with the server service and provide the user with results and information provided by the server service using the display device 109. The users referred to here are the requesting doctor 201, the interpretation doctor 202, and the medical engineer 203.

  An imaging device 217 that captures a medical image is connected to the network 210. Various imaging settings in the imaging apparatus 217 and provision of obtained medical images are controlled and managed from various server services and PC clients 211, 213, and 215 via the network 210.

  The inspection order server 221 is used when performing inspection. The examination order server 221 uses the examination order management service 222 to provide a function for registering, storing, referencing, sharing, instructing, and managing examination order information from the requesting doctor 201. More specifically, the examination order management service 222 receives the examination instruction from the requesting doctor 201 and its contents, registers and manages it as the examination order 223, and notifies the medical engineer 203 and the interpretation doctor 202 of the examination order 223. Make a provision. Further, the inspection order management service 222 captures and stores the inspection result when the inspection is completed, or stores information associated with the inspection result on the server or the service providing the inspection result, and the requesting doctor 201 stores the inspection result. Make it available.

  Further, the inspection order management service 222 may have a function of performing a use schedule of inspection equipment including the inspection image photographing device 217, assignment / management of a person in charge of the inspection engineer and a schedule, and the like. In this case, the inspection order management service 222 provides a function for presenting an empty schedule of the inspection equipment and inspection engineer that can be executed and the person in charge of the inspection equipment and inspection engineer to be used in response to the input of the inspection instruction and content of the requesting doctor 201. It also has a function of performing allocation and the like.

  The electronic medical record server 224 uses the electronic medical record management service 225 to provide functions for storing, describing, referring to, sharing, and managing electronic medical record information (hereinafter, electronic medical record 226). The electronic medical record management service 225 accumulates and manages the electronic medical record 226 for each patient described by the requesting doctor 201 and related medical staff, and enables the electronic medical record 226 to be shared between doctors and medical staff.

  The medical image server 227 provides a function of storing, describing, referencing, sharing, and managing the medical image 229 using the medical image management service 228. The medical image management service 228 accumulates medical images 229 taken by the medical engineer 203 or obtained from the outside, and provides an environment for related medical staff such as the requesting doctor 201 and the interpretation doctor 202 to refer to and share. To do.

  The interpretation report server 230 provides a function for creating, registering, storing, managing, referring to, and sharing the interpretation report 234 created by the interpretation doctor 202 using the interpretation report management service 233. The interpretation report work management service 232 provides interpretation support for the interpretation doctor 202 such as assignment of interpretation report creation work, maintenance and management of work status, management of work progress information and correction history information. . For example, the image interpretation doctor 202 interprets a medical image 229 that is captured by the imaging device 217 and stored in the medical image server 227 via the network 210, and describes the result in an image interpretation report that can be referred to by the requesting doctor 201. The interpretation report work management service 232 provides a workflow cooperation operation regarding such an interpretation report.

  The interpretation report structuring service 231 provides an interpretation report creation function to the interpretation doctor 202. At this time, the interpretation report structuring service 231 provides the description contents of the interpretation report in a structured manner so that the interpretation doctor 202 can edit and input the contents. As a result, the interpretation report structuring service 231 realizes a function that supports the creation, input, and editing of an interpretation report by the interpretation doctor 202.

  In the present embodiment, each server such as the examination order server 221, the electronic medical record server 224, the medical image server 227, and the image interpretation report server 230 is a server-type computer (information processing apparatus). Server services (222, 225, 228, 231, 232, 233) operate on each server type computer. The server service may be realized by cooperation of a plurality of computers, or a plurality of server configurations may be provided so as to realize each function in the service, and such a configuration may be provided via a network, the Internet, etc. It may be realized by a spatially different computer. In any form, the server / service that the user wants to use is operated on the server, and the client application that operates on the PC client communicates and cooperates with the server / service to provide the user with a desired service function. If it is.

  That is, these servers have one or a plurality of internal configurations shown in FIG. Then, by connecting to the network 210 via the NCU 107, communication is performed with client applications (212, 214, 216, etc.) on the PC clients (211, 213, 215, etc.) corresponding to the service. The client application corresponding to the server service may be installed in advance in the external storage device 106 or the ROM 102, or may be downloaded from each server or server service via the NCU 107 and the network 210. Then, the CPU 101 of the PC client arranges and operates such a client application on the RAM 103. In this way, each server service communicates with each PC client and client application via the NCU 107 and the network 210 to provide functions to the user. This also conveys user operation instructions and intentions from the PC client and client application, operates the provided functions that are the essence of the server service, and processes results and information to the PC client and client application. Communicated.

  The interpretation report creation system according to the embodiment having the above-described configuration performs a cooperative operation regarding an interpretation report in the following workflow.

  First, when making a diagnosis of the patient 204, the requesting doctor 201 generates an examination order from the PC client 211 when he / she wants to refer to an interpretation report as an interpretation result in addition to medical images such as CT and MRI. The requesting doctor 201 uses the client application 214 corresponding to the examination order management service 222 on the PC client 213 to generate the order information by inputting the target patient, imaging contents, method, and the like. The order information is transmitted to the inspection order management service 222 via the network 210. The inspection order management service 222 stores and manages the transmitted order information as the inspection order 223. The examination order 223 is transmitted as information on the imaging instruction from the examination order management service 222 to the PC client 215 of the medical technician 203 who is in charge of imaging as appropriate. The transmission of the imaging instruction information is performed by the medical engineer 203 using the client application 216 corresponding to the examination order management service 222 on the PC client 215.

  Next, based on the contents of the examination order 223, the medical engineer 203 uses the imaging device 217 for obtaining the designated examination image to photograph the designated patient 204 using the designated imaging method. . The client application 216 transmits the examination image as the imaging result to the medical image management service 228 via the network 210. The medical image management service 228 registers and stores the transmitted examination images as medical images 229 and manages them. The examination order management service 222 is notified of the completion of imaging regarding the examination order 223 and the management information when the medical image 229 is registered. The inspection order management service 222 updates the contents of the corresponding inspection order by this notification. Since the examination order 223 requests an interpretation report of the taken medical image, the examination order management service 222 transmits interpretation instruction information to the interpretation doctor 202 in charge of interpretation. This transmission is performed by the image interpretation doctor 202 using a client application corresponding to the examination order management service 222 on the PC client 213.

  The image interpretation doctor 202 performs an image interpretation operation on the medical image instructed by the examination order 223. The image interpretation doctor 202 can identify and refer to a medical image to be interpreted from the medical image 229 held by using the examination order 223. Further, based on the patient information of the examination order 223, the electronic medical record of the patient 204 can be identified and referred to from the electronic medical record 226 held. The inspection order management service 222 and the interpretation report management service 233 can register and hold an interpretation report 234 that records the interpretation result corresponding to the inspection order 223.

  The interpretation doctor 202 performs interpretation (image diagnosis) based on information such as medical images and electronic medical records indicated by the examination order 223, describes the result, and creates a patient interpretation report 234. As described above, the created interpretation report 234 is registered and managed by the interpretation report management service 233. When the interpretation report 234 is registered, the inspection order management service 222 updates the inspection order 223. As a result, the corresponding interpretation report can be referred from other client applications (for example, the client application 212 of the requesting doctor 201). These are performed by the image interpretation doctor 202 using a client application corresponding to the examination order management service 222, the medical image management service 228, and the electronic medical record management service 225 on the PC client 213. Note that when creating an interpretation report, an interpretation report structuring service 231 is used.

  As described above, when the interpretation report requested by the requesting doctor 201 becomes available, the examination order management service 222 notifies the requesting doctor 201 of this fact. This notification is made when the requesting doctor 201 uses a client application corresponding to the examination order management service 222 on the PC client 211. Through the above procedure, the workflow linked operation for the interpretation report is performed, and the requesting doctor 201 can obtain the necessary medical image of the patient and the interpretation report for it, and information such as electronic medical record information and other examinations. In addition, comprehensive diagnosis can be performed.

  FIG. 3 is a diagram showing in detail an example of the functional configuration of the interpretation report server 230 that creates an interpretation report used in the present embodiment and supports the creation of the interpretation report, and the client application 214 corresponding thereto. In FIG. 3, the same components as those in FIG. 2 are denoted by the same reference numerals.

  The electronic medical record generation unit 344 provides a function for browsing and retouching the electronic medical record 226 held and managed by the electronic medical record management service 225 to the interpretation doctor 202 who is a user. The medical image viewer 342 is provided by the medical image management service 228 and provides the interpretation doctor 202 with a browsing function of the medical image 229 managed. Further, the examination order instruction / result display 345 is stored in the examination order management service 222 and provides the interpretation doctor 202 with a function to display, add, delete, etc. the examination order 223 being managed.

  The interpretation report described below refers to a structured interpretation report in which items such as findings and diagnosis are individually handled and the relationship between these items is recorded. The interpretation report generation unit 341 has functions of structured display / input 346 and detailed item display / input 347, and provides a function of inputting and editing a report described in text. The structured display / input 346 enables the interpretation report to be displayed and input by dividing it into a plurality of items having different attributes such as findings and diagnosis, and the input and display of the relationship between these items. To be able to The detailed item display / input 347 inputs and displays the detailed items in the items and the description contents of the detailed items, indicates the items and input candidates in the input template data, and inputs by selecting the input candidates. Make it possible. A detailed item is an item unit that further classifies descriptions in items classified by attributes such as findings and diagnosis in a structured interpretation report, and the details will become more apparent from the explanation of FIG. The interpretation report generation unit 341 cooperates with the interpretation report structuring service 231 to provide these functions. Details of screen display and operation when the structured display / input 346 and the detailed item display / input 347 are used will be described in the following screen examples and processing descriptions.

  The interpretation report management service 233 provides functions for registering, storing, managing, referring to, and sharing interpretation reports 234 that have been created or are being created. The interpretation report 234 is input and created by the interpretation doctor 202 as a user using the interpretation report generation unit 341, and is stored and managed by the interpretation report management service 233. At this time, the interpretation report structuring service 231 is used to realize a function for supporting creation, editing, and correction of a structured interpretation report.

  The interpretation report work management service 232 performs business support and management related to interpretation report creation, such as assignment of interpretation report creation work, work notification, work progress management, report revision history management, and the like. Interpretation report work management service 232 divides work in units of interpretation reports or interprets reports that require urgency when there are a plurality of interpretation doctors 202 or when it is necessary to create a large number of interpretation reports. Provides a function for preferential assignment of creation work. Interpretation work information 351 is recorded and accumulated information on the creation work state for each interpretation report. The interpretation report work management service 232 restores the work environment, state, and correction history on the interpretation report generation unit 341 when resuming the creation of the interpretation report. For this purpose, the interpretation report work management service 232 stores the interpretation work status and correction history information as interpretation report status / history information 352. Using these pieces of information, the interpretation report work management service 232 supports interpretation report creation work and manages correction history.

  The interpretation report structuring service 231 supports creation, editing, and correction of a structured interpretation report. The interpretation report structuring service 231 of this embodiment has functions of format conversion / management 361, medical document structuring 362, medical term / accompanying expression extraction 370, and natural language processing 374. Hereinafter, these functions will be described.

  The format conversion / management 361 can store and communicate in accordance with the recording format of the medical document so that the structured content of the medical document such as a structured interpretation report can be held. The recording format of the medical document here is defined by an original or published standard such as an electronic medical record or an interpretation report, and may be a combination or a hybrid thereof. Here, the document converted into the medical document recording format is stored and managed as an interpretation report 234. In addition, the format conversion / management 361 exchanges documents with the client application 214 and medical-related services in accordance with user instructions from the interpretation report generation unit 341, and provides information and obtains information.

  The medical document structuring 362 provides functions such as creating, editing and modifying structured interpretation reports. The medical document structuring 362 has functions of a structure input / edit 363, item information extraction 364, an input template search 365, and an input candidate search / addition 366, and holds input template data 367.

  The structure input / editing 363 realizes an input and editing function of a structured interpretation report, and these functions are given to the interpretation doctor 202 via the structure display / input 346 of the interpretation report generation unit 341. I will provide a. Thereby, the image interpretation doctor 202 can input and edit the structured image interpretation report.

  The item information extraction 364 extracts the description part of the important information from the text description contents when a text description finding or diagnosis is input as a part of the contents of the interpretation report, and structures the interpretation information. Provide a function that supports report creation. The important information description part includes important detailed information items (detail items) and their contents. The item information extraction 364 provides a function for structuring the detailed items and their contents in the interpretation report structuring. . The item information extraction 364 provides the above function by extracting item information based on the analysis result of the medical term / accompanying expression extraction 370 and the natural language processing 374 with respect to the description content. Details of this will be described later.

  The input template data 367 is composed of a plurality of input templates created in units such as names of normal and abnormal phenomena and disease names that mainly occur in lesions and bodies. The input template is used to provide input support when creating a structured interpretation report. The input template has one or more items such as findings and diagnoses. Besides that, typical description contents of the item (typical description contents), detail items to be described, and details of the detail items It also has relationships between items such as content and value candidates (input candidates), findings and diagnosis. The typical description content can be used as a template for the input content, and the user can reduce the input operation by using the same as it is or after partially correcting it. In addition, the detailed items described in the input template can suppress omissions at the time of writing the interpretation report, and enable selective input using input candidates of the detailed items. Thereby, it is possible to further reduce the load on the user when creating the interpretation report. In addition, the relationship between the findings and diagnosis items described in the input template should be structured in order to clarify the reason and rationale for the diagnosis content to be derived from the content of the findings and specific details. Reduce the burden of using and describing relationships. The input template acquired from the input template data 367 is displayed and used by the detailed item display / input 347 of the interpretation report generation unit 341.

  The input template search 365 searches for an appropriate input template from the input template data 367 based on the description content of the structured interpretation report. The item information extraction 364 extracts, as detailed item information, if a detailed item is extracted from the description content of the interpretation report, if there is a name of a lesion or a phenomenon occurring in the body, a disease name, or the like. The input template search 365 searches the input template data 367 using the extracted detailed item information as a search keyword to find an appropriate input template. This search is automatically performed according to the description. For this reason, if information such as detailed lesions increases as the contents of the interpretation report increase, an appropriate input template may change. In addition, since a plurality of different lesions, conditions, illnesses, and the like may occur simultaneously, a plurality of input templates may be applied within one interpretation report. In many cases, one template is searched for and applied to each item such as findings and diagnosis, but a plurality of input templates may be combined and applied. When an input template is applied, items such as findings and diagnoses, details, and contents and values that have already been input and described by a doctor are treated as input and described in the applied input template. If there are items, detailed items, contents and values that are not in the applied input template, they are processed by adding the description.

  The input candidate search / addition 366 adds an input candidate (content and / or value) to an uninput item or detailed item of the applied input template. Normally, input candidates can be used by referring to information stored in advance in the input template or information based on systematic knowledge outside the input template prepared according to the contents of the input template. Many. In particular, in recent years, there are many cases where detailed items frequently used and their contents / values are obtained and used in an input template by using data such as interpretation reports created in the past and knowledge obtained therefrom. The input candidate search / addition 366 adds input candidates for detailed items from the contents of items such as findings and diagnosis already described in the interpretation report using structuring. That is, for the item to be described, the item that becomes the input candidate of the detailed item is searched from the description contents of the item related by structuring and added to the input template. The details / value candidates of the detail items are added not only from the details and the contents / values of the input contents held by the input template and the externally referenced input contents, but also from the contents already described and entered. It becomes possible to input easily by selection operation. Further, as input candidates to be added, items that are easy to reuse are added assuming that input target items and information of input contents are reused.

  Based on the processing result of the natural language processing 374, the medical term / supplemental expression extraction 370 extracts language expressions such as medical terms that appear in the processing result, words that become the auxiliary expression, and wordings from the medical text. Provide functionality. Based on the medical terms extracted by the medical term / accompanying expression extraction 370 and the accompanying expressions, the structure input / editing 363 performs a process of classifying and structuring information on terms and words included in the medical text.

  The medical term / accompanying expression extraction 370 uses a medical term dictionary 371 that stores information such as a name of an abnormal portion on an image, a medical term notation character string such as a lesion name and a disease name, and an expression pattern. Extract medical terms. In addition, the medical term dictionary 371 includes a description character string of incidental expression terms (terms indicating degree, size, shape, etc.) indicating contents and states of abnormal part names, lesion names, disease names, and the like on medical images. Holds information such as expression patterns. The medical term / accompanying expression extraction 370 uses the medical term dictionary 371 to extract such an attendant expression from the medical text. Further, the medical term / accompanying expression extraction 370 has co-occurrence pattern statistical information 372 that is information about what words and expressions co-occur when a medical term appears in a sentence. The medical term / accompanying expression extraction 370 uses the co-occurrence pattern statistical information 372 to estimate a term when an unknown medical term or incidental expression appears. Further, the medical term / accompanying expression extraction 370 extracts the perceptual expression from the medical sentence using the perceptual expression dictionary 373 that holds the perceptual expression information. Perceptual expressions include “has there” and “has seen” to indicate existence and confirmation, “acknowledges” and “thinks” to indicate thoughts and judgments, “to” to indicate requests and requests Please "or" please hope ", or expressions that indicate negation.

  The natural language processing 374 analyzes the text / sentence for the medical sentence. This is realized by so-called morphological analysis / syntactic analysis 375. In the morphological analysis, a general dictionary 377 which is a word dictionary is used to divide a character string in a sentence into words and classify them into parts of speech. In addition, usage, refraction, and the like are removed, and original expressions such as a prototype and a basic form are obtained. Moreover, the classification information of the change pattern of the form such as its utilization and refraction is also obtained. Thereby, a sentence is analyzed and it becomes a form of a word string. In the syntax analysis, the word string that is the result of the morphological analysis is obtained by analyzing the relationship and structure such as the syntax and dependency using information such as grammar. At the time of this analysis, grammatical information such as syntax relationship and structure of the syntax rule 376 is used. By syntactic analysis, the word string is in the form of a word tree structure (syntax tree) based on syntax, a dependency network structure (dependency relationship), or the like. The medical term / accompanying expression extraction 370 performs the above-described term extraction and extraction of the accompanying expression based on the analysis result of the natural language processing 374.

  With the above-described configuration, creation work such as input and editing when the interpretation doctor 202 creates a structured interpretation report is realized. The interpreting doctor 202 who is a user can browse the electronic medical record information of the patient and obtain information from the electronic medical record management service 225 using the electronic medical record generation unit 344. Then, the image interpretation doctor 202 uses the medical image viewer 342 to acquire and view the captured medical image from the medical image management service 228 and perform image diagnosis. The interpretation doctor 202 describes and edits the structured findings and diagnosis using the interpretation report generation unit 341 when describing the result of image diagnosis as an interpretation report, and sends the result to the interpretation report management service 233. Record. Further, the image interpretation doctor 202 uses the image interpretation report generation unit 341 and the image interpretation report management service 233 as necessary to refer to and compare the patient's past image interpretation reports. At this time, the interpreting doctor 202 can refer to a medical image in the past (particularly when the interpretation report is written) by using the medical image viewer 342 and the medical image management service 228. When findings such as a follow-up observation are described in the interpretation report that is being created for findings in the past interpretation report, the relationship is also recorded as structured information of the interpretation report.

  In addition, as a record at the time of the interpretation work, a description such as structured findings and diagnosis in the interpretation report generation unit 341 and the work content at the time of editing are recorded in the interpretation report work management service 232. As a result, when resuming after the work is interrupted, the interpretation report generation unit 341 can reproduce the work situation according to the interpretation report being worked on.

  In creating an interpretation report, the interpretation doctor 202 can describe structured information such as findings and diagnosis by using the interpretation report structuring service 231 via the interpretation report generation unit 341. Further, as described above, the description contents such as the findings of the past interpretation report being referred to and the findings of the currently created interpretation report can be related and structured.

  In addition, the interpretation report generation unit 341 divides observations and diagnoses into individual items when the interpretation doctor 202 creates an interpretation report, and inputs the relationship between the items, and makes it easy to understand the relationship between each finding and the diagnosis. indicate. In addition, the description of each item of observation and diagnosis can be related to other interpretation reports, so that it is possible to understand the possibility of the effect of the description correction, and at the same time copy or edit the description This makes it easy to write interpretation reports. Furthermore, the structured format conversion / management 361 can convert an interpretation report recorded in a structured state into a common structured format and provide it to other devices, and reuse the interpretation report. Enable.

  FIG. 4, FIG. 5, and FIG. 6 show examples of screens when creating a structured interpretation report. FIG. 4 is an example of a screen (image viewer window 401) displayed on the display device 109 by the medical image viewer 342. The image viewer window 401 has a menu bar 402 for calling up processes and functions, and a display area 403 for displaying a medical image 405. The menu bar 402 includes menu elements 404 such as “image selection” and “display”. The image interpretation doctor 202 displays various medical images in a desired size, position, display mode, and the like in the display area 403 by selecting and operating menu elements indicating processing or functions desired to be performed from the menu bar 402. be able to. In FIG. 4, a state where a medical image 405 of a cross section of a human body observed by CT or the like is displayed in the display area 403 as the medical image 405 is shown.

  The annotation 406 is an area where the interpretation doctor 202 can write a comment such as a finding when there is a part of interest in a specific part or area in the displayed medical image. The annotation 406 is added by the image interpretation doctor 202 by calling the corresponding function from the menu bar 402 when browsing an image or creating an image interpretation report. A plurality of annotations 406 can be created, and the text description content such as a specific portion or region in the instructed image and a finding is held. The annotation 406 is managed by a number so that it can be individually identified. The annotation information created by the interpretation doctor 202 is stored and managed separately from the medical image itself. In the embodiment, annotation information is accumulated and managed as information in an interpretation report.

  FIG. 5 shows an example of an interpretation report creation screen displayed by the interpretation report generation unit 341, and shows an example of a screen when a form for displaying the text described in the item and the relationship between the items is used. . The creation screen is primarily controlled by structured display / input 346. In the interpretation report generation window 501, there are a menu bar 502 for calling up processes and functions, patient information 503, examination information 504, image diagnosis request information 505 from the requesting doctor, and structured interpretation report content display 506. is there. In the menu bar 502, there are menu elements 508 such as “report selection”, “input”, and “display”. The interpretation doctor 202 selects a menu element indicating the processing / function to be performed from the menu bar 502, calls the interpretation report, displays the contents on the contents display 506, and describes the findings and diagnosis in a structured state. can do. In addition, it is possible to relate to a medical image corresponding to the finding, and to describe a relationship such as finding among a plurality of interpretation reports.

  In FIG. 5, a thumbnail 510 of a medical image is pasted in the “image” field of the interpretation report generation window 501. The thumbnail 510 is generated by using all or part of the medical image displayed by the medical image viewer 342 and pasted in the interpretation report. When the thumbnail 510 is selected, the medical image viewer 342 displays a medical image corresponding to the thumbnail 510 in the image viewer window 401 as shown in FIG. Information on the medical image that is the basis of the thumbnail 510 and information such as the position and size of the medical image to be displayed (the display state of the medical image when the thumbnail 510 is generated) are added. 351 is stored as a part of 351. The medical image viewer 342 displays a medical image corresponding to the thumbnail 510 using such interpretation work information. The information such as the position and size for displaying the medical image may include various parameters used when the image is displayed by the image viewer 342 in addition to the position and size. For example, the used image conversion filter, parameters at the time of use, display density setting (window width, window level, etc.), and the like.

  The medical report creation system of this embodiment supports creation of a medical report structured by a plurality of items having different attributes. In this embodiment, it is structured by attributes of images, findings, diagnosis, and plan / treatment. Finding items 511, 515, and 516, which are items in the finding column (items having finding attributes), describe the contents of the finding. The diagnosis items 512 and 513, which are items in the diagnosis column (items having diagnosis attributes), describe the contents of diagnosis. Corresponding items 514 that are items in the plan / treatment column (items having a plan / treatment attribute) describe correspondence contents of future doctors and radiographers such as plans / treatments.

  In addition, relationship lines are displayed between the thumbnail 510 and the finding item 511, between the finding item 511 and the diagnostic item 512, between the finding item 511 and the diagnostic item 513, and between the diagnostic item 513 and the corresponding item 514. Yes. The relationship line between the thumbnail 510 and the finding item 511 indicates that the finding described in the finding item 511 is a finding obtained by observing the whole or part of the medical image indicated by the thumbnail. It should be noted that there is no relationship line between the thumbnail 510 and the finding item describing the finding obtained from other than the medical image or the finding not obtained from the medical image corresponding to the thumbnail 510.

  In findings items 511, 515, and 516, the contents of what lesions and phenomena are considered to occur based on the image to be examined are described as findings. The relationship lines between the finding item 511 and the diagnostic item 512 and between the finding item 511 and the diagnostic item 513 indicate the relationship between the finding and the diagnosis based thereon. That is, in the example of FIG. 5, it is shown that the disease names of both the diagnosis item 512 and the diagnosis item 513 are referred to based on the findings of the thumbnail 510. In this case, it is expressed in the diagnosis item 512 that the diagnosis “pneumonia” is suspected as a diagnosis, and the diagnosis item 513 refers to the possibility of “lung cancer” as a diagnosis. There is also a relationship line between the diagnosis item 513 and the corresponding item 514. For the disease described in the diagnosis item 513, the corresponding item 514 is associated with an indication that a follow-up is requested. The follow-up observation here indicates that the diagnosis by the same examination (image diagnosis described in the examination information 504 in this example) should be performed again after a certain period of time. Therefore, the description content of the corresponding item 514 is a request from the interpretation doctor 202 that the requesting doctor 201 wants to give an instruction for examination and interpretation to perform the request.

  A cursor 518 is a cursor for inputting characters. When a character is input in this state, a character is input at the position of the cursor 518. In the example of FIG. 5, the diagnosis item 513 is selected as an input target, a selection frame 517 indicating the selection state is displayed, and the cursor 518 is held. Note that finding items, diagnostic items, and corresponding items can be selected by performing a selection operation with a mouse or the like. Also, the position of the cursor 518 in the text can be designated by a designation operation using a mouse or the like.

  In the request information 505, an association frame 509 indicating the association is displayed for the description associated with the selected finding item. In the example of FIG. 5, the diagnosis item 513 is selected as an input target, and in the description in the request information 505, the corresponding description is shown in a related frame 509 (indicated by a broken line in the drawing). Has been. Thereby, it is understood that the diagnosis item 513 is associated with “suspected lung cancer” in the request information 505. This indicates that the diagnosis item 513 refers to the description “suspected lung cancer” described as the request information when the requesting doctor 201 makes an interpretation request. The display by the related frame 509 is displayed only while the diagnosis item 513 is selected as an input target. Conversely, when “suspected lung cancer” described in the request information 505 is selected with a mouse or the like, a related frame is displayed for the diagnosis item 513, and the relationship between them can be displayed. Yes.

  In this manner, the interpretation report generation unit 341 and the structure input / editing 363 allow the user to call up the interpretation report to be edited and create images, findings, diagnosis, and plan / treatment items, and the findings and diagnosis are included therein. To be able to describe such contents. In addition, the relationship between the thumbnail, finding, diagnosis, and plan / procedure items is clarified by adding a relationship line. This relationship line mainly corresponds to a logical relationship, such as a cause-result or a basis-causal causal relationship, or a simple correspondence relationship. The content recognized by the interpretation doctor from the medical image by the interpretation doctor is the finding item, and the correspondence between them is expressed by the relationship line between the thumbnail corresponding to the medical image and the finding item. In addition, regarding the findings described in the findings items, the contents that the interpreting physician judged the type or condition of the disease or pointed out the possibility are diagnostic items, and the causal relationship between them is expressed by a relationship line. . Similarly, for the diagnosis described in the diagnosis item, the contents of the treatment and examination determined by the interpretation doctor to be performed are the corresponding items, and the corresponding relationship and the causal relationship are expressed by relationship lines. In this way, a structured interpretation report is created.

  FIG. 6 shows the same interpretation report creation screen as in FIG. 5, but the display form is different. In the interpretation report generation window 501 of FIG. 6, items are shown together with an input template, and analysis by natural language processing is also applied to sentences (texts) that are description contents. As a result, the item name and content are entered for each detailed item with respect to the description content in the item. That is, by using an input template that holds item names (categories) of detailed items to be described in each of a plurality of items having different attributes such as findings, diagnosis, planning / treatment, and input candidates, Creation is supported. This display is realized by combining the display of the relationship of the structured display / input 346 and the like and the display of the detailed item display / input 347. The contents of the interpretation report displayed in FIG. 5 and FIG. 6 are the same, and the same reference numbers are assigned to the display elements in FIG.

  Description items 611, 615, 616, diagnosis items 612, 613, and corresponding item 614 are described in tabular form in sentences (text) having the same contents as the finding items 511, 515, 516, diagnosis items 512, 513, and corresponding item 514. (Hereafter, the table part) is added. In addition, about the same description (text) as the item of FIG. 5, the one part is abbreviate | omitted by "...". The upper part in the finding item 611 is “subject” — “nodule (1) <recognized>” to “state” — “pleural infiltration << none >>”, and the “left” is located below the finding item 611. In the lung S8, a nodule ... "is a text description portion having the same content as the finding item 511 in FIG. Detailed items and their contents are displayed in the table part, and the presence of this table part is a major difference between the display forms of FIGS.

  In the table part, detailed items are arranged vertically, and in each detailed item, the item name, contents and values are arranged horizontally. For example, in the case of the finding item 611, there are “target”, “part”, and the like as the detailed item names, and “nodule (1) <recognized>”, “left lung S8”, etc. as the contents and values of the corresponding detailed items. There is. The table portion is created from the detailed item information extracted by the item information extraction 364 and the input template searched by the input template search 365 for the contents described in the text in the item. Details of the process for creating the table portion will be described later.

  The contents and values of the detailed items in the input template are in an input state if there are items corresponding to the detailed item information extracted by the item information extraction 364, but are not input in other cases. For detailed items that have not been input, the contents and values held in the input template are input candidates. Therefore, when a non-input state portion of the table portion is selected, a list of input candidates (candidate list) as shown by 1021 in FIG. 10 is displayed. The user can input details and values of detailed items by selecting a desired input candidate from the displayed candidate list. Details of the candidate list will be described later. Further, in the display of the table portion, it is possible to correct the item name, content and value of the detailed item. When the correction target is the item name, content, or value extracted by the item information extraction 364, the corresponding portion of the text description that is the extraction target is also corrected. Further, using the function called from the menu bar 502, the item itself of the detailed item information can be added to the table portion.

  In the item name “Target”, important information such as the name of the lesion or condition in the case of a finding item, the name of a disease name in the case of a diagnostic item, and the name of an examination or treatment in the case of a corresponding item is described. Is done. This “target” is a detailed item that each item must have. For example, in the case of the finding item 611, “nodule (1) <recognized>” is described as the content for the item name “target” of the detailed item. Here, “nodule” is the lesion name, and there is a possibility that a plurality of lesions may appear. Therefore, “Nod” is numbered and “(1)” is added. This numbering is used when the structure input / editing 363 issues and manages the number independently, and when there is a number added to the annotation to the image specific part in the medical image viewer 342, the number is used. In some cases, it is added to ensure identification. Further, “<recognize>” is the contents described in the text and is added because there is a perceptual expression for “nodule”. In the case of the perceptual expression indicating negative, the perceptual expression is added by changing the symbol as in “<< None >>”. Similarly, in the finding item 611, “left lung S8” is extracted from the text description for the item name “part” of the detailed item, and the searched input template also has the detailed item “part”. Are displayed in combination. In this way, display is performed by cooperation between the item information extraction 364 and the input template. In the finding item 615, the detailed item “part” is generated from the input template. However, since there is no expression related to the part in the text description, the content and value are not input and are blank. As a result, when the interpretation doctor 202 finds such an unfilled detail item while creating the interpretation report, he / she notices that there is a lack of description content and can make a description if necessary. Become. Further, when the interpreting physician 202 determines that the item is a detailed item that does not need to be clearly described, the interpreting physician 202 can call the function from the menu bar 502 and delete the detailed item from the table portion.

  FIG. 7 is a flowchart showing a process of creating information on the table portion in the finding item and the diagnostic item shown in FIG. 6 in the processing flow of the system of the present embodiment. Detailed item information in the table portion is created by combining terms such as medical terms extracted by performing language analysis or the like on the text description and an input template. Hereinafter, each step of the processing of FIG. 7 will be described. Note that the processing in FIG. 7 is started when a text description is input or edited in a finding item or a diagnostic item.

  In step S <b> 701, the structure input / edit 363 acquires text (contents) of a sentence input to a specific item via the structured display / input 346 by the interpretation doctor. Here, the description will be made on the assumption that the content of FIG. 8A (described in the text of the finding item 511) is input as an example sentence. In step S <b> 702, the item information extraction 364 performs analysis using natural language processing or the like to obtain detailed item information from the text acquired by the structure input / edit 363. The item information extraction 364 uses the natural language processing 374 to obtain a natural language analysis result for the acquired text. The result is information of “notation”, “part of speech”, and “syntax structure” in FIG.

  The column “notation” in FIG. 8B shows a state in which the example sentence in FIG. 8A is separated into words by morphological analysis. Also, in the “part of speech” column, information on the part of speech given to each notation by morphological analysis is shown. This is the output result of the morphological analysis. The column “Syntax Structure” shows the result of adding syntax structure information for each notation, and this is the output result of the syntax analysis. In the syntax analysis of the embodiment, the phrase structure is mainly output. Therefore, in the present embodiment, the “syntax structure” has two layers of a part constituting a basic unit of a phrase such as a noun phrase and a verb phrase, and a part such as a postposition and sentence ending added thereto. Has a syntactic structure. In addition, the main verb phrases that are main in relation to the modification and the syntactic structure are also extracted. In the case of Japanese, a particle appears immediately after a noun (phrase) and has a syntactic relationship with other noun phrases and verb phrases. , And the noun phrases accompanying it are expressed as postpositional phrases. This postpositional phrase is sometimes called a phrase.

  When performing the natural language processing as described above, the natural language processing 374 is a general dictionary 377 that holds words in units of words and word information, combinations of words that form phrase structures, and relationships and structures between phrase structures. The syntax rule 376 holding is used. The morphological analysis / syntax analysis 375 uses the general dictionary 377 and the syntax rules 376 to divide a target sentence into words, add information such as parts of speech, and assemble it into a syntax structure. Note that the morphological analysis / syntax analysis 375 processing method and processing result form are basically as described above, but there are various details in detail. In the present embodiment, it is only necessary to obtain the above processing results, and the processing methods of morphological analysis and syntax analysis are not limited.

  Next, in S703, the medical term / accompanying expression extraction 370 finds a medical term (term expression), a medical term incidental expression, or a perceptual expression from the analysis result by natural language processing obtained in S702. Divide into categories. At this time, the medical term dictionary 371, the co-occurrence pattern statistical information 372, and the perceptual expression dictionary 373 are used. As a simple technique for extracting and estimating term expressions, incidental expressions, and perceptual expressions, there is a method of obtaining corresponding expressions by matching with a dictionary. Other than that, there are various expressions such as the structure of the notation of the expression itself and the method of estimating using other words that co-occur with the expression even if the expression is not registered in the dictionary using statistical information etc. There is something. Also, the form of the processing result is basically the one shown here, but there are various details in detail. Any method may be used as long as the processing result used in the present embodiment can be obtained.

  The contents of the processing result of S703 are shown in columns of "term expression", "accompanying expression", and "perceptual expression" in FIG. 8B. Note that “term expression”, “accompanying expression”, and “perceptual expression” are collectively referred to as “extraction expression”. The extracted expression is obtained by assigning a category to an expression in which a specific notation or a list of notations is collected. The term expression is obtained by extracting expressions such as a site name, a lesion name, a state name, and a disease name. Categories such as “part name”, “lesion name”, “state name”, and “disease name” are assigned to the term expressions.

  The incidental expression is obtained by extracting an expression added to the term expression. The incidental expression indicates information that is an attribute of the term expression to which it is added, and a category such as “shape” or “size” is assigned. In some cases, an incidental expression is added to the incidental expression. In this case, there is a relationship of addition of another information or addition of information limitation. This additional relationship appears in the syntax structure. For example, in FIG. 8B, the position: “inside” has an information-restricted additional relationship with the density: “ground glass density”.

  Perceptual expressions are those that correspond to direct expressions such as “acknowledge”, “visible”, “suspect”, and the presence or absence of “present”, “accompanied”, etc. An expression to be confirmed is extracted. At that time, categories such as “perception” and “recognition” are extracted. This perceptual expression expresses a will and an idea to the contents indicated by the term expression or incidental expression, and if it means denial such as “not allowed”, it is also an attribute of the category. Will be assigned and extracted. The perceptual expression expresses the written interpretation doctor's recognition or degree of perception, state, and the like with respect to the term expression and the incidental expression, and generates a structure in the form of addition in the syntax structure. In FIG. 8B, recognition: “acknowledge” is a perceptual expression that is added to the lesion name: “nodule” and expresses the doctor's thoughts on the nodule lesion. In addition, recognition: “none” is a perceptual expression that is added to the state: “pleural infiltration” and expresses the doctor's view of the state of pleural invasion, and recognition (negative): negative by the expression “none”. The idea is expressed.

  Next, in S704, the structure input / edit 363 determines the contents and values for each item (item name) of the detailed item based on the extraction result of the medical term / accompanying expression extraction 370 in S703. Create the contents of. First, if there is an extracted expression of an important category such as a lesion name, disease name, examination name, or treatment name in the extraction result, the structure input / edit 363 sets this extracted expression as a detailed item of “target”. Its contents and value. For the remaining term expressions and incidental expressions, the category is used as the item name of the detailed item, and the extracted expression is used as the content and value of the corresponding detailed item. If there is an extracted expression to be added to the term expression or incidental expression, it is added as an additional expression including the relationship of the syntax structure that is the reason for addition to the contents and values of the detailed items of the term expression or incidental expression to be added. Is done.

  In FIG. 8B, the lesion name “nodule” is selected as the content of the detailed item “target”, and the recognition “acknowledge” is added to it (the relation of the syntax structure is “statement”). Therefore, “nodule <recognized>” is obtained as the content and value of the detailed item of the item name “target”. Here, for the sake of easy understanding, a notation that uses different symbols depending on the relationship of the syntax structure as the reason for addition is used. In the present embodiment, “<” and “>” are used for positive assertion, “<<” and “>>” are used for negative assertion, and “[” and “]” are used for modification such as limitation. ing.

  Next, in S705, the input template search 365 extracts a search keyword based on the result extracted in S703, and searches for an input template using the extracted search keyword. The input template search 365 selects a specific term expression from the extraction result of the medical term / accompanying expression extraction 370 in S703, and searches the input template data 367 using this as a search keyword. Each input template of the input template data 367 has a search keyword in advance so that it can be easily searched, and is constructed so that high-speed search is possible. For example, the input template search 365 searches the input template data 367 from the extraction result in S703 using the term expressions of categories such as a site name, lesion name, disease name, examination name, and treatment name as search keywords. In the case of FIG. 8B, the part name “left lung S8” and the lesion name “nodule” are selected as search keywords, the input template data 367 is searched, and the input template of the search result is the input template. can get.

  FIG. 9 is an example of the searched input template. In FIG. 9, the input template management information 900 includes rows 901 to 903. A row 901 is a template ID for identifying an input template, a row 902 is a template title for identification display, and a row 903 is a template type indicating the type of the input template.

  The search information 910 describes a search key constituting search information used when searching for an input template. The search key is identified by a search key ID. The search key has a category of terms such as “part name”, “disease name”, and “lesion name” as search conditions, and search keywords such as “lung”, “left lung”, and “right lung” for each category. Is held. For the search keywords of each category of the search condition in the search key, comparison and search index correspondence are performed at the time of search, and if there is a match for each category in the search keyword, this input template is included in the search results Will be. For example, when a search is performed using the region name “left lung S8” and the lesion name “nodule” as search keywords, the region name “left lung S8” and the lesion are included in the search condition of the search key ID = 1 (line 911). Since the name “nodule” exists, the illustrated input template is searched.

  The input item 920 is a part related to the input content of the input template. In each line of the input item 920, when input is performed using an input template, item names and input candidates (contents and / or values) necessary as detailed items in each item such as finding items and diagnostic items Is described. For example, line 921 indicates that the text description of the finding must be input, and there is a text description content such as “accept nodules” as an input candidate. A line 922 indicates that the item name “target” of the detailed item is a detailed item that must be input, and “nodule” or the like is included as an input candidate.

  In addition, each line of the input item 920 describes an input candidate search condition and an input candidate corresponding restriction for adding an input candidate for the content and value of the detailed item. These correspond to categories that become search criteria when adding input items for detailed items and values, and items that are displayed preferentially when displaying candidates in the search results (defaults) It is a restriction of whether or not to do. These contents and usage will be described in the processing of S707 described later.

  Next, in S706, the structured input / edit 363 combines the detailed items created from the text description of the items obtained in S704 and the detailed items obtained from the input template in S705 into the item items. Create detailed items for the table part of. At this time, the structured input / edit 363 obtains the corresponding content and value from the detailed items created from the text description content obtained in S704 among the detailed items according to the content of the input item 920 of the input template. If it is, the contents and values are entered. Further, at this time, input candidates of detailed items obtained from the input template are left as input candidates not selected, and are displayed as a candidate list at the time of display. On the other hand, if there is no detail item content or value corresponding to the text description content obtained in S704, which is a detail item obtained from the input template, the detail item content or value is not entered, It is blank when displayed (only the item name is displayed).

  Next, in step S707, the input candidate search / addition 366 searches for and adds input candidates for detailed items that have not been input. That is, the input candidate search / addition 366 is based on the input description of the interpretation report using the search condition (input candidate search condition) described in association with the detailed item in the input template as shown in FIG. Search for input candidates. The contents of this processing will be described later in detail with reference to the flowchart of FIG.

  In step S708, the structured display / input 346 and the detailed item display / input 347 display the interpretation report items using the processing result in step S707. First, the structure input / edit 363 sends information such as items and relationships held therein and item detailed information in each item to the interpretation report generation unit 341. The structured display / input 346 mainly displays items and their relationship, and the detailed item display / input 347 mainly displays detailed items in the items. This display result becomes the display content of the screen of FIG.

  Next, in S709, the interpretation report generation unit 341 acquires the user operation performed on the content displayed in S708, and sends this to the structuring / editing 363, so that the process according to the user operation is performed. Perform a branch. There are various operations for branching the process, but the following are the operations for detailed items: “Detail item selection operation”, “Detail item change / edit operation”, “Detail item confirmation” The process corresponding to “operation” will be described. If an operation for selecting a detailed item is performed, the process proceeds to S710. If an operation for changing / editing a detailed item is performed, the process proceeds to S711. If an operation for confirming the detailed item is performed, The process proceeds to S712.

  When a detail item selection operation is performed, in step S710, the detail item display / input 347 acquires the content of the selection operation and sends it to the structuring / editing 363 via the interpretation report generation unit 341. The structuring / editing 363 sends the contents of the selected detail item and the input candidates for the value to the interpretation report generation unit 341. The detailed item display / input 347 lists input candidates received from the structuring / editing 363 and displays them as a candidate list so that the user can select them. In this way, the input candidates searched in S707 are added as input candidates for the detailed items associated with the input candidate search conditions in order to support the creation of the interpretation report. When the process of S710 ends, the process returns to S709.

  When a detail item change / edit operation has been performed, the detail item display / input 347 acquires the change and edit contents in S 711, and sends them to the structuring / editing 363 via the interpretation report generation unit 341. The structuring / editing 363 updates the content and value of the selected detailed item according to the received change and editing content. When the process of S711 ends, the process returns to S709.

  When the detail item confirmation operation is performed, in step S712, the detail item display / input 347 notifies the structuring / editing 363 that the confirmation operation has been performed via the interpretation report generation unit 341. Note that the confirmation operation occurs, for example, when the item or the detailed item is no longer selected (input enabled state). The structuring / editing 363 records the contents of the detailed items as an interpretation report 234 via the interpretation report management service 233. Then, the detailed item display / input 347 is notified via the interpretation report generation unit 341 that the confirmation has been made, and the detailed item display / input 347 performs non-selection display in the normal state. When the process of S712 ends, the process of FIG. 7 ends.

  In this way, when creating an interpretation report separately for each item such as findings and diagnosis, display and input detailed items using both the input template and the contents such as findings and diagnosis by text description. A screen for performing the operation is displayed. An example of such a screen is shown in FIG. When the display of the screen of FIG. 6 and the operation using the screen of FIG. 6 are performed, input of detailed items (contents and values) is added by the processing of S707 of FIG. Hereinafter, input candidate addition processing will be described.

  FIG. 10 shows a screen that uses the result of adding a content or value input candidate in S710 when a user selects an unfilled detail item and in S710. FIG. 10 is the same screen as that in FIG. In FIG. 10, display elements similar to those in FIG. 6 are denoted by the same reference numerals. In FIG. 6, the diagnosis item 613 is selected, but in FIG. 10, the plan / treatment correspondence item 614 is selected. Therefore, a selection frame 1017 is displayed for the corresponding item 614. The detailed item 1019 in the corresponding item 614 has an item name “inspection”, which is not input in FIG. 6, but “CT” is input in FIG. 10. The detailed item 1020 in the corresponding item 614 is selected for input, and a character input cursor 1018 and a candidate list 1021 indicating input candidates are displayed.

  The candidate list 1021 displays the contents of the details item 1020 in an unfilled state and input candidates for values, and the user can select a desired input candidate from the candidate list 1021. In the candidate list 1021, the input candidates searched in step S707 are also displayed. Input candidates surrounded by a solid line in the candidate list 1021 are input candidates in a selected state. In addition, input candidates surrounded by a dotted line indicate that they are unselected input candidates. Note that at the start of displaying the candidate list 1021, one of the input candidates is in a state designated by default.

  The user can input the contents of the detailed item 1020 by selecting one of the input candidates listed in the candidate list 1021. Thus, if the content to be input is in the candidate list 1021, character input can be performed by a simple operation of selecting it. When there is no appropriate input candidate in the candidate list 1021, when the text can be input very easily, when inputting characters by copying / pasting from another part, the user can input the cursor 1018 for the character input. Can input characters. In this way, it is possible to perform input using the input candidates when inputting to the detailed items.

  In the screen shown in FIG. 10, the detailed item 1019 that has not been filled in is selected, and the input candidate “CT” is selected and input from the candidate list. Further, the unfilled detail item 1020 is selected and the candidate list 1021 is displayed.

  FIG. 11 is a flowchart showing details of the processing in S707 of FIG. 7 (processing for searching for and adding input candidates). This process is performed by input candidate search / addition 366. Note that the processing in FIG. 11 is executed for each detail item for which the content and value of the detail item are not input. FIG. 12 is a diagram for explaining the processing content when obtaining additional input candidates for the detailed item 1019 and the detailed item 1020 of FIG. 10 by the processing shown in FIG.

  In S1101, the input candidate search / addition 366 acquires the input candidate search condition and the input candidate constraint condition from the input template for the detailed item (the unfilled detailed item) having no input content or value. Thereby, preparation for adding input candidates for contents and values is made. For example, in the corresponding item 614, the target is “follow-up” of the image inspection based on the text description content. According to the input template shown in FIG. 9, when the target is an image examination name in the plan / treatment item, the input candidate search condition corresponding to the detailed item “examination” is “examination name”, and the input candidate constraint condition Becomes “image inspection name”. Further, according to the input template, when the target is the image examination name in the plan / treatment item, the input candidate search condition corresponding to the detailed item “part” is “part name”, and the input candidate constraint condition is “image examination”. Range ". This is shown in FIG. 12 (see the column for search conditions and the column for constraint conditions).

  Next, in step S1102, the input candidate search / addition 366 searches the detailed items and examination information in the items of images, findings, diagnoses, plans / treatments related to unfilled detailed items by structuring. Add. For example, an item associated with the item to which the unfilled detail item 1019 belongs (in FIG. 10, a diagnostic item 613 associated with the corresponding item 614 and a finding item 611 associated with the diagnostic item 613) is searched. It becomes a target.

  In S1103, another document associated with an item to which an unfilled detail item belongs is set as a search target. In step S <b> 1103, the input candidate search / addition 366 adds information on a request form, past findings, and past interpretation report portions related to an unfilled detail item having no content or value input content to the search target. For example, related request forms, past findings, and past interpretation reports are selected and set for the same patient by referring to patient information. In addition, regarding the past interpretation report of the same patient, the items of finding, diagnosis, and plan / treatment are selected as search targets. In this case, not only the same patient but also the same or similar patient may be used. In addition, a plurality of different types of image examinations may be performed on the same patient, and an interpretation report may be created for each. Therefore, these interpretation reports may be targeted. In S1104, the input candidate search / addition 366 further adds inspection information (inspection information 504) to be described in the report to the search target. The information of the examination information 504 is also structured by categorizing the medical terms into categories (category and content pairs) by medical term / accompanying expression extraction 370, like items such as findings and diagnosis. To do. This is because a search is performed by a search for input candidates (S1105) described later.

  The items to be searched in FIG. 12 are set by the processing from S1102 to S1104. In rows 1201 to 1203, detailed items in the items of related images, findings, diagnosis, and planning / treatment are set as search targets. In line 1204, inspection information 504 is set as an item to be searched. In the row 1205, “related examination / report” is set as an item to be searched based on a related request form / past finding.

  In step S1105, the input candidate search / addition 366 searches the extracted items of the search targets collected in steps S1102 to S1104 based on the “search condition” acquired in step S1101 for the detailed items that do not have the input contents or values. I do. By this search, a search result of input candidates for a detailed item having no content or value is obtained. The input candidates searched by this search are shown in the column of “extraction expression searched by search conditions” in rows 1201 to 1205 in FIG. Further, input candidates searched for the detailed item 1020 are shown in the column of “extracted expression searched by search conditions” in rows 1206 to 1210.

  In step S1106, the input candidate search / addition 366 branches the process depending on whether or not the search result in step S1105 exists. If there is no search result, the processing in FIG. 11 ends. On the other hand, if there is a search result, the process proceeds to S1107. In step S1107, the input candidate search / addition 366 further sorts the search results in step S1106 based on the input candidate constraint conditions obtained in step S1101, and divides the search results into search results that do not correspond to the constraint conditions. .

  In step S1108, the input candidate search / addition 366 branches the process depending on whether or not the inspection result in step S1107 corresponds to the constraint condition. If there is no search result corresponding to the constraint condition in S1108, the process proceeds to S1111. If there is a search result corresponding to the constraint condition, the process proceeds to S1109. In S1109, the input candidate search / addition 366 displays the search results (input candidates) selected as corresponding to the constraint conditions in S1108 as input candidates held in the input template for the detailed items to be processed. Add to the top of the list. Then, the input candidate added to the head is set as a default candidate.

  In step S1110, the input candidate search / addition 366 adds search results (input candidates) that do not satisfy the constraint conditions to the back of the list formed by the input candidates held in the input template. As described above, when the result searched in S1105 is added to the list of input candidates for detailed item information, the position in the list of input candidates differs depending on whether or not the constraint condition is met. When the process of S1110 ends, the process of FIG. 11 ends.

  As described above, the contents of detailed items and input candidates for values are added. FIG. 12 shows a state in which a row 1204 (“Category” is “Image inspection” and “Contents and values” is “CT”) corresponds to the constraint condition. Further, in the input item search processing results (rows 1206 to 1210) related to the detailed item 1020, the row 1209 (“category” is “part name (image examination)” and “contents and values” is “chest”) is a constraint. It shows how it became relevant. Therefore, the input candidates (contents / values) determined to be applicable are added as a default to the top of the list of input candidates held by the input template.

  FIG. 13 is a screen display when the process of FIG. 11 is applied to another interpretation report. In FIG. 13, the same reference numerals are assigned to display elements similar to those in FIG. The display elements with reference numbers 1311 to 1321 are the same as 1011 to 1021 in FIG. 10, but the description contents of each item are partly different. Is different.

  In the case of FIG. 13, as in the case of FIG. 10, input candidate addition processing is performed for the detailed item 1319, and “biopsy” is entered as the content of the item name “examination”. Further, input candidate addition processing is performed for the detailed item 1320, and the biopsy is a method in which the affected part is taken out and inspected, so that it can be seen that the lesion name that is the affected part is an input candidate for the part.

  FIG. 14 is a diagram illustrating an example of processing contents when searching for input candidates to be added for the detailed item 1319 and the detailed item 1320 of FIG. 13 (S707). In the case of FIG. 13, since the target is “affected site examination” and the content and value is “biopsy” from the text description of the item 1314, input candidates for the detailed items 1319 and 1320 are selected based on this result. Processing to obtain is performed. From the input template shown in FIG. 9, when the target is an affected area examination name in the plan / treatment item, the “input candidate search condition” is “part name and lesion name”, and the “input candidate constraint condition” is “lesion name”. Become. As described above, the categories of “part name” and “lesion name” are searched in S1105 for the search target set in S1102 to S1104, and are shown in the column of “extraction expression searched by search conditions” in rows 1401 to 1406. Since the restriction condition is “lesion name”, “nodule (1)” in the row 1403 is obtained as a corresponding input candidate.

  As described above, the processing shown in FIGS. 7 and 11 is executed, and the display and operation as shown in FIGS. 6, 10, and 13 are performed, thereby utilizing the structured relationship of the interpretation report being described. Then, input candidates are automatically added from the described contents for the uninput items of the input template. As a result, it is now easier to enter items that have not been entered. In addition, if the interpretation report is only text, it tries to obtain input candidates from the entire written text, so complicated analysis and processing are required. If the accuracy of the analysis is not very high, the candidate is incorrect. May also be included. On the other hand, by using the structured relationship of the interpretation report, it is possible to keep the impact of analysis accuracy and processing burden low by targeting only the text description in the item and the detailed items obtained from it. Became possible. Moreover, according to the information input item to which the input candidate is input, it is easier to preferentially select contents and values that can be easily reused, and contents and values that are easy to reuse are targeted for input.

  According to this embodiment, when creating an interpretation report, both text input (natural language input) and description in detailed items are possible. In addition, when input items and detailed input items are performed using an input template, appropriate input candidates can be used when inputting the contents and values of the detailed items. This made it easier to create interpretation reports.

  As described above, according to the above-described embodiment, when a medical staff such as an interpretation doctor uses a structured interpretation report, it becomes easy to describe the interpretation report and the work load is reduced. . In addition, it becomes easy to understand information that needs to be input, and it is possible to create and use a higher-quality interpretation report. In addition, since the description content that can be easily reused increases, it becomes possible to create the inspection request by reusing the description information of the interpretation report as it is, and the preparation of the inspection request becomes easy.

  In the embodiment described above, support for creating a medical report related to medical care has been described, but the present invention is not limited to this. The present invention is structured by a plurality of items having different attributes, and can be applied to document creation support in which each item is composed of detailed items including item name (category) and content pairs.

(Other embodiments)
The present invention supplies a program that realizes one or more functions of the above-described embodiments to a system or apparatus via a network or a storage medium, and one or more processors in a computer of the system or apparatus read and execute the program This process can be realized. It can also be realized by a circuit (for example, ASIC) that realizes one or more functions.

100: Information processing device, 210: Network, 211, 213, 215: PC client, 212, 214, 216: Client application, 217: Imaging device, 221: Inspection order server, 224: Electronic medical record server, 227: Medical image server , 230: Interpretation report server

Claims (13)

A medical report creation device for creating a medical report structured by a plurality of items having different attributes,
A support means for supporting creation of a medical report by a user, using an input template that holds item names and input candidates of detailed items to be described in each of the plurality of items;
Search means for searching for input candidates from the already entered description of the medical report using a search condition described in association with a detailed item in the input template;
For the creation support by the support means, an addition means for adding the input candidate searched by the search means to the input candidate of the detailed item associated with the search condition is provided. apparatus. The input template further has a constraint condition associated with a detailed item,
The medical report creation apparatus according to claim 1, wherein the adding unit preferentially uses an input candidate satisfying the constraint condition among input candidates searched by the search unit.   The medical report creation apparatus according to claim 2, wherein the adding unit uses an input candidate corresponding to the constraint condition as an input candidate that is selected by default.   The medical report creation apparatus according to claim 2 or 3, wherein the adding unit arranges and presents an input candidate corresponding to the constraint condition at a head of a candidate list. Analyzing means for analyzing a natural language sentence described in the plurality of items;
The medical report creation according to claim 1, further comprising: an acquisition unit that acquires the input template used for creation support based on an expression obtained as a result of analysis by the analysis unit. apparatus.   6. The medical device according to claim 5, wherein the acquisition unit searches for an input template using a site name, a disease name, and a lesion name included in the analysis result obtained by the analysis unit as keywords. Report creation device.   2. The search unit according to claim 1, wherein the search target is the content already described in the item associated with the item to which the detailed item to which the search condition is associated belongs. The medical report creation apparatus according to any one of 1 to 6.   8. The medical report creation apparatus according to claim 7, wherein the search unit searches for another document associated with an item to which a detailed item associated with the search condition belongs. In the structuring, the item includes a category and a detailed item including its contents,
The medical report creation apparatus according to any one of claims 1 to 7, wherein the retrieval unit obtains, as the input candidates, contents described regarding a category specified by the search condition.   The medical report creation apparatus according to claim 1, wherein the search unit searches for input candidates for unfilled detail items. A method for controlling a medical report creation apparatus for creating a medical report structured by a plurality of items having different attributes,
A support step for supporting creation of a medical report by a user, using an input template that holds item names and input candidates of detailed items to be described in each of the plurality of items;
A search step for searching for input candidates from the already entered description of the medical report using a search condition described in association with a detailed item in the input template;
And a supplementary step of adding the input candidates searched in the search step to the input candidates of the detailed items associated with the search conditions for the creation support in the support step. Control method of the device. A medical report creation system that has a server and a client capable of communicating with each other, and creates a medical report structured by a plurality of items having different attributes,
A support means for supporting creation of a medical report by a user, using an input template that holds item names and input candidates of detailed items to be described in each of the plurality of items;
Search means for searching for input candidates from the already entered description of the medical report using a search condition described in association with a detailed item in the input template;
Adding means for adding the input candidate searched by the search means to the input candidate of the detailed item associated with the search condition for the creation support by the support means;
The medical report creation system, wherein the server functions as at least part of the support means, the search means, and the addition means.   The program for functioning a computer as each means of the medical report production apparatus described in any one of Claims 1 thru | or 11.

Images