JP6813549B2 - Methods and systems for generating medical reports - Google Patents

Description

In medical imaging, the interpreters of the examination are free to report on the presence or absence of diagnostic imaging findings interpreted by those interpreters and their judgment regarding the diagnostic significance of such findings. To generate. A great deal of effort is expended by the individual laboratory interpreters who typically produce reports containing repetitive phrases, structures, and concepts. The brain labor and time involved in producing such reports are the main factors limiting productivity.

To date, this issue has been addressed in a limited way through the use of prefabricated phrases and reporting templates. Pre-made phrases are a list of commonly used expressions, and report writers can insert relevant phrases into the report text and splice such default expressions together with additional free form. By including the text of, the list of expressions can be utilized when generating the report, forming the final report. Templates are a framework that is pre-made for a complete report of commonly seen findings, leaving some information blank, and the report writer fills in the blanks when preparing the final report.

Generating a report through the use of default expressions involves the brain work involved in selecting the appropriate expression for the report, grouping the expressions, and eliminating or correcting inconsistent expressions. It remains a pain because it leaves the writer's work entirely behind. In fact, the writer of the report will have to devote additional time to ensure that the pre-made phrases inserted in the report do not contain any conflicting features.

Another limitation of the prewritten phrase system is that only commonly used phrases that will relate to the user's "critical mass" of the prewritten phrase system are the report writer. Is available to. Such a "copy and paste" pre-written expression system does not adequately address the needs of the user writing reports of anomalous situations that may be seen repeatedly, and the anomalous situations are set in advance. Frequently not enough to include the appropriate phrase in the standard "glossary" of the phrase. Placing such rarely used too many phrases within a standard distributed set of phrases would make the set of phrases large and unwieldy and difficult to manipulate. ..

When a template is used, the writer of the report must devote considerable effort to modifying the template to suit the unique context of the reported case. A particular limitation of template-based systems used in existing report generation techniques is that such systems are highly structured and tightly defined. Such a system consists of tightly formed blocks of text with blank areas for the writer to fill by voice recognition, typing, or other means. This technique does not provide sufficient flexibility for use in reporting cases that deviate from a limited set of predetermined patterns.

Therefore, there is a need for report writers to use "smart" report generation methods to generate reports in a more time-efficient manner. There is also a need to allow report writers to have a mechanism to reduce the possibility of reporting errors or oversights.

Embodiments of the invention are a consistent and time-efficient way for radiologists and other medical imaging test interpreters to report both normal and abnormal medical findings using frequently repeated phrases. It can provide a good way. The inventor independently realizes that phrases commonly used in radiomedical reports do not exist in isolation, but rather in predictable, interrelated patterns, and create new report generation tools. As you are using this phrase. Furthermore, by recognizing the existence of predictable, interrelated patterns, the inventor's system deviates from the traditional view that report generation would not be able to be automated to this level. .. The inventor has made decisions by the previous user regarding the insertion or deletion of phrases from the report, as well as the phrases extracted from the text of the report generated by the previous user, for future report writers. I further noticed that the data could be used to generate suggestions for the content of the report.

The report generation method is a relationship between medical phrases commonly used to help in manipulating available phrases, such as one that is initially clearly defined by the (s) users. Utilizing the presence of, with additional phrases subsequently extracted by the system through data collected through previous user experience with useful phrases, users can use these useful phrases in a more time-efficient manner. , Allows you to generate reports using interrelated medical phrases.

Such systems will also address the needs of mechanisms that reduce the likelihood of reporting errors, such as failure to report essential information in a given medical context.

The present invention deviates from existing report generation tools that do not take advantage of the existence of relationships between phrases, and the existing report generation tools also draw data collected in the process of using the system by the writer of previous reports. It is not utilized and therefore cannot be automated to the level of the present invention.

The present invention seeks to facilitate the generation of medical imaging test reports by utilizing repetitive theme patterns and networked ideas to speed up report generation. These patterns exist in the logic of medical reports and can be used to speed up and simplify the process of generating medical reports. These patterns are, for example, a predetermined generally expressed medical idea that is associated with or suggests another commonly expressed medical idea, or a predetermined generally expressed medical idea that excludes other commonly expressed medical ideas. Alternatively, dealing with a given subject in such a report may include the fact that it often suggests a reusable list of additional subjects that need to be addressed. Such inclusion patterns, also known as inclusion rules, are used in phrases selected by the report writer to provide suggestions for additional phrases that the writer may wish to insert in the report while in progress. Applies. Similarly, exclusion patterns, also known as exclusion rules, are applied to selected and related phrases to eliminate mutually contradictory phrases to ensure the consistency of reported findings. To.

The first phrase used in the system is clearly defined by the user, and the relationships between the phrases (phrases that are related to each other through inclusion or exclusion rules, or "potential alternative" rules described below). , First clearly defined by the user. For example, the user may define some phrases, and then when a given phrase is inserted in the report, the other given phrase is potentially to be considered for insertion in the report. Indicates that it should be flagged as useful. Alternatively, the user may specify that a given phrase is inconsistent and that when one phrase is inserted in the report, the other given phrase (if any) should be removed. Good. These relationships involve "suggested additional" and "excluded" phrases.

Additional types of relationships that may be specified include "potential alternative" phrases. When a given phrase is excluded from the report due to inconsistency with another phrase, if the potential alternative phrase remains consistent with the other phrases in the report, then "potential alternative" The "" phrase may be automatically inserted at the position of the excluded phrase.

The inventor has included such a reporting system as it is used over time by multiple users who use it to create a complete medical imaging report. Information about the insertion and deletion of specific phrases performed by the previous user in the process of writing the report, as well as the text of the previous report, is a valuable set of information about potentially useful phrases and future users. Noticed that when writing a report, it provides those relationships with each other that may be used to suggest to future users. This is due to the fact that reporting-related diagnostic imaging is performed on specific body parts and specific diagnostic imaging methods within the scope of predictable pathological or normal findings, as such. Reports tend to be repetitive and contain numerous elements that are frequently reused. Therefore, the inventor's report generation system not only allows the user to define useful phrases and their relationships, but also about their relevance to the current writer's report in progress. By investigating patterns of system use by the writer of the report, we will also actively pursue the definition and suggestion of potentially useful phrases.

The system previously wrote a potentially useful text by the presence of a rare word in a previously generated text that matches the rare word in the current writer's report in progress, for example. You may identify from. If the writer selects the text in question and inserts the text in the report in progress, the system is informed that the text or "phrase" is really potentially useful. The system then not only features various features about the phrase, but also other actions taken by the user in the same report in which the phrase was inserted, eg, (will be an "additional" phrase proposed). Stores information such as inserting other phrases and removing other phrases (which will get an "excluded" relationship with the first inserted phrase). Since the "phrases" generated by such an automatic method are used repeatedly, the usage pattern for such phrases should be to insert the phrase in question along with other given phrases. And so on, the system with such phrases and other phrases that would be used to improve the system's ability to provide users with suggestions that would be useful when the user writes a report. Develop a database of information about relationships.

In one practice of the invention, the user defines a set of phrases that are useful for a particular anatomical site of interest, and the user limits the complete set of expected phrases to the immediate medical care. Allows you to suggest only the phrases that are most relevant to your imaging test. Based on the selection of test type data based on anatomical sites, relevant phrases or templates are presented to the report writer for consideration of insertion into the text field.

The proposed set of phrases may also be influenced by other medical imaging tests related to "metadata", which "metadata" are digital images and communications in medical use that are almost universally used (metadata). It is stored with the actual image in most medical image data formats such as DICOM) format. Such metadata is information about the type of diagnostic imaging performed, not only information about which anatomical site was imaged, but also other potentially relevant, such as patient age and gender. Also includes information to be done.

Another embodiment of the invention is a system for generating medical imaging test reports, such as inputting medical imaging test data and user selection of test types, phrase selection and other graphics or text. Generate medical imaging test reports with one or more input devices configured in, and one or more processors configured to process medical imaging test data, test type selection, and phrase selection. One or more memories configured to store one or more templates, test type data, phrase data, and medical report files containing multiple text fields and coupled to one or more processors. User-selected with the system and one or more processors configured to process medical imaging data to influence which phrases are presented to the user as being most potentially useful. Handles one or more memory systems coupled to one or more processors and one or more inclusion rules related to the phrase, configured to store the checked type data and associated phrase data. Generated with one or more processors configured to handle exclusion rules associated with the phrase in order to omit inconsistent phrases from presentation to the user. For a system configured to display medical reports and with an output device connected to a processor.

It is a figure of the computer system which concerns on an exemplary embodiment of this invention. It is a flowchart of the method which concerns on an exemplary embodiment of this invention. FIG. 5 illustrates a computer interface at various stages of generating a medical image data report according to an exemplary embodiment of the present invention. FIG. 5 illustrates a computer interface at various stages of generating a medical image data report according to an exemplary embodiment of the present invention. FIG. 5 illustrates a computer interface at various stages of generating a medical image data report according to an exemplary embodiment of the present invention. FIG. 5 illustrates a computer interface at various stages of generating a medical image data report according to an exemplary embodiment of the present invention. FIG. 5 illustrates a computer interface at various stages of generating a medical image data report according to an exemplary embodiment of the present invention. FIG. 5 illustrates a computer interface at various stages of generating a medical image data report according to an exemplary embodiment of the present invention. FIG. 5 illustrates a computer interface at various stages of generating a medical image data report according to an exemplary embodiment of the present invention. FIG. 5 illustrates a computer interface at various stages of generating a medical image data report according to an exemplary embodiment of the present invention. FIG. 5 illustrates a computer interface at various stages of generating a medical image data report according to an exemplary embodiment of the present invention. FIG. 5 illustrates a computer interface at various stages of generating a medical image data report according to an exemplary embodiment of the present invention. FIG. 5 illustrates a computer interface at various stages of generating a medical image data report according to an exemplary embodiment of the present invention. FIG. 5 illustrates a computer interface at various stages of generating a medical image data report according to an exemplary embodiment of the present invention. FIG. 5 illustrates a computer interface at various stages of generating a medical image data report according to an exemplary embodiment of the present invention. FIG. 5 illustrates a computer interface at various stages of generating a medical image data report according to an exemplary embodiment of the present invention. FIG. 5 illustrates a computer interface at various stages of generating a medical image data report according to an exemplary embodiment of the present invention. FIG. 5 illustrates a computer interface at various stages of generating a medical image data report according to an exemplary embodiment of the present invention. FIG. 5 illustrates a computer interface at various stages of generating a medical image data report according to an exemplary embodiment of the present invention. FIG. 5 illustrates a computer interface at various stages of generating a medical image data report according to an exemplary embodiment of the present invention. FIG. 5 illustrates a computer interface at various stages of generating a medical image data report according to an exemplary embodiment of the present invention. It is a screenshot of the system interface according to an exemplary embodiment of the present invention. It is a screenshot of the system interface according to an exemplary embodiment of the present invention.

The following is a description of methods and systems for creating and generating medical imaging test reports according to exemplary embodiments of the invention.

The methods and systems described herein allow the user to quickly systematically represent and generate medical imaging test reports. The elements of the system are the test types that correspond to the anatomical site to be examined, and the test types that may limit or influence the phrases presented for review. A reporting framework consisting of a set of text fields that correspond to commonly used components, in which reports are generally organized within the text fields (eg, "findings" and "feelings" columns). A reporting framework in which the actual reporting text will be placed in that field, a set of "phrases", or a textual representation that may be useful to insert in the report, and such phrases (eg, given). Includes relationships defined between (such as certain phrases that suggest inclusion or exclusion of other phrases), as well as an option to select a "template".

The term "template" is used in conventional work to indicate a relatively complete report produced in advance, and the relatively complete report is filled in by the report writer to produce a complete report. Includes fields. The present invention provides a means of initiating the process of modifying a report with a relatively complete report, hence the term "template" is used again in the current context to describe similar ideas. .. However, in the case of the present invention, such a "template" is simply a strict text frame that must be manually modified in detail to fit the unique case details for the report to which the template is applied. It does not include work, but rather, in the present invention, a "template" consists of a set of phrases that are continuously used to generate a stream of reporting text. The decisive difference between the template for the practice of the present invention and the "template" used in conventional work is that each phrase in the report retains its unique identity as a phrase and is only within the report. It is to maintain relationships with other phrases both in the phrase database of the present invention. This means that the processing of the report text can be done, for example, through the insertion of additional phrases into the reporting framework that was initially occupied by the text by the template, as the template is customized during the final report for a particular case. , Means to be influenced by the relationship between the template phrase and other phrases. For example, the newly inserted phrase may conflict with the phrase used in the template. That is, when such a phrase is inserted, the phrase that conflicts with that phrase may be automatically removed from the report or flagged for consideration of removal. Similarly, the phrase pattern suggested to consider inclusion in the report is included in the report, whether due to inclusion in the original template or due to later insertion by the user. It will be similarly affected by the entire set of phrases.

The phrase can include a verbose or long form for insertion into the standard "findings" section of the image report, as well as a short form for inclusion within the standard "feelings" section of the image report. The "Findings" column contains a detailed description of the imaging findings and a thorough discussion of their significance, and the "Findings" column provides a concise summary of the main conclusions of the examiner.

The knowledge database of the system contains not only phrases but also information about rules or relationships between phrases (see exemplary example 1 below). The system selects phrases from the knowledge database based on factors, including patterns that define the relationships between the phrases, for suggestions to the user, and such phrases for the user to enter in the report in progress. May be selected. When you select a phrase to be inserted in the report structure, additional phrases are then selected by the processor from the knowledge database as suggested to the user. This reduces the likelihood that the user will overlook a detailed report, or generally considered information related to the context of other information discussed by the user within the report. Exclusion rules based on inconsistencies between phrases in the knowledge database apply to phrases selected to exclude and / or identify phrases that are inconsistent with other contained phrases and report inconsistent findings. Reduce the possibility of including errors. The processor tracks usage patterns (decisions made by the user in the process of editing the report regarding inclusion and exclusion of phrases) and uploads such patterns to the knowledge database.

FIG. 1 shows a report generation system 100 according to an exemplary embodiment of the present invention. This figure illustrates the basic configuration of system 100, in which a central server or cluster of servers manages multiple coexisting users of a reporting and editing system via network 160, with templates, phrases, phrases and Access the database with data on template selection patterns and dynamically propose report contents for multiple users. The database may also include, over time, phrases extracted from previously written reports and the relationships observed between such phrases.

The system 100 generally includes a central computer 104, such as a server or a collection of servers, and one or more (N) local computers 120 connected through a network 160. The local computer 120 may be, for example, a workstation, an image observation station, or an individual computer. The central computer 104 processes and stores the medical imaging test report file. Thus, the central computer 104 includes at least one processor 108 and at least one knowledge database processor 110. The specified processor may be isolated or may be a single processor with multiple functions. The knowledge database processor 110 processes medical image data from input 102 and data about phrases and relationships between phrases to generate phrases presented to the user via output 114 for selection to be inserted in the report. To do.

One or more input devices 102 input data and information to the central computer 104. Input devices for computer-based, textual, or audio formats may include, for example, a keyboard, touch screen, or dictaphone. The input device 102 captures data such as medical image data and various concepts and phrase data that are selected and modified.

The central computer 104 is also functionally connected to one or more output devices 114. The output device 114 may include, for example, a display, a projector, a printer, a speaker, a diskette, or other medium for storing and displaying the report files generated in various formats. The output device 114 allows the user to see the completed report or to see the modifications in progress at the stage of the creative process for evaluation. The output device can also provide reporting of various file formats stored on a separate storage device such as a DVD, USB storage device, or memory card.

Although the central computer 104 is shown to have storage components 106, one or more additional storage devices 112 may also be functionally connected to the central computer 104. Such storage may include, for example, random access memory (RAM) and read-only memory (ROM) devices, CD-ROMs, flash memory, and various other storage disks. Other memory components may also be incorporated into the system to perform computer functions.

The local computer 120 may be used by the user to generate, review and modify the phrases and concepts for the report contained within the report file on the central computer 104. Therefore, the local computer 120 is shown to have a processor 122 and a storage 124. In certain embodiments of the invention, application of patterns to various phrases and generation of reports are performed and stored within central computer 104, and only phrases and concepts are selected and modified on local computer 120. To. In another embodiment, the selection of phrases and concepts and the application of patterns to various phrases and concepts are performed on the local computer 120. Like the central computer 104, the local computer 120 will have one or more input devices 103 and one or more output devices 128, and will also have additional storage 129 of the exemplary type described above. May also have.

Both the central computer 104 and the local computer 120 may include a graphical user interface for manipulating and displaying the proposed and selected phrases in the report file, as shown in FIG.

Each computer described herein is capable of receiving input data, processing the data, communicating with other computers or processors in the network, and allowing the user to view various data. It may operate independently.

Embodiments of the invention also use other computer systems, such as networks of multiple processors and one or more storage units, or computers with a single processor and one or more storage units. May be used.

In an exemplary embodiment as shown in FIG. 1, the central computer 104 and the local computer 120 may be embodied within a single computer system, or, for example, in parallel, in series, or in hub and It may be connected through the network 160 in various configurations such as a spoke configuration. The computer network may include, for example, an internetwork such as a local area network (LAN), a corporate network, or the Internet. In this exemplary embodiment, the computer is connected via a LAN, such as an intranet within the organization. The network allows multiple users to work simultaneously on multiple sets of medical image data within an organization. The network may also be set up via the Internet to allow multiple parties to enter, view, or generate medical imaging reports.

Both the central computer 104 and the local computer 120 are central processing units (CPUs), other centralized or main processors, graphics processing units (GPUs), computer-executable instruction sets, software applications for processing, or medical applications. It may be one or more software applications for processing data related to the generation of imaging inspection reports, including any combination of the above processors.

Input image data is generated by imaging techniques such as ultrasound, computed tomography (CT), computed tomography (CAT), nuclear medicine, positron emission tomography (PET) and magnetic resonance imaging (MRI). It should be noted that it may include data representing the image, but is not limited to these data. Images can also be acquired from modalities such as MRI scanners to workstations through networks such as the Internet, local area networks (LANs), wide area networks (WANs), and other networks.

It should be further noted that data entry into the system can be by any suitable method, including but not limited to keyboards, touch screens, or voice.

FIG. 2 is a flowchart for generating a medical imaging test report according to an exemplary embodiment of the present invention. The report file is first created on or locally on the central computer (S10) and then stored on the central computer. The medical image data can be read into the report file or can be a separate file. The report file has an adaptive structure that includes the type of examination associated with the anatomical site being examined and one or more fields or templates to contain the imaging examination interpretation and diagnostic findings. The contents of the report file will be described in more detail below. Since there may be more than one area of interest corresponding to a given anatomical site, one or more test types representing such areas of interest are the subject of the report. It may be presented to the user via the output device for selection (S20). The user then determines which test type to report. The selected test type is then entered in the report file. The type of test is similar to the subject of the report. For each test type, one or more diagnostic findings typically associated with a given test type are generated by applying rule-based concepts such as inclusion rules in the knowledge database within the central server. .. Further, more phrases are proposed to the user on the output device as related phrases or templates (S30). The rules and patterns in the knowledge database will be described in more detail below. When the user's selection is entered through the input device, the selected phrase is further on the server by applying an exclusion rule from the knowledge database to exclude inconsistent or conflicting phrases as exclusion phrases. It is processed. The substitution rule may replace the exclusion phrase with an alternative phrase (S40). If one selected phrase representing one medical finding or concept conflicts with another selected phrase or concept, the user will be warned of such conflicts on the output device, or , The system can remove conflicting phrases. In certain embodiments of the invention, such phrases are specified text in the reporting framework for the user to see potential inconsistencies with the remaining selected phrases and / or proposed phrases. It may be presented in the field. This provides the user with a safety measure that reduces reporting errors. A preview of the report at this stage of the report is constantly available during the process of creating and modifying the report (S50). The steps may be repeated if it is desired to revise the report or add additional findings and findings to the report. Once all selections and modifications are complete, the report is completed and generated via the output device (S60). The pattern in which the user selects or excludes a phrase may be repeated, may be generated as a new rule uploaded to the knowledge database for future use by multiple users (S70), or its. You can update the user-specific knowledge database. A more detailed description of the form of report generation according to an exemplary embodiment of the present invention follows.

There are several major systems, organs, and related concepts for virtually any type of examination, and these body systems, organs, parts, and concepts are most often defined as "normal" forms. Medical imaging examination reports are particularly adapted to this type of reporting system, given that they have a limited and defined type of "abnormal" findings. Moreover, the anomalous findings do not exist in isolation, thereby having the equivalent opportunity that each normal and each anomalous finding exists within a given report. Rather, certain anomalous findings exclude the presence of certain normal findings. Also, certain anomalous findings suggest that other, related, anomalous findings may also be present.

Various embodiments of the invention take advantage of the fact that medical imaging reports, which are far from widespread open-ended reporting, often contain a set of predetermined interrelated concepts. The interrelated concept is a system that recognizes the existence of such relationships, so that the user puts together a report for the user as he inserts a new idea into the generated report. The possibility of inclusion of other concepts in the report may be proposed or excluded in order to generate a system that uses the existence of such relationships. The concept of association that exists between commonly used phrases allows the user to define new phrases and how such phrases relate to other phrases in the system. , By doing so, customize the system's "knowledge base" for phrases used in report generation. This allows the system to leverage and leverage those relationships to minimize the effort required to generate new reports for new cases.

The knowledge database contains a library of commonly used medical phrases and data on how the phrases relate to each other. In addition, a template consisting of a set of phrases associated with commonly reported situations, such as a given type of standard normal examination, can be created. The phrase as well as the template may also contain blank fields, and the user is selected from his own text or a list of possibilities, such as a list of adjectives of very mild, mild, moderate, severe, etc. You can put the text inside that blank field.

The rapid generation of well-structured, complete radiological reports is that the commonly used phrases in radiological reports do not exist in isolation, but rather in predictable, interrelated patterns. It can be facilitated by recognizing and utilizing the fact that it does. Within that interrelated pattern, the use of one phrase may suggest the need to insert one or more related phrases, or the use of that one phrase may suggest the other phrase. You may suggest that you may exclude it.

Each of the proposed related phrases can be associated with a priority value defined and entered by the user, or can be determined by the system based on the pattern of phrase placement in the previous user's report. Such values are assigned according to the importance of the phrase, for example, higher values indicate more important information that should be presented first in the report before less important information. For example, a phrase that refers to a life-threatening condition would be associated with a higher priority value, and if this phrase were added to the report following the addition of less important findings. Even if it is the last item, it will be automatically inserted towards the beginning of the report text while it is in progress. The user would be able to manually prioritize this priority value-based arrangement if desired. Traditional systems require users to manually compile reports. Therefore, the priority value feature of the present invention can save a considerable amount of time and effort for the report writer.

In another aspect of the exemplary embodiment of the invention, the user can define "variables" such as dates, measurements, etc. in expressions that the user can insert within subtext fields. That is, the user says, "There is a [#] cm mass in the right colon, which probably represents colon cancer. This [#] cm mass extends to the abdominal wall, and possibly the abdominal wall. It would be possible to present an expression stating that "invades." If the user updates a single case of the measurement, the case will be propagated to both positions within the text editing field on the user's screen when the template is inserted. Similarly, if the system extracts a sentence from the user's current text editing field for insertion into the database as an expected text suggestion, the system will use it for other cases of future user use of the text representation. Variables that can be set to the specific values required could be used to replace date, measurements, and other context-specific data.

An embodiment of the invention can maintain a database of many or all phrases previously used in the report or inserted within a standard template by all users of the system. An exemplary embodiment of the system can incorporate the concept of a "standard template" by allowing the user to define a set of templates for their own use, which templates also , Will be part of a general database used or modified by other users. In addition, the text in the report generated through the use of this system may be returned to the database and stored in order to constantly improve the suggestions made to the user when writing the report. In an exemplary embodiment of the invention, all text in all reports is returned to the database and stored. The knowledge or report generation database is a means of suggesting revisions to a report to users who continue to work on the ongoing report, based on the frequency of use of the previous user's given phrase usage and based on usage patterns. Utilized by the system, in the pattern of its use, the insertion of a given phrase suggests a high probability that another phrase will be used, or the insertion of a given phrase into the body of the text , Often accompanies the deletion of other phrases.

The system will self-improve over time. A user who finds an expression or template generated by another user that suits the user's needs but needs modification or improvement is free to make such modification or improvement to the template. The template is then made publicly available again to all users or selected users. If the modified phrase or template is selected before the modification, more often than the original version, and then for use by other users, then the new modified version of the phrase or template is this. It will be prioritized by factors, which will result in the modified phrase or template being generally presented to future users of the system.

When utilizing all text in all reports (or specified text in a specified report) generated by the previous user, the system generalizes the text in the previous actual report and personalizes it. The name and identification number can be deleted, and the display of specific measured values, left-right difference, severity, etc. can be generalized. For example, a measured value such as "5 cm" can be changed to "[#] cm" in which a specific number of measured values is replaced with a blank. Similarly, phrases such as "moderate" can be replaced by a set of choices, allowing the user to insert "mild," "moderate," or "severe" from the choice into its reporting position. it can.

The user can call the report phrase suggestion using the search box as shown in FIG. 23, and the user types some words in the search box related to what the user wants to report. , That would result in the database being searched for fragments of text or default phrases that were previously generated by the user in the past, including such words. For example, in FIG. 23, a previously generated phrase is presented to the user by searching for the word "injured". The text suggestions called by this search could be stored according to the expected usefulness. Its expected usefulness is the frequency with which other users have selected the text suggestion in question, and the other user has selected another text suggestion written by the same writer as a given text suggestion. Frequency and how often the current user of the system chooses another text representation written by the writer of the text proposal in question, and also appears in the text proposal in question and is worked by the current user of the system. The number of words in the current text editing field that can be continued, and this last factor is the number of words (also present in the user's current report text), which is increased by the rarity of the word in question. Words that are rarely used and that also appear in the expected text proposal increase the likelihood of the text proposal being displayed, resulting in the text proposal being displayed more prominently). And could be based on medical imaging metadata such as the patient's age and gender, and other factors such as such factors.

Over time, the system will develop phrases that are applicable even in unusual situations, and will begin to incorporate forms of subject knowledge for future user use. become. Therefore, the system could be a knowledge database, in addition to a mere phrase suggestion body. Proposal presentations represent accurate information or concepts, although inaccurate information may enter the system due to being influenced by the frequency with which the user accepts or rejects a given expression. An attractive tool will be over time when a system is used by a group of users, and the system will be based on user decisions based on the system's aggregated knowledge. Enjoy the benefits. For example, in the case of diagnostic imaging report generation, a list of expected diagnoses for a given finding is in the system, "There is a nodule of about [#] cm in the [left or right] adrenal gland. The system measurement is [#] HU. Given the low hounce field unit measurement, this probably represents an adenoma or myelolipoma. MRI with repeated phase imaging is further evaluated. Will be. "

The means by which the system will propose phrase insertion or deletion has a more detailed description.

The system may use expressions that are generally selected following the use of other expressions, or expressions that are generally excluded from the body of the report following the use of other expressions, or other expected inclusions in the report text. Over time, with respect to commonly selected expressions, for example, based on the type of test, patient age, and other text extant in the report text, to intelligently suggest expected exclusions from the report text. It is possible to take advantage of the patterns of use of expressions found with.

That is, if it is observed that a given expression, which will be referred to as expression # 2, is generally inserted in the text body after expression # 1 is inserted, the system will list the proposals containing expression # 2. May be presented to the user, and the user may consider inserting that expression # 2 in the report.

In addition, the system will note that if expression # 3 is present in the report, that expression # 3 is usually removed after expression # 1 is inserted. The system may propose that the user remove expression # 3 from the system under these circumstances.

Also, any information available to the system that will affect expressiveness can be utilized for the purpose of making appropriate proposals. For example, other text currently present in the user's report body may be searched for words, especially rare words, and these may be compared to words in expressions available to prioritize their suggestions. For example, if a radiologist is writing a report on an unusual type of tumor, it is suggested that other expressions, and other expressions of such tumor types, have been stated by other radiologist users in the system. Can be displayed.

Three exemplary examples are shown below to illustrate the steps involved in generating a medical imaging test report. Illustrative Example 1 illustrates the data structures (knowledge base elements such as phrases and associated rules) used in the following two examples.

Illustrative Example 1: The system has the following data structures: (1) test type, (2) phrase, and (3) group. Each test type has the following characteristics: (i) the name of the test type, (ii) a group of phrases associated with the test type, and (iii) phrases that are stitched together to create a standard normal report. Has an ID # of. Each phrase has the following characteristics: (i) a phrase ID # that is not visible to the end user but is useful for programming, (ii) a title for the user to refer to a phrase in the menu for identification. Includes name, (iii) priority value indicating the relative importance of the findings if present in the report, (iv) other phrases that should be excluded from the report if this phrase is inserted. Exclusion list, (v) Other phrases that the user would want to insert if this phrase is inserted in the report, and that the system substitutes for this phrase if this phrase is excluded. Have a suggestion list that includes alternative phrases that you will try. Each group is a plurality of phrases having an element, that is, the name of the group and the ID # of the phrase within the group.

The following structural definitions are used.
Definition of test type CT abdominal pelvis CT phrase group associated with abdominal pelvis:
Lung floor, abdomen, pelvis, bone and soft tissue CT Standard normal report for abdominal pelvis:
Insert phrase: 1, 2, 4, 8
Phrase group definition:
Lung bottom
Inclusion phrase: 1
abdomen
Inclusive phrases: 2, 3, 4, 5, 6, 7, 10, 11, 12
pelvis
Containing phrases: (not used in this example)
Bone and soft tissue
Inclusive phrases: 8, 9, 13
Phrase definition 1) Main report text Phrase:
The bottom of the lungs is clear. Pleural effusion or pulmonary consolidation is not clearly visible on the lung floor.
Title for menu: Normal lung floor impression equivalent:
The bottom of the lungs has a normal appearance.
Priority value: 1
Exclusion: None Suggestion: None If excluded, try to insert: None Included in group: Abdomen 2) Main report Body phrase:
There is a normal appearance of the liver, spleen, spleen, pancreas, kidneys, adrenal glands, and intestines.
Title for menu: normal abdominal organs and intestines.
Equivalents: Same as the complete phrase Priority value: 1
Exclusion: None Suggestion: None If excluded, try to insert: 3, then (... list of other possibilities)
3) Main report text phrase:
There is a normal appearance of the liver, spleen, pancreas, kidneys, adrenal glands, and intestines.
Title for menu: Normal abdominal organs / intestinal feeling equivalent except for bile sac: Same as main phrase 4) Main report Body phrase:
No free liquid or free gas.
Title for menu: Same as main phrase Impression equivalent: Same as main phrase Priority value: 1
Exclusion: None Suggestion: None If excluded, try to insert: 5, then 6 if 5 is not possible
5) Main report text phrase:
No free liquid.
Title for menu: Same as main phrase Impression equivalent: Same as main phrase Priority value: 1
Exclusion: None Suggestion: None If excluded, try to insert: None 6) Main Report Body Phrase:
No free gas.
Title for menu: Same as main phrase Impression equivalent: Same as main phrase Priority value: 1
Exclusion: None Suggestion: None If excluded, try to insert: None 7) Main Report Body Phrase:
No serious lymphadenopathy.
Equivalents: Same as the main phrase Priority value: 1
Exclusion: None Suggestion: None If excluded, try to insert: None 8) Main Report Body Phrase:
Bone and soft tissues appear within normal limits.
Menu title: Normal bone and soft tissue Equivalent: Same as key phrase Priority value: 1
Exclusion: None Suggestion: None If excluded, try to insert: 9, (... then list of other possibilities)
9) Main report text phrase:
No bone lesions appearing to be invasive. Soft tissue appears within normal limits.
Title for menu: No invasive bone lesions. Normal soft tissue.
Equivalent impression: Same as the main phrase Priority value: 5
Exclusion: None Suggestion: None If excluded, try to insert: None 10) Main Report Body Phrase:
Gallstones are found in the slightly dilated gallstones. There is mild hypertrophy of the cholecyst wall and slight pericystic fluid. The findings suggest acute cholecystitis. Clinical correlation is recommended.
Menu title: Acute cholecystitis Equivalent: Mild gallstone wall hypertrophy, dilation of the cholecyst, and gallstones found in the bile sac with peri-biliary fluid suggest acute cholecystitis.
Priority value: 70
Exclusions: 2, 4, 5, (... and others)
Suggestions: 11, 12
If excluded, try to insert: None 11) Main Report Body Phrase:
No bile duct dilation is seen. No common bile duct stones are seen.
Title for menu: No bile duct dilation or stones Feeling equivalent:
No bile duct dilation or common bile duct stones.
Priority value: 5
Exclusion: None Suggestion: None If excluded, try to insert: None 12) Main Report Body Phrase:
[#] mm gallstones are also found in the common bile duct at the head of the pancreas with [mild / moderate / severe] intrahepatic and extrahepatic bile duct dilation.
Title for menu: Gallstones in the common bile duct (CBD) with bile duct dilation Equivalent:
[#] Mm gallstones in the common bile duct at the head of the pancreas with [mild / moderate / severe] intrahepatic and extrahepatic bile duct dilation.
Priority value: 5
Exclusion: None Suggestion: None If excluded, try to insert: None 13) Main Report Body Phrase:
There is a mild degenerative disease of the lumbar spine. Mild degenerative disease of the lumbar spine.
Title for menu: Mild lumbar degenerative disease Equivalent to feeling:
Mild lumbar degenerative disease.
Priority value: 30
Exclusion: 8
Suggestion: None If excluded, try to insert: None

The selection of phrases based on the above definition will be exemplified in Examples 2 and 3.

Illustrative Example 2: The following is a workflow performed according to an exemplary embodiment of the present invention, using the structural definition defined in Example 1. First, the user selects a test type, such as abdominal and pelvic CT, from a list of test types, as illustrated in FIG. The report text is dominated by standard normal templates for this type of test. That is, a standard normal reporting template consisting of a set of standard phrases that are inserted together in the report and used to describe a typical normal test is used. The normal reporting of this standard can be defined as such under this system. FIG. 4 illustrates the appearance of the report editing field after the normal template of this standard has been applied.

When proceeding from the normal reporting of this standard, the user inserts pathological or other findings in stages. The phrases in this example are grouped together for easy user selection. First, the user is presented with a set of pop-up menus that reference various anatomical sites that are visible or controversial on the "CT of the abdomen and pelvis". As illustrated in FIG. 5, there will be pop-up menus or other GUI elements that allow the user to select a medical condition for the lung floor, abdomen, pelvis, or bone and soft tissue. If the user clicks, for example, "abdomen," the user selects the lower hierarchy, "cholecyst," and the following standard phrase, "gallstones, is mildly expanded," which indicates signs of acute cholecystitis. It is found in the cholecyst. There is mild hypertrophy of the cholecyst wall and a slight peri-cystic fluid. Findings suggest acute cholecystitis. Clinical correlation is recommended. " The title of this phrase for a brief reference in the menu is "Acute Cholecystitis".

The phrase will also be associated with the "feeling" equivalent "gallstones found in the bile sac, with mild biliary wall hypertrophy, biliary dilatation, and peri-biliary fluid, suggest acute cholecystitis." ..

This phrase is also associated with exclusion rules for some standard normal expressions. For example, the report cannot state that there is no free fluid because there is free fluid around the bile. The report also cannot state that there is a normal appearance of the abdominal organs and intestines. Exclusion rules that exclude the phrase "no free liquid or free gas" will be applied. There are also exclusion rules that prohibit phrases that state that the abdominal organs and intestines are normal. The phrase "no free liquid or free gas" is possible for itself if the above rule regarding free liquid is excluded by a rule stating that the phrase of bile sac / cholecystitis cannot exist in association with this phrase. We propose "no free gas". This is due to the relationship between phrases, in which the phrase "no free gas" attempts to be inserted by the system in the report text when "free liquid or no free gas" is excluded. Is a potential alternative phrase to the standard that would be. This alternative phrase is not excluded by any other rule, so the alternative phrase is inserted.

When anomalous findings are inserted in the report, the system will find the first suitable substitute phrase that describes a smaller set of normal findings, so that the system is from the "most normal" phrase. Start, search through the list to find the first normal expression that is not excluded by other phrases present in the report, and finally insert the first "most normal" normal expression that is not excluded, Many sets of standard normal descriptions of abdominal organs may be created.

From an algorithmic point of view, when a "normal" expression is excluded from the report, the behavior is associated with this exclusion and the phrase suggests that the program insert another normal expression in its place. This next expression is checked for exclusion, and if that expression is further excluded, suggests another normal expression. This continues from one malnormal phrase to another, until the final phrase that can be inserted is found. This finally insertable phrase is inserted in the report.

Each representation also has a "priority" number that determines the order of insertion within the report. Items with higher "priority" numbers are inserted first. Items with lower "priority" numbers are placed later. Higher "priority" numbers are associated with more serious, life-threatening items or items that require immediate intervention. The gall bladder phrase for cholecystitis will have a high priority number, probably 70 out of the 100 possible range. The standard normal representation has a low priority number, such as 1. The report then includes additional phrases selected by the user and is illustrated in FIG.

The system then proposes generally associated phrases to the user via the knowledge database. These phrases may be defined by the user at the time the user puts them together, or may be automatically determined based on the previous usage / insertion pattern of the phrases. A deliberate system will contain a great many phrases from each type of source.

In this example, those associated with the bile duct / cholecystitis phrase are the following commonly used phrases (a) "No bile duct dilation. No common bile duct stones." And (b) "[#]. mm gallstones are also found in the common bile duct at the pancreatic head, with [mild / moderate / severe] intrahepatic and external bile duct dilation. "

The user selects (b) when gallstones are visible in the dilated common bile duct. When this phrase is selected, the user types "5", which indicates a gallstone measurement, in the blank space of [#]. The user also chooses from "mild," "moderate," and "severe" to indicate the degree of bile duct dilation. The equivalent of the impression of this phrase is "[#] mm gallstones in the common bile duct with dilation of the [#] bile duct." Therefore, once the phrase is inserted in the report, the user only includes the measured value and the degree of severity information. However, doing so will at the same time update the information within the impression equivalent. The updated report is illustrated in FIG.

The user generally does not want to review the list of associated expressions and select nothing further. The user may then select a statement from the "Bone and Soft Tissue" pop-up menu stating "There is a mild degenerative disease of the lumbar spine". This expression has a priority value of "5", and the impression equivalent of the expression "mild degenerative disease of the lumbar spine" has a priority value of "5". Therefore, these items are less important than the description of the gall, but more important than the standard normal report. These statements exclude the statement "Bone and soft tissue are within normal limits." Since that phrase is excluded, we attempt to propose a replacement phrase that is not excluded by any of the phrases currently in the report: "No visible bone lesions are found. Soft tissue is within normal limits." .. Therefore, this replacement phrase is inserted. The updated report is shown in FIG.

Alternatively, the user will also prefer to have a concise impression. The user can arbitrarily set a threshold value of the priority value for including the phrase element in the impression. For example, unless such findings have a priority level of 50 or higher, no more than three findings will be reported. The user will then ensure that any findings required within the impression, if inserted within the report, would have to have a priority level of 50 or higher. .. Since the user has specified that no more than four impression items should be included unless the priority value is 50 or more, the final report excludes the fifth item and is also illustrated in FIG. To.

Illustrative Example 3: This example illustrates the use of another exemplary embodiment of the invention for editing a text field in a medical imaging test report. In this example, a report on the interpretation of normal abdominal CT imaging is illustrated. First, the user opens a blank reporting screen as shown in FIG. The user then searches for a normal reporting template for reporting a normal abdominal CT imaging test and types in a search term such as "negative abdominal CT". The system generates some suggested phrases on the server. These phrases are previously defined and associated with search terms. The proposed phrase is then displayed for the user to review, as shown in FIG. The user has selected the first suggested phrase to be placed within the report edit field, as shown in FIG. In doing so, some updated suggestions are created based on this user's system, other users in the system, and previous usage patterns of words in the report text. In this example, as illustrated in FIG. 13, the patient is a 70 year old male, and his age and gender information is also entered into the system, which is then almost certainly such as osteopenia. Used to suggest other phrases and expressions, which are generally selected when the user edits a report about a patient in that age and gender group. The user may store the entire template or part of the template in a general knowledge database for future use when using similar findings.

The user wants to report anomalies while having a basic reporting framework in place. In this example, a right renal mass with an intermediate density of about 5 cm occludes the right kidney (right hydronephrosis). The user decides to search for a phrase about the renal mass in the search box of the reporting interface, as shown in FIG. At the time of image interpretation, the user is not sure what the mass is, but considers the first representation in FIG. 14 to be a useful framework to start with, and therefore considers that representation. select. The user also enters a value in the field given the choice between "left" and "right" for the size and parameters of the tumor. Directional data (ie, left or right) and size data need only be entered in one position, as shown in FIG. 15, and are reflected throughout the text. This allows the user to save time by entering repetitive information and reduce reporting errors. When you add a renal mass phrase, the system applies exclusion rules to that phrase to detect reciprocity and inconsistencies. Expressions in the first normal report inserted by the user that are inconsistent with renal mass findings are, for example, red in italics and flagged to warn the user of potential reciprocity. The user can click the red expression in italics to delete, edit, or select a commonly substituted expression, as shown in FIG. FIG. 17 shows a substitute phrase suggested by the system when the user clicks on the red representation in the first italic. The user may update the report as shown in FIG.

FIG. 19 shows how a user can also insert free-form text in a subtext field into a defined representation to report details not contained in the ordinary representation from the database. Is shown. This allows the user to deviate from the standard defined representation in order to fully customize the report. In this example, the user added "or hemorrhagic vascular myelolipoma" within the impression. Adding this text, the system identifies "vascular myelolipoma" as a rare term that may be worth suggesting additional phrases. Additional phrases containing the term vascular myelolipoma are then suggested to the user via an interface as shown in FIG. The user chooses to insert an additional phrase regarding vascular myelolipoma in the report as shown in FIG. 21 to complete the report.

FIG. 22 shows a screenshot of a system interface according to an exemplary embodiment of the present invention.

The present invention includes methods as described herein, computer-readable media programmed to perform the methods, and computer systems configured to perform the methods. A computer system is a machine-readable recording medium containing executable code, a device having one or more processors, a memory coupled to the processor, and a machine-readable medium having machine-readable program code. And an input and output device connected to the processor (s) for making reports or other material. Although the invention has been described by exemplary embodiments, further advantages and modifications will come to the minds of those skilled in the art. Accordingly, the invention of the superordinate aspects of the invention is not limited to the particular details presented and described herein.

Modifications, such as modifications to the type of report and specific features of the software, may be made without departing from the spirit and scope of the invention. Therefore, the present invention is not limited to a specific exemplary embodiment, but within the entire purpose and scope of the described embodiments and the appended claims, and within their equivalents. It is intended to be interpreted as being.

Claims (18)

A computer-based method for generating medical imaging reports,
(A) Phrases related to multiple imaging test types that can be interpreted in medical imaging, (b) Relationships between those phrases, and (c) Templates consisting of a set of such phrases, and / or (d). ) Make a medical image report generation database into a computer-readable medium, including one or more of the complete texts of previously produced reports from within and / or out of range of the system from which the phrase suggestion can be derived. Steps to store and
The step of storing the executable computer code in a computer processor connected to the computer-readable medium,
A step of generating a medical imaging test report using the stored report generation database by executing the computer code using the computer processor, wherein the medical imaging test report is one or more. Steps to generate a medical imaging report, including a structure that contains multiple text fields,
When the computer processor receives data indicating the inspection type from an external system, it is indicated to the computer processor based on the indicated inspection type and / or by executing the computer code using the computer processor. The step of optionally providing the external system with one or more first phrases of potential interest from the report generation database, and
When the computer processor receives input of a phrase and / or arbitrary text from an external system, the computer processor is used to execute the computer code to provide one or more inclusion or exclusion rules based on usage patterns. A pattern to apply to existing report text and / or the selected phrase and / or to identify potentially useful text from other reports stored in the previously written radiomedical report database. The steps of applying matching rules and presenting one or more proposed phrases and / or arbitrary texts to an external system via an output method.
The one or more initial phrases and / or the one or more to identify one or more exclusion phrases excluded from the report by executing the computer code with the computer processor. A step of applying one or more exclusion rules based on the pattern of use to multiple related phrases and / or said reports in progress and generating reports resulting from these processes sent to an external system.
A method comprising the step of applying a substitute rule that replaces the exclusion phrase with an alternative phrase by executing the computer code with the computer processor to provide a report to an external system resulting from these processes. The first aspect of the present invention further comprises a step of optionally updating the exclusion and inclusion rules based on at least a portion of the generated report and information input to the computer processor by an external system. Method. Further including steps to implement the method through the network
The method of claim 2, wherein updating the exclusion and inclusion rules is based on at least a portion of one or more reports generated by the use of the computer processor . The method of claim 1, wherein at least a portion of the one or more text fields is occupied by one or more templates, each template containing a set of phrases associated with the selected test type. .. A step of assigning a priority value to one or more of the phrases,
The method of claim 1, further comprising the step of ordering the phrases in the report according to the priority value by executing the computer code with the computer processor. The one or more text fields further include one or more subfields for the information entered, the information being entered optionally within the text field of the relevant phrase in the report. The method of claim 1, which is propagated. A step of saving data representing the frequency of use of the modified phrase in the medical image reporting database, and
A step of comparing the frequency of use of the modified phrase with the frequency of use of the corresponding uncorrected phrase.
The method of claim 1, further comprising the step of presenting any proposed phrase as a modified phrase at the position of any corresponding uncorrected phrase having a lower frequency of use. A step of saving data representing the frequency of use of the modified template in the medical image reporting database, and
A step of comparing the frequency of use of the modified template with the frequency of use of the corresponding unmodified template.
The method of claim 1, further comprising the step of presenting the modified template as a proposed template at the location of any corresponding unmodified template having a lower frequency of use. A medical imaging test report generation system
One or more input methods to enable inspection type selection, phrase selection, and text input,
With one or more processors for processing inspection type selection, phrase selection, input text, and one or more rule-based concepts.
With one or more memory systems functionally coupled to the processor
With an output device functionally connected to the processor,
The system is configured to perform each step of claim 1 report creation. A computer-based method for generating medical imaging reports,
(A) Phrases associated with multiple imaging test types interpreted in medical imaging tests and inclusion and exclusion rules, and / or (b) a reporting template consisting of a collection of such phrases, and / or Of the database of (c) data on patterns prior to the use of such phrases in cases prior to the use of the system and / or (d) the complete report text that can be used to identify additional phrase suggestions. A step of storing a medical image report generation database on a computer-readable medium, including at least one,
The steps of executing computer code using a computer processor connected to the computer-readable medium, and
By executing the computer code with the computer processor, the stored report generation database is used to generate a medical imaging test report containing a structure containing one or more text fields.
Upon receiving the data indicating the inspection type, the computer processor executes the computer code with the computer processor to provide a report template having a plurality of phrases based on the selected inspection type.
A step of outputting one or more phrases related to the template phrase via an output method for use by an external system.
When the computer processor receives data indicating the selection of one or more phrases or any text entered, one or more based on the pattern of use by executing the computer code with the computer processor. And the step of applying the inclusion rule to the template phrase and the selected related phrase,
When the computer processor receives data indicating the selection of one or more related phrases, the computer processor is used to execute computer code to exclude one or more based on the pattern of use for the phrase. A step of applying the rule to the template phrase and the selected related phrase, thereby identifying one or more phrases excluded from the medical imaging report.
A step of carrying the list of alternative phrases to an external system by applying a substitute rule that replaces the excluded phrase with an alternative phrase by executing the computer code with the computer processor.
A step of generating a medical image report containing the selected phrase in the text field and the test type via a report output device, and
By storing at least some or all of the text in the generated report and the inclusion and exclusion decisions and information provided to the computer processor by an external system back into the database. Methods, including steps to update the database. One or more template phrases and one or more related phrases are associated with priority values, and the method is:
The one or more prioritized related phrases and prioritized template phrases ordered according to their associated priority values are sent to an external system via an output device in the medical report. 10. The method of claim 10, further comprising the steps presented. 10. The method of claim 10, further comprising defining a set of templates associated with a special use case, such as a special external system used for a particular purpose. 10. The method of claim 10, further comprising the step of presenting the phrase based on the pattern prior to the selection of the phrase. Steps to present the phrase based on how often the phrase is used in similar reports,
10. The method of claim 10, further comprising identifying a new phrase based on its use in the previous report. A step of saving data representing the frequency of use of the modified phrase in the medical image reporting database, and
A step of comparing the frequency of use of the modified phrase with the frequency of use of the corresponding uncorrected phrase.
A step of including or proposing a phrase modified at the position of any corresponding uncorrected phrase with a lower frequency of use as a proposed phrase, or transporting it to an external system.
The method according to claim 1 or 10, further comprising. A step of saving data representing the frequency of use of the modified template in the medical image reporting database, and
A step of comparing the frequency of use of the modified template with the frequency of use of the corresponding unmodified template.
With the step of including or proposing a modified template for use in the position of the corresponding unmodified template with a lower frequency of use, or transporting it to an external system.
The method according to claim 1 or 10, further comprising. A the text generated using the data derived from the external system said reporting, all text including any new text entered in uniquely generated in said computer processor by the computer processor or The method of claim 1 or 10, further comprising the step of storing a portion in the medical image reporting database. If any phrase or text is placed in said computer processor, said not a phrase defined previously in the computer processor only from the text contained in the database of previously written radiological report, phrases 10. The method of claim 10, further comprising the step of proposing additional phrases for expected incorporation into the report using a pattern matching method for identifying.

Images