A medical report processing method and program product

Abstract

The application discloses a medical report processing method and a program product. The method comprises the following steps: acquiring diagnosis description information and examination item information of a to-be-detected medical report, determining a report type of the to-be-detected medical report according to the diagnosis description information and the examination item information; determining a target retrieval task according to the report type of the to-be-detected medical report, and determining a problem list of the to-be-detected medical report according to the target retrieval task and target reference data corresponding to the target retrieval task. The technical scheme adopts target reference evidence to specially detect the accuracy and expression precision of professional terms in different types of medical reports, so that each problem existing in the to-be-detected medical report is determined, error positioning and tracking adjustment of the target problem are facilitated, and the efficiency, convenience and interpretability of the medical report quality analysis and processing are improved.

Description

Technical Field

[0001] This invention relates to the field of report text processing technology, and in particular to a medical report processing method and program product. Background Technology

[0002] With the development of modern medicine, medical test reports have become an indispensable part of the diagnostic process for doctors. However, due to problems such as deviations in equipment parameters, non-standard human operation, and errors in information entry during actual testing, a certain number of incorrect descriptions of the condition may appear in medical test reports. As a result, making a medical diagnosis based on an incorrect medical test report may lead to serious consequences such as medication errors and omissions in examinations.

[0003] In related technologies, the primary method for detecting medical reports is through rule engines. However, this approach heavily relies on manually pre-defined verification logic. Furthermore, medical report language contains numerous contextual dependencies, making it difficult for rule engines to accurately understand these relationships. This leads to inaccurate error detection and insufficient error localization precision. Moreover, rule-based verification methods struggle to cover the diverse range of medical report detection scenarios. Therefore, current technologies are insufficient for accurate, comprehensive, and reliable quality inspection of various types of medical reports. Summary of the Invention

[0004] This invention provides a medical report processing method and program product. By defining corresponding target retrieval tasks and target reference data for different types of medical reports, more targeted professional testing can be performed on various medical reports, thereby solving the technical problem of insufficient accuracy in quality testing of different medical reports in related technologies.

[0005] According to one aspect of the present invention, a method for processing medical reports is provided, the method comprising:

[0006] Obtain the diagnostic description information and examination item information of the medical report to be tested, and determine the report type of the medical report to be tested based on the diagnostic description information and the examination item information;

[0007] The target retrieval task is determined based on the report type of the medical report to be tested, and the question list of the medical report to be tested is determined based on the target retrieval task and the target reference data corresponding to the target retrieval task.

[0008] According to another aspect of the present invention, a medical report processing apparatus is provided, the apparatus comprising:

[0009] The report acquisition module is used to acquire the diagnostic description information and examination item information of the medical report to be tested, and determine the report type of the medical report to be tested based on the diagnostic description information and the examination item information;

[0010] The retrieval and analysis module is used to determine the target retrieval task based on the report type of the medical report to be tested, and to determine the problem list of the medical report to be tested based on the target retrieval task and the target reference data corresponding to the target retrieval task.

[0011] According to another aspect of the present invention, an electronic device is provided, the electronic device comprising:

[0012] At least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores a computer program executable by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform a medical report processing method according to any embodiment of the present invention.

[0013] According to another aspect of the present invention, a computer-readable storage medium is provided, the computer-readable storage medium storing computer instructions for causing a processor to execute and implement a medical report processing method according to any embodiment of the present invention.

[0014] According to another aspect of the present invention, embodiments of this disclosure also provide a computer program product, including a computer program that, when executed by a processor, implements a medical report processing method as described in any of the embodiments of this disclosure.

[0015] The technical solution of this invention can acquire diagnostic description information and examination item information of a medical report to be tested, and determine the report type of the medical report to be tested based on the diagnostic description information and the examination item information. By using dual information to comprehensively determine the report type, the accuracy of medical report type classification can be effectively improved, and the efficiency of automated processing of medical reports can be enhanced, facilitating data retrieval and archiving of different medical reports. Subsequently, a target retrieval task can be determined based on the report type of the medical report to be tested, and a problem list of the medical report to be tested can be determined based on the target retrieval task and the target reference data corresponding to the target retrieval task. By acquiring the retrieval task corresponding to the target report, a refined retrieval of the problem report can be performed to identify potential omissions in the report, thereby improving the efficiency and accuracy of medical report testing. Therefore, this technical solution, by employing the above technical means, can perform relatively accurate intelligent and standardized testing of medical reports, improve the interpretability and standardized expression of problem content in medical reports, and thus ensure the overall quality of medical reports.

[0016] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of the present invention, nor is it intended to limit the scope of the invention. Other features of the invention will become readily apparent from the following description. Attached Figure Description

[0017] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0018] Figure 1 This is a flowchart of a medical report processing method provided in Embodiment 1 of the present invention;

[0019] Figure 2 This is a flowchart of a medical report processing method provided in Embodiment 2 of the present invention;

[0020] Figure 3 This is a schematic diagram of the structure of a medical report processing device according to Embodiment 3 of the present invention;

[0021] Figure 4 This is a schematic diagram of the structure of an electronic device that implements a medical report processing method provided in Embodiment 4 of the present invention. Detailed Implementation

[0022] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0023] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0024] It should be noted that the terms "a" and "a plurality of" used in this disclosure are illustrative rather than restrictive, and those skilled in the art should understand that, unless otherwise expressly indicated in the context, they should be understood as "one or more".

[0025] The names of messages or information exchanged between multiple devices in the embodiments of this disclosure are for illustrative purposes only and are not intended to limit the scope of such messages or information.

[0026] It is understood that before using the technical solutions disclosed in the various embodiments of this disclosure, users should be informed of the types, scope of use, and usage scenarios of the personal information involved in this disclosure in an appropriate manner in accordance with relevant laws and regulations, and user authorization should be obtained.

[0027] For example, upon receiving a user's active request, a prompt message is sent to the user to explicitly inform them that the requested operation will require the acquisition and use of the user's personal information. This allows the user to independently choose whether to provide personal information to the software or hardware, such as the electronic device, application, server, or storage medium performing the operations of this disclosed technical solution, based on the prompt message.

[0028] As an optional but non-limiting implementation, in response to a user's active request, sending a prompt message to the user can be done via a pop-up window, where the prompt message can be presented in text format. Furthermore, the pop-up window can also include a selection control allowing the user to choose "agree" or "disagree" to provide personal information to the electronic device.

[0029] It is understood that the above notification and user authorization process are merely illustrative and do not constitute a limitation on the implementation of this disclosure. Other methods that comply with relevant laws and regulations may also be applied to the implementation of this disclosure.

[0030] It is understood that the data involved in this technical solution (including but not limited to the data itself, the acquisition or use of the data) shall comply with the requirements of relevant laws, regulations and related provisions.

[0031] Example 1

[0032] Figure 1 This invention provides a flowchart of a medical report processing method according to Embodiment 1. This embodiment is applicable to scenarios involving quality control of test reports, particularly for highly specialized texts such as medical test reports. The method can be executed by a medical report processing device, which can be implemented in hardware and / or software, optionally through an electronic device such as a mobile terminal, PC, or server. Figure 1 As shown, the method may specifically include:

[0033] S110. Obtain the diagnostic description information and examination item information of the medical report to be tested, and determine the report type of the medical report to be tested based on the diagnostic description information and the examination item information.

[0034] The medical report to be tested can be understood as a medical condition statement written by a doctor based on medical images and patient descriptions, or a medical document exported from a hospital information system. Diagnostic description information can be understood as a subjective description or objective finding of the patient's condition, i.e., a summary judgment based on the examination results. Examination item information can be understood as the specific technical means, equipment names, or examination sites used to obtain the current medical report; specifically, examination item information can include at least one of the following: CT scan, ultrasound, puncture, plain scan, etc. Report type can be understood as the category of medical document to which the medical report belongs, determined based on the medical report information; specifically, medical report types can include at least one of the following: imaging report, pathology report, laboratory test report, endoscopic examination report, and clinical assessment report.

[0035] Specifically, the diagnostic descriptions and examination item information contained in the medical report to be tested are obtained. Then, using rule-based, machine learning-based, and deep learning-based methods, key target content is extracted from the diagnostic descriptions and examination item information. This key target content can then be matched with different types of medical reports to determine the report type of the medical report to be tested. Through comprehensive extraction and analysis of data information from medical reports, the accuracy of matching medical report types can be effectively improved, and the efficiency of classifying, summarizing, and retrieving medical reports can be enhanced.

[0036] In one embodiment, determining the report type of the medical report to be tested based on the diagnostic description information and the examination item information includes: segmenting the diagnostic description information and the examination item information of the medical report to be tested respectively to determine at least one text segment, and determining the report type of the medical report to be tested based on the text segment, wherein the text segment includes at least one of sentence segments and fields.

[0037] Specifically, by using pre-defined extraction rules, characteristic segments or fields in diagnostic descriptions and examination item information can be extracted and segmented to obtain multiple segments or fields. These segments or fields can then be combined to generate text fragments. This technical solution extracts text fragments from the content of the medical report to be tested, thereby analyzing and processing the main features of the medical report. This reduces the complexity of analysis and computation, preserves the dependencies between different text fragments, and enhances the ability to discover potential problems.

[0038] Furthermore, when segmenting diagnostic description information and examination item information, segmentation can also be performed based on punctuation marks to extract target sentence segments or target fields and generate text fragments; or machine learning can be used to process diagnostic description information and examination item information to combine the semantic relationships between different data information, automatically capture interrelated sentence segments or fields, extract target sentence segments or target fields, and generate text fragments.

[0039] S120. Determine the target retrieval task based on the report type of the medical report to be tested, and determine the problem list of the medical report to be tested based on the target retrieval task and the target reference data corresponding to the target retrieval task.

[0040] The target retrieval task can be understood as the specific task information used to perform matching retrieval, which may include the data information to be retrieved. In this technical solution, the target retrieval task may include at least one segmented text fragment. Specifically, the target retrieval task may include at least one of the following tasks: reference evidence retrieval task, medical knowledge retrieval task, standard evidence retrieval task, etc. The target reference data may include at least one of the following: reference report database, medical knowledge base, standard report database, etc. The problem list can be understood as a summary list of various problems that may exist in medical reports, such as missing information, descriptive errors, logical contradictions, etc.

[0041] Specifically, the method involves acquiring the report type of the medical report to be tested, as well as at least one text fragment. A target retrieval task is then constructed based on this report type and the text fragment. Corresponding target reference data is determined according to the type of the target retrieval task. By matching the target retrieval task with the target reference data, discrepancies are identified, and a problem list of the medical report to be tested is generated based on these discrepancies. This technical solution, through data matching between the constructed target retrieval task and the target reference data, enables automated discrepancy analysis of medical reports. Furthermore, by comparing with multiple reference materials, it can efficiently and accurately identify various potential problems in the medical report, improving the standardization and accuracy of the medical report's presentation.

[0042] In one embodiment, after determining the problem list of the medical report to be tested based on the target retrieval task and the target reference data corresponding to the target retrieval task, the method further includes: generating a correctable report of the medical report to be tested based on the problem list, wherein the correctable report is used to indicate the modifiable content in the medical report to be tested and the modifiable methods corresponding to the modifiable content.

[0043] The modifiable methods can include the specific content to be modified and the operation method for modifying the content of the problem. For example, to change "Field A" to "Field B" in a certain problem, the modification method can include directly deleting "Field A" and then filling it with "Field B".

[0044] Specifically, after obtaining the problem list, each problem in the medical report to be tested can be marked, and each modifiable item in the report can be specially marked and recorded, along with the appropriate modification method for that item. This results in a correctable report that includes the modifiable content (i.e., the problem) and the corresponding modification method. By marking and recording each problem (modifiable content) in the medical report in detail, the correctable report clearly shows the location, content, and modification method of each problem, allowing users to clearly and conveniently understand the overall quality of the report.

[0045] For example, taking the statement "A nodule with a diameter of approximately 5 cm is visible in the upper lobe of the right lung, with smooth edges, considered a lithological lesion" as an example, after comparing with reference data, this content can be specially marked. The "smooth edges" mark for this nodule can be changed to "lobulated edges" using the "direct deletion" method; the "lithological lesion" mark can be changed to "enhanced scan or biopsy recommended" using the "add" method. By directly marking the erroneous content, detailed modifications can be displayed at the problematic location (where the content can be modified), allowing users to intuitively understand the location of the problem and the corresponding modification methods.

[0046] In one implementation, after generating a correctable report of the medical report to be tested based on the problem list, the method may further include: correcting the medical report to be tested based on the correctable report to obtain a target medical report. This technical solution enables automated correction of the medical report to be tested, making the correction process more targeted. It not only improves the efficiency of the correction work but also ensures the logical rigor and accuracy of the final target medical report, thereby effectively improving the standardization and reliability of medical reports.

[0047] The target medical report can be understood as a medical report that has been revised to address various issues.

[0048] Specifically, after generating the correctable report, specific correction actions can be performed on the test report according to each modifiable content and modification method marked in the correctable report, thereby obtaining the modified target medical report.

[0049] In one implementation, specific problems or modifiable content can be directly modified in the provided modifiable manner, and modification traces for the problems or modifications can be retained, so that users can directly view the modified content and modification traces of the medical report to be tested.

[0050] In another implementation, after determining the problem list of the medical report to be tested based on the target retrieval task and the target reference data corresponding to the target retrieval task, the method includes: annotating the medical report to be tested according to the problem list to obtain an annotated medical report, wherein the annotated medical report is used at least to highlight the diagnostic description information in the medical report to be tested that has problems and the target reference evidence in the target reference evidence set that is associated with the diagnostic description information.

[0051] Target reference evidence can be understood as a reference for correcting a problem, and it can represent the specific reason for modifying a particular problem. The target reference evidence set is a collection of evidence obtained by combining multiple target reference evidence sets.

[0052] Specifically, the system can highlight the diagnostic descriptions of each problem in the medical report and annotate the corresponding target reference evidence. This demonstrates the specific basis for correcting each problem, generating an annotated medical report containing the target reference evidence for each issue. By annotating the target reference evidence, the system effectively ensures traceability of problem corrections, improving the convenience of reviewing medical reports.

[0053] In one method of generating annotated medical reports, the problematic diagnostic description information can be directly highlighted in the medical report to be tested, and the associated target reference evidence can be directly identified at the problematic diagnostic description information, forming an annotated report containing modification traces; alternatively, a separate identical medical report can be generated, and the problematic diagnostic description information can be highlighted in the newly generated medical report using a side annotation format, and the associated target reference evidence can be identified and displayed in the side, thereby displaying the target reference evidence in the medical report; the above methods are used to generate an annotated medical report for the medical report to be tested.

[0054] In another embodiment, the step of determining the problem list of the medical report to be tested based on the target retrieval task and the target reference data corresponding to the target retrieval task further includes: searching and matching the problem list with a rating rule base to determine the error level corresponding to each problem; and calculating the total score of the report to be tested based on the error level corresponding to each problem.

[0055] The rating rule base includes error levels and corresponding scoring rules for different questions.

[0056] By matching each question in the question list with a rating rule base, the error level of each question is determined, and a score can be calculated based on the error level of each question. The total score of the medical report under test is calculated by summing the scores of each question. This technical solution uses a rating rule base to score the medical report under test, directly generating a quantitative quality score for the overall medical report. This facilitates statistical and trend analysis of different medical reports, improving the convenience of quality assessment for various medical reports.

[0057] The technical solution of this invention can acquire diagnostic description information and examination item information of a medical report to be tested, and determine the report type of the medical report to be tested based on the diagnostic description information and the examination item information. By using dual information to comprehensively determine the report type, the accuracy of medical report type classification can be effectively improved, and the efficiency of automated processing of medical reports can be enhanced, facilitating data retrieval and archiving of different medical reports. Subsequently, a target retrieval task can be determined based on the report type of the medical report to be tested, and a problem list of the medical report to be tested can be determined based on the target retrieval task and the target reference data corresponding to the target retrieval task. By acquiring the retrieval task corresponding to the target report, a refined retrieval of the problem report can be performed to identify potential omissions in the report, thereby improving the efficiency and accuracy of medical report testing. Therefore, this technical solution, by employing the above technical means, can perform relatively accurate intelligent and standardized testing of medical reports, improve the interpretability and standardized expression of problem content in medical reports, and thus ensure the overall quality of medical reports.

[0058] Example 2

[0059] Figure 2 This is a flowchart of a medical report processing method provided in Embodiment 2 of the present invention. This embodiment is a refinement of the technical solution of "determining the problem list of the medical report to be detected based on the target retrieval task and the target reference data corresponding to the target retrieval task" based on the above embodiments. Specific implementation details can be found in the description of this embodiment. Technical features that are the same as or similar to those in the foregoing embodiments will not be repeated here. Figure 2 As shown, the method may specifically include:

[0060] S210. Obtain the diagnostic description information and examination item information of the medical report to be tested, and determine the report type of the medical report to be tested based on the diagnostic description information and the examination item information.

[0061] S220. Determine the target retrieval task based on the report type of the medical report to be tested.

[0062] S230. Determine the entity field corresponding to at least one of the text fragments according to the reference evidence retrieval task, and construct the mapping relationship between the text fragments and the entity fields.

[0063] The reference evidence retrieval task can be understood as performing a retrieval from a high-quality report database. An entity field can be understood as characteristic attribute data representing a specific thing itself. For example, in describing tuberculosis, the size, color, location, and other descriptive information of tuberculosis symptoms can be used as entity fields for tuberculosis. A mapping relationship can be understood as representing the corresponding entity relationship between descriptive information in a text fragment and descriptive information in an entity field; it can be used for data matching between text fragments and entity fields.

[0064] Specifically, based on the text fragments describing the illness in the reference evidence retrieval task, the corresponding entity fields are determined. In other words, the descriptive information of the illness itself is determined based on the current illness description information, and a mapping relationship is constructed between the determined entity fields and the text fragments. This determines the content of the illness description information. By constructing such a mapping relationship, users can easily determine whether the patient's condition conforms to a normal condition state based on the text information of the medical report to be tested, thereby improving the accuracy of the analysis of the test report.

[0065] S240. Execute the reference evidence retrieval task based on the reference report library to obtain the target reference evidence set of the medical report to be tested.

[0066] The reference report library can be understood as a report library composed of multiple high-quality reports, and high-quality reports can be understood as medical reports that have been reviewed and confirmed by professionals.

[0067] Specifically, at least one text fragment in the reference evidence retrieval task is matched with various reports in the reference report database to determine the reference evidence corresponding to each text fragment. Multiple reference evidences are then combined sequentially to generate a target reference evidence set corresponding to the medical report to be tested. By matching and retrieving data from the reference report database, descriptive text corresponding to the text fragment can be obtained, which can be used for difference localization and problem identification of the text fragment, thus improving the detection accuracy of medical reports.

[0068] S250. Based on the text fragment, the target reference evidence set, and the mapping relationship, determine a first problem list for the medical report to be tested. The first problem list includes the problems existing in the medical report to be tested and the target reference evidence corresponding to the problems.

[0069] Specifically, based on text fragments in the medical report to be tested, the corresponding set of target reference evidence, and a pre-determined mapping relationship, a first list of problems in the medical report can be determined by comparing each text fragment with its corresponding target reference evidence. Through data matching of reference evidence, various problems in the medical report can be identified efficiently and conveniently, improving the accuracy of problem detection in medical reports.

[0070] In one implementation, the step of performing the reference evidence retrieval task based on the reference report library to obtain a target reference evidence set for the medical report to be tested includes: selecting a preset number of initial reference reports as candidate reference reports from a plurality of initial reference reports according to preset rules, wherein the preset rules include at least one of the similarity of the initial reference reports to the diagnostic categories in the medical report to be tested, the semantic similarity of the initial reference reports to the medical report to be tested, and the text description quality of the initial reference reports; determining a target retrieval method corresponding to the reference report library according to the reference evidence retrieval task, wherein the target retrieval method includes at least one of the examination item matching degree, semantic matching degree, and field completeness; and retrieving the candidate reference reports based on the target retrieval method and at least one text fragment in the reference evidence retrieval task to obtain a target reference evidence set matching the medical report to be tested.

[0071] The initial reference report can be understood as the various medical reports stored in the reference report library. The candidate reference reports can be understood as a predetermined number of selected medical reports. The textual description quality of the initial reference reports can be understood as the report score data of the reference reports.

[0072] Specifically, based on the similarity of the diagnostic category between the initial reference report and the medical report to be tested, the semantic similarity between the initial reference report and the medical report to be tested, and the textual description quality of the initial reference report, a predetermined number of initial reference reports are selected as candidate reference reports from multiple initial reference reports in the reference report database. This selection effectively reduces the number of reference reports required for matching and improves the relevance between the initial reference reports and the medical report to be tested. Next, based on the data characteristics of each text segment in the reference evidence retrieval task, the target retrieval method corresponding to the reference report database is determined. Finally, based on the determined target retrieval method and at least one text segment in the reference evidence retrieval task, a set of target reference evidence matching the medical report to be tested is retrieved from the pre-acquired candidate reference reports. By selecting and matching initial reference reports, the association similarity between the reference reports used for data matching and retrieval with the medical report to be tested can be effectively improved, thereby enhancing the retrieval accuracy of each text segment in the medical report to be tested and ensuring the reliability of the obtained reference evidence.

[0073] In another embodiment, the target retrieval task further includes a medical knowledge retrieval task; the target reference data further includes a medical knowledge base; the question list further includes a second question list; determining the question list of the medical report to be tested based on the target retrieval task and the target reference data corresponding to the target retrieval task includes: performing a retrieval and matching operation between at least one text fragment in the medical knowledge retrieval task and the medical knowledge base to determine medical description information corresponding to each text fragment; determining a second question list of the medical report to be tested based on the medical description information, the second question list being used to indicate medical terms in the medical knowledge base that match the medical description information; and merging the first question list and the second question list after deduplication according to a preset merging strategy to determine the question list of the medical report to be tested.

[0074] The medical knowledge base can be understood as a knowledge collection library consisting of a knowledge graph of various standard medical terms and the relationships between medical information. Medical description information can be understood as the descriptive information corresponding to the medical report stored in the knowledge base. Preset merging rules can include at least one of the following merging methods: merging based on reference evidence, merging based on key fields, priority merging, and strong constraint merging.

[0075] Specifically, text fragments from medical knowledge retrieval tasks can be matched with the acquired medical knowledge base to determine the medical description information corresponding to each text fragment. Based on multiple medical descriptions, a second list of issues in the medical report to be tested can be determined. By using the medical knowledge base to further verify text fragment matching in the medical report, data verification can be performed on the medical report from different dimensions, ensuring the comprehensiveness and accuracy of the matching verification. Furthermore, according to a preset merging strategy, the acquired first and second issue lists can be deduplicated and merged to obtain an issue list consisting of all issues in the medical report to be tested. By merging and organizing the issues obtained from different dimensions, duplicate marking of the same issue can be avoided, making the final issue list more comprehensive and orderly, and improving the comprehensiveness and reliability of issue detection in the medical report to be tested.

[0076] This technical solution can determine entity fields corresponding to at least one text fragment based on the reference evidence retrieval task, and construct a mapping relationship between the text fragments and the entity fields; it executes the reference evidence retrieval task based on the reference report library to obtain a set of target reference evidence for the medical report to be tested; and it determines a first problem list for the medical report to be tested based on the text fragments, the set of target reference evidence, and the mapping relationship. The first problem list includes the problems existing in the medical report to be tested and the target reference evidence corresponding to the problems. Therefore, based on the pre-established correspondence between text fields and text information in each reference report, the target reference evidence corresponding to each text field can be obtained from the reference report library, and a problem list for the medical report to be tested can be generated, effectively improving the efficiency and accuracy of medical report testing.

[0077] Example 3

[0078] Figure 3 This is a schematic diagram of a medical report processing device provided in Embodiment 3 of the present invention. Figure 3 As shown, the device includes a report acquisition module 301 and a retrieval and analysis module 302.

[0079] The report acquisition module 301 is used to acquire the diagnostic description information and examination item information of the medical report to be tested, and determine the report type of the medical report to be tested based on the diagnostic description information and the examination item information; the retrieval and analysis module 302 is used to determine the target retrieval task based on the report type of the medical report to be tested, and determine the problem list of the medical report to be tested based on the target retrieval task and the target reference data corresponding to the target retrieval task.

[0080] In this embodiment of the invention, the report acquisition module 301 can acquire the diagnostic description information and examination item information of the medical report to be tested, and determine the report type of the medical report to be tested based on the diagnostic description information and the examination item information. By using dual information to comprehensively determine the report type, the accuracy of medical report type classification can be effectively improved, and the efficiency of automated processing of medical reports can be enhanced, facilitating data retrieval and archiving of different medical reports. Subsequently, the retrieval and analysis module 302 can determine the target retrieval task based on the report type of the medical report to be tested, and determine the problem list of the medical report to be tested based on the target retrieval task and the target reference data corresponding to the target retrieval task. By acquiring the retrieval task corresponding to the target report, a refined retrieval of the problem report can be performed to identify potential omissions in the report, thereby improving the efficiency and accuracy of medical report testing. Therefore, this technical solution, by adopting the above technical means, can perform relatively accurate intelligent and standardized testing of medical reports, improve the interpretability adjustment and standardized expression of problem content in medical reports, thereby ensuring the overall quality of medical reports.

[0081] Based on the above-mentioned optional technical solutions, the report acquisition module 301 may optionally include a report segmentation unit. The report segmentation unit is used to segment the diagnostic description information and examination item information of the medical report to be tested, respectively, to determine at least one text segment, and to determine the report type of the medical report to be tested based on the text segment. The text segment includes at least one of sentence segments and fields.

[0082] Based on the above-mentioned optional technical solutions, the retrieval and analysis module 302 may optionally include: a mapping relationship construction unit, a reference evidence acquisition unit, and a first problem list determination unit. Specifically, the target retrieval task includes a reference evidence retrieval task; the target reference data includes a reference report library; the problem list includes a first problem list; the mapping relationship construction unit is used to determine entity fields corresponding to at least one of the text fragments based on the reference evidence retrieval task, and construct a mapping relationship between the text fragments and the entity fields; the reference evidence acquisition unit is used to execute the reference evidence retrieval task based on the reference report library to obtain a set of target reference evidence for the medical report to be tested; the first problem list determination unit is used to determine a first problem list for the medical report to be tested based on the text fragments, the set of target reference evidence, and the mapping relationship, wherein the first problem list includes problems existing in the medical report to be tested and the target reference evidence corresponding to the problems.

[0083] Based on the above-mentioned optional technical solutions, the reference evidence acquisition unit may optionally include: a reference report screening unit, a retrieval method determination unit, and a reference evidence retrieval unit. Specifically, the reference report library stores multiple initial reference reports; the reference report screening unit selects a preset number of initial reference reports as candidate reference reports from the multiple initial reference reports according to preset rules, the preset rules including at least one of the similarity between the initial reference report and the diagnostic category in the medical report to be tested, the semantic similarity between the initial reference report and the medical report to be tested, and the text description quality of the initial reference report; the retrieval method determination unit determines a target retrieval method corresponding to the reference report library according to the reference evidence retrieval task, the target retrieval method including at least one of the examination item matching degree, semantic matching degree, and field completeness; the reference evidence retrieval unit performs a retrieval in the candidate reference reports based on the target retrieval method and at least one text fragment in the reference evidence retrieval task to obtain a set of target reference evidence matching the medical report to be tested.

[0084] Based on the above-mentioned optional technical solutions, the retrieval and analysis module 302 may optionally include: a medical description information determination unit, a second question list determination unit, and a question list generation unit. Specifically, the target retrieval task further includes a medical knowledge retrieval task; the target reference data further includes a medical knowledge base; the question list further includes a second question list; the medical description information determination unit is used to perform a retrieval and matching operation between at least one text fragment in the medical knowledge retrieval task and the medical knowledge base to determine the medical description information corresponding to each text fragment; the second question list determination unit is used to determine a second question list in the medical report to be tested based on the medical description information, the second question list indicating medical terms in the medical knowledge base that match the medical description information; and the question list generation unit is used to merge the first question list and the second question list according to a preset merging strategy to determine the question list of the medical report to be tested.

[0085] Based on the above-mentioned optional technical solutions, the medical report processing device may optionally further include: a correctable report generation module. The correctable report generation module is used to generate a correctable report of the medical report to be tested based on the problem list. The correctable report indicates the modifiable content in the medical report to be tested and the corresponding modifiable methods.

[0086] Based on the above-mentioned optional technical solutions, the medical report processing device may optionally further include: a labeled medical report generation module. The labeled medical report generation module is used to label the medical report to be tested according to the problem list to obtain a labeled medical report. The labeled medical report is used to highlight at least the diagnostic description information with problems in the medical report to be tested and the target reference evidence in the target reference evidence set associated with the diagnostic description information.

[0087] Based on the above-mentioned optional technical solutions, the report type may optionally include at least one of the following: imaging report, pathology report, laboratory test report, laparoscopic examination report, and clinical assessment report.

[0088] The medical report processing device provided in this embodiment of the invention can execute a medical report processing method provided in any embodiment of the invention, and has the corresponding functional modules and beneficial effects for executing a medical report processing method. Technical details not described in detail in this embodiment can be found in any of the medical report processing methods described in this embodiment of the invention.

[0089] Example 4

[0090] Figure 4 A schematic diagram of an electronic device 10, which can be used to implement embodiments of the present invention, is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices (e.g., helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the invention described and / or claimed herein.

[0091] like Figure 4As shown, the electronic device 10 includes at least one processor 11 and a memory, such as a read-only memory (ROM) 12 or a random access memory (RAM) 13, communicatively connected to the at least one processor 11. The memory stores computer programs executable by the at least one processor. The processor 11 can perform various appropriate actions and processes based on the computer program stored in the ROM 12 or loaded from storage unit 18 into the RAM 13. The RAM 13 can also store various programs and data required for the operation of the electronic device 10. The processor 11, ROM 12, and RAM 13 are interconnected via a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0092] Multiple components in electronic device 10 are connected to I / O interface 15, including: input unit 16, such as keyboard, mouse, etc.; output unit 17, such as various types of displays, speakers, etc.; storage unit 18, such as disk, optical disk, etc.; and communication unit 19, such as network card, modem, wireless transceiver, etc. Communication unit 19 allows electronic device 10 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0093] Processor 11 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. Processor 11 performs the various methods and processes described above, such as a medical report processing method.

[0094] In some embodiments, a medical report processing method may be implemented as a computer program tangibly contained in a computer-readable storage medium, such as storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or mounted on electronic device 10 via ROM 12 and / or communication unit 19. When the computer program is loaded into RAM 13 and executed by processor 11, one or more steps of a medical report processing method described above may be performed. Alternatively, in other embodiments, processor 11 may be configured to perform a medical report processing method by any other suitable means (e.g., by means of firmware).

[0095] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), payload-programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0096] Computer programs used to implement the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when executed by the processor, the computer programs cause the functions / operations specified in the flowcharts and / or block diagrams to be performed. The computer programs may be executed entirely on a machine, partially on a machine, or as a standalone software package, partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0097] In the context of this invention, a computer-readable storage medium can be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, apparatus, or device. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination thereof. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0098] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0099] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or middleware components (e.g., application servers), or frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include local area networks (LANs), wide area networks (WANs), blockchain networks, and the Internet.

[0100] A computing system can include clients and servers. Clients and servers are generally located far apart and typically interact through communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a hosting product within the cloud computing service system to address the shortcomings of traditional physical hosts and VPS services, such as high management difficulty and weak business scalability.

[0101] In particular, according to embodiments of the present invention, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of the present invention include a computer program product comprising a computer program carried on a non-transitory computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via communication unit 19, or installed from storage unit 18, or installed from ROM 12. When the computer program is executed by processor 11, it performs the functions defined in the methods of the embodiments of the present invention.

[0102] It should be understood that the various forms of processes shown above can be used, with steps reordered, added, or deleted. For example, the steps described in this invention can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this invention can be achieved, and this is not limited herein.

[0103] The specific embodiments described above do not constitute a limitation on the scope of protection of this invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this invention should be included within the scope of protection of this invention.

Claims

1. A method for processing medical reports, characterized in that, include: Obtain the diagnostic description information and examination item information of the medical report to be tested, and determine the report type of the medical report to be tested based on the diagnostic description information and the examination item information; The target retrieval task is determined based on the report type of the medical report to be tested, and the question list of the medical report to be tested is determined based on the target retrieval task and the target reference data corresponding to the target retrieval task.

2. The medical report processing method according to claim 1, characterized in that, The step of determining the report type of the medical report to be tested based on the diagnostic description information and the examination item information includes: The diagnostic description information and examination item information of the medical report to be tested are segmented to determine at least one text segment. The report type of the medical report to be tested is determined based on the text segment. The text segment includes at least one of sentence segments and fields.

3. The medical report processing method according to claim 1, characterized in that, The target retrieval task includes a reference evidence retrieval task; the target reference data includes a reference report database; the question list includes a first question list; determining the question list of the medical report to be tested based on the target retrieval task and the target reference data corresponding to the target retrieval task includes: Based on the reference evidence retrieval task, determine the entity field corresponding to at least one of the text fragments, and construct the mapping relationship between the text fragments and the entity fields; The reference evidence retrieval task is performed based on the reference report database to obtain the target reference evidence set for the medical report to be tested. Based on the text fragment, the target reference evidence set, and the mapping relationship, a first problem list is determined for the medical report to be tested. The first problem list includes the problems existing in the medical report to be tested and the target reference evidence corresponding to the problems.

4. The medical report processing method according to claim 3, characterized in that, The reference report library is used to store multiple initial reference reports; the reference evidence retrieval task based on the reference report library to obtain the target reference evidence set for the medical report to be tested includes: A predetermined number of initial reference reports are selected as candidate reference reports from multiple initial reference reports according to preset rules. The preset rules include at least one of the following: the similarity of the diagnostic category between the initial reference report and the medical report to be tested, the semantic similarity between the initial reference report and the medical report to be tested, and the text description quality of the initial reference report. Based on the reference evidence retrieval task, a target retrieval method corresponding to the reference report database is determined, wherein the target retrieval method includes at least one of checking item matching degree, semantic matching degree, and field completeness; Based on the target retrieval method and at least one of the text fragments in the reference evidence retrieval task, a search is performed in the candidate reference report to obtain a set of target reference evidence that matches the medical report to be tested.

5. The medical report processing method according to claim 3, characterized in that, The target retrieval task further includes a medical knowledge retrieval task; the target reference data further includes a medical knowledge base; the question list further includes a second question list; determining the question list of the medical report to be tested based on the target retrieval task and the target reference data corresponding to the target retrieval task includes: At least one of the text fragments in the medical knowledge retrieval task is matched with the medical knowledge base to determine the medical description information corresponding to each text fragment; Based on the medical description information, a second list of questions is determined from the medical report to be tested. The second list of questions is used to indicate medical terms in the medical knowledge base that match the medical description information. According to the preset merging strategy, the first problem list and the second problem list are deduplicated and merged to determine the problem list of the medical report to be tested.

6. The medical report processing method according to claim 5, characterized in that, After determining the problem list of the medical report to be tested based on the target retrieval task and the target reference data corresponding to the target retrieval task, the method further includes: Based on the problem list, a correctable report is generated for the medical report to be tested. The correctable report is used to indicate the modifiable content in the medical report to be tested and the corresponding modifiable methods.

7. The medical report processing method according to claim 6, characterized in that, After generating the correctable report of the medical report to be tested based on the problem list, the method further includes: The medical report to be tested is corrected based on the correctable report to obtain the target medical report.

8. The medical report processing method according to claim 3, characterized in that, After determining the problem list of the medical report to be tested based on the target retrieval task and the target reference data corresponding to the target retrieval task, the process includes: The medical report to be tested is annotated according to the problem list to obtain an annotated medical report. The annotated medical report is used to highlight the diagnostic description information with problems in the medical report to be tested and the target reference evidence in the target reference evidence set associated with the diagnostic description information.

9. The medical report processing method according to claim 2, characterized in that, The report types include at least one of the following: imaging reports, pathology reports, laboratory test reports, laparoscopic examination reports, and clinical assessment reports.

10. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the medical report processing method as described in any one of claims 1-9.

Images