Medical record rule generation method and device, medical record detection method and device, electronic equipment and medium
Through natural language understanding technology, the generation and detection of medical record rules is solved, and the problem of low efficiency in the update and configuration of medical record rules in the existing technology is achieved, and efficient medical record quality management is achieved.
Patent Information
- Application Number
- CN202310520234.8
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2023-05-09
- Publication Date
- 2024-11-12
AI Technical Summary
The existing medical record rules are implemented by writing code, and the update and configuration are inefficient, making it difficult to adapt to the actual management needs of the hospital.
Provide a method for generating and testing medical record rules, using natural language understanding technology to obtain the target rule template selected by the user, display the corresponding rule configuration page, respond to the user's visual rule configuration operations, generate medical record rules, and perform medical record documents based on medical record rules. Quality inspection.
The configuration process of medical record rules is simplified and efficiency is improved. The paragraphs, medical entities and attributes are identified through natural language understanding technology, and the quality detection of medical record documents is achieved, with a short processing process and high efficiency.
Smart Images

Figure CN118942601A_ABST
Abstract
Description
Technical Field
[0001] The present disclosure relates to the field of artificial intelligence technology, specifically to natural language understanding technology, and more particularly to a method, device, electronic device and medium for generating medical record rules and detecting medical records. Background Art
[0002] Medical records are the carrier of medical behavior, and their quality is particularly important. The standard requirements for medical record quality can be transformed into medical record quality management rules (referred to as medical record rules) and embedded in the hospital's electronic medical record system to help quality management personnel complete the quality management of medical records. At present, medical record rules are implemented by writing codes. Medical record rules need to be constantly updated or adaptively configured in combination with the actual management needs of the hospital. The processing process is long and inefficient by writing codes. Summary of the invention
[0003] Provided are a method, device, electronic device and medium for generating medical record rules and detecting medical records.
[0004] According to a first aspect, a method for generating medical record rules is provided, comprising: obtaining a target rule template selected by a user; displaying a corresponding rule configuration page according to the target rule template; and generating medical record rules in response to a visual rule configuration operation performed by the user on the rule configuration page.
[0005] According to the second aspect, a medical record detection method is provided, comprising: obtaining a medical record document; identifying paragraphs, medical entities and attributes of medical entities from the medical record document based on natural language understanding; using the medical record document, the paragraphs, the medical entities and the attributes of the medical entities as elements to be quality controlled; and performing quality detection on the medical record document based on medical record rules and the elements to be quality controlled, wherein the medical record rules are generated according to the method for generating medical record rules described in the first aspect of the present disclosure.
[0006] According to a third aspect, a device for generating medical record rules is provided, comprising: a first acquisition module for acquiring a target rule template selected by a user; a display module for displaying a corresponding rule configuration page according to the target rule template; and a response module for generating medical record rules in response to a visual rule configuration operation performed by the user on the rule configuration page.
[0007] According to the fourth aspect, a medical record detection device is provided, comprising: a second acquisition module for acquiring medical record documents; an identification module for identifying paragraphs, medical entities and attributes of medical entities from the medical record documents based on natural language understanding; a determination module for determining the medical record documents, the paragraphs, the medical entities and the attributes of the medical entities as elements to be quality controlled; and a detection module for performing quality detection on the medical record documents based on medical record rules and the elements to be quality controlled, wherein the medical record rules are generated by the medical record rule generation device described in the third aspect of the present disclosure.
[0008] According to the fifth aspect, an electronic device is provided, comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the method for generating medical record rules described in the first aspect of the present disclosure, or execute the medical record detection method described in the second aspect of the present disclosure.
[0009] According to the sixth aspect, a non-transitory computer-readable storage medium storing computer instructions is provided, wherein the computer instructions are used to enable the computer to execute the method for generating medical record rules according to the first aspect of the present disclosure, or to execute the medical record detection method according to the second aspect of the present disclosure.
[0010] According to the seventh aspect, a computer program product is provided, comprising a computer program, which, when executed by a processor, implements the steps of the method for generating medical record rules according to the first aspect of the present disclosure, or implements the steps of the method for detecting medical records according to the second aspect of the present disclosure.
[0011] It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present disclosure, nor is it intended to limit the scope of the present disclosure. Other features of the present disclosure will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS
[0012] The accompanying drawings are used to better understand the present solution and do not constitute a limitation of the present disclosure.
[0013] Figure 1 is a flowchart of a method for generating medical record rules according to the first embodiment of the present disclosure;
[0014] Figure 2 This is a schematic diagram of the new rule page;
[0015] Figure 3 This is a schematic diagram of rule configuration page 1;
[0016] Figure 4This is a schematic diagram of the rule configuration page 2;
[0017] Figure 5 This is a schematic diagram of the rule publishing page;
[0018] Figure 6 is a flowchart of a method for generating medical record rules according to a second embodiment of the present disclosure;
[0019] Figure 7 is a flowchart of a method for generating medical record rules according to a third embodiment of the present disclosure;
[0020] Figure 8 It is a four-level display diagram of medical record documents;
[0021] Fig. 9 It is a schematic diagram of the construction process of consistency rules;
[0022] Fig.10 It is a schematic diagram of the construction process of integrity rules;
[0023] Fig.11 It is a schematic diagram of the construction process of timeliness rules;
[0024] Fig.12 It is a schematic diagram of the construction process of rationality rules;
[0025] Fig.13 It is a schematic diagram of the construction process of normative rules;
[0026] Fig.14 is a flowchart of a medical record detection method according to the first embodiment of the present disclosure;
[0027] Fig.15 is a block diagram of a device for generating medical record rules according to a first embodiment of the present disclosure;
[0028] Fig.16 is a block diagram of a device for generating medical record rules according to a second embodiment of the present disclosure;
[0029] Fig.17 is a block diagram of a medical record detection device according to a first embodiment of the present disclosure;
[0030] Fig.18 The block diagram is a block diagram of an electronic device for implementing the method of the embodiment of the present disclosure. DETAILED DESCRIPTION
[0031] The following is a description of exemplary embodiments of the present disclosure in conjunction with the accompanying drawings, including various details of the embodiments of the present disclosure to facilitate understanding, which should be considered as merely exemplary. Therefore, it should be recognized by those of ordinary skill in the art that various changes and modifications may be made to the embodiments described herein without departing from the scope and spirit of the present disclosure. Similarly, for the sake of clarity and conciseness, descriptions of well-known functions and structures are omitted in the following description.
[0032] Artificial Intelligence (AI) is a technical science that studies and develops theories, methods, technologies and application systems for simulating, extending and expanding human intelligence. At present, AI technology has the advantages of high automation, high precision and low cost, and has been widely used.
[0033] Natural Language Understanding (NLU) is a general term for all methods, models or tasks that support machines to understand text content. NLU plays a very important role in text information processing systems and is an essential module for recommendation, question-answering, search and other systems.
[0034] The following describes the generation of medical record rules and the medical record detection method, device, electronic device and storage medium of the embodiments of the present disclosure in conjunction with the accompanying drawings.
[0035] Figure 1 It is a flowchart of a method for generating medical record rules according to the first embodiment of the present disclosure.
[0036] like Figure 1 As shown, the method for generating medical record rules in the embodiment of the present disclosure may specifically include the following steps:
[0037] S101, obtaining a target rule template selected by a user.
[0038] Specifically, the execution subject of the method for generating medical record rules of the embodiment of the present disclosure may be the device for generating medical record rules provided by the embodiment of the present disclosure, and the device for generating medical record rules may be a hardware device with data information processing capabilities and / or the necessary software required to drive the hardware device to work. Optionally, the execution subject may include a workstation, a server, a computer, a user terminal and other devices. Among them, the user terminal includes but is not limited to a mobile phone, a computer, an intelligent voice interaction device, a smart home appliance, a car terminal, etc. The method for generating medical record rules of the embodiment of the present disclosure can be specifically applied to the medical record rule editing platform. The medical record rule editing platform can be input to the medical record quality control system, and embedded in the hospital medical record system by means of a software development kit (SDK) or an application programming interface (API), so as to improve the quality of medical record writing, meet the hospital's needs in operation management, performance evaluation, medical quality control, medical insurance payment, etc., and help public hospitals develop high-quality development.
[0039] In the disclosed embodiment, multiple rule templates can be pre-built in the medical record rule editing platform according to the specification and the knowledge of medical record documents, and displayed to the user for selection when the user needs to generate medical record rules. The user selects the required template from the multiple rule templates as the target rule template, for example Figure 2 As shown, in the new rule page, the user can select the required target rule template "Two Elements Inconsistent" from multiple rule templates by means of a drop-down selection, and the medical record rule editing platform obtains the target rule template "Two Elements Inconsistent" selected by the user.
[0040] S102: Display a corresponding rule configuration page according to the target rule template.
[0041] In the disclosed embodiment, the medical record rule editing platform displays the rule configuration page corresponding to the target rule template selected by the user in step S101 to the user. Figure 3 The rule configuration page corresponding to the target rule template "Two elements are inconsistent" is shown.
[0042] S103, generating medical record rules in response to the visual rule configuration operation performed by the user on the rule configuration page.
[0043] In the disclosed embodiment, the user can perform simple visual rule configuration operations on the rule configuration page displayed in step S102, such as dragging, drop-down selection, etc. The medical record rule editing platform responds to the user's operation to generate medical record rules. Figure 3 In the example, users can drag the target element to the target position (corresponding to Figure 3In the box that says "Please drag elements", select "Equal" from the drop-down list among multiple relationships between elements, such as <, ≤, ≥, >, Equal, Contains, Does not contain, etc.
[0044] It should be noted here that if Figure 2 As shown, when the user selects a target rule template, the user can also customize the rule template. The initial canvas in the corresponding rule configuration page is blank, as shown in Figure 4 As shown, the user performs visual rule configuration operations as needed, such as dragging target elements, dragging element relationships, dragging element group relationships, drop-down selection, etc.
[0045] After the medical record rule is constructed, it can be tested. If the test passes, the medical record rule can be published. Figure 5 As shown, the user clicks the "Publish" button corresponding to the rule to display the rule publishing page. On the rule publishing page, the user can select the medical record document to which the medical record rule belongs, for example Figure 5 The medical record documents include but are not limited to daily medical records, admission records, discharge records, etc. The user clicks the "OK" button to generate a rule release instruction, which includes the medical record documents to which the medical record rule belongs. The medical record rule editing platform obtains the rule release instruction and releases the medical record rule according to the rule release instruction.
[0046] In addition, after the medical record rule is constructed, it can also be deleted. Figure 5 As shown, the user clicks the "Delete" button corresponding to the rule to generate a rule deletion instruction. The medical record rule editing platform obtains the rule deletion instruction and deletes the corresponding medical record rule according to the rule deletion instruction.
[0047] In summary, the method for generating medical record rules in the disclosed embodiment displays the corresponding rule configuration page according to the target rule template selected by the user, and generates medical record rules in response to the visual rule configuration operation performed by the user on the rule configuration page. The disclosed embodiment can realize the configuration of rules through simple visual operations, with a short processing flow and high efficiency.
[0048] Figure 6 It is a flowchart of a method for generating medical record rules according to the second embodiment of the present disclosure.
[0049] like Figure 6 As shown, in Figure 1 Based on the illustrated embodiment, the method for generating medical record rules in the embodiment of the present disclosure may specifically include the following steps:
[0050] In the above embodiment, step S101 “obtaining a target rule template selected by a user” may specifically include the following steps S601 - S603 .
[0051] S601, obtaining the target rule type selected by the user.
[0052] In the disclosed embodiment, multiple rule types can be pre-set in the medical record rule editing platform, and displayed to the user for selection when the user needs to generate medical record rules. The user selects the required type from multiple rule types as the target rule type, for example Figure 2 As shown, users can select from multiple rule types (corresponding to Figure 2 In the quality control type in the , select the required target rule type "consistency", and the medical record rule editing platform obtains the target rule type "consistency" selected by the user. The target rule type may include but is not limited to any of the following types: consistency rule, integrity rule, timeliness rule, rationality rule and normative rule, etc.
[0053] Among them, the consistency rule refers to whether there are elements with the same name but inconsistent values. The integrity rule refers to whether there is a situation where the medical information required by the specification is not filled in. The timeliness rule refers to whether the medical information is not filled in within the time limit required by the specification. The rationality rule refers to whether there is a situation where the filled content is unreasonable. The standardization rule refers to whether the filled content does not comply with industry specifications.
[0054] S602: Acquire multiple rule templates corresponding to the target rule type.
[0055] In the embodiment of the present disclosure, according to the target rule type selected by the user in step S601, multiple rule templates corresponding to the target rule type are obtained and displayed to the user.
[0056] S603: Obtain a target rule template selected by the user from multiple rule templates.
[0057] In the embodiment of the present disclosure, the user selects a template from multiple rule templates as a target rule template.
[0058] S604: Display a corresponding rule configuration page according to the target rule template.
[0059] S606 , generating medical record rules in response to the visual rule configuration operation performed by the user on the rule configuration page.
[0060] In the embodiment of the present disclosure, steps S604-S606 are the same as steps S102-S103 in the above embodiment and are not described again here.
[0061] Further, such as Figure 7 As shown, step S601 in the above embodiment, “obtaining the target rule type selected by the user”, may specifically include the following steps S701-S703.
[0062] S701, obtaining a new rule creation instruction from a user.
[0063] In the disclosed embodiment, when a user wants to construct a new rule, he or she can click the "New Rule" button in the medical record rule editing platform to generate a new rule instruction, and the medical record rule editing platform obtains the new rule instruction.
[0064] S702, displaying a new rule page according to the new rule instruction.
[0065] In the disclosed embodiment, the medical record rule editing platform displays a new rule page to the user according to the new rule instruction, such as Figure 2 shown.
[0066] S703, obtaining the target rule type selected by the user on the new rule page.
[0067] In the embodiment of the present disclosure, the user can select a desired target rule type from multiple rule types on a new rule page.
[0068] Furthermore, the "visual rule configuration operation performed by the user on the rule configuration page" in the above step S605 may specifically include the following operations: an operation of dragging a target element from a medical record element library to a target position, where the medical record element library includes multiple elements.
[0069] Among them, multiple elements in the medical record element library are arranged in multiple levels.
[0070] It should be noted here that the medical record element library can be constructed in the following way: based on the paragraphs, medical entities and attributes of medical entities manually identified from the medical record documents, a medical record element library is constructed, and the medical record documents, paragraphs, medical entities and attributes of medical entities are used as elements in the medical record element library.
[0071] In the disclosed embodiment, according to the user's cognition of the medical record document, paragraphs, medical entities and attributes of medical entities are identified from the medical record document, so that the medical record document is disassembled into the granularity of medical record document-paragraph-element (medical entity)-attribute (attribute of medical entity), such as admission record-chief complaint-disease-onset time, and the medical record document, paragraph, medical entity and attribute of medical entity are used as elements in the medical record element library to complete the construction of the medical record element library. The four-level display of medical record documents: medical record document-paragraph-element-attribute, such as Figure 8As shown, the medical record level includes elements such as patient information, outpatient records, and admission records; the paragraph level includes elements such as department, ward, and record content; the element level includes elements such as disease, symptoms, and signs; and the attribute level includes elements such as hypernyms, yin and yang, and whether it is accompanied.
[0072] Furthermore, the "visual rule configuration operation performed by the user on the rule configuration page" in the above step S605 may also specifically include at least one of the following operations: visually configuring the relationship between target elements to generate an element group; visually configuring the constraints of the target elements to generate an element group; visually configuring the relationship between element groups to generate a condition group; visually configuring the relationship between condition groups and element groups to generate a condition group; visually configuring the relationship between condition groups and condition groups to generate a condition group; and visually configuring parameters in the constraints.
[0073] Combine the following Figure 9-13 The process of visual rule configuration for five types of medical record rules (consistency rule, completeness rule, timeliness rule, rationality rule and standardization rule) is described exemplarily.
[0074] Fig. 9 This is a schematic diagram of the construction process of consistency rules. Fig. 9 As shown in the figure, the rule to be constructed is the consistency rule - admission record - the description of the onset time of the disease in the chief complaint and the history of the present illness is inconsistent. The relationship between the onset time, relief time, aggravation time, and duration of the disease in the chief complaint and the history of the present illness can be configured by dragging and dropping. As shown in the name of the quality control point, to configure this rule, it is necessary to determine whether the onset time of the disease in the chief complaint and the history of the present illness is inconsistent, and it is also necessary to determine whether the relief time, aggravation time, and duration of the disease in the chief complaint and the history of the present illness are equal. Specifically, the following configuration can be performed: Step 1) Drag the target elements "chief complaint, occurrence time in current medical history, relief time, aggravation time, duration" to the target position, Step 2) Configure "occurrence time in chief complaint" ≠ "occurrence time in current medical history" to establish element group 1; Step 3) Configure "relief time in chief complaint" = "relief time in current medical history" to establish element group 2; Step 4) Configure "aggravation time in chief complaint" = "aggravation time in current medical history" to establish element group 3; Step 5) Configure "duration time in chief complaint" = "duration time in current medical history" to establish element group 4; Step 6) Combine element group 2, element group 3 and element group 4 through the element group relationship "or" to establish condition group 1; Step 7) Combine element group 1 and condition group 1 through the element group relationship "and".
[0075] Fig.10 This is a schematic diagram of the construction process of integrity rules. Fig.10As shown, the rule to be constructed is the completeness rule - hospital admission record - marriage and childbearing history - missing marital status. As the name of the quality control point indicates, to configure this rule, it is necessary to determine whether the marriage and childbearing history is non-empty. If the marriage and childbearing history is not empty and the marital status is empty, the quality control point is triggered. The specific configuration can be as follows: Step 1) Drag the target element "marriage and childbearing history, marital status" to the target position; Step 2) Configure the constraint condition of "marriage and childbearing history" to "non-empty" to generate element group 1; Step 3) Configure the constraint condition of "marital status" to "empty" to generate element group 2; Step 4) Combine element group 1 and element group 2 through the element group relationship "and".
[0076] Fig.11 This is a schematic diagram of the construction process of timeliness rules. Fig.11 As shown, the rule to be constructed is the timeliness rule - medical record - failure to fill in the medical record for 3 consecutive days after surgery. As shown in the name of the quality control point, to configure this rule, it is necessary to determine whether there is a medical record on the 1st, 2nd, and 3rd day after the surgery record time. If any of them is missing, the quality control point will be triggered. The specific configuration can be as follows: Step 1) Drag the target element "Surgery Record-Record Time" to the element position before time; Step 2) Drag the target element "Postoperative Medical Record-Record Time" to the element position after time; Step 3) Configure the time relationship between the two elements as "single interval time is 24h (hours), time frequency is 3 times".
[0077] Fig.12 This is a schematic diagram of the construction process of rationality rules. Fig.12 As shown, the rule to be constructed is the rationality rule - hospital admission record - menstrual history - inconsistency between menstrual cycle and age group. As shown in the name of the quality control point, to configure this rule, you need to first determine whether the menstrual cycle is "non-empty", then determine whether the gender is "female", and finally determine whether the age group is "<10 years old". If so, trigger this quality control point. The specific configuration can be as follows: Step 1) Drag the target element "menstrual cycle, gender, age" to the target position; Step 2) Configure the constraint condition of "menstrual cycle" to "non-empty" to generate element group 1; Step 3) Configure the constraint condition of "gender" to "female" to generate element group 2; Step 4) Configure the constraint condition of "age" to "<10 years old" to generate tuple element 3; Step 5) Combine element group 1, element group 2 and element group 3 through the element group relationship "and".
[0078] Fig.13 This is a schematic diagram of the construction process of normative rules. Fig.13As shown, the rule to be constructed is a normative rule - medical record homepage - anesthesia method code is not within the value range. As shown in the name of the quality control point, to configure this rule, it is necessary to determine whether the value of the anesthesia method is within the value range. If not, the quality control point is triggered. The specific configuration can be as follows: Step 1) Drag the target element "anesthesia method" to the target position; Step 2) Configure the constraint condition of "anesthesia method" to "not within the value range"; Step 3) Configure the parameter "value range" in the constraint condition.
[0079] In summary, the method for generating medical record rules in the disclosed embodiment displays the corresponding rule configuration page according to the target rule template selected by the user in the target rule type, and responds to the visual rule configuration operation performed by the user on the rule configuration page, such as dragging the target element from the medical record element library to the target position, visually configuring the relationship between the target elements, the constraints of the target elements, the relationship between the element groups, the relationship between the condition groups and the element groups, the relationship between the condition groups and the condition groups, and the parameters in the constraints, to generate medical record rules. The disclosed embodiment can realize the configuration of rules through simple visual operations, with a short processing flow and high efficiency.
[0080] Fig.14 It is a flowchart of the medical record detection method according to the first embodiment of the present disclosure.
[0081] like Fig.14 As shown, the medical record detection method of the embodiment of the present disclosure may specifically include the following steps:
[0082] S1401, obtain medical record documents.
[0083] In this embodiment, a medical record document to be quality inspected is obtained.
[0084] S1402, identifying paragraphs, medical entities, and attributes of medical entities from medical records based on natural language understanding.
[0085] In this embodiment, based on natural language understanding technology and a medical record element library, information is extracted from the medical record document to extract paragraphs, medical entities, and attributes of the medical entities in the medical record document.
[0086] S1403, taking medical record documents, paragraphs, medical entities and attributes of medical entities as elements to be quality controlled.
[0087] In this embodiment, the medical record document and the paragraphs, medical entities and attributes of the medical entities identified in step S1402 are taken as elements to be quality inspected, that is, elements to be quality controlled.
[0088] S1404, performing quality inspection on the medical record document based on the medical record rules and the elements to be quality controlled, where the medical record rules are generated according to the method for generating medical record rules in any of the above embodiments.
[0089] In this embodiment, quality inspection is performed on medical record documents based on the medical record rules generated by the method for generating medical record rules in any of the above embodiments and the elements to be quality controlled involved in the rules.
[0090] In summary, the medical record detection method of the embodiment of the present disclosure identifies the elements to be controlled from the medical record documents based on natural language understanding, and performs quality detection on the medical record documents based on the medical record rules constructed by visualization. The medical record rules can be implemented through simple visualization operations, with a short processing flow and high efficiency.
[0091] Fig.15 It is a block diagram of a device for generating medical record rules according to the first embodiment of the present disclosure.
[0092] like Fig.15 As shown, the medical record rule generation device 1500 of the embodiment of the present disclosure includes: a first acquisition module 1501, a display module 1502 and a response module 1503.
[0093] The first acquisition module 1501 is used to acquire a target rule template selected by a user.
[0094] The display module 1502 is used to display the corresponding rule configuration page according to the target rule template.
[0095] The response module 1503 is used to generate medical record rules in response to the visual rule configuration operation performed by the user on the rule configuration page.
[0096] It should be noted that the above explanation of the embodiment of the method for generating medical record rules is also applicable to the device for generating medical record rules in the embodiment of the present disclosure, and the specific process will not be repeated here.
[0097] In summary, the medical record rule generation device of the disclosed embodiment displays the corresponding rule configuration page according to the target rule template selected by the user, and generates the medical record rule in response to the visual rule configuration operation performed by the user on the rule configuration page. The disclosed embodiment can realize the configuration of the rule through simple visual operation, with short processing flow and high efficiency.
[0098] Fig.16 It is a block diagram of a device for generating medical record rules according to a second embodiment of the present disclosure.
[0099] like Fig.16 As shown, the medical record rule generation device 1600 of the embodiment of the present disclosure includes: a first acquisition module 1601, a display module 1602 and a response module 1603.
[0100] The first acquisition module 1601 has the same structure and function as the first acquisition module 1401 in the previous embodiment, the display module 1602 has the same structure and function as the display module 1402 in the previous embodiment, and the response module 1603 has the same structure and function as the response module 1403 in the previous embodiment.
[0101] Furthermore, the first acquisition module 1601 is further used to: acquire a target rule type selected by a user; acquire multiple rule templates corresponding to the target rule type; and acquire a target rule template selected by the user from the multiple rule templates.
[0102] Furthermore, the target rule type includes any one of the following types: consistency rule, integrity rule, timeliness rule, rationality rule and normative rule.
[0103] Furthermore, the first acquisition module 1601 is further used to: acquire a new rule instruction from the user; display a new rule page according to the new rule instruction; and acquire a target rule type selected by the user on the new rule page.
[0104] Furthermore, the visualization rule configuration operation includes: dragging a target element from a medical record element library to a target position, and the medical record element library includes multiple elements.
[0105] Furthermore, the visualization rule configuration operation also includes at least one of the following operations: visualization of the relationship between target elements to generate an element group; visualization of the constraint conditions of the target elements to generate an element group; visualization of the relationship between element groups to generate a condition group; visualization of the relationship between a condition group and an element group to generate a condition group; visualization of the relationship between a condition group and a condition group to generate a condition group; and visualization of the parameters in the constraint conditions.
[0106] Furthermore, multiple elements are arranged in multiple levels.
[0107] Furthermore, the medical record rule generation device 1600 of the embodiment of the present disclosure also includes: a construction module 1604, which is used to construct a medical record element library based on paragraphs, medical entities and attributes of medical entities manually identified from medical record documents, and the medical record documents, paragraphs, medical entities and attributes of medical entities serve as elements in the medical record element library.
[0108] It should be noted that the above explanation of the embodiment of the method for generating medical record rules is also applicable to the device for generating medical record rules in the embodiment of the present disclosure, and the specific process will not be repeated here.
[0109] In summary, the device for generating medical record rules of the disclosed embodiment displays the corresponding rule configuration page according to the target rule template selected by the user in the target rule type, and responds to the visual rule configuration operation performed by the user on the rule configuration page, such as dragging the target element from the medical record element library to the target position, visually configuring the relationship between the target elements, the constraint conditions of the target elements, the relationship between the element groups, the relationship between the condition groups and the element groups, the relationship between the condition groups and the condition groups, and the parameters in the constraint conditions, to generate medical record rules. The disclosed embodiment can realize the configuration of rules through simple visual operations, with a short processing flow and high efficiency.
[0110] Fig.17 is a block diagram of a medical record detection device according to a first embodiment of the present disclosure.
[0111] like Fig.17 As shown, the medical record detection device 1700 of the embodiment of the present disclosure includes: a second acquisition module 1701, an identification module 1702, a determination module 1703 and a detection module 1704.
[0112] The second acquisition module 1701 is used to acquire medical record documents.
[0113] The recognition module 1702 is used to recognize paragraphs, medical entities and attributes of medical entities from medical records based on natural language understanding.
[0114] The determination module 1703 is used to determine the medical record documents, paragraphs, medical entities and attributes of medical entities as elements to be quality controlled.
[0115] The detection module 1704 is used to perform quality detection on the medical record document based on the medical record rules and the elements to be quality controlled. The medical record rules are generated by the medical record rule generation device of any of the above embodiments.
[0116] It should be noted that the above explanation of the medical record detection method embodiment is also applicable to the medical record detection device of the embodiment of the present disclosure, and the specific process will not be repeated here.
[0117] In summary, the medical record detection device of the embodiment of the present disclosure identifies the elements to be controlled from the medical record documents based on natural language understanding, and performs quality detection on the medical record documents based on the medical record rules constructed by visualization. The medical record rules can be implemented through simple visualization operations, with a short processing flow and high efficiency.
[0118] In the technical solution of the present disclosure, the collection, storage, use, processing, transmission, provision and disclosure of user personal information involved are in compliance with the provisions of relevant laws and regulations and do not violate public order and good morals.
[0119] According to an embodiment of the present disclosure, the present disclosure also provides an electronic device, a readable storage medium and a computer program product.
[0120] Fig.18 A schematic block diagram of an example electronic device 1800 that can be used to implement an embodiment of the present disclosure 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 processing, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present disclosure described and / or required herein.
[0121] like Fig.18 As shown, the electronic device 1800 includes a computing unit 1801, which can perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) 1802 or a computer program loaded from a storage unit 1808 into a random access memory (RAM) 1803. In the RAM 1803, various programs and data required for the operation of the electronic device 1800 can also be stored. The computing unit 1801, the ROM 1802, and the RAM 1803 are connected to each other via a bus 1804. An input / output (I / O) interface 1805 is also connected to the bus 1804.
[0122] Multiple components in the electronic device 1800 are connected to the I / O interface 1805, including: an input unit 1806, such as a keyboard, a mouse, etc.; an output unit 1807, such as various types of displays, speakers, etc.; a storage unit 1808, such as a disk, an optical disk, etc.; and a communication unit 1809, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 1809 allows the electronic device 1800 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.
[0123] The computing unit 1801 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the computing unit 1801 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The computing unit 1801 performs the various methods and processes described above, such as Figures 1 to 13 The method for generating medical record rules shown in Fig.14The medical record detection method shown. For example, in some embodiments, the method for generating medical record rules and the medical record detection method may be implemented as a computer software program, which is tangibly contained in a machine-readable medium, such as a storage unit 1808. In some embodiments, part or all of the computer program may be loaded and / or installed on the electronic device 1800 via ROM1802 and / or the communication unit 1809. When the computer program is loaded into RAM1803 and executed by the computing unit 1801, one or more steps of the semantic parsing method described above may be performed. Alternatively, in other embodiments, the computing unit 1801 may be configured to execute the method for generating medical record rules and the medical record detection method in any other appropriate manner (e.g., by means of firmware).
[0124] Various implementations 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 chips (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.
[0125] The program code for implementing the method of the present disclosure may be written in any combination of one or more programming languages. These program codes may be provided to a processor or controller of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that the program code, when executed by the processor or controller, enables the functions / operations specified in the flow chart and / or block diagram to be implemented. The program code may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.
[0126] In the context of the present disclosure, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, device, or equipment. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or equipment, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.
[0127] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer 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 can provide input to the computer. Other types of devices can also be used to provide interaction with the user; for example, the 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 acoustic input, voice input, or tactile input).
[0128] The systems and techniques described herein may be implemented in a computing system that includes backend components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes frontend components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such backend components, middleware components, or frontend components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), the Internet, and a blockchain network.
[0129] A computer system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The relationship between the client and the server is generated by computer programs running on the corresponding computers and having a client-server relationship with each other. The server may be a cloud server, also known as a cloud computing server or a cloud host, which is a host product in the cloud computing service system to solve the defects of difficult management and weak business scalability in traditional physical hosts and VPS services ("Virtual Private Server", or "VPS" for short). The server may also be a server for a distributed system, or a server combined with a blockchain.
[0130] According to an embodiment of the present disclosure, the present disclosure also provides a computer program product, including a computer program, wherein when the computer program is executed by a processor, the computer program implements the steps of the medical record rule generation method and the medical record detection method shown in the above embodiment of the present disclosure.
[0131] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps recorded in this disclosure can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solutions disclosed in this disclosure can be achieved, and this document does not limit this.
[0132] The above specific implementations do not constitute a limitation on the protection scope of the present disclosure. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present disclosure shall be included in the protection scope of the present disclosure.
Claims
1. A method for generating medical record rules, comprising: Get the target rule template selected by the user; Displaying a corresponding rule configuration page according to the target rule template; as well as In response to the visual rule configuration operation performed by the user on the rule configuration page, a medical record rule is generated.
2. The generation method according to claim 1, wherein: The step of obtaining the target rule template selected by the user includes: Obtaining the target rule type selected by the user; Acquire multiple rule templates corresponding to the target rule type; and The target rule template selected by the user from among the multiple rule templates is obtained.
3. The generation method according to claim 2, wherein: The target rule type includes any one of the following types: Consistency rules, integrity rules, timeliness rules, rationality rules and standardization rules.
4. The generation method according to claim 2, wherein: The obtaining of the target rule type selected by the user includes: Obtaining a new rule instruction of the user; Displaying a new rule page according to the new rule instruction; and The target rule type selected by the user on the new rule page is obtained.
5. The generation method according to claim 1, wherein: The visualization rule configuration operation includes: An operation of dragging a target element from a medical record element library to a target position, wherein the medical record element library includes multiple elements.
6. The generation method according to claim 5, wherein: The visualization rule configuration operation further includes at least one of the following operations: visually configuring the relationship between the target elements to generate an element group; visually configuring the constraint conditions of the target element to generate the element group; visually configuring the relationship between the element groups to generate condition groups; visually configuring the relationship between the condition group and the element group to generate the condition group; visually configuring the condition groups and the relationships between the condition groups to generate the condition groups; as well as, Visually configure the parameters in the constraints.
7. The generation method according to claim 5, wherein: The plurality of elements are arranged in a plurality of levels.
8. The generating method according to claim 5, further comprising: The medical record element library is constructed based on the paragraphs, medical entities and attributes of the medical entities manually identified from the medical record documents, and the medical record documents, the paragraphs, the medical entities and the attributes of the medical entities serve as the elements in the medical record element library.
9. The generating method according to claim 1, further comprising: The medical record rules are tested.
10. The generating method according to claim 9, further comprising: If the test of the medical record rule passes, the medical record rule will be published.
11. The generation method according to claim 10, wherein: The releasing of the medical record rules includes: Obtaining a rule publishing instruction of the user; The medical record rule is published according to the rule publishing instruction.
12. The generation method according to claim 11, wherein: The rule issuing instruction includes the medical record document to which the medical record rule belongs.
13. The generating method according to claim 1, further comprising: Obtaining a rule deletion instruction of the user; Delete the corresponding medical record rule according to the rule deletion instruction.
14. A medical record detection method, comprising: Obtain medical records; Identifying paragraphs, medical entities, and attributes of medical entities from the medical record document based on natural language understanding; The medical record document, the paragraph, the medical entity and the attribute of the medical entity are taken as elements to be controlled; as well as The medical record document is quality checked based on the medical record rules and the elements to be quality controlled, wherein the medical record rules are generated according to the method for generating medical record rules according to any one of claims 1 to 13.
15. A device for generating medical record rules, comprising: A first acquisition module is used to acquire a target rule template selected by a user; A display module, used to display a corresponding rule configuration page according to the target rule template; as well as The response module is used to generate medical record rules in response to the visual rule configuration operation performed by the user on the rule configuration page.
16. The generating device according to claim 15, wherein: The first acquisition module is further used for: Obtaining the target rule type selected by the user; Acquire multiple rule templates corresponding to the target rule type; and The target rule template selected by the user from among the multiple rule templates is obtained.
17. The generating device according to claim 16, wherein: The target rule type includes any one of the following types: Consistency rules, integrity rules, timeliness rules, rationality rules and standardization rules.
18. The generating device according to claim 16, wherein: The first acquisition module is further used for: Obtaining a new rule instruction of the user; Displaying a new rule page according to the new rule instruction; and The target rule type selected by the user on the new rule page is obtained.
19. The generating device according to claim 15, wherein: The visualization rule configuration operation includes: An operation of dragging a target element from a medical record element library to a target position, wherein the medical record element library includes multiple elements.
20. The generating device according to claim 19, wherein: The visualization rule configuration operation further includes at least one of the following operations: visually configuring the relationship between the target elements to generate an element group; visually configuring the constraint conditions of the target element to generate the element group; visually configuring the relationship between the element groups to generate condition groups; visually configuring the relationship between the condition group and the element group to generate the condition group; visually configuring the condition groups and the relationships between the condition groups to generate the condition groups; as well as, Visually configure the parameters in the constraints.
21. The generating device according to claim 19, wherein: The plurality of elements are arranged in a plurality of levels.
22. The generating device according to claim 19, further comprising: A construction module is used to construct the medical record element library based on paragraphs, medical entities and attributes of medical entities manually identified from medical record documents, and the medical record documents, the paragraphs, the medical entities and the attributes of the medical entities serve as the elements in the medical record element library.
23. The generating device according to claim 15, further comprising: A testing module is used to test the medical record rules.
24. The generating device according to claim 23, further comprising: The publishing module is used to publish the medical record rules if the test of the medical record rules passes.
25. The generating device according to claim 24, wherein: The publishing module is further used for: Obtaining a rule publishing instruction of the user; The medical record rule is published according to the rule publishing instruction.
26. The generating device according to claim 25, wherein: The rule issuing instruction includes the medical record document to which the medical record rule belongs.
27. The generating device according to claim 15, further comprising: The deletion module is used to obtain the rule deletion instruction of the user and delete the corresponding medical record rule according to the rule deletion instruction.
28. A medical record detection device, comprising: The second acquisition module is used to obtain medical records; A recognition module, for recognizing paragraphs, medical entities and attributes of medical entities from the medical record document based on natural language understanding; A determination module, used for determining the medical record document, the paragraph, the medical entity and the attribute of the medical entity as elements to be quality controlled; as well as A detection module is used to perform quality detection on the medical record document based on the medical record rules and the elements to be quality controlled, wherein the medical record rules are generated by the medical record rule generation device described in any one of claims 15-27.
29. An electronic device comprising: at least one processor; as well as a memory communicatively connected to the at least one processor; wherein, The memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to execute the method of any one of claims 1 to 13, or the method of claim 14.
30. A non-transitory computer-readable storage medium storing computer instructions, wherein: The computer instructions are used to cause the computer to execute the method according to any one of claims 1 to 13, or to execute the method according to claim 14.
31. A computer program product, comprising a computer program, wherein when the computer program is executed by a processor, the computer program implements the steps of the method according to any one of claims 1 to 13, or implements the steps of the method according to claim 14.
Citation Information
Cited By
Data quality inspection method based on dynamic parameter transmission and related equipment
CN121959171A
