CN113297853A - Quality control method and device for electronic medical record, electronic equipment and storage medium - Google Patents

Quality control method and device for electronic medical record, electronic equipment and storage medium Download PDF

Info

Publication number
CN113297853A
CN113297853A CN202110847667.5A CN202110847667A CN113297853A CN 113297853 A CN113297853 A CN 113297853A CN 202110847667 A CN202110847667 A CN 202110847667A CN 113297853 A CN113297853 A CN 113297853A
Authority
CN
China
Prior art keywords
target
quality control
module
identifier
rule
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Granted
Application number
CN202110847667.5A
Other languages
Chinese (zh)
Other versions
CN113297853B (en
Inventor
吴哲夫
王实
张奇
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Beijing Huimeiyun Technology Co ltd
Original Assignee
Beijing Huimeiyun Technology Co ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Beijing Huimeiyun Technology Co ltd filed Critical Beijing Huimeiyun Technology Co ltd
Priority to CN202110847667.5A priority Critical patent/CN113297853B/en
Publication of CN113297853A publication Critical patent/CN113297853A/en
Application granted granted Critical
Publication of CN113297853B publication Critical patent/CN113297853B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F40/00—Handling natural language data
    • G06F40/20—Natural language analysis
    • G06F40/279—Recognition of textual entities
    • G06F40/289—Phrasal analysis, e.g. finite state techniques or chunking
    • G06F40/295—Named entity recognition
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
    • G06F16/33—Querying
    • G06F16/3331—Query processing
    • G06F16/334—Query execution
    • G06F16/3344—Query execution using natural language analysis
    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
    • G16H10/00—ICT specially adapted for the handling or processing of patient-related medical or healthcare data
    • G16H10/60—ICT specially adapted for the handling or processing of patient-related medical or healthcare data for patient-specific data, e.g. for electronic patient records

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Artificial Intelligence (AREA)
  • Computational Linguistics (AREA)
  • General Health & Medical Sciences (AREA)
  • Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • Health & Medical Sciences (AREA)
  • Audiology, Speech & Language Pathology (AREA)
  • Data Mining & Analysis (AREA)
  • Databases & Information Systems (AREA)
  • Epidemiology (AREA)
  • Medical Informatics (AREA)
  • Primary Health Care (AREA)
  • Public Health (AREA)
  • Medical Treatment And Welfare Office Work (AREA)

Abstract

The application provides a quality control method and device of an electronic medical record, electronic equipment and a storage medium, wherein the quality control method comprises the following steps: extracting a target medical entity corresponding to the medical entity identification according to the medical entity identification carried in the quality control request, selecting a plurality of target rule modules according to the module selection identification carried in the quality control request, and responding to the creation operation aiming at the rule engine to obtain the target rule engine aiming at the electronic medical record to be quality controlled; the target rule engine comprises a plurality of target rule modules which are sequentially connected according to a target logic sequence, the target logic sequence is determined according to a connection sequence identifier carried in the quality control request, and the target rule engine is adopted to perform quality control processing on the target medical entity to obtain a quality control result of the electronic medical record to be quality controlled. Furthermore, the rule engine for quality control of the electronic medical record is created in a user-defined mode according to the quality control request of the target user for the electronic medical record, and the quality control reliability and the quality control efficiency of the electronic medical record can be improved.

Description

Quality control method and device for electronic medical record, electronic equipment and storage medium
Technical Field
The application relates to the technical field of medical quality control, in particular to a quality control method and device of an electronic medical record, electronic equipment and a storage medium.
Background
Electronic medical records in the medical field are important criteria for evaluating medical quality. In actual medical work, the adverse phenomena of incorrect content description, partial content loss, mass copying and pasting of the content and the like of the electronic medical record exist, and certain influence is caused on subsequent medical diagnosis work.
At present, in the existing quality control system of the electronic medical record, a plurality of logic rules are generally set, and the logic rules are operated, so that the quality control result of the electronic medical record can be output. However, in practical situations, writing formats of electronic medical records are not uniform among different doctors in different hospitals, and quality control requirements for each electronic medical record may also be different, and even new quality control requirements need to be added again. At this time, the underlying program of the quality control system needs to be modified again for each electronic medical record, but because the number of the electronic medical records is large, the writing formats of each hospital are not uniform, the requirements for the quality control of the electronic medical records are different, and a large amount of time and energy are needed to modify the underlying program corresponding to the logic rules of the electronic medical records.
Disclosure of Invention
In view of this, an object of the present application is to provide a method, an apparatus, an electronic device, and a storage medium for quality control of an electronic medical record, which can create a rule engine for quality control of the electronic medical record in a customized manner according to a quality control request of a target user for the electronic medical record, so as to improve the reliability and efficiency of quality control of the electronic medical record.
In a first aspect, an embodiment of the present application provides a quality control method for an electronic medical record, where the quality control method includes:
acquiring a quality control request of a target user for a to-be-quality-controlled electronic medical record; the quality control request carries a medical entity identifier, a module selection identifier and a connection sequence identifier;
extracting a target medical entity corresponding to the medical entity identifier from the electronic medical record to be quality-controlled according to the medical entity identifier carried in the quality control request;
selecting a plurality of target rule modules from a preset rule module library according to a module selection identifier carried in the quality control request;
responding to the creation operation aiming at the rule engine, and obtaining a target rule engine aiming at the electronic medical record to be controlled; the target rule engine comprises a plurality of target rule modules which are sequentially connected according to a target logic sequence, and the target logic sequence is determined according to a connection sequence identifier carried in the quality control request;
and performing quality control processing on the target medical entity by adopting the target rule engine to obtain a quality control result of the electronic medical record to be quality controlled.
Optionally, the target rule modules include a first target rule module and a second target rule module, and the module selection identifier includes a type sub identifier, where the type sub identifier is a coarse-grained identifier or a fine-grained identifier;
determining a step of selecting a plurality of target rule modules from a preset rule module library according to the module selection identification carried in the quality control request, wherein the step comprises the following steps:
if the type sub-identifier is a coarse-grained identifier, selecting a first rule module corresponding to the coarse-grained identifier from a rule module library, and responding to parameter selection operation aiming at each selected first rule module to obtain a plurality of first target rule modules;
and if the type sub-identifier is a fine-grained identifier, selecting a second rule module corresponding to the fine-grained identifier from the rule module library, and responding to the parameter selection operation aiming at each selected second rule module to obtain a plurality of second target rule modules.
Optionally, if the type sub-identifier is a coarse-grained identifier, a target rule engine for the electronic medical record to be quality-controlled is created in the following manner:
carrying out hierarchical classification on the plurality of first target rule modules according to a preset hierarchical type to obtain a plurality of first target hierarchies; wherein each first target level corresponds to a first target rule module;
determining the level priority of each first target level according to the connection sequence identification carried in the quality control request to obtain a first target logic sequence for representing the connection sequence among the first target rule modules;
and sequentially connecting a plurality of first target rule modules according to the first target logic sequence to obtain a target rule engine for the electronic medical record to be controlled.
Optionally, if the type sub-identifier is a fine-grained identifier, a target rule engine for the electronic medical record to be controlled is created in the following manner:
carrying out hierarchical classification on the plurality of second target rule modules according to a preset hierarchical type to obtain a plurality of second target hierarchies; wherein each second target level corresponds to at least one second target rule module;
for at least one second target rule module belonging to the same second target level, performing attribute classification on the at least one second target rule module belonging to the same second target level according to the attribute characteristics related to the target medical entity to obtain a plurality of attribute module sets comprising the second target rule modules with the same attribute;
determining the level priority of each second target level according to the connection sequence identification carried in the quality control request to obtain a second target logic sequence for representing the connection sequence among the attribute module sets of the plurality of second target rule modules;
and sequentially connecting the attribute module sets according to the second target logic sequence, and connecting the second target rule modules in the attribute module sets in parallel to obtain a target rule engine for the electronic medical record to be controlled.
Optionally, different target hierarchies of the target rules engine are displayed with different labels; the marks are color marks and/or symbol marks.
Optionally, each target rule module of the first plurality of target rule modules or the second plurality of target rule modules comprises a loss unit, a learning unit, an activation unit, and a genetic unit;
responding to parameter selection operation aiming at the loss unit, the learning unit, the activation unit and the genetic unit according to the module selection identifier and the identifier type of the module selection identifier to obtain the set loss unit, learning unit, activation unit and genetic unit;
inputting the target medical entity into the learning unit to obtain a medical entity learning result;
inputting the medical entity learning result output by the learning unit into the activation unit for filtering, and determining the filtered medical entity learning result as a sub-quality control result by the activation unit;
transmitting the sub-quality control result output by the activation unit to the genetic unit, and transmitting the sub-quality control result to a learning unit of a next target rule module through the genetic unit;
wherein the loss unit is used for controlling the data input formats of the learning unit and the activation unit.
Optionally, the performing, by using the target rule engine, quality control processing on the target medical entity to obtain a quality control result of the electronic medical record to be quality controlled includes:
inputting the target medical entity into the target rule engine, and performing quality control processing on the target medical entity through target rule modules which are sequentially connected in the target rule engine according to a target logic sequence; the input of the current target rule module is the output of the previous target rule module positioned before the current target rule module in the target logic sequence, and the output of the current target rule module is the input of the next target rule module positioned after the current target rule module in the target logic sequence until the output of the last target rule module, so that the quality control result of the electronic medical record to be quality controlled is obtained.
In a second aspect, an embodiment of the present application further provides a quality control device for an electronic medical record, where the quality control device includes:
the quality control request acquisition module is used for acquiring a quality control request of a target user for the electronic medical record to be subjected to quality control; the quality control request carries a medical entity identifier, a module selection identifier and a connection sequence identifier;
the medical entity extraction module is used for extracting a target medical entity corresponding to the medical entity identifier from the electronic medical record to be quality controlled according to the medical entity identifier carried in the quality control request;
the rule module selection module is used for selecting a plurality of target rule modules from a preset rule module library according to the module selection identification carried in the quality control request;
the rule engine creating module is used for responding to creating operation aiming at the rule engine to obtain a target rule engine aiming at the electronic medical record to be controlled; the target rule engine comprises a plurality of target rule modules which are sequentially connected according to a target logic sequence, and the target logic sequence is determined according to a connection sequence identifier carried in the quality control request;
and the quality control processing module is used for performing quality control processing on the target medical entity by adopting the target rule engine to obtain a quality control result of the electronic medical record to be quality controlled.
In a third aspect, an embodiment of the present application further provides an electronic device, including: the electronic medical record comprises a processor, a memory and a bus, wherein the memory stores machine-readable instructions executable by the processor, the processor and the memory are communicated through the bus when the electronic device runs, and the machine-readable instructions are executed by the processor to execute the steps of the quality control method of the electronic medical record.
In a fourth aspect, the present application further provides a computer-readable storage medium, where a computer program is stored on the computer-readable storage medium, and when the computer program is executed by a processor, the steps of the quality control method for electronic medical records are performed as described above.
The embodiment of the application provides a quality control method and device for an electronic medical record, electronic equipment and a storage medium, wherein the quality control method comprises the following steps: firstly, extracting a target medical entity corresponding to a medical entity identifier from an electronic medical record to be controlled according to the medical entity identifier carried in a quality control request of the electronic medical record to be controlled by a target user, then selecting the identifier according to a module carried in the quality control request, selecting a plurality of target rule modules from a preset rule module library, and then responding to the creation operation aiming at the rule engine to obtain the target rule engine aiming at the electronic medical record to be controlled; the target rule engine comprises a plurality of target rule modules which are sequentially connected according to a target logic sequence, the target logic sequence is determined according to a connection sequence identifier carried in the quality control request, and finally the target rule engine is adopted to carry out quality control processing on the target medical entity to obtain a quality control result of the electronic medical record to be quality controlled.
Therefore, a target user can establish a target rule engine capable of controlling the electronic medical record according to different quality control requests of the electronic medical record, so that the newly established target rule engine can better adapt to different quality control requests of the electronic medical record, and bottom programs of a quality control system are not required to be modified.
In order to make the aforementioned objects, features and advantages of the present application more comprehensible, preferred embodiments accompanied with figures are described in detail below.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings that are required to be used in the embodiments will be briefly described below, it should be understood that the following drawings only illustrate some embodiments of the present application and therefore should not be considered as limiting the scope, and for those skilled in the art, other related drawings can be obtained from the drawings without inventive effort.
Fig. 1 is a flowchart of a quality control method for an electronic medical record according to an embodiment of the present disclosure;
FIG. 2 is a schematic structural diagram of a first target rule engine according to an embodiment of the present disclosure;
FIG. 3 is a schematic structural diagram of a second target rule engine provided in an embodiment of the present application;
fig. 4 is a schematic structural diagram of a target rule module according to an embodiment of the present disclosure;
fig. 5 is a schematic structural diagram of a quality control apparatus for an electronic medical record according to an embodiment of the present disclosure;
fig. 6 is a schematic structural diagram of an electronic device according to an embodiment of the present application.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only a part of the embodiments of the present application, and not all the embodiments. The components of the embodiments of the present application, generally described and illustrated in the figures herein, can be arranged and designed in a wide variety of different configurations. Thus, the following detailed description of the embodiments of the present application, presented in the accompanying drawings, is not intended to limit the scope of the claimed application, but is merely representative of selected embodiments of the application. Every other embodiment that can be obtained by a person skilled in the art without making creative efforts based on the embodiments of the present application falls within the protection scope of the present application.
First, an application scenario to which the present application is applicable will be described. The method and the device can be applied to quality control of the electronic medical record in the medical field. The medical record is the summary of experience of a doctor flexibly applying medical knowledge in a long-term clinical practice process, objectively and completely records the change of the state of an illness of a patient and the whole process of diagnosis and treatment, and is the sum of data such as characters, charts, images, slices and the like formed by medical staff in the process of medical activities. Nowadays, with the increasingly developed information technology, the electronic medical record system is gradually popularized in hospitals at all levels, and compared with the traditional paper medical record, the electronic medical record has the characteristics of convenience in writing, convenience in interaction, flexibility in access and the like, and the electronic medical record system facilitates writing and query of medical staff and improves the working efficiency.
However, since electronic medical records are applied to various hospitals in China, because the electronic medical records have more templates which can be used indiscriminately, the bad phenomena of incorrect description of the content of the electronic medical records, copying and pasting of the content and the like exist in the actual medical work, the quality of the electronic medical records is greatly reduced, and the subsequent medical diagnosis work is influenced. Therefore, there is a need for quality control of electronic medical records.
In the prior art, the function of an electronic medical record quality control system has great limitation. The quality control doctor who is specially responsible for the quality control of the medical records still needs to evaluate and check the medical records filled by the clinician manually, so that the quality control flow efficiency is low, the processing process is delayed, and the quality condition of the medical records cannot be reflected in time.
With the continuous research on the field of quality control of electronic medical records, a plurality of rules can be set in the quality control system of some electronic medical records, and if the operation rules are utilized, the quality control results of the electronic medical records can be output. The rules are used for using document contents in the electronic medical record as detection bases, and detecting whether medical entities such as diseases and symptoms appearing in the context in the document contents are consistent or not, or whether the medical entities in the context have missing items and missing items or not. However, in practical cases, the same disease may have multiple names (for example, the cold may be called fever, flu, etc.), there may be an internal relationship between diseases and symptoms (for example, the cold causes cough symptom), and the dosage of the medicine may be different for different diseases, symptoms and orders. However, the existing rules are only to compare the document contents in the electronic medical records, and the situation that the context contents do not conform to the rules due to non-uniform symptoms or disease names may occur, and the actual requirements cannot be met. Therefore, the existing electronic medical record quality control system has lower quality control level and lower reliability of quality control.
In addition, in practical situations, the quality control requirements of different doctors in different hospitals for each electronic medical record may be different, and even new quality control requests need to be added again. At this time, the underlying program of the quality control system needs to be modified again for each electronic medical record, but because the number of the electronic medical records is large, the writing formats of each hospital are not uniform, the requirements for the quality control of the electronic medical records are different, and a large amount of time and energy are needed to modify the underlying program corresponding to the logic rules of the electronic medical records.
Here, when the electronic medical record is subjected to quality control, it is necessary to perform quality control on a medical entity related to the electronic medical record or attribute characteristics related to the medical entity. The medical entities in the embodiments of the present application include particular entities in the medical fields of diagnosis, symptoms, examinations, signs, tumor stages, and the like; the attribute characteristics related to the medical entity comprise the characteristics of the occurrence time, the duration time and the like of the medical entity, wherein the characteristics of the occurrence time, the duration time and the like of the medical entity can be comprehensively judged according to the writing time, the occurrence time and the information acquisition time of the medical record.
However, when the quality control is performed on the electronic medical record, the types and the number of medical entities in the medical field are various and have no definite definition; for persons in non-medical field, it is difficult to determine the medical entity and control the quality of the electronic medical record, such as: symptoms include which features, how they should be described, etc. Therefore, when the quality control request of the electronic medical record is changed, the non-medical field personnel can not easily know how to modify the bottom layer program according to the changed quality control request without communicating with the medical field personnel. However, in the process of communicating between the personnel in the non-medical field and the personnel in the medical field, because of cross-field communication and different cognition on business rules, the communication efficiency of the personnel in the two fields is low easily, and a good cooperation mode cannot be achieved, so that certain difficulty is undoubtedly caused for the perfection and modification of a rule engine of the quality control electronic medical record.
Based on the above-mentioned problems, embodiments of the present application provide a quality control method and apparatus for an electronic medical record, an electronic device, and a storage medium, which can create a rule engine for quality control of the electronic medical record in a user-defined manner according to a quality control request of a target user for the electronic medical record, thereby improving quality control reliability and quality control efficiency of the electronic medical record.
In order to facilitate understanding of the present embodiment, a method, an apparatus, an electronic device, and a storage medium for quality control of an electronic medical record provided in the embodiments of the present application are described in detail below.
As shown in fig. 1, a quality control method provided in an embodiment of the present application includes:
s110, acquiring a quality control request of a target user aiming at a to-be-controlled electronic medical record; the quality control request carries a medical entity identifier, a module selection identifier and a connection sequence identifier.
And S120, extracting a target medical entity corresponding to the medical entity identifier from the electronic medical record to be quality-controlled according to the medical entity identifier carried in the quality control request.
And S130, selecting a plurality of target rule modules from a preset rule module library according to the module selection identification carried in the quality control request.
S140, responding to the creation operation aiming at the rule engine, and obtaining a target rule engine aiming at the electronic medical record to be controlled; the target rule engine comprises a plurality of target rule modules which are sequentially connected according to a target logic sequence, and the target logic sequence is determined according to a connection sequence identifier carried in the quality control request.
S150, performing quality control processing on the target medical entity by adopting a target rule engine to obtain a quality control result of the electronic medical record to be quality controlled.
In step S110, the target user related to the embodiment of the present application may be a doctor, a nurse, or a quality control person in the hospital, which is specially responsible for quality control of medical records. The electronic medical record to be controlled can be an electronic medical record edited by a doctor at the current moment or an electronic medical record edited by the doctor in a previous period. The quality control request refers to a request initiated by monitoring the quality condition of the electronic medical record, the quality control request is mainly used for indicating what kind of detection is performed aiming at what kind of content of the electronic medical record, and the quality control request carries a medical entity identifier, a module selection identifier and a connection sequence identifier, wherein the medical entity identifier is used for indicating a target medical entity detected in the electronic medical record to be quality controlled by a target user, and the target medical entity corresponds to the medical entity identifier, namely the target medical entity corresponding to the medical entity identifier can be extracted from the electronic medical record to be quality controlled through the medical entity identifier; the module selection identifier is used for indicating that a target rule module used for constructing a target rule engine is extracted from a rule module library; and the connection sequence identifier is used for indicating the extracted target rule modules to be connected according to the connection sequence corresponding to the connection sequence identifier so as to construct a target rule engine.
For example, the quality control request may include a diagnosis list, a drug list, a surgery list, an examination report, a test report, and the like. Finer grained, doctors can configure and diagnose ICD9, 10, 11 codes, operation categories, test items, test index abnormality identification; the particle size is larger, doctors can configure whether certain past diseases exist, whether liver and kidney dysfunction exists, whether chemotherapy is performed, and the like.
In step S120, a target medical entity corresponding to the medical entity identifier is extracted from the electronic medical record to be quality-controlled. And taking the extracted target medical entity as an input of a target rule engine.
Here, the target medical entity corresponding to the medical entity identifier can be extracted from the electronic medical record to be controlled by the following steps:
presetting a medical entity library, wherein a large number of medical entities and preset medical entity identifications corresponding to each medical entity are stored in the medical entity library, comparing the medical entity identifications in the quality control request with the preset medical entity identifications in the medical entity library, calculating similarity values between the medical entity identifications in the quality control request and the preset medical entity identifications in the medical entity library, and determining the medical entities corresponding to the preset medical entity identifications with the similarity values larger than a first similarity threshold value as preset target medical entities; and extracting the medical entity from the electronic medical record to be quality-controlled, calculating the similarity value between the extracted medical entity and a preset target medical entity, and determining the medical entity with the similarity value larger than a second similarity threshold value as the target medical entity.
In step S130, a plurality of target rule modules are selected from a preset rule module library according to the module selection identifier carried in the quality control request.
Here, the preset rule module library has a large number of rule modules and module identifiers corresponding to each rule module, and each rule module can implement a specific function, such as screening, comparing, combining, inputting and outputting. Specifically, a similarity value between the module selection identifier and the module identifier of each rule module in the rule module library may also be calculated, and the rule module corresponding to the module identifier whose similarity value is greater than the third similarity threshold is determined as the target rule module, where one module selection identifier may include a plurality of sub-identifiers, and each sub-identifier may correspondingly select one target rule module, so that a plurality of target rule modules may be selected based on one module selection identifier.
As a preferred embodiment, the plurality of target rule modules include a plurality of first target rule modules and a plurality of second target rule modules, and the module selection identifier includes a type sub identifier, which is a coarse-grained identifier or a fine-grained identifier.
After the module selection identifier is input into the quality control system, the quality control system can identify the type of the module selection identifier according to the type sub-identifier in the module selection identifier, and further determine which area to select the target rule module; the type sub-identifier can be a coarse-grained identifier or a fine-grained identifier; the type sub-identifier refers to an identifier corresponding to the type of the module selection identifier, wherein the identifier is used for indicating the module selection identifier, the type sub-identifier can be a coarse-grained identifier, the coarse-grained identifier refers to an identifier corresponding to a rule module which contains more contents and is complex, and the rule module corresponding to the coarse-grained identifier has higher integration level; the fine-grained identification refers to the identification corresponding to the rule module with higher reusability and clearness, the rule module corresponding to the fine-grained identification has higher universality and reusability, the function is clear, and other functions can be realized by free combination.
Further, step S130 specifically includes: if the type sub-identifier is a coarse-grained identifier, selecting a first rule module corresponding to the coarse-grained identifier from a rule module library, and responding to parameter selection operation aiming at each selected first rule module to obtain a plurality of first target rule modules; and if the type sub-identifier is a fine-grained identifier, selecting a second rule module corresponding to the fine-grained identifier from the rule module library, and responding to the parameter selection operation aiming at each selected second rule module to obtain a plurality of second target rule modules.
Here, in response to a parameter selection operation of the target user for each selected first rule module, adding a rule parameter for controlling the duration of the electronic disease to be controlled to the target rule module through the parameter selection operation to obtain a first target rule module specially used for the control request; similarly, the parameter selection operation for the second rule module is also for the same reason.
In step S140, a target logic sequence is determined according to the connection sequence identifier carried in the quality control request, and the target rule modules are sequentially connected according to the target logic sequence to obtain a target rule engine. Here, in response to the creation operation for the rule engine being either the target user manually selecting creation or the target user clicking a creation button, the quality control system automatically performs creation of the rule engine.
Here, the target logical order is determined by:
and presetting a relational database for representing the connection sequence among the rule modules, wherein the relational database comprises a plurality of connection sequences and preset connection sequence identifiers corresponding to the connection sequences, comparing the connection sequence identifiers carried in the quality control request with the preset connection sequence identifiers in the relational database, calculating the similarity value between the connection sequence identifiers carried in the quality control request and the preset connection sequence identifiers in the relational database, and determining the connection sequence corresponding to the preset connection sequence identifier with the similarity value larger than a fourth similarity threshold value as a target logic sequence corresponding to the connection sequence identifier carried in the quality control request.
It should be noted that the first similarity threshold, the second similarity threshold, the third similarity threshold, and the fourth similarity threshold may be set according to the actual situation and the actual quality control request, and the similarity thresholds may be continuously adjusted.
In a preferred embodiment of the present application, if the type sub-identifier is a coarse-grained identifier, step S140 creates a target rule engine for the electronic medical record to be controlled by:
carrying out hierarchical classification on the plurality of first target rule modules according to a preset hierarchical type to obtain a plurality of first target hierarchies; each first target level corresponds to one first target rule module; determining the level priority of each first target level according to the connection sequence identification carried in the quality control request to obtain a first target logic sequence for representing the connection sequence among the first target rule modules; and sequentially connecting the plurality of first target rule modules according to a first target logic sequence to obtain a target rule engine for the electronic medical record to be controlled.
Here, the preset hierarchy type refers to a hierarchy type corresponding to a hierarchy type in which a target rule engine is divided into a plurality of hierarchies according to functions which can be realized by a rule module; wherein, each hierarchy structure comprises more than one function, and the functions belonging to the same level can be divided into one hierarchy structure. The order of the hierarchical priority is determined according to the connection order identifier carried in the quality control request.
When the type sub-identifier is a coarse-grained identifier, each first target level only corresponds to one first target rule module; according to the connection sequence identification carried in the quality control request, determining the hierarchical priority of the first target hierarchy corresponding to each first target rule module, determining the hierarchical priority from high to low as a first target logic sequence, and further, sequentially connecting the plurality of first target rule modules according to the first target logic sequence to obtain the target rule engine aiming at the electronic medical record to be quality controlled.
It should be noted that different marks are displayed according to different target levels of the target rule engine; the mark is known as a color mark and/or a symbol mark: when the plurality of first target rule modules are hierarchically classified according to the preset hierarchical type to obtain a plurality of first target hierarchies, a color mark and/or a symbol mark may be added to each first target hierarchy.
Specifically, each first target level in the target rule engine displays a mark, wherein the mark can be a color mark, a symbol mark or a mark with both color and symbol; wherein, color marking means displaying different first target levels by different colors, such as red for a first target level, yellow for a second first target level, and blue for a third first target level; the symbolic marking refers to displaying different target levels by different symbols, such as a number 1 indicating a first target level, a number 2 indicating a second first target level, a number 3 indicating a third first target level, etc.
Therefore, different marks are arranged for different levels and displayed on the graphical user interface, so that the target user can observe conveniently, and the connection relation among the first target rule modules is clearly shown. If the target rule engine is created by the target user through individual selection, the set marks can assist the target user to quickly and normally complete the creation of the target rule engine; if the target rule engine is automatically generated by the terminal, the displayed mark can be convenient for a target user to correct the generated target rule engine, so that the working efficiency is improved, the time is saved, and the experience of the user is improved.
For example, as shown in fig. 2, the target rule engine is created for coarse-grained identifiers, each first target rule module is a first target hierarchy, and the target rule engine can be obtained through connection between the first target rule modules.
In another preferred embodiment of the present application, if the type sub-identifier is a fine-grained identifier, step S140 creates a target rule engine for the electronic medical record to be controlled by:
carrying out hierarchical classification on the plurality of second target rule modules according to a preset hierarchical type to obtain a plurality of second target hierarchies; each second target level corresponds to at least one second target rule module; for at least one second target rule module belonging to the same second target level, performing attribute classification on the at least one second target rule module belonging to the same second target level according to the attribute characteristics related to the target medical entity to obtain a plurality of attribute module sets containing the second target rule modules with the same attribute; determining the level priority of each second target level according to the connection sequence identification carried in the quality control request to obtain a second target logic sequence for representing the connection sequence among the attribute module sets of the plurality of second target rule modules; and sequentially connecting the attribute module sets according to a second target logic sequence, and connecting the second target rule modules in the attribute module sets in parallel to obtain a target rule engine for the electronic medical record to be controlled.
Here, since the type sub-identifier is a fine-grained identifier, due to the refinement of the function, each second target level may correspond to at least one second target rule module, where the example that the second target level corresponds to a plurality of second target rule modules is: on the same second target level, the second target rule modules may be subjected to attribute classification to obtain a plurality of attribute module sets including the second target rule modules with the same attribute, that is, one second target level includes a plurality of different attribute module sets, and each attribute module set includes the second target rule modules with the same attribute. In this way, when the second target rule modules are connected, there is no connection order for the second target rule modules in the same attribute module set, so that according to the connection order identifier carried in the quality control request, a second target logic order for representing the connection order between the attribute module sets of the plurality of second target rule modules can be determined.
After the second target logic sequence is obtained, how to connect the second target rule modules according to the second target logic sequence to obtain a scheme of the target rule engine, and how to display the marks for different second target hierarchies may refer to the above description, and the same features are not described in detail.
It should be added that, for the same second target level, different labels may also be displayed between different attribute module sets, so that when displaying the labels, different display labels may be set between different second target levels and different attribute module sets of the same second target level.
For example, as shown in FIG. 3, the target rules engine is created for fine-grained identification. The first second target level comprises three second target rule modules, the second target level comprises a second target rule module and an attribute module set (the attribute module set comprises two second target rule modules), the third second target level comprises a second target rule module, the fourth second target level also comprises a second target rule module, and a target rule engine can be obtained through connection between different second target levels, wherein the attribute module set included in the second target level can be directly connected with the second target rule module included in the third second target level.
In an embodiment of the present application, each of the plurality of first target rule modules or the plurality of second target rule modules includes a loss unit, a learning unit, an activation unit, and a genetic unit; responding to parameter selection operation aiming at the loss unit, the learning unit, the activation unit and the genetic unit according to the module selection identifier and the identifier type of the module selection identifier to obtain the set loss unit, learning unit, activation unit and genetic unit; inputting a target medical entity into a learning unit to obtain a medical entity learning result; inputting the medical entity learning result output by the learning unit into an activation unit for filtering, and determining the filtered medical entity learning result as a sub-quality control result by the activation unit; transmitting the sub-quality control result output by the activation unit to the genetic unit, and transmitting the sub-quality control result to the learning unit of the next target rule module through the genetic unit; the loss unit is used for controlling the data input formats of the learning unit and the activation unit.
Specifically, each target rule module 400 has a structure as shown in fig. 4, where the genetic unit 440 enables the node to smoothly transmit necessary valid information to a subsequent node for continuing logic execution after the logic execution of the node is completed; the activation state is used for judging whether the execution result is successful or not after the node is executed; the loss unit 410 is used for informing the activation unit 430 and the learning unit 420 of the format of the input data, and further controlling the execution processes of the activation unit 430 and the learning unit 420; the learning unit 420 is used for executing a certain data processing procedure, such as extraction of medical entities (operations, diagnosis, etc.), calculation of drug dosage, and judgment of safe drug dosage range; the activation unit 430 is configured to filter the required data according to the result of the learning function, incorporate the structured data, and form genetic data, so that the genetic data can be continuously executed in series with other types of nodes, and for the termination type of nodes, the activation unit 430 omits the process of structured data.
Wherein, the learning unit may include a learning function, and the functions that the learning function can realize include: entity extraction (achieved by machine learning, or AC scanning, or regular matching, or dictionary matching), sorting, comparison, merging, etc.; the activation unit may include activation functions, and the activation functions may satisfy a certain condition at will, or one of them satisfies a certain condition, or two of them satisfy a certain condition, or exist, etc.; the loss unit can comprise a loss function, and the loss function can be of a list type or a word typical type; because the loss unit can control the data input formats of the learning unit and the activation unit, when the loss function of the loss unit is of a list type, the comparison method of the learning function is pairwise comparison and Dierka comparison, and the merging method of the learning function is pairwise merging and Cartesian merging; the activation function is that any one of the lists meets a certain condition, or one of the lists meets a certain condition, etc.; when the loss function of the loss unit is of a dictionary type, the comparison method of the learning function is comparison of corresponding fields of the dictionary, comparison of the fields with a configuration dictionary, existence of an activation function, and the like.
The embodiment of the application can create a target rule engine aiming at the electronic medical record to be subjected to quality control, and by redesigning the rule flow, the visualization and manageability of the support rule can be realized, the unified and efficient management can be realized, the set is suitable for the bottom NLP entity, the attribute difference and the hospital case information field difference, the flexibility, the integrity, the tightness and the execution efficiency of updating control configuration of different hospitals are improved, the increasing future requirements of the hospitals can be adapted, and the complete and rapid configuration can be continuously carried out on the increasing quality control of the medical record. Therefore, the established rule engine can be used for realizing the rule engine in the medical field, and the flows of quickly constructing the logic rule, displaying the logic rule and modifying the logic rule can be realized.
The unified rule design flow can greatly reduce the understanding depth of developers on the service, and also can greatly reduce the understanding and dependence of the service personnel on the change of an entity extraction structure and the change of a real medical record field of a hospital in Neuro-Linguistic Programming (NLP); the medical entities, relationships and logics in the electronic medical records are mined and optimized, so that a unified optimization scheme and strategy are provided for unified icd standards, medical record codes and novel drug identification. Because the rule is visual, can manage, the rule module can be used repeatedly, very big promotion quality control efficiency.
In step S150, the target medical entity is input into the target rule engine, and the target medical entity is subjected to quality control processing by the target rule modules sequentially connected in the target rule engine according to the target logic sequence; the input of the current target rule module is the output of the previous target rule module positioned before the current target rule module in the target logic sequence, and the output of the current target rule module is the input of the next target rule module positioned after the current target rule module in the target logic sequence until the output of the last target rule module, so that the quality control result of the electronic medical record to be quality controlled is obtained.
The target medical entity is input into the target rule engine, the execution is started from a first target rule module of the target rule engine, the output of the first target rule module is used as the input of a second target rule module, all target rule modules in the target rule engine are completely executed according to the target logic sequence, and the output of the last target rule module is used as the output of the target rule engine, namely the quality control result of the electronic medical record to be quality controlled.
For example, the quality control result in the embodiment of the present application may be directly problem annotation on an electronic medical record, and output in a format of the electronic medical record with the problem annotation; or the content with error or non-conforming quality control can be output separately.
In the quality control method for the electronic medical record provided by the embodiment of the application, the target user can establish the target rule engine capable of controlling the electronic medical record according to different quality control requests of the electronic medical record, the target rule engine which is re-established can better adapt to different electronic medical record quality control requests without modifying the bottom layer program of the quality control system, even if the writing formats of all hospitals are not uniform, the quality control processing aiming at the electronic medical record can be carried out through the extracted entity characteristics, the quality control aiming at the electronic medical record with different quality control requests can be realized without spending a large amount of time and energy, furthermore, according to the embodiment of the application, the rule engine for quality control of the electronic medical record is created in a user-defined mode according to the quality control request of the target user for the electronic medical record, so that the quality control reliability and the quality control efficiency of the electronic medical record are improved to a certain extent.
Based on the same inventive concept, the embodiment of the present application further provides a quality control device for an electronic medical record corresponding to the quality control method for an electronic medical record, and since the principle of solving the problem of the device in the embodiment of the present application is similar to that of the quality control method for an electronic medical record in the embodiment of the present application, the implementation of the device can refer to the implementation of the method, and repeated details are not repeated.
Referring to fig. 5, fig. 5 is a schematic structural diagram of a quality control device for an electronic medical record according to an embodiment of the present application. As shown in fig. 5, the quality control device 500 includes:
a quality control request obtaining module 510, configured to obtain a quality control request of a target user for a to-be-quality-controlled electronic medical record; the quality control request carries a medical entity identifier, a module selection identifier and a connection sequence identifier;
a medical entity extraction module 520, configured to extract a target medical entity corresponding to the medical entity identifier from the electronic medical record to be quality controlled according to the medical entity identifier carried in the quality control request;
a rule module selection module 530, configured to select a plurality of target rule modules from a preset rule module library according to a module selection identifier carried in the quality control request;
the rule engine creating module 540 is configured to respond to a creating operation for a rule engine to obtain a target rule engine for the electronic medical record to be controlled; the target rule engine comprises a plurality of target rule modules which are sequentially connected according to a target logic sequence, and the target logic sequence is determined according to a connection sequence identifier carried in the quality control request;
and a quality control processing module 550, configured to perform quality control processing on the target medical entity by using the target rule engine, so as to obtain a quality control result of the electronic medical record to be quality controlled.
Optionally, the plurality of target rule modules include a plurality of first target rule modules and a plurality of second target rule modules, the module selection identifier includes a type sub-identifier, and the type sub-identifier is a coarse-grained identifier or a fine-grained identifier;
the rule module selecting module 530 is specifically configured to:
if the type sub-identifier is a coarse-grained identifier, selecting a first rule module corresponding to the coarse-grained identifier from a rule module library, and responding to parameter selection operation aiming at each selected first rule module to obtain a plurality of first target rule modules;
and if the type sub-identifier is a fine-grained identifier, selecting a second rule module corresponding to the fine-grained identifier from the rule module library, and responding to the parameter selection operation aiming at each selected second rule module to obtain a plurality of second target rule modules.
Optionally, if the type sub-identifier is a coarse-grained identifier, the rule engine creating module 540 is configured to create a target rule engine for the electronic medical record to be quality-controlled by:
carrying out hierarchical classification on the plurality of first target rule modules according to a preset hierarchical type to obtain a plurality of first target hierarchies; each first target level corresponds to one first target rule module;
determining the level priority of each first target level according to the connection sequence identification carried in the quality control request to obtain a first target logic sequence for representing the connection sequence among the first target rule modules;
and sequentially connecting the plurality of first target rule modules according to a first target logic sequence to obtain a target rule engine for the electronic medical record to be controlled.
Optionally, if the type sub-identifier is a fine-grained identifier, the rule engine creating module 540 is configured to create a target rule engine for the electronic medical record to be quality-controlled by:
carrying out hierarchical classification on the plurality of second target rule modules according to a preset hierarchical type to obtain a plurality of second target hierarchies; each second target level corresponds to at least one second target rule module;
for at least one second target rule module belonging to the same second target level, performing attribute classification on the at least one second target rule module belonging to the same second target level according to the attribute characteristics related to the target medical entity to obtain a plurality of attribute module sets containing the second target rule modules with the same attribute;
determining the level priority of each second target level according to the connection sequence identification carried in the quality control request to obtain a second target logic sequence for representing the connection sequence among the attribute module sets of the plurality of second target rule modules;
and sequentially connecting the attribute module sets according to a second target logic sequence, and connecting the second target rule modules in the attribute module sets in parallel to obtain a target rule engine for the electronic medical record to be controlled.
Optionally, different target levels of the target rules engine are displayed with different labels; the mark is a color mark and/or a symbol mark.
Optionally, each target rule module of the plurality of first target rule modules or the plurality of second target rule modules comprises a loss unit, a learning unit, an activation unit, and a genetic unit;
responding to parameter selection operation aiming at the loss unit, the learning unit, the activation unit and the genetic unit according to the module selection identifier and the identifier type of the module selection identifier to obtain the set loss unit, learning unit, activation unit and genetic unit;
inputting a target medical entity into the learning unit to obtain a medical entity learning result;
inputting the medical entity learning result output by the learning unit into an activation unit for filtering, and determining the filtered medical entity learning result as a sub-quality control result by the activation unit;
transmitting the sub-quality control result output by the activation unit to the genetic unit, and transmitting the sub-quality control result to the learning unit of the next target rule module through the genetic unit;
the loss unit is used for controlling the data input formats of the learning unit and the activation unit.
Optionally, the quality control processing module 550 is specifically configured to:
inputting the target medical entity into a target rule engine, and performing quality control processing on the target medical entity through target rule modules which are sequentially connected in the target rule engine according to a target logic sequence; the input of the current target rule module is the output of the previous target rule module positioned before the current target rule module in the target logic sequence, and the output of the current target rule module is the input of the next target rule module positioned after the current target rule module in the target logic sequence until the output of the last target rule module, so that the quality control result of the electronic medical record to be quality controlled is obtained.
The quality control device of the electronic medical record provided by the embodiment of the application comprises a quality control request acquisition module, a medical entity extraction module, a rule module selection module, a rule engine creation module and a quality control processing module, wherein the modules form a target rule engine capable of controlling the electronic medical record in a quality mode, so that the newly created target rule engine can better adapt to different quality control requests of the electronic medical record, a bottom program of a quality control system is not required to be modified, even if the writing formats of hospitals are not uniform, the quality control processing aiming at the electronic medical record can be carried out through the entity characteristics of the medical record, the quality control aiming at the electronic medical record with different quality control requests can be realized without spending a large amount of time and energy, and further, the embodiment of the application can create the rule engine of the quality control electronic medical record in a user-defined mode according to the quality control request of a target user to the electronic medical record, the quality control reliability and the quality control efficiency of the electronic medical record are improved to a certain extent.
Referring to fig. 6, fig. 6 is a schematic structural diagram of an electronic device according to an embodiment of the present disclosure. As shown in fig. 6, the electronic device 600 includes a processor 610, a memory 620, and a bus 630.
The memory 620 stores machine-readable instructions executable by the processor 610, when the electronic device 600 runs, the processor 610 communicates with the memory 620 through the bus 630, and when the machine-readable instructions are executed by the processor 610, the steps of the quality control method of the electronic medical record in the embodiment of the method shown in fig. 1 can be executed.
An embodiment of the present application further provides a computer-readable storage medium, where a computer program is stored on the computer-readable storage medium, and when the computer program is executed by a processor, the steps of the quality control method for an electronic medical record in the method embodiment shown in fig. 1 may be executed.
It is clear to those skilled in the art that, for convenience and brevity of description, the specific working processes of the above-described systems, apparatuses and units may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again.
In the several embodiments provided in the present application, it should be understood that the disclosed system, apparatus and method may be implemented in other ways. The above-described embodiments of the apparatus are merely illustrative, and for example, the division of the units is only one logical division, and there may be other divisions when actually implemented, and for example, a plurality of units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection of devices or units through some communication interfaces, and may be in an electrical, mechanical or other form.
The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.
In addition, functional units in the embodiments of the present application may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit.
The functions, if implemented in the form of software functional units and sold or used as a stand-alone product, may be stored in a non-volatile computer-readable storage medium executable by a processor. Based on such understanding, the technical solution of the present application or portions thereof that substantially contribute to the prior art may be embodied in the form of a software product stored in a storage medium and including instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present application. And the aforementioned storage medium includes: various media capable of storing program codes, such as a usb disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk, or an optical disk.
Finally, it should be noted that: the above-mentioned embodiments are only specific embodiments of the present application, and are used for illustrating the technical solutions of the present application, but not limiting the same, and the scope of the present application is not limited thereto, and although the present application is described in detail with reference to the foregoing embodiments, those skilled in the art should understand that: any person skilled in the art can modify or easily conceive the technical solutions described in the foregoing embodiments or equivalent substitutes for some technical features within the technical scope disclosed in the present application; such modifications, changes or substitutions do not depart from the spirit and scope of the exemplary embodiments of the present application, and are intended to be covered by the scope of the present application. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.

Claims (10)

1. A quality control method of an electronic medical record is characterized by comprising the following steps:
acquiring a quality control request of a target user for a to-be-quality-controlled electronic medical record; the quality control request carries a medical entity identifier, a module selection identifier and a connection sequence identifier;
extracting a target medical entity corresponding to the medical entity identifier from the electronic medical record to be quality-controlled according to the medical entity identifier carried in the quality control request;
selecting a plurality of target rule modules from a preset rule module library according to a module selection identifier carried in the quality control request;
responding to the creation operation aiming at the rule engine, and obtaining a target rule engine aiming at the electronic medical record to be controlled; the target rule engine comprises a plurality of target rule modules which are sequentially connected according to a target logic sequence, and the target logic sequence is determined according to a connection sequence identifier carried in the quality control request;
and performing quality control processing on the target medical entity by adopting the target rule engine to obtain a quality control result of the electronic medical record to be quality controlled.
2. The quality control method according to claim 1, wherein the plurality of target rule modules include a plurality of first target rule modules and a plurality of second target rule modules, the module selection identifier includes a type sub identifier, and the type sub identifier is a coarse-grained identifier or a fine-grained identifier;
determining a step of selecting a plurality of target rule modules from a preset rule module library according to the module selection identification carried in the quality control request, wherein the step comprises the following steps:
if the type sub-identifier is a coarse-grained identifier, selecting a first rule module corresponding to the coarse-grained identifier from a rule module library, and responding to parameter selection operation aiming at each selected first rule module to obtain a plurality of first target rule modules;
and if the type sub-identifier is a fine-grained identifier, selecting a second rule module corresponding to the fine-grained identifier from the rule module library, and responding to the parameter selection operation aiming at each selected second rule module to obtain a plurality of second target rule modules.
3. The quality control method according to claim 2, wherein if the type sub-identifier is a coarse-grained identifier, a target rule engine for the electronic medical record to be quality controlled is created by:
carrying out hierarchical classification on the plurality of first target rule modules according to a preset hierarchical type to obtain a plurality of first target hierarchies; wherein each first target level corresponds to a first target rule module;
determining the level priority of each first target level according to the connection sequence identification carried in the quality control request to obtain a first target logic sequence for representing the connection sequence among the first target rule modules;
and sequentially connecting a plurality of first target rule modules according to the first target logic sequence to obtain a target rule engine for the electronic medical record to be controlled.
4. The quality control method according to claim 2, wherein if the type sub-identifier is a fine-grained identifier, a target rule engine for the electronic medical record to be quality controlled is created by:
carrying out hierarchical classification on the plurality of second target rule modules according to a preset hierarchical type to obtain a plurality of second target hierarchies; wherein each second target level corresponds to at least one second target rule module;
for at least one second target rule module belonging to the same second target level, performing attribute classification on the at least one second target rule module belonging to the same second target level according to the attribute characteristics related to the target medical entity to obtain a plurality of attribute module sets comprising the second target rule modules with the same attribute;
determining the level priority of each second target level according to the connection sequence identification carried in the quality control request to obtain a second target logic sequence for representing the connection sequence among the attribute module sets of the plurality of second target rule modules;
and sequentially connecting the attribute module sets according to the second target logic sequence, and connecting the second target rule modules in the attribute module sets in parallel to obtain a target rule engine for the electronic medical record to be controlled.
5. The quality control method according to claim 3 or 4, wherein different target levels of the target rule engine are displayed with different marks; the marks are color marks and/or symbol marks.
6. The quality control method according to claim 2, wherein each of the plurality of first target rule modules or the plurality of second target rule modules includes a loss unit, a learning unit, an activation unit, and a genetic unit;
responding to parameter selection operation aiming at the loss unit, the learning unit, the activation unit and the genetic unit according to the module selection identifier and the identifier type of the module selection identifier to obtain the set loss unit, learning unit, activation unit and genetic unit;
inputting the target medical entity into the learning unit to obtain a medical entity learning result;
inputting the medical entity learning result output by the learning unit into the activation unit for filtering, and determining the filtered medical entity learning result as a sub-quality control result by the activation unit;
transmitting the sub-quality control result output by the activation unit to the genetic unit, and transmitting the sub-quality control result to a learning unit of a next target rule module through the genetic unit;
wherein the loss unit is used for controlling the data input formats of the learning unit and the activation unit.
7. The quality control method according to claim 1, wherein the performing the quality control process on the target medical entity by using the target rule engine to obtain the quality control result of the electronic medical record to be quality controlled comprises:
inputting the target medical entity into the target rule engine, and performing quality control processing on the target medical entity through target rule modules which are sequentially connected in the target rule engine according to a target logic sequence; the input of the current target rule module is the output of the previous target rule module positioned before the current target rule module in the target logic sequence, and the output of the current target rule module is the input of the next target rule module positioned after the current target rule module in the target logic sequence until the output of the last target rule module, so that the quality control result of the electronic medical record to be quality controlled is obtained.
8. A quality control device of an electronic medical record is characterized by comprising:
the quality control request acquisition module is used for acquiring a quality control request of a target user for the electronic medical record to be subjected to quality control; the quality control request carries a medical entity identifier, a module selection identifier and a connection sequence identifier;
the medical entity extraction module is used for extracting a target medical entity corresponding to the medical entity identifier from the electronic medical record to be quality controlled according to the medical entity identifier carried in the quality control request;
the rule module selection module is used for selecting a plurality of target rule modules from a preset rule module library according to the module selection identification carried in the quality control request;
the rule engine creating module is used for responding to creating operation aiming at the rule engine to obtain a target rule engine aiming at the electronic medical record to be controlled; the target rule engine comprises a plurality of target rule modules which are sequentially connected according to a target logic sequence, and the target logic sequence is determined according to a connection sequence identifier carried in the quality control request;
and the quality control processing module is used for performing quality control processing on the target medical entity by adopting the target rule engine to obtain a quality control result of the electronic medical record to be quality controlled.
9. An electronic device, comprising: a processor, a memory and a bus, wherein the memory stores machine-readable instructions executable by the processor, the processor and the memory communicate through the bus when the electronic device runs, and the processor executes the machine-readable instructions to execute the steps of the quality control method of the electronic medical record according to any one of claims 1 to 7.
10. A computer-readable storage medium, wherein a computer program is stored on the computer-readable storage medium, and when executed by a processor, the computer program performs the steps of the method for quality control of an electronic medical record according to any one of claims 1 to 7.
CN202110847667.5A 2021-07-27 2021-07-27 Quality control method and device for electronic medical record, electronic equipment and storage medium Active CN113297853B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202110847667.5A CN113297853B (en) 2021-07-27 2021-07-27 Quality control method and device for electronic medical record, electronic equipment and storage medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202110847667.5A CN113297853B (en) 2021-07-27 2021-07-27 Quality control method and device for electronic medical record, electronic equipment and storage medium

Publications (2)

Publication Number Publication Date
CN113297853A true CN113297853A (en) 2021-08-24
CN113297853B CN113297853B (en) 2021-10-01

Family

ID=77331087

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202110847667.5A Active CN113297853B (en) 2021-07-27 2021-07-27 Quality control method and device for electronic medical record, electronic equipment and storage medium

Country Status (1)

Country Link
CN (1) CN113297853B (en)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114496139A (en) * 2021-12-31 2022-05-13 医渡云（北京）技术有限公司 Quality control method, device, equipment and system of electronic medical record and readable medium
CN114496141A (en) * 2021-12-31 2022-05-13 医渡云（北京）技术有限公司 Method, device, medium and electronic equipment for constructing search engine index

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20190206525A1 (en) * 2017-12-28 2019-07-04 International Business Machines Corporation Evaluating Completeness and Data Quality of Electronic Medical Record Data Sources
CN111681728A (en) * 2020-06-09 2020-09-18 北京嘉和海森健康科技有限公司 Content quality control method and device for electronic medical record
CN111813399A (en) * 2020-07-23 2020-10-23 平安医疗健康管理股份有限公司 Machine learning-based auditing rule processing method and device and computer equipment
CN112711581A (en) * 2020-12-30 2021-04-27 医渡云（北京）技术有限公司 Medical data verification method and device, electronic equipment and storage medium

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20190206525A1 (en) * 2017-12-28 2019-07-04 International Business Machines Corporation Evaluating Completeness and Data Quality of Electronic Medical Record Data Sources
CN111681728A (en) * 2020-06-09 2020-09-18 北京嘉和海森健康科技有限公司 Content quality control method and device for electronic medical record
CN111813399A (en) * 2020-07-23 2020-10-23 平安医疗健康管理股份有限公司 Machine learning-based auditing rule processing method and device and computer equipment
CN112711581A (en) * 2020-12-30 2021-04-27 医渡云（北京）技术有限公司 Medical data verification method and device, electronic equipment and storage medium

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114496139A (en) * 2021-12-31 2022-05-13 医渡云（北京）技术有限公司 Quality control method, device, equipment and system of electronic medical record and readable medium
CN114496141A (en) * 2021-12-31 2022-05-13 医渡云（北京）技术有限公司 Method, device, medium and electronic equipment for constructing search engine index

Also Published As

Publication number Publication date
CN113297853B (en) 2021-10-01

Similar Documents

Publication Publication Date Title
US11410760B2 (en) Medical evaluation system and method for use therewith
CN109766445B (en) Knowledge graph construction method and data processing device
US10452813B2 (en) Medical image identification and interpretation
US10181012B2 (en) Extracting clinical care pathways correlated with outcomes
RU2543563C2 (en) Systems and methods for clinical decision support
CN113297853B (en) Quality control method and device for electronic medical record, electronic equipment and storage medium
US10191956B2 (en) Event detection and characterization in big data streams
US20220172809A9 (en) Report generating system and methods for use therewith
CN105940401A (en) Context sensitive medical data entry system
CN110291555B (en) Systems and methods for facilitating computational analysis of health conditions
WO2021108100A1 (en) Medical scan co-registration and methods for use therewith
US20140257045A1 (en) Hierarchical exploration of longitudinal medical events
CN117501375A (en) System and method for artificial intelligence assisted image analysis
US9824148B2 (en) Method and device for searching and displaying scattered logs
Glueck et al. PhenoBlocks: Phenotype comparison visualizations
US12061994B2 (en) Inference process visualization system for medical scans
JP7544024B2 (en) Filtering by lookup value context
US20120259661A1 (en) Systems and methods for data mining of DICOM structured reports
CN109074871A (en) The mode discovery visual analysis system of patient group is generated for analyzing clinical data feature
WO2022155607A1 (en) Oncology workflow for clinical decision support
CN108710636B (en) Medical record screening method, terminal equipment and computer readable storage medium
Mougin et al. Visualizing omics and clinical data: Which challenges for dealing with their variety?
Mittelstädt et al. Advanced visual analytics interfaces for adverse drug event detection
Zamora et al. Characterizing chronic disease and polymedication prescription patterns from electronic health records
CN101788977A (en) Method for implementing editing and modifying of medical examination report

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant