Medical rule metadata management method and device

Abstract

The invention provides a medical rule metadata management method and device, and the method comprises the steps: constructing medical knowledge metadata based on a medical knowledge meta-model and medical data; and constructing a medical record field meta-model based on data information in data sources of different business systems of a hospital and the medical knowledge metadata, and performing standard management on a calculation caliber, a field and a field value domain in the medical rule metadata through the medical knowledge metadata and the medical record field meta-model to realize the consistency and maintainability of the rule.

Description

Technical Field

[0001] This application relates to the field of computer technology, and in particular to a method and apparatus for managing medical rule metadata. Background Technology

[0002] Currently in the medical field, medical record data originates from various business systems (such as HIS, LIS, PACS, etc.), and data governance involves cleaning, processing, or performing calculations on fields. To maintain quality control, early warning, and alerts for medical record data, rule-based data needs to be maintained. In addition to structured data, there is also a large amount of unstructured medical record data, which requires natural language processing to derive structured fields for use by researchers.

[0003] Currently, business expansion has led to the use of tens of thousands of rule data entries, but due to diverse syntax and logic, there is a lack of unified management standards. Problems include frequent rule data changes, version inconsistencies, inconsistent quality, and difficulty in effectively managing the entire lifecycle. Summary of the Invention

[0004] In view of this, this application provides a method and apparatus for managing medical rule metadata. By constructing medical knowledge metadata and medical record field meta-models, the method and apparatus manage medical rule metadata in a standardized manner, thereby achieving consistency and maintainability of the rules.

[0005] The first aspect of this application provides a method for managing medical rule metadata, including:

[0006] Based on a medical knowledge meta-model and medical data, medical knowledge metadata is constructed; wherein, the medical knowledge meta-model is a model that defines the attributes of knowledge metadata and the relationships between knowledge metadata; the medical data includes at least medical literature, medical books, and electronic medical records.

[0007] Based on data information from different business systems of the hospital and the medical knowledge metadata, a medical record field meta-model is constructed.

[0008] The calculation methods in medical rule metadata are identified and managed programmatically; wherein, the medical rule metadata is obtained by segmenting medical rule data according to logical operators; the medical rule metadata includes fields, calculation methods, and field value ranges; the calculation methods include calculation standards, logic, and algorithms;

[0009] The fields in the medical rule metadata are managed based on the aforementioned medical record field metamodel;

[0010] The field value ranges in the medical rule metadata are managed based on the medical knowledge metadata and the field value ranges in the medical record field metamodel.

[0011] Optionally, the construction of a medical record field meta-model based on data information from different business systems of the hospital and the medical knowledge metadata includes:

[0012] A basic field meta-model is established based on the first information of the data fields in the data information from the data sources of different business systems of the hospital; wherein, the first information of the data fields includes at least the field name, type, level and whether it is duplicate information;

[0013] For unstructured basic fields, define the derived field metamodel corresponding to the unstructured basic fields;

[0014] Based on business requirements, define the field metamodel corresponding to the business requirements;

[0015] By combining the basic field metamodel, the derived field metamodel corresponding to the unstructured basic field, and the field metamodel corresponding to the business requirements, a medical record field metamodel is generated.

[0016] Optionally, the method for managing the medical rule metadata further includes:

[0017] Based on the dictionary data, national standard fields, and standard metadata documents of each field in the data sources of different business systems of the hospital, the knowledge metadata is mapped to the case field in the medical record field metamodel, and the value range attribute and value range constraint of the medical record field are defined.

[0018] Optionally, the identification and programmatic management of the calculation criteria in the medical rule metadata includes:

[0019] For each of the medical rule metadata, the medical rule metadata is denoised to obtain a denoised medical rule metadata set; wherein, the denoised medical rule metadata set includes at least one denoised medical rule metadata.

[0020] All the denoised medical rule metadata is divided into a preset number of categories according to a predefined classification. The data points in each category have the smallest Euclidean distance to the cluster center of that category. The data points are obtained by vectorizing the denoised medical rule metadata. The cluster centers of each category are obtained through iterative processing based on all data points and the initial cluster centers of the category. The initial cluster centers of each category are randomly selected data points.

[0021] The calculation method for the denoised medical rule metadata is determined based on the classification group to which it belongs.

[0022] The calculation method of the denoised medical rule metadata is converted into a program description language;

[0023] The denoised medical rule metadata is programmed according to the program description language.

[0024] Optionally, the method for managing the medical rule metadata further includes:

[0025] Extract constant values ​​or preset parameters from the calculation caliber into configurable parameters.

[0026] Optionally, the method for managing the medical rule metadata further includes:

[0027] Receive and respond to a calculation caliber management request; wherein, the calculation caliber management request includes modifying the calculation caliber and arranging or combining the calculation calibers.

[0028] Optionally, the program for calculating the aperture has reserved expansion points.

[0029] Optionally, the method for managing the medical rule metadata further includes:

[0030] Extract the fields and field value ranges from the current medical rule metadata;

[0031] The current version of the medical record field metamodel and medical knowledge metadata are used to validate the fields and field value ranges in the current medical rule metadata, and the validation results are obtained.

[0032] If the verification result shows that there are fields and / or field value ranges in the current medical rule metadata that have failed the verification, then the current medical rule metadata will be marked as an invalid rule.

[0033] Optionally, the method for managing the medical rule metadata further includes:

[0034] When the medical record field metamodel changes, the operation records of the medical record field metamodel change are traced and parsed, and the latest medical rule metadata fields are generated.

[0035] Operation logs recording the update process of the aforementioned medical rule metadata.

[0036] A second aspect of this application provides a management device for medical rule metadata, comprising:

[0037] The first construction unit is used to construct medical knowledge metadata based on a medical knowledge meta-model and medical data; wherein, the medical knowledge meta-model is a model that defines the attributes of knowledge metadata and the relationships between knowledge metadata; the medical data includes at least medical literature, medical books, and electronic medical records.

[0038] The second construction unit is used to construct a medical record field meta-model based on data information from data sources in different business systems of the hospital and the medical knowledge metadata.

[0039] The management unit is used to identify and programmatically manage the calculation methods in the medical rule metadata; wherein, the medical rule metadata is obtained by segmenting medical rule data according to logical operators; the medical rule metadata includes fields, calculation methods, and field value ranges; the calculation method includes calculation standards, logic, and algorithms;

[0040] The management unit is also used to manage the fields in the medical rule metadata according to the medical record field metamodel;

[0041] The management unit is also used to manage the field value ranges in the medical rule metadata based on the medical knowledge metadata and the field value ranges in the medical record field metamodel.

[0042] Optionally, the second building unit includes:

[0043] The establishment unit is used to establish a basic field meta-model based on the first information of the data fields in the data information from different business systems of the hospital; wherein, the first information of the data fields includes at least the field name, type, level and whether it is duplicate information;

[0044] The first definition unit is used to define the derived field metamodel corresponding to the unstructured basic field for the unstructured basic field;

[0045] The second definition unit is used to define the field metamodel corresponding to the business requirements based on the business requirements;

[0046] The generation unit is used to combine the basic field meta-model, the derived field meta-model corresponding to the unstructured basic field, and the field meta-model corresponding to the business requirements to generate a medical record field meta-model.

[0047] Optionally, the management device for medical rule metadata further includes:

[0048] The processing unit is used to map the knowledge metadata to the case field in the medical record field metamodel based on the dictionary data, national standard fields and standard metadata documents of each field in the data source of different business systems of the hospital, and to define the value range attribute and value range constraint of the medical record field.

[0049] Optionally, the management unit includes:

[0050] A denoising unit is used to denoise each of the medical rule metadata to obtain a denoised medical rule metadata set; wherein the denoised medical rule metadata set includes at least one denoised medical rule metadata.

[0051] A classification unit is used to divide all the denoised medical rule metadata into a preset number of classification groups according to a preset classification. Each data point in a classification group has the smallest Euclidean distance to its cluster center. The data points are obtained by vectorizing the denoised medical rule metadata. The cluster centers of the classification groups are obtained by iterative processing based on all data points and the initial cluster centers of the classification groups. The initial cluster centers of the classification groups are randomly selected data points.

[0052] The identification unit is used to determine the calculation caliber of the denoised medical rule metadata based on the classification group to which the denoised medical rule metadata belongs;

[0053] A conversion unit is used to convert the calculation method of the denoised medical rule metadata into a program description language;

[0054] The programming unit is used to programmatically process the denoised medical rule metadata according to the programming description language.

[0055] Optionally, the management device for medical rule metadata further includes:

[0056] The first extraction unit is used to extract constant values ​​or preset parameters from the calculation caliber into configurable parameters.

[0057] Optionally, the management device for medical rule metadata further includes:

[0058] A receiving unit is used to receive and respond to a computational aperture management request; wherein the computational aperture management request includes modifying the computational aperture and arranging or combining computational apertures.

[0059] Optionally, the program for calculating the aperture has reserved expansion points.

[0060] Optionally, the management device for medical rule metadata further includes:

[0061] The second extraction unit is used to extract the fields and field value ranges from the current medical rule metadata.

[0062] The verification unit is used to verify the fields and field value ranges in the current medical rule metadata using the current version of the medical record field metamodel and medical knowledge metadata, and obtain the verification results.

[0063] The marking unit is used to mark the current medical rule metadata as an invalid rule if the verification result shows that there are fields and / or field value ranges in the current medical rule metadata that have failed the verification.

[0064] Optionally, the management device for medical rule metadata further includes:

[0065] The source tracing and parsing unit is used to perform source tracing and parsing on the operation records of the change of the medical record field metamodel when the medical record field metamodel changes, and to generate the fields of the latest medical rule metadata.

[0066] The recording unit is used to record the operation log of the update process of medical rule metadata.

[0067] A third aspect of this application provides an electronic device, comprising:

[0068] One or more processors;

[0069] A storage device on which one or more programs are stored;

[0070] When the one or more programs are executed by the one or more processors, the one or more processors implement the method for managing medical rule metadata as described in any one of the first aspects.

[0071] The fourth aspect of this application provides a computer storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the method for managing medical rule metadata as described in any one of the first aspects.

[0072] As can be seen from the above solutions, this application provides a method and apparatus for managing medical rule metadata. The method for managing medical rule metadata constructs medical knowledge metadata based on medical knowledge metadata and medical data. It also constructs a medical record field metadata model based on data information from different business systems of the hospital and the medical knowledge metadata. The calculation methods, fields, and field value ranges in the medical rule metadata are managed in a standardized manner through the medical knowledge metadata and the medical record field metadata model, thereby achieving consistency and maintainability of the rules. Attached Figure Description

[0073] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on the provided drawings without creative effort.

[0074] Figure 1A flowchart illustrating a method for managing medical rule metadata provided in this application embodiment;

[0075] Figure 2 An example diagram of a medical knowledge meta-model provided for another embodiment of this application;

[0076] Figure 3 An example diagram of a medical knowledge meta-model provided for another embodiment of this application;

[0077] Figure 4 An example diagram of a knowledge entity attribute metamodel provided in another embodiment of this application;

[0078] Figure 5 Example diagram of medical knowledge metadata provided for another embodiment of this application;

[0079] Figure 6 A flowchart illustrating a method for constructing a meta-model of medical record fields, provided in another embodiment of this application;

[0080] Figure 7 An example diagram of a derived field metamodel corresponding to an unstructured basic field provided in another embodiment of this application;

[0081] Figure 8 Example diagram of a field metamodel corresponding to a business requirement provided in another embodiment of this application;

[0082] Figure 9 An example diagram of an associated value range provided for another embodiment of this application;

[0083] Figure 10 A flowchart for identifying and programmatically managing the calculation criteria in medical rule metadata, as provided in another embodiment of this application;

[0084] Figure 11 An example diagram illustrating rule item field management provided in another embodiment of this application;

[0085] Figure 12 This is an example diagram illustrating the use of SQL queries for value domain management, provided as another embodiment of this application.

[0086] Figure 13 An example diagram illustrating the flexible and automatic management of rule metadata, provided for another embodiment of this application;

[0087] Figure 14 An example diagram illustrating a method for generating medical rules, provided as another embodiment of this application;

[0088] Figure 15 A flowchart illustrating a method for verifying medical rule metadata, as provided in another embodiment of this application;

[0089] Figure 16 A flowchart illustrating a method for automatically updating medical rule metadata, as provided in another embodiment of this application;

[0090] Figure 17 A schematic diagram of a medical rule metadata management device provided for another embodiment of this application;

[0091] Figure 18 A schematic diagram of an electronic device for implementing a method for managing medical rule metadata, as provided in another embodiment of this application. Detailed Implementation

[0092] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0093] The term "comprising" and its variations as used herein are open-ended inclusions, meaning "including but not limited to". The term "based on" means "at least partially based on". The term "one embodiment" means "at least one embodiment"; the term "another embodiment" means "at least one additional embodiment"; the term "some embodiments" means "at least some embodiments". Definitions of other terms will be given in the description below.

[0094] It should be noted that the information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of related data must comply with the relevant laws, regulations and standards of the relevant countries and regions.

[0095] It should be noted that the concepts of "first" and "second" mentioned in this application are only used to distinguish different devices, modules or units, and are not used to limit the order of functions performed by these devices, modules or units or their interdependencies.

[0096] It should be noted that the terms "a" and "a plurality of" used in this application are illustrative rather than restrictive, and those skilled in the art should understand that, unless otherwise expressly indicated in the context, they should be understood as "one or more".

[0097] First, the technical terms appearing in this application will be explained:

[0098] Metadata: Data that describes data and is used to better understand and manage knowledge and information in the medical field.

[0099] Field metadata: This includes the definition of data fields, such as data type and length, and is used for data structuring and management.

[0100] Rule metadata includes the definition of the rules, specifies the logic for data processing and management, and is used for data quality and standardization control.

[0101] Medical knowledge metadata: Metadata describing knowledge in the medical field, used to build and manage medical knowledge bases.

[0102] This application provides a method for managing medical rule metadata, such as... Figure 1 As shown, the specific steps include:

[0103] S101. Construct medical knowledge metadata based on medical knowledge meta-model and medical data.

[0104] Among them, the medical knowledge meta-model is a model that defines the attributes of knowledge metadata and the relationships between knowledge metadata; medical data includes at least medical literature, medical books and electronic medical records.

[0105] In the specific implementation of this application, the medical knowledge meta-model includes, but is not limited to, disease ontology, symptom ontology, test ontology, and examination ontology, etc., which are not limited here. Taking the examination ontology as an example, attributes include overview, category, code, etc.; relations include related diseases and related symptoms of the examination, etc.

[0106] like Figure 2 The diagram shown is an example of a medical knowledge meta-model, which includes disease ontology, disease category ontology, etc. Figure 3 As shown, taking the examination of the ontology as an example, after clicking on the disease ontology, you can see its ID, standard name, etc. Taking the adaptation status as an example, after clicking on the adaptation status, you can see its related diseases, related symptoms, etc.

[0107] In the specific implementation of this application, a knowledge entity attribute metamodel can also be defined, such as Figure 4 As shown, taking the attribute meta-model of the inspected entity as an example, the neck ultrasound examination includes attributes such as gland size and presence or absence of echoes.

[0108] Specifically, by combining medical literature, medical books, and electronic medical records, algorithms such as named entity recognition, entity relation extraction, and knowledge fusion iteration are used to build medical knowledge metadata. For example... Figure 5 As shown, hypertension metadata is used as an example.

[0109] S102. Construct a meta-model of medical record fields based on data information and medical knowledge metadata from different business systems of the hospital.

[0110] Optionally, in another embodiment of this application, one implementation of step S102 is as follows: Figure 6 As shown, it includes:

[0111] S601. Based on the first information of the data fields in the data information of the different business systems of the hospital, establish a basic field meta-model.

[0112] The first information of the data field includes at least the field name, type, level, and whether it is a duplicate, but this is not limited here.

[0113] S602. For unstructured basic fields, define the derived field meta-model corresponding to the unstructured basic fields.

[0114] The basic structured fields include, but are not limited to, chief complaint and present medical history, etc., which are not specified here.

[0115] Specifically, in the implementation of this application, natural language processing techniques can be used to define a meta-model of derived fields corresponding to unstructured basic fields, such as chief complaint-symptoms, present medical history-disease, etc. Figure 7 As shown.

[0116] S603. Based on business requirements, define the field meta-model corresponding to the business requirements.

[0117] Business requirements include, but are not limited to, processing and cleaning, etc., which are not specified here. Figure 8 As shown, you can select age, unified medical department, etc. to establish a meta-model of the processing and cleaning fields.

[0118] S604. Combine the basic field meta-model, the derived field meta-model corresponding to the unstructured basic fields, and the field meta-model corresponding to the business requirements to generate the medical record field meta-model.

[0119] In the specific implementation of this application, value range constraints will also be applied to the medical record field metamodel. Based on the dictionary data, national standard fields, and standard metadata documents of each field in the data sources of different business systems of the hospital, the knowledge metadata will be mapped to the case field in the medical record field metamodel, and the value range attributes and value range constraints of the medical record fields will be defined. For example, in the patient information field, gender includes "male", "female", and "other"; age range is 0 to 200 years old; blood type includes "A", "B", "AB", and "O"; the drug dosage field is defined as a floating-point number greater than zero; and the delivery method uses the national standard dictionary delivery method code table, such as... Figure 9The associated value range is shown in the figure.

[0120] In the specific implementation process of this application, the usage paths of various application products will also be mapped based on the path of the medical record field metamodel, as shown in Table 1:

[0121] Serial Number Application Product Path Medical record field metamodel path 1 Admission time Medical Record Cover Page_Visit Information_Visit Time 2 symptom Admission Record - Chief Complaint - Symptoms

[0122] Table 1

[0123] It should be noted that when the metamodel of medical record fields changes, each product can perform source analysis on the operation that modified the field, thereby achieving seamless automatic change mapping. For example, the operation on the field of Medical Record Homepage_Visit Information_Admission Time is as follows:

[0124] Medical Record Homepage - Consultation Information - Consultation Time: Change "Consultation Time" to "Admission Time".

[0125] Map the medical record field metamodel path: Medical Record Homepage_Patient Information_Patient Time. If there are operation records, perform source tracing and parsing on the operation records to generate the latest medical record field metamodel path: Medical Record Homepage_Patient Information_Admission Time.

[0126] The construction of medical knowledge metadata and medical record field metamodels provides strong standardized support for the management of fields and field value domains of medical rule metadata.

[0127] S103. Identify and programmatically manage the calculation criteria in medical rule metadata.

[0128] Among them, medical rule metadata is obtained by cutting medical rule data according to logical operators; medical rule metadata includes fields, calculation methods, and field value ranges; calculation methods include calculation standards, logic, and algorithms, such as average values, and one calculation method corresponds to a corresponding interface program.

[0129] In the specific implementation process of this application, existing medical rule data is summarized, including medical rule data such as electronic medical record data cleaning and processing; quality control, early warning, and reminders of electronic medical record data, as shown in Table 2.

[0130]

[0131]

[0132] Table 2

[0133] It should be noted that since medical rules organize multiple medical rule metadata using logical operators, the rules are first segmented according to the logical operators (and|or|not) to refine them into sample medical rule metadata data, as follows:

[0134] Before cutting: Inpatient medical record homepage - basic information - ID number, check if it is 18 digits. If so, the second to last digit is odd and Inpatient medical record homepage - basic information - gender name == male.

[0135] After cutting: Inpatient medical record homepage - basic information - ID number, check if it is 18 digits. If so, the second to last digit is odd.

[0136] Inpatient Medical Record Front Page - Basic Information - Gender and Name == Male.

[0137] Optionally, in another embodiment of this application, one implementation of step S103 is as follows: Figure 10 As shown, it includes:

[0138] S1001. For each medical rule metadata, denoise the medical rule metadata to obtain a set of denoised medical rule metadata.

[0139] The denoised medical rule metadata set includes at least one denoised medical rule metadata set.

[0140] Specifically, the fields and field value ranges in the medical rule metadata obtained after segmentation are denoised and replaced to avoid affecting subsequent classification operations.

[0141] Before noise reduction: Inpatient medical record homepage - basic information - ID number, determine if it is 18 digits. If so, the second to last digit is odd.

[0142] After noise reduction: A checks if it is 18 bits. If so, the second to last bit is odd.

[0143] Before noise reduction: Inpatient medical record homepage - Basic information - Gender and name == Male.

[0144] After noise reduction: A = B.

[0145] S1002. Divide all the denoised medical rule metadata into preset categories to obtain a preset number of category groups.

[0146] The preset classifications include, but are not limited to, calculation classes, set classes, Boolean classes, event classes, etc., which are not limited here; the data points in each classification group have the minimum Euclidean distance from the cluster center of the classification group; the data points are obtained by vectorizing the denoised medical rule metadata; the cluster center of the classification group is obtained by iterative processing based on all data points and the initial cluster center of the classification group; the initial cluster center of the classification group is a randomly selected data point.

[0147] Specifically, four data points are randomly selected as initial cluster centers. All data points are assigned to the nearest classification group. Based on all the data points assigned to each classification group, the cluster centers of the classification groups are recalculated. Then, the data point assignment and the updating of the cluster centers of the classification groups are iteratively performed until the cluster centers of each classification group no longer change or change at a slow rate, so that the data points of each classification group's cluster centers are aggregated together.

[0148] In the specific implementation of this application, the Euclidean distance can be used to calculate the distance between the data point and each cluster center, as shown in the following formula:

[0149] Where D represents the number of attributes of the data object, d∈D, x i Let i represent data point C. j Let j represent the cluster center point.

[0150] Update the cluster centers by setting them to the average of the cluster's centers. Continue this process until the cluster centers stop changing or change at a slow rate. The formula for updating cluster centers is as follows:

[0151] Among them, S k Let |S| represent the k-th category. k | represents the number of data objects in the k-th category. The summation here refers to the number of categories S. k The sum of all elements in each column attribute.

[0152] Table 3 shows the results after classification:

[0153]

[0154]

[0155] Table 3

[0156] S1003. Determine the calculation method of the denoised medical rule metadata according to the classification group to which it belongs.

[0157] In the specific implementation of this application, after determining the classification group to which the denoised medical rule metadata belongs, the calculation caliber of the denoised medical rule metadata can be obtained by querying the identifier of the denoised medical rule metadata in the classification group to which the denoised medical rule metadata belongs.

[0158] S1004. Convert the calculation method of the denoised medical rule metadata into a program description language.

[0159] In the specific implementation process of this application, the calculation scope of the denoised medical rule metadata is refined (that is, the calculation standard, logic, algorithm, etc. in the calculation scope of the denoised medical rule metadata are subdivided) to obtain multiple refined data. Then, for each refined data, the refined data is converted into a program description language.

[0160] Programming description languages ​​are a prerequisite for programming; they are a type of program design that facilitates programming, as shown in Table 4.

[0161]

[0162] Table 4

[0163] S1005. Based on the program description language, programmatically process the denoised medical rule metadata.

[0164] The medical rule metadata calculation caliber management scheme in this application includes designs for rule denoising, rule metadata classification algorithms, and calculation caliber programs, which can support a more comprehensive calculation caliber and cover all rule requirements.

[0165] In the specific implementation of this application, constant values ​​or preset parameters in the calculation can be extracted as configurable parameters. This allows for adjustment of parameter values ​​as needed without modifying the algorithm code. Parameterization enables flexible calculations based on different scenarios and requirements. For example, in the rule: B occurs N days after A, N can be configured as a parameter.

[0166] In the specific implementation of this application, new calculation methods can be modified and rearranged according to user needs. By freely combining calculation methods, different conditions can be dynamically combined according to business requirements to create new rule metadata calculation methods. For example: Does the document A equals Band contain A?

[0167] In the specific implementation of this application, extension points can be reserved in the calculation caliber program, allowing the insertion of custom logic JavaScript at specific execution points. These specific execution points are pre-set points that allow insertion operations, and additional logical functions can be implemented by writing custom extension code. For example, if the existing calculation caliber is: A includes B, before the inclusion execution point, normalization processing for A is inserted.

[0168] S104. Manage the fields in the medical rule metadata according to the medical record field metamodel.

[0169] It should be noted that the medical record field metamodel defines the key attributes of the fields used in the rules, such as... Figure 11As shown, this includes name, data type, length, etc. This makes rule item field management more intuitive and flexible, while also possessing good scalability to adapt to future business changes.

[0170] S105. Manage the field value ranges in the medical rule metadata based on the field value ranges in the medical knowledge metadata and the medical record field metamodel.

[0171] Specifically, the management of the value range of rule metadata fields can be based on the value range in the field metamodel and medical knowledge metadata, and the value range of rule metadata can be controlled and managed in terms of standards and boundaries.

[0172] In addition, this application also supports the flexible use of SQL queries for value range management, in order to adapt to the complex rule requirements of different hospitals, such as... Figure 12 As shown.

[0173] 1) The metadata of a certain medical rule requires the selection of medications prescribed within the most recent year for the value field. The SQL value field management is as follows:

[0174] SELECT drug_name FROM medication_records WHERE prescription_date>=NOW()-INTERVAL 1YEAR;

[0175] 2) The value range in the metadata of a certain medical rule requires penicillin-type drugs to be present in the actual database. The SQL value range management is as follows:

[0176] SELECT drug_name FROM allergy_records WHERE drug_category='penicillin'.

[0177] After implementing flexible management of calculation methods, fields, and field value ranges in medical rule metadata through this application, flexible management of rule metadata can be achieved automatically, such as... Figure 13 The interface shown in the document.

[0178] It is understandable that different medical rules can be freely composed of one or more medical rule metadata; for specific methods, please refer to [link / reference]. Figure 14 It can combine multiple medical rule metadata into logical expressions using logical operators, and finally generate medical rules.

[0179] Based on the management of medical rule metadata in this application, the medical rule metadata can be standardized. For example, rule metadata: medical record homepage_discharge diagnosis_diagnosis name, including hypertension.

[0180]

[0181] Different rule metadata forms a rule, and the rule is also managed in a standardized manner, as follows:

[0182] Rules: Medical record cover page_Discharge diagnosis_Diagnosis name, including hypertension and hospitalization_Medical record cover page_Basic information_Gender name equal to male and hospitalization_Medical order information_Medical order item name, including antibiotics.

[0183]

[0184] In the specific implementation of this application, in order to maintain the real-time nature and consistency of medical rule metadata with current medical record data, automatic detection and updating of medical rule metadata is required. This aims to promptly address changes in the medical field metamodel and medical knowledge metadata, ensuring the effectiveness and accuracy of the medical rule metadata. Figure 15 As shown, one implementation of the method for managing medical rule metadata also includes:

[0185] S1501. Extract the fields and field value ranges from the current medical rule metadata.

[0186] S1502. Use the current version of the medical record field metamodel and medical knowledge metadata to validate the fields and field value ranges in the current medical rule metadata, and obtain the validation results.

[0187] Specifically, the fields and field value ranges of the medical rule metadata stored in the current version of the medical record field metamodel and medical knowledge metadata are extracted. The fields and field value ranges of the medical rule metadata stored in the current version of the medical record field metamodel and medical knowledge metadata are compared with the fields and field value ranges in the current medical rule metadata. If the fields and field value ranges of the medical rule metadata stored in the current version of the medical record field metamodel and medical knowledge metadata are consistent with the fields and field value ranges in the current medical rule metadata, a verification result of passing the verification is generated. If there are fields and / or field value ranges of the medical rule metadata stored in the current version of the medical record field metamodel and medical knowledge metadata that fail the verification, a verification result of failing the verification is generated.

[0188] S1503. If the verification result shows that there are fields and / or field value ranges in the current medical rule metadata that have not passed the verification, then the current medical rule metadata will be marked as an invalid rule.

[0189] Optionally, in another embodiment of this application, one implementation of the method for managing medical rule metadata is as follows: Figure 16 As shown, it also includes:

[0190] S1601. When the medical record field metamodel changes, the operation record of the change in the medical record field metamodel is traced and parsed, and the latest medical rule metadata fields are generated.

[0191] For example, the operation record for changing the medical record field metamodel is: Medical Record Homepage_Consultation Information_Consultation Time: Modified from "Consultation Time" to "Admission Time". That is, the medical rule metadata before the change was Medical Record Homepage_Consultation Information_Consultation Time, and the medical rule metadata after the change is Medical Record Homepage_Consultation Information_Admission Time. Then, we can trace the source according to the path of the medical record field metamodel to find the application product that contains the medical rule metadata before the change (such as Medical Record Homepage_Consultation Information_Consultation Time), and change the medical rule metadata (such as Medical Record Homepage_Consultation Information_Consultation Time) in this application product to Medical Record Homepage_Consultation Information_Admission Time.

[0192] S1602, Operation logs for recording the update process of medical rule metadata.

[0193] Similarly, operation records of medical knowledge metadata can also be traced and parsed to generate the latest rule metadata field value range and record the operation records of the rule metadata update process, so as to track the automatic update history of medical rule metadata.

[0194] As can be seen from the above scheme, this application provides a method for managing medical rule metadata. By constructing medical knowledge metadata based on medical knowledge metadata model and medical data, and constructing a medical record field metadata model based on data information and medical knowledge metadata from different business systems of the hospital, the calculation scope, fields and field value range in medical rule metadata are standardized and managed through medical knowledge metadata and medical record field metadata model, so as to achieve consistency and maintainability of rules.

[0195] This application provides a device for managing medical rule metadata, such as... Figure 17 As shown, it specifically includes:

[0196] The first building unit 1701 is used to build medical knowledge metadata based on the medical knowledge meta-model and medical data.

[0197] Among them, the medical knowledge meta-model is a model that defines the attributes of knowledge metadata and the relationships between knowledge metadata; medical data includes at least medical literature, medical books and electronic medical records.

[0198] The second building unit 1702 is used to construct a medical record field metamodel based on data information and medical knowledge metadata from different business systems of the hospital.

[0199] Management unit 1703 is used to identify and programmatically manage the calculation criteria in medical rule metadata.

[0200] Among them, medical rule metadata is obtained by cutting medical rule data according to logical operators; medical rule metadata includes fields, calculation methods, and field value ranges; calculation methods include calculation standards, logic, and algorithms.

[0201] Management unit 1703 is also used to manage fields in medical rule metadata based on the medical record field metamodel.

[0202] Management unit 1703 is also used to manage the field value ranges in medical rule metadata based on the field value ranges in medical knowledge metadata and medical record field metamodel.

[0203] For details on the specific working process of the units disclosed in the above embodiments of this application, please refer to the corresponding method embodiments, such as... Figure 1 As shown, it will not be elaborated further here.

[0204] As can be seen from the above scheme, this application provides a management device for medical rule metadata. The first construction unit 1701 constructs medical knowledge metadata based on medical knowledge metadata model and medical data. The second construction unit 1702 constructs medical record field metadata model based on data information and medical knowledge metadata from different business systems of the hospital. The management unit 1703 manages the calculation scope, fields and field value range in medical rule metadata in a standardized manner through medical knowledge metadata and medical record field metadata model, so as to achieve consistency and maintainability of rules.

[0205] The functions described above in this document can be performed, at least in part, by one or more hardware logic components. For example, exemplary types of hardware logic components that can be used, without limitation, include: Field Programmable Gate Arrays (FPGAs), Application-Specific Integrated Circuits (ASICs), Application Standard Products (ASSPs), System-on-Chip (SoCs), Complex Programmable Logic Devices (CPLDs), and so on.

[0206] Another embodiment of this application provides an electronic device, such as... Figure 18 As shown, it includes:

[0207] One or more processors 1801.

[0208] Storage device 1802, on which one or more programs are stored.

[0209] When the one or more programs are executed by the one or more processors 1801, the one or more processors 1801 implement the medical rule metadata management method as described in any of the above embodiments.

[0210] Another embodiment of this application provides a computer storage medium storing a computer program thereon, wherein the computer program, when executed by a processor, implements the medical rule metadata management method as described in any of the above embodiments.

[0211] In the context of this application, a machine-readable medium can be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, apparatus, or device. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. Machine-readable media can be, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0212] It should be noted that the computer-readable medium described above in this application can be a computer-readable signal medium, a computer-readable storage medium, or any combination of the two. A computer-readable storage medium can be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of a computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In this application, a computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. In this application, a computer-readable signal medium can include a data signal propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals can take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A computer-readable signal medium can be any computer-readable medium other than a computer-readable storage medium, which can send, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium can be transmitted using any suitable medium, including but not limited to: wires, optical fibers, RF (radio frequency), etc., or any suitable combination thereof.

[0213] The aforementioned computer-readable medium may be included in the aforementioned electronic device; or it may exist independently and not assembled into the electronic device.

[0214] Another embodiment of this application provides a computer program product, which, when executed, performs a method for managing medical rule metadata as described above.

[0215] Specifically, according to embodiments of this application, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of this application include a computer program product comprising a computer program carried on a non-transitory computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via a communication device, or installed from a storage device, or installed from a ROM. When the computer program is executed by a processing device, it performs the functions defined in the methods of the embodiments of this application.

[0216] Although the subject matter has been described using language specific to structural features and / or methodological logic, it should be understood that the subject matter defined in the appended claims is not necessarily limited to the specific features or actions described above. Rather, the specific features and actions described above are merely illustrative examples of implementing the claims.

[0217] While several specific implementation details are included in the foregoing discussion, these should not be construed as limiting the scope of this application. Certain features described in the context of individual embodiments may also be implemented in combination in a single embodiment. Conversely, various features described in the context of a single embodiment may also be implemented individually or in any suitable sub-combination in multiple embodiments.

[0218] The above description is merely a preferred embodiment of this application and an explanation of the technical principles employed. Those skilled in the art should understand that the scope of this application is not limited to technical solutions formed by specific combinations of the above-described technical features, but should also cover other technical solutions formed by arbitrary combinations of the above-described technical features or their equivalents without departing from the above-described application concept. For example, technical solutions formed by substituting the above-described features with (but not limited to) technical features with similar functions claimed in this application.

Claims

1. A method for managing medical rule metadata, characterized in that, include: Based on a medical knowledge meta-model and medical data, medical knowledge metadata is constructed; wherein, the medical knowledge meta-model is a model that defines the attributes of knowledge metadata and the relationships between knowledge metadata; the medical data includes at least medical literature, medical books, and electronic medical records. Based on data information from different business systems of the hospital and the aforementioned medical knowledge metadata, a meta-model of medical record fields is constructed. The calculation methods in medical rule metadata are identified and managed programmatically; wherein, the medical rule metadata is obtained by segmenting medical rule data according to logical operators; the medical rule metadata includes fields, calculation methods, and field value ranges; the calculation methods include calculation standards, logic, and algorithms; The fields in the medical rule metadata are managed based on the aforementioned medical record field metamodel; The field value ranges in the medical rule metadata are managed based on the medical knowledge metadata and the field value ranges in the medical record field metamodel.

2. The method for managing medical rule metadata according to claim 1, characterized in that, The medical record field meta-model is constructed based on data information from different business systems of the hospital and the medical knowledge metadata, including: A basic field meta-model is established based on the first information of the data fields in the data information from the data sources of different business systems of the hospital; wherein, the first information of the data fields includes at least the field name, type, level and whether it is duplicate information; For unstructured basic fields, define the derived field metamodel corresponding to the unstructured basic fields; Based on business requirements, define the field metamodel corresponding to the business requirements; By combining the basic field metamodel, the derived field metamodel corresponding to the unstructured basic field, and the field metamodel corresponding to the business requirements, a medical record field metamodel is generated.

3. The method for managing medical rule metadata according to claim 2, characterized in that, Also includes: Based on the dictionary data, national standard fields, and standard metadata documents of each field in the data sources of different business systems of the hospital, the knowledge metadata is mapped to the case field in the medical record field metamodel, and the value range attribute and value range constraint of the medical record field are defined.

4. The method for managing medical rule metadata according to claim 1, characterized in that, The identification and programmatic management of the calculation criteria in medical rule metadata includes: For each of the medical rule metadata, the medical rule metadata is denoised to obtain a denoised medical rule metadata set; wherein, the denoised medical rule metadata set includes at least one denoised medical rule metadata. All the denoised medical rule metadata is divided into a preset number of categories according to a predefined classification. The data points in each category have the smallest Euclidean distance to the cluster center of that category. The data points are obtained by vectorizing the denoised medical rule metadata. The cluster centers of each category are obtained through iterative processing based on all data points and the initial cluster center of the category. The initial cluster center of each category is a randomly selected data point. The calculation method for the denoised medical rule metadata is determined based on the classification group to which it belongs. The calculation method of the denoised medical rule metadata is converted into a program description language; The denoised medical rule metadata is programmed according to the program description language.

5. The method for managing medical rule metadata according to claim 1, characterized in that, Also includes: Extract constant values ​​or preset parameters from the calculation caliber into configurable parameters.

6. The method for managing medical rule metadata according to claim 1, characterized in that, Also includes: Receive and respond to a calculation caliber management request; wherein, the calculation caliber management request includes modifying the calculation caliber and arranging or combining the calculation calibers.

7. The method for managing medical rule metadata according to claim 1, characterized in that, The program for calculating the aperture has reserved expansion points.

8. The method for managing medical rule metadata according to claim 1, characterized in that, Also includes: Extract the fields and field value ranges from the current medical rule metadata; The current version of the medical record field metamodel and medical knowledge metadata are used to validate the fields and field value ranges in the current medical rule metadata, and the validation results are obtained. If the verification result shows that there are fields and / or field value ranges in the current medical rule metadata that have failed the verification, then the current medical rule metadata will be marked as an invalid rule.

9. The method for managing medical rule metadata according to claim 1, characterized in that, Also includes: When the medical record field metamodel changes, the operation records of the medical record field metamodel change are traced and parsed, and the latest medical rule metadata fields are generated. Operation logs recording the update process of the aforementioned medical rule metadata.

10. A management device for medical rule metadata, characterized in that, include: The first construction unit is used to construct medical knowledge metadata based on a medical knowledge meta-model and medical data; wherein, the medical knowledge meta-model is a model that defines the attributes of knowledge metadata and the relationships between knowledge metadata; the medical data includes at least medical literature, medical books, and electronic medical records. The second construction unit is used to construct a medical record field meta-model based on data information from data sources in different business systems of the hospital and the medical knowledge metadata. The management unit is used to identify and programmatically manage the calculation methods in the medical rule metadata; wherein, the medical rule metadata is obtained by segmenting medical rule data according to logical operators; the medical rule metadata includes fields, calculation methods, and field value ranges; the calculation method includes calculation standards, logic, and algorithms; The management unit is also used to manage the fields in the medical rule metadata according to the medical record field metamodel; The management unit is also used to manage the field value ranges in the medical rule metadata based on the medical knowledge metadata and the field value ranges in the medical record field metamodel.

Images