Medical data quality assessment method and device, equipment and storage medium

Abstract

The invention discloses a medical data quality assessment method, device and equipment and a storage medium, and relates to the technical field of data quality assessment, and the method comprises the steps: determining a dimension verification rule corresponding to a medical data quality assessment dimension; verifying the medical data based on the dimension verification rule to obtain a data verification result; the value of the medical data is evaluated through a value evaluation dimension, a value evaluation result is obtained, and the value evaluation dimension is determined based on user demands; and generating a data quality evaluation result corresponding to the medical data based on the data verification result and the value evaluation result. By applying the technical scheme, the technical problem that the medical data quality evaluation method in the prior art generally adopts a unified quality evaluation system, and cannot fully consider special requirements and application scenes of different user roles in a data use process, so that the practicability is not high is solved.

Description

Technical Field

[0001] The present application relates to the technical field of data quality assessment, and in particular to a medical data quality assessment method, apparatus, device and storage medium. Background Art

[0002] Data quality assessment methods are to link data quality attributes with measurable items (measured values) that can be accurately calculated. For example, the ratio of the total number of missing values ​​to the total number of records in a database can be used as a measure of the "completeness" attribute. Existing medical data quality assessment methods usually break down the assessment content into multiple data quality dimensions, each of which represents a specific aspect or feature of data quality. In the medical field, data users include but are not limited to clinicians, researchers, etc. Different end users have significantly different expectations and requirements for data accuracy, completeness, consistency, and timeliness. However, existing medical data quality assessment methods often adopt a unified quality evaluation system. Therefore, when conducting quality evaluation, they cannot fully consider the special needs and application scenarios of different user roles in the process of data use, resulting in low practicality.

[0003] The above contents are only used to assist in understanding the technical solution of the present invention and do not constitute an admission that the above contents are prior art. Summary of the invention

[0004] The main purpose of this application is to provide a medical data quality assessment method, device, equipment and storage medium, aiming to solve the technical problem that the medical data quality assessment method in the prior art usually adopts a unified quality evaluation system, which cannot fully consider the special needs and application scenarios of different user roles in the process of data use, resulting in low practicality.

[0005] To achieve the above objectives, the present application proposes a method for evaluating the quality of medical data, the method comprising:

[0006] Determine the dimension verification rules corresponding to the medical data quality assessment dimensions;

[0007] Verify the medical data based on the dimension verification rule to obtain a data verification result;

[0008] Evaluating the value of the medical data through value evaluation dimensions to obtain a value evaluation result, wherein the value evaluation dimensions are determined based on user needs;

[0009] A data quality assessment result corresponding to the medical data is generated based on the data verification result and the value assessment result.

[0010] In one embodiment, the medical data quality assessment dimension includes: an accuracy dimension; the step of determining a dimension verification rule corresponding to the medical data quality assessment dimension includes:

[0011] If the medical data quality assessment dimension is an accuracy dimension, determining the dimension verification rule corresponding to the accuracy dimension as the accuracy verification rule;

[0012] The step of verifying the medical data based on the dimension verification rule to obtain the data verification result includes:

[0013] Determine data source constraints, data uniqueness constraints, enumeration value range limitation constraints and data verification rules based on the accuracy verification rules;

[0014] Verify the medical data through the data source constraint, the data uniqueness constraint, the enumeration value range limitation constraint and the data verification rule to obtain a data verification result;

[0015] Among them, the data source constraint is provided with an identity authentication system, and the identity authentication system is used to score the medical data; the data uniqueness constraint is provided with a number of unique fields, and the unique fields are used to perform uniqueness detection on the medical data; the enumeration value domain limitation constraint is provided with a number of enumeration value domains, and the enumeration value domains are used to perform enumeration value detection on the medical data; the data verification rule is used to determine the mean and standard deviation corresponding to the medical data, and judge whether the medical data has abnormalities based on the mean and the standard deviation.

[0016] In one embodiment, the medical data quality assessment dimension includes: an integrity dimension; the step of determining the dimension verification rule corresponding to the medical data quality assessment dimension includes:

[0017] If the medical data quality assessment dimension is an integrity dimension, determining the dimension verification rule corresponding to the integrity dimension as the integrity verification rule;

[0018] The step of verifying the medical data based on the dimension verification rule to obtain the data verification result includes:

[0019] Determine the attribute non-empty constraint and the conditional non-empty constraint based on the integrity check rule;

[0020] Verifying the medical data through the attribute non-empty constraint and the conditional non-empty constraint to obtain a data verification result;

[0021] Among them, the attribute non-empty constraint is used to detect in real time whether there are abnormal values ​​when data is inserted and / or updated in the medical data, and the abnormal values ​​include null values ​​and missing values; the conditional non-empty constraint is used to perform non-empty constraints on non-empty medical data fields, and the non-empty medical data fields include: patient identifier, diagnosis code, treatment date and drug dosage.

[0022] In one embodiment, the medical data quality assessment dimension includes: a timeliness dimension; the step of determining a dimension verification rule corresponding to the medical data quality assessment dimension includes:

[0023] If the medical data quality assessment dimension is a timeliness dimension, then the dimension verification rule corresponding to the timeliness dimension is determined as the timeliness verification rule;

[0024] The step of verifying the medical data based on the dimension verification rule to obtain the data verification result includes:

[0025] Timely processing of medical data based on timeliness verification rules, the timeliness processing includes: timely data upload processing;

[0026] When the processing is completed, the time series records corresponding to the medical data are verified based on the event occurrence sequence corresponding to the medical data to obtain a data verification result.

[0027] In one embodiment, the medical data quality assessment dimension includes: a normative dimension; the step of determining the dimension verification rule corresponding to the medical data quality assessment dimension includes:

[0028] If the medical data quality assessment dimension is a normative dimension, determining the dimension verification rule corresponding to the normative dimension as the normative verification rule;

[0029] The step of verifying the medical data based on the dimension verification rule to obtain the data verification result includes:

[0030] Obtain the data storage format, data encoding standard and data transmission protocol corresponding to medical data;

[0031] Based on the data storage format, the data encoding standard and the data transmission protocol, the medical data is subjected to a normative verification through the normative verification rules to obtain a data verification result.

[0032] In one embodiment, the medical data quality assessment dimension includes: a consistency dimension; the step of determining the dimension verification rule corresponding to the medical data quality assessment dimension includes:

[0033] If the medical data quality assessment dimension is a consistency dimension, determining the dimension verification rule corresponding to the consistency dimension as the consistency verification rule;

[0034] The step of verifying the medical data based on the dimension verification rule to obtain the data verification result includes:

[0035] Determine equivalent consistency constraints, logical consistency constraints, diagnosis and treatment consistency constraints, and distributed data consistency constraints based on the consistency verification rules;

[0036] Verifying the medical data through the equivalent consistency constraint, the logical consistency constraint, the diagnosis and treatment consistency constraint, and the distributed data consistency constraint to obtain a data verification result;

[0037] Among them, the equivalence consistency constraint is used to verify the numerical equivalence between the first data items in the medical data; the logical consistency constraint is used to verify the logical dependencies between the second data items in the medical data; the diagnosis and treatment consistency constraint is used to verify the logical consistency between the user diagnosis information and the treatment plan, and the correspondence between the diagnosis code in the diagnosis information and the treatment measures in the treatment plan is mapped through a knowledge graph; the distributed data consistency constraint is used to verify the consistency between the storage location and application of the third data item in the medical data.

[0038] In one embodiment, the medical data quality assessment dimension includes: a validity dimension; the step of determining the dimension verification rule corresponding to the medical data quality assessment dimension includes:

[0039] If the medical data quality assessment dimension is a validity dimension, determining the dimension verification rule corresponding to the validity dimension as the validity verification rule;

[0040] The step of verifying the medical data based on the dimension verification rule to obtain the data verification result includes:

[0041] Determine the data type, structured degree and data format corresponding to medical data;

[0042] Based on the data type, the degree of structuring and the data format, the medical data is verified using the validity verification rules to obtain a data verification result.

[0043] In addition, to achieve the above objectives, the present application also proposes a medical data quality assessment device, the device comprising:

[0044] A verification rule determination module is used to determine the dimension verification rules corresponding to the medical data quality assessment dimension;

[0045] A verification result acquisition module, used to verify the medical data based on the dimension verification rule to obtain a data verification result;

[0046] A value assessment module, used to assess the value of the medical data through value assessment dimensions to obtain a value assessment result, wherein the value assessment dimensions are determined based on user needs;

[0047] An evaluation result generating module is used to generate a data quality evaluation result corresponding to the medical data based on the data verification result and the value evaluation result.

[0048] In addition, to achieve the above-mentioned purpose, the present application also proposes a medical data quality assessment device, which includes: a memory, a processor, and a computer program stored in the memory and executable on the processor, and the computer program is configured to implement the steps of the medical data quality assessment method described above.

[0049] In addition, to achieve the above-mentioned purpose, the present application also proposes a storage medium, which is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by a processor, the steps of the medical data quality assessment method described above are implemented.

[0050] The present application provides a medical data quality assessment method, which discloses dimension verification rules corresponding to medical data quality assessment dimensions; verifying medical data based on the dimension verification rules to obtain data verification results; evaluating the value of medical data through value assessment dimensions to obtain value assessment results, wherein the value assessment dimensions are determined based on user needs; generating data quality assessment results corresponding to the medical data based on the data verification results and the value assessment results; compared with the medical data quality assessment methods in the prior art that usually adopt a unified quality evaluation system, which makes it impossible to fully consider the special needs and application scenarios of different user roles in the data use process when performing quality evaluation, the present invention can use the value assessment dimensions determined based on user needs to evaluate the value of medical data to obtain value assessment results, and then generate the final data quality assessment results based on the data verification results and the value assessment results of the medical data, thereby solving the technical problem that the medical data quality assessment methods in the prior art usually adopt a unified quality evaluation system, which cannot fully consider the special needs and application scenarios of different user roles in the data use process, resulting in low practicality. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0052] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0053] Figure 1 A flowchart of the first embodiment of the medical data quality assessment method of the present application is provided;

[0054] Figure 2 A diagram showing the medical data quality evaluation dimensions in the medical data quality evaluation method of this application;

[0055] Figure 3 A flowchart of the second embodiment of the medical data quality assessment method of the present application is provided;

[0056] Figure 4 This is a diagram of a medical data quality assessment framework in the medical data quality assessment method of this application;

[0057] Figure 5 This is a schematic diagram of the module structure of the medical data quality assessment device according to an embodiment of the present application;

[0058] Figure 6 Schematic diagram of the device structure of the hardware operating environment involved in the medical data quality assessment method in the embodiment of the present application.

[0059] The purpose, features and advantages of this application will be further described in conjunction with the embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0060] It should be understood that the specific embodiments described herein are only used to explain the technical solutions of the present application and are not used to limit the present application.

[0061] In order to better understand the technical solution of the present application, a detailed description will be given below in conjunction with the accompanying drawings and specific implementation methods.

[0062] The main solution of the embodiment of the present application is: determine the dimension verification rules corresponding to the medical data quality assessment dimension; verify the medical data based on the dimension verification rules to obtain data verification results; evaluate the value of the medical data through the value assessment dimension to obtain a value assessment result, and the value assessment dimension is determined based on user needs; generate a data quality assessment result corresponding to the medical data based on the data verification result and the value assessment result.

[0063] Because the medical data quality assessment methods in the prior art usually adopt a unified quality evaluation system, it is impossible to fully consider the special needs and application scenarios of different user roles in the process of data use when performing quality evaluation.

[0064] The present application provides a solution, which can evaluate the value of medical data using a value assessment dimension determined based on user needs, obtain a value assessment result, and then generate a final data quality assessment result based on the data verification result and the value assessment result of the medical data, thereby solving the technical problem that the medical data quality assessment method in the prior art usually adopts a unified quality evaluation system, which cannot fully consider the special needs and application scenarios of different user roles in the process of data use, resulting in low practicality.

[0065] It should be noted that the execution subject of this embodiment can be a computing service device with data processing, network communication and program running functions, such as a tablet computer, a personal computer, a mobile phone, etc., or an electronic device capable of realizing the above functions, a medical data quality assessment device, etc. The following takes the medical data quality assessment device as an example (hereinafter referred to as the device) to illustrate this embodiment and the following embodiments.

[0066] Based on this, the present application embodiment provides a method for evaluating the quality of medical data. Figure 1 , Figure 1 This is a flowchart of the first embodiment of the medical data quality assessment method of the present application.

[0067] In this embodiment, the medical data quality assessment method includes steps S10 to S40:

[0068] Step S10: Determine the dimension verification rules corresponding to the medical data quality assessment dimension.

[0069] It should be noted that the data quality dimension is a feature or part of information used to classify information and data requirements. The above-mentioned medical data quality assessment dimension can be the specific indicator and standard used to measure the quality of medical data in this embodiment. Correspondingly, the above-mentioned dimension verification rules can be the rules used when verifying medical data using indicators of different dimensions.

[0070] Step S20: verify the medical data based on the dimension verification rule to obtain a data verification result.

[0071] It should be understood that medical data can be various types of data generated in the fields of medical research, clinical practice, public health management, etc. In practical applications, these data come from various aspects of medical care, including but not limited to electronic health records (EHR), electronic medical records (EMR), medical imaging, genomic data, patient self-report data, medical equipment and sensor data, etc. Like general big data, medical big data also has the commonality of 5V, namely Volume, Velocity, Variety, Value, and Veracity. In addition, from the perspective of data quality assessment, medical big data also has the characteristics of high sensitivity, spatiotemporal correlation, and complex data structure.

[0072] In this embodiment, refer to Figure 2 , Figure 2 This is a diagram showing the medical data quality evaluation dimensions in the medical data quality evaluation method of this application. Figure 2As shown, the medical data quality assessment dimensions in this embodiment may include but are not limited to accuracy dimension, standardization dimension, integrity dimension, timeliness dimension, effectiveness dimension and consistency dimension. Among them, using the verification rules corresponding to the accuracy dimension to verify medical data may include: data source constraints, data uniqueness constraints, enumeration value range limitation constraints and the formulation of data verification rules to ensure that the value range and logic of medical data are consistent with established business rules and standards; using the verification rules corresponding to the standardization dimension to verify medical data may include data representation and coding standardization to ensure that the storage and transmission of medical data follow standardized format protocols; using the verification rules corresponding to the integrity dimension to verify medical data may include: attribute non-empty constraints and conditional non-empty constraints to ensure that data records contain all necessary information items, and measure whether the data set is exhaustive by detecting the existence of data, thereby avoiding information omissions; using the verification rules corresponding to the timeliness dimension to verify medical data can Including: real-time data update, logical consistency and version control to ensure that the data can accurately reflect the real situation of the medical entity it represents (such as patient status, medical activities, etc.) at a specific time point or time period. A series of specifications and requirements; using the verification rules corresponding to the validity dimension to verify medical data can include: the difficulty of visual analysis, so as to visualize the data quality evaluation results, and users can intuitively obtain the total number of rule templates, the application efficiency of the rules, the coverage of the data table, and the scores of each indicator; using the verification rules corresponding to the consistency dimension to verify medical data can include: equivalent consistency constraints, logical consistency constraints, diagnosis and treatment consistency constraints, and distributed data consistency constraints to ensure the internal logical consistency of the data and compatibility across data sets. After verifying the medical data through the dimension verification rules corresponding to the above dimensions, the corresponding data verification results can be obtained.

[0073] Step S30: Evaluate the value of the medical data through value evaluation dimensions to obtain a value evaluation result, wherein the value evaluation dimensions are determined based on user needs.

[0074] It can be understood that the above-mentioned value assessment dimensions can be dimensions used to assess the value of medical data.

[0075] In practical applications, given the complexity and diversity of medical data, different stakeholders have different expectations and demands for data quality, but in general, they can be summarized into three main dimensions: clinical decision support, disease monitoring and prevention, and clinical research and drug development. Among them, for clinical decision support: medical data provides key information resources for clinical medical practice, including but not limited to detailed patient cases, medical imaging data, etc. With these data, medical professionals can make more accurate and timely clinical diagnosis and treatment decisions, thereby improving the quality and efficiency of medical services. For disease monitoring and prevention: medical data plays a vital role in disease monitoring and prevention. Through systematic analysis of data, it can effectively track the epidemic trend of diseases, reduce the possibility of disease transmission, and protect public health safety. For clinical research and drug development: medical data provides valuable data support for clinical research and drug development. Through in-depth analysis of clinical trial data and patient medical records, researchers can evaluate the safety, effectiveness and potential side effects of drugs, thereby providing a scientific basis for the development and market access of new drugs. In addition, high-quality medical data can also promote the innovation of medical knowledge and the advancement of medical data. This embodiment can respectively evaluate the value of medical data in three dimensions: clinical decision support, disease monitoring and prevention, and clinical research and drug development, and obtain corresponding evaluation results, which can reflect the value of the medical data.

[0076] In this embodiment, if a dataset is of greater value, it will naturally be downloaded by more doctors. Therefore, the value of the dataset can be intuitively reflected through the number of downloads and collections of each dataset. In addition, since each user has authenticated his or her research direction, department, etc., the platform can use this user information to create a separate user profile for each dataset. For example, if a dataset is downloaded by more dermatologists, it means that the dataset is of greater value to dermatology. The platform will push the dataset to the appropriate user through the recommendation system combined with the above information.

[0077] Step S40: Generate a data quality assessment result corresponding to the medical data based on the data verification result and the value assessment result.

[0078] It should be understood that after obtaining the data verification results and value assessment results corresponding to the medical data, the device can accurately capture the overall quality of the medical data based on the data verification results and value assessment results, thereby obtaining the final data quality assessment results of the medical data.

[0079] It should be noted that in order to improve the utilization efficiency and application value of medical data, this solution has developed a refined and differentiated data quality evaluation method. Through in-depth analysis of the data usage behavior and needs of different user roles, a data quality evaluation index system that can reflect the needs of different users is constructed, thereby realizing the personalization and customization of data quality management. Through this method, the specific requirements of different terminals in the use of medical data can be better met, and the availability and reliability of data can be met. In addition, in order to better utilize the semantic information in medical data, this solution can also introduce a large language model, which can specifically identify patterns and trends in the data through a variety of pre-defined prompts, parse complex medical terms and concepts, help standardize the expression and structure of medical data, reduce ambiguity and errors, and help semantic alignment and interoperability between different data sets, thereby achieving the versatility and accuracy of data quality assessment. By introducing a large language model, this solution can be adapted to different medical scenarios and medical data in different formats.

[0080] In this embodiment, in view of the diversity of values ​​carried by medical data in various application scenarios, the construction of the evaluation index system and its weight distribution need to be customized for the specific use of the data. In other words, the final use of the data will directly affect the selection and priority ranking of the data quality evaluation criteria, thereby ensuring that the evaluation process can accurately reflect the value and utility of the data in a specific application context. In practical applications, when scoring the quality evaluation, the platform can first give a specific quality evaluation report for each data set, and the content of the report contains all the content mentioned above, such as certain values ​​that violate the uniqueness constraint, or which direction the data set is more valuable for research, etc. In addition, a total score will be given, which is obtained by multiplying the scores of each evaluation system by the weight and finally adding them up. The weight of each evaluation system is determined by discussing with experts in a meeting. Finally, the data quality of medical data can be evaluated based on the evaluation system and the weight corresponding to the evaluation system.

[0081] The present embodiment provides a medical data quality assessment method, which discloses a dimension verification rule corresponding to a medical data quality assessment dimension; verifies the medical data based on the dimension verification rule to obtain a data verification result; evaluates the value of the medical data through a value assessment dimension to obtain a value assessment result, wherein the value assessment dimension is determined based on user needs; generates a data quality assessment result corresponding to the medical data based on the data verification result and the value assessment result; compared with the medical data quality assessment method in the prior art which usually adopts a unified quality evaluation system, which makes it impossible to fully consider the special needs and application scenarios of different user roles in the process of data use when performing quality evaluation, since the present embodiment can use the value assessment dimension determined based on user needs to evaluate the value of medical data to obtain a value assessment result, and then generate the final data quality assessment result based on the data verification result and the value assessment result of the medical data, the technical problem that the medical data quality assessment method in the prior art usually adopts a unified quality evaluation system, which cannot fully consider the special needs and application scenarios of different user roles in the process of data use, resulting in low practicality.

[0082] Based on the first embodiment of the present application, in the second embodiment of the present application, the same or similar contents as those in the above-mentioned embodiment 1 can be referred to the above introduction, and will not be repeated in the following. Figure 3 , Figure 3 A flowchart of the second embodiment of the medical data quality assessment method of the present application is provided.

[0083] In this embodiment, the medical data quality assessment dimension includes: accuracy dimension; step S10 includes:

[0084] Step S101: If the medical data quality assessment dimension is an accuracy dimension, a dimension verification rule corresponding to the accuracy dimension is determined as an accuracy verification rule.

[0085] Accordingly, the step S20 includes:

[0086] Step S201: Determine data source constraints, data uniqueness constraints, enumeration value range limitation constraints and data verification rules based on the accuracy verification rules.

[0087] It should be noted that the above accuracy verification rules may be rules for performing accuracy verification on medical data.

[0088] Step S202: verify the medical data through the data source constraint, the data uniqueness constraint, the enumeration value range limitation constraint and the data verification rule to obtain a data verification result.

[0089] Among them, the data source constraint is provided with an identity authentication system, and the identity authentication system is used to score the medical data; the data uniqueness constraint is provided with a number of unique fields, and the unique fields are used to perform uniqueness detection on the medical data; the enumeration value domain limitation constraint is provided with a number of enumeration value domains, and the enumeration value domains are used to perform enumeration value detection on the medical data; the data verification rule is used to determine the mean and standard deviation corresponding to the medical data, and judge whether the medical data has abnormalities based on the mean and the standard deviation.

[0090] It should be noted that the accuracy verification rules in this embodiment may be provided with: data source constraints, data uniqueness constraints, enumeration value domain limitation constraints and the formulation of data verification rules. Among them, the data source constraint focuses on the original source of the data. For example, if the data comes from a high-level medical institution, such as a tertiary hospital or a secondary hospital, its credibility is usually high, so it will receive a higher evaluation in the evaluation system. In view of the data source constraint, in this embodiment, a set of identity authentication systems can be designed for users of the platform. Users can update the information of their hospitals or institutions through real-name authentication. When users upload data, the platform can automatically label the data with user-related information. In addition, the platform also has a scoring function, and users can score the quality of data sets uploaded by other users. Therefore, if a user's previously uploaded data sets have received high evaluations, the next data set will receive a higher reliability evaluation.

[0091] In practical applications, the data source score of a data set can be composed of three parts: the institution score, the previous score of the uploading user, and the current score of the data set. Among them, the institution score rules can be: first-level hospital: 100 points; second-level hospital: 90 points; third-level A-level hospital: 80 points; third-level B-level hospital: 75 points; third-level C-level hospital: 70 points. The calculation method of the previous score of the uploading user can be: first calculate the score of all data sets uploaded by the user in the past, and then calculate the average. The current score of the data set is obtained by directly scoring by other users and taking the average. For a data set, if the weight of the institution score is 50%, the initial weights of the previous score of the uploading user and the current score of the data set are 50% and 0%, then as the number of people who score the current data set increases, the weight of the previous score of the uploading user gradually decreases. When the number of scorers reaches 10, the initial weights of the previous score of the uploading user and the current score of the data set are 25% and 25%. Finally, the data source score is obtained by weighting the above three scores.

[0092] In this embodiment, the data uniqueness constraint is used to identify and select fields that should be unique in mathematical logic, such as patient ID, medical record number, etc., and create a unique index for the selected field. The index is enforced in the database management system to ensure that the field values ​​covered by the index will not be repeated. In actual applications, the platform can preset multiple unique fields, such as patient ID, etc. When the column name of the phenotypic file uploaded by the user is a preset unique field, the uniqueness test will be automatically triggered. In addition, the user can add other unique fields by himself, wherein the uniqueness test will check whether there are duplicate values ​​in the column, such as there cannot be two identical patient IDs, and at the same time, the uniqueness test will ignore null values. It should be noted that in actual applications, there may be a situation where the same field is a unique field in one data set, but not a unique field in another data set. At this time, the user can remove the misjudged field in the result by himself.

[0093] In this embodiment, the definition of the attribute value domain in the enumeration value domain limitation constraint is achieved by defining a clear set that contains all allowed values. Taking the "gender" field as an example, let S be the set of all legal possible values ​​of the "gender" field. In this case, S is strictly defined as {male, female}, which means that the value domain of the "gender" field is limited to only contain elements in the set S. In a medical database or data set, any record of the "gender" field should be an element of the set S to ensure the consistency and accuracy of the data. If there are values ​​that do not conform to the set, such as unexpected values ​​due to input errors or unauthorized data expansion (for example, other gender identifiers besides "male" and "female"), these records violate the limitation of the value domain. In actual applications, the platform can preset multiple common enumeration value domains, such as gender, etc. When the column name of the phenotypic file uploaded by the user is a preset enumeration value field, the enumeration value detection will be automatically triggered. In addition, users can add other enumeration value fields themselves. The enumeration values ​​preset by the platform may include but are not limited to: Gender: male, female, other; Blood type: A, B, AB, O; Smoking status: never smoked, former smoker, current smoker; Drinking status: never drink, occasional drinker, regular drinker; Drug allergy: none, mild, moderate, severe; Pregnancy status: not pregnant, pregnant, postpartum; Drug dosage: low dose, medium dose, high dose; Vaccination status: not vaccinated, partially vaccinated, fully vaccinated, etc.

[0094] In this embodiment, the formulation of data verification rules can be based on business needs and medical data characteristics, and a set of detailed data verification rules can be formulated to set quantitative indicators that can be accurately calculated to ensure that medical data conforms to the established scope and business logic. In addition, for abnormal values ​​in the detected files, the system should automatically trigger the corresponding processing mechanism, such as abnormal value marking, error correction, etc. In this embodiment, algorithm templates such as Z-score, IQR, K-Means clustering, LOF, etc. can be preset to help identify data points where medical data does not conform to the expected pattern, thereby realizing the identification of abnormal values ​​and improving the quality and reliability of the data. In practical applications, the data verification rules can be used to preliminarily determine whether the data is abnormal by calculating the mean and standard deviation of the data. For example, if the value of a data point differs from the mean by more than 3 times the standard deviation, the data point can be considered to be an abnormal value. In addition, the standard score (Z-Score) of the data point can be calculated, that is, the distance between the data point and the mean divided by the standard deviation to identify abnormal values. For example, if the data point with an absolute value of Z-Score greater than 3 is considered an abnormal value. In addition, the DBScan method (a density-based clustering method) can be used to identify noise points that do not belong to any cluster and regard these points as outliers.

[0095] Furthermore, the medical data quality assessment dimension includes: integrity dimension; step S10 includes:

[0096] Step S111: If the medical data quality assessment dimension is an integrity dimension, the dimension verification rule corresponding to the integrity dimension is determined as the integrity verification rule.

[0097] It should be noted that the above integrity verification rules may be rules for verifying the integrity of medical data.

[0098] The step S20 comprises:

[0099] Step S211: Determine the attribute non-null constraint and the conditional non-null constraint based on the integrity check rule.

[0100] Step S212: verify the medical data through the attribute non-empty constraint and the conditional non-empty constraint to obtain a data verification result.

[0101] Among them, the attribute non-empty constraint is used to detect in real time whether there are abnormal values ​​when data is inserted and / or updated in the medical data, and the abnormal values ​​include null values ​​and missing values; the conditional non-empty constraint is used to perform non-empty constraints on non-empty medical data fields, and the non-empty medical data fields include: patient identifier, diagnosis code, treatment date and drug dosage.

[0102] It should be noted that in the integrity check rules of this embodiment, attribute non-empty constraints and conditional non-empty constraints can be set. Among them, the attribute non-empty constraint can be to impose non-empty constraints on specific data columns in the database architecture to ensure that these columns do not accept null values ​​and missing values ​​during data insertion or update; the conditional non-empty constraint can be for certain attributes in the database, in specific business logic or data context, certain fields must contain non-empty values ​​when certain conditions are met. In practical applications, integrity constraints can automatically detect all null values ​​and missing values ​​in phenotypic data, and detect whether the columns corresponding to these values ​​have non-empty constraints. For missing values, the platform provides a variety of interpolation methods, such as linear interpolation, Lagrange interpolation, etc.

[0103] In this embodiment, non-empty constrained medical data fields may include: patient identifiers: such as patient ID or medical record number, which are unique keys for identifying patients and must not be empty; diagnosis codes: such as ICD-10 codes, which are crucial for recording the patient's diagnosis results and should not be empty; treatment date: recording the specific date on which the patient received treatment, which is necessary for tracking the treatment process and effect analysis, and therefore is generally not allowed to be empty; drug name and dosage: in drug prescription records, drug name and dosage are key information for treatment and accurate data must be provided; laboratory test results: such as blood tests, pathology reports, etc., these test results are crucial for diagnosis and treatment decisions and should not have empty values; surgery name and surgery date: in surgical records, surgery name and surgery date are basic and necessary information and need to be accurately recorded; key clinical parameters: such as blood pressure, blood sugar levels, etc., these parameters are essential for patient health status assessment and treatment monitoring; patient admission and discharge dates: these dates are necessary for calculating hospitalization time, resource allocation, and healthcare management; allergy history: recording the patient's allergy history is crucial to avoid the use of drugs that may cause allergic reactions during treatment.

[0104] Furthermore, the medical data quality assessment dimension includes: timeliness dimension; the step S10 includes:

[0105] Step S121: If the medical data quality assessment dimension is a timeliness dimension, the dimension verification rule corresponding to the timeliness dimension is determined as the timeliness verification rule.

[0106] It should be noted that the above-mentioned timeliness verification rules can be used to verify the timeliness of medical data to ensure that the data can accurately reflect the actual situation of the medical entity it represents (such as patient conditions, medical activities, etc.) at a specific time point or time period.

[0107] The step S20 comprises:

[0108] Step S221: Timely processing of medical data based on timeliness verification rules, the timeliness processing includes: timely data upload processing.

[0109] Step S222: When the processing is completed, the time series records corresponding to the medical data are verified based on the event occurrence sequence corresponding to the medical data to obtain a data verification result.

[0110] It should be noted that the timeliness verification rules in this embodiment may include real-time data update, logical consistency and version control.

[0111] It is understandable that medical data must follow the principle of real-time, that is, data must be entered and processed immediately after acquisition to ensure that the data can instantly reflect the patient's current medical condition. In addition, the time series recording of medical data must strictly follow the chronological order of events to maintain the logical coherence of the data. At the same time, the system should allow the data status to be traced back to a specific point in time when necessary, formulate reasonable data retention periods and archiving requirements, and ensure that the data change process can be tracked in detail.

[0112] In this embodiment, the timeliness constraint can be: after uploading the data, the user can generate a version for the current data. The version is similar to git commit, and the user can name and annotate the version. When in use, the user can go back to each previous version at will, and see the information of all files under the version, and can also track the data change history in detail through the version submission log. In actual applications, the device can verify the currently recorded time sequence according to the time sequence of events corresponding to the medical data to ensure that the time sequence of events corresponding to the medical data is equal to the time sequence of the event recorded in the event sequence record, thereby ensuring the logical coherence of the medical data.

[0113] Furthermore, the medical data quality assessment dimension includes: a normative dimension; and step S10 includes:

[0114] Step S131: If the medical data quality assessment dimension is a normative dimension, the dimension verification rule corresponding to the normative dimension is determined as the normative verification rule.

[0115] It should be noted that the above-mentioned normative verification rules may be rules for performing normative verification on medical data to verify the compliance of the medical data.

[0116] The step S20 comprises:

[0117] Step S231: Acquire the data storage format, data encoding standard and data transmission protocol corresponding to the medical data.

[0118] Step S232: Based on the data storage format, the data encoding standard and the data transmission protocol, the medical data is subjected to a normative verification rule to obtain a data verification result.

[0119] In this embodiment, the normative verification rules may include data representation and coding standardization to ensure that the storage and transmission of data follow standardized format protocols, such as XML, JSON, HL7, DICOM, etc., so as to achieve interoperability between different systems. In addition, the update of data classification coding, such as migration from ICD-9 to ICD-10 or ICD-9-CM to ICD-10-CM, is crucial to the accuracy of statistical analysis and may have a significant impact on the statistical data of mortality and injury degree. In practical applications, in order to impose normative constraints on medical data, a data model can be defined, including basic information of patients, diagnosis results, treatment process, etc., and a suitable library can be selected to process formats such as XML, JSON, HL7, DICOM, etc. A mapping table can then be created to map the old coding to the new coding to achieve coding conversion, such as from ICD-9 to ICD-10. In addition, regular expressions can be used to implement data validation logic to ensure that the converted coding meets the requirements of the new standard, thereby realizing the function of importing data from the original format into the system and exporting the processed data to a standardized format.

[0120] Furthermore, the medical data quality assessment dimension includes: consistency dimension; the step S10 includes:

[0121] Step S141: If the medical data quality assessment dimension is a consistency dimension, the dimension verification rule corresponding to the consistency dimension is determined as the consistency verification rule.

[0122] It should be noted that the above consistency check rules may be rules for performing consistency check on medical data to ensure the internal logical consistency of the data and compatibility across data sets.

[0123] The step S20 comprises:

[0124] Step S241: Determine an equivalent consistency constraint, a logical consistency constraint, a diagnosis and treatment consistency constraint, and a distributed data consistency constraint based on the consistency verification rule;

[0125] Step S242: verifying the medical data through the equivalent consistency constraint, the logical consistency constraint, the diagnosis and treatment consistency constraint and the distributed data consistency constraint to obtain a data verification result;

[0126] Among them, the equivalence consistency constraint is used to verify the numerical equivalence between the first data items in the medical data; the logical consistency constraint is used to verify the logical dependencies between the second data items in the medical data; the diagnosis and treatment consistency constraint is used to verify the logical consistency between the user diagnosis information and the treatment plan, and the correspondence between the diagnosis code in the diagnosis information and the treatment measures in the treatment plan is mapped through a knowledge graph; the distributed data consistency constraint is used to verify the consistency between the storage location and application of the third data item in the medical data.

[0127] It should be noted that the above consistency verification rules may be provided with: equivalence consistency constraints, logical consistency constraints, diagnosis and treatment consistency constraints, and distributed data consistency constraints. In this embodiment, the implementation of these consistency constraints involves semantic understanding, which can be implemented with the help of a large language model. Among them, the consistency constraint mainly focuses on binary relationships. For all fields, the two-by-two combinations determine whether there are consistency constraints between them. For phenotypic data, the column name and the pre-written prompt can be assembled and input into the large language model. In addition, if there are fields involving consistency constraints, it is necessary to further ask the large model the detection code corresponding to the consistency constraint, and then automatically assemble the code returned by the large model into a script to run to test the data. At the same time, the platform will also preset multiple consistency constraint rules in advance. If the field meets the conditions of the rule, the preset rules will be used for inspection first.

[0128] In practical applications, the equivalent consistency constraint means that in a data table, the value of a field must be equal to the value calculated from other fields to ensure the numerical equivalence between data items. For example, in a patient record, if the age field is calculated from the date of birth, logic should be implemented to ensure the consistency of the two values. Violation of this constraint may trigger a data validation error and require the data administrator to intervene to resolve the inconsistency. Logical consistency constraints are used to ensure that the value of a single field in a data table satisfies a specific logical relationship with the values ​​of other fields, such as an order or comparison relationship. The implementation of this constraint usually requires in-depth analysis of the logical dependencies between data items and customization of corresponding validation rules. For example, to ensure that the patient's discharge date is later than the hospitalization date in time, data items that violate this logical relationship will be considered invalid and need to be corrected. Diagnosis and treatment consistency constraints are used to ensure that there is logical consistency between the patient's diagnosis information and their treatment plan or prescribed drugs. The correspondence between the diagnosis code and the treatment measures will be mapped in detail using the knowledge graph and verified in real time when the data is entered or updated. For example, if the system detects that the patient is diagnosed with hypertension, but the treatment plan includes drugs for the treatment of diabetes, this inconsistency will be marked and the relevant personnel will be notified for review. Distributed data consistency constraints are used to ensure that in a distributed database management system, the storage and application of the same data in different locations must remain consistent. For example, in a multi-site medical information system, the patient's updated information needs to be synchronized in all relevant databases to ensure the global consistency of the data.

[0129] Furthermore, the medical data quality assessment dimension includes: effectiveness dimension; the step S10 includes:

[0130] Step S151: If the medical data quality assessment dimension is a validity dimension, the dimension verification rule corresponding to the validity dimension is determined as the validity verification rule.

[0131] It should be noted that the above validity verification rules may be rules for evaluating the difficulty of visualizing medical data.

[0132] The step S20 comprises:

[0133] Step S251: Determine the data type, structuring level and data format corresponding to the medical data.

[0134] Step S252: Based on the data type, the degree of structuring and the data format, the medical data is verified using the validity verification rules to obtain a data verification result.

[0135] It should be noted that in the field of data science, the difficulty of data visualization analysis is significantly affected by the data type, degree of structure, format, scale and complexity. Structured data such as tables are easier to directly convert into visualization forms due to their standardization, while unstructured data such as text, images or audio need to be preprocessed and converted to reveal their inherent information; at the same time, the scale and dimension of the data, including the size of the data volume and the correlation between the data, also affect the complexity of visualization. In addition, high-dimensional data usually needs to rely on dimensionality reduction methods to extract key features and select appropriate visualization techniques to effectively display the deep structure and relationship of the data. Therefore, in this embodiment, the validity of medical data can be verified based on its corresponding data type, degree of structure and data format to determine the difficulty of visualizing the medical data, thereby obtaining data verification results.

[0136] In practical applications, visualization of data quality is a key component in medical data management practice. It involves quantitative analysis of data quality rules. By building an interactive data dashboard, key indicators of data quality assessment are graphically displayed. Users can intuitively obtain information about the total number of rule templates, the application efficiency of rules, the coverage of data tables, and the scores of various indicators based on the dashboard, which are key factors in measuring data quality. The process of validity constraints in this embodiment can be: first, data preprocessing is performed. For structured data, such as tables, data cleaning is ensured, including processing missing values, outliers, duplicate records, etc.; for unstructured data, such as text, images or audio, natural language processing, image processing or signal processing technology is used for preprocessing to extract useful information. Then, NLP technology can be applied to process text data, including word segmentation, part-of-speech tagging, named entity recognition, relationship extraction, and event extraction to identify entities (such as disease names, drug names), relationships (such as drug side effects) and events (such as medical events) in the text. In addition, ISP technology can be used to convert images or videos into digital form, including noise removal, filtering, automatic exposure, autofocus, HDR correction and image sharpening, to improve the quality of medical images for more accurate diagnosis. Next, exploratory data analysis can be performed to understand the distribution, central trend, and discreteness of the data. For high-dimensional data, dimensionality reduction techniques (such as principal component analysis) are used to reduce the dimension. In this embodiment, the platform provides a variety of charts, such as bar charts, line charts, scatter plots, heat maps, network diagrams, etc., and constructs an interactive data dashboard. Users can select the appropriate chart type through interactive operations (such as clicking, dragging, and zooming) and according to the data type and analysis objectives.

[0137] In this embodiment, a medical data quality assessment framework can also be provided. Figure 4 , Figure 4This is a diagram of the medical data quality assessment framework in the medical data quality assessment method of this application. Figure 4 As shown, the medical data quality assessment framework in this embodiment can include: accurately defining business needs, clarifying medical data quality assessment dimensions, data improvement and management, and quality warning and improvement. Among them, the module of accurately defining business needs is used to deeply analyze the specific application scenarios of medical data in business processes, clarify the supporting role of data in decision-making, and clarify the focus of data assessment; the module of clarifying medical data quality assessment dimensions is used to formulate detailed data quality assessment rules, confirm the weight of each assessment dimension and preset data internal attribute detection algorithm template and other related contents; the data improvement and management module is used to accurately identify the specific types and sources of data problems according to the results of data quality assessment, design and implement targeted improvement measures and strategies, and formulate data governance standardization processes. In addition, since data quality management is not a one-time job, but a continuous iterative process, it is also necessary to continuously track data quality through a quality monitoring system, and timely adjust and optimize data quality management strategies according to changes in data sources, conversion processes, and business rules to ensure that data quality is improved synchronously with business development.

[0138] In this embodiment, the medical data quality assessment dimensions are disclosed, including: accuracy dimension, completeness dimension, timeliness dimension, standardization dimension, consistency dimension and effectiveness dimension, and the verification rules corresponding to these dimensions are used to verify the medical data to obtain data verification results, so as to achieve accuracy verification, completeness verification, timeliness verification, standardization verification, consistency verification and effectiveness verification of the medical data, thereby improving the assessment quality of the medical data.

[0139] It should be noted that the above examples are only used to understand the present application and do not constitute a limitation on the medical data quality assessment method of the present application. More simple transformations based on this technical concept are all within the scope of protection of the present application.

[0140] This application also provides a medical data quality assessment device, please refer to Figure 5 , the medical data quality assessment device comprises:

[0141] A verification rule determination module 10 is used to determine the dimension verification rule corresponding to the medical data quality assessment dimension;

[0142] A verification result acquisition module 20, used to verify the medical data based on the dimension verification rule to obtain a data verification result;

[0143] A value assessment module 30, used to assess the value of the medical data through value assessment dimensions to obtain a value assessment result, wherein the value assessment dimensions are determined based on user needs;

[0144] The evaluation result generating module 40 is used to generate a data quality evaluation result corresponding to the medical data based on the data verification result and the value evaluation result.

[0145] The medical data quality assessment device provided by the present application adopts the medical data quality assessment method in the above-mentioned embodiment, which can solve the technical problem that the medical data quality assessment method in the prior art usually adopts a unified quality evaluation system and cannot fully consider the special needs and application scenarios of different user roles in the process of data use, resulting in low practicality. Compared with the prior art, the beneficial effects of the medical data quality assessment device provided by the present application are the same as the beneficial effects of the medical data quality assessment method provided by the above-mentioned embodiment, and the other technical features in the medical data quality assessment device are the same as the features disclosed in the above-mentioned embodiment method, which will not be repeated here.

[0146] The present application provides a medical data quality assessment device, which includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the medical data quality assessment method in the above-mentioned embodiment 1.

[0147] Reference below Figure 6 , which shows a schematic diagram of the structure of a medical data quality assessment device suitable for implementing the embodiment of the present application. The medical data quality assessment device in the embodiment of the present application may include but is not limited to mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (Portable Application Descriptions), PMPs (Portable Media Players), vehicle-mounted terminals (such as vehicle-mounted navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc. Figure 6 The medical data quality assessment device shown is merely an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0148] like Figure 6As shown, the medical data quality assessment device may include a processing device 1001 (e.g., a central processing unit, a graphics processor, etc.), which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM: Read Only Memory) 1002 or a program loaded from a storage device 1003 to a random access memory (RAM: Random Access Memory) 1004. In RAM1004, various programs and data required for the operation of the medical data quality assessment device are also stored. The processing device 1001, ROM1002, and RAM1004 are connected to each other through a bus 1005. An input / output (I / O) interface 1006 is also connected to the bus. Generally, the following systems can be connected to the I / O interface 1006: an input device 1007 including, for example, a touch screen, a touch pad, a keyboard, a mouse, an image sensor, a microphone, an accelerometer, a gyroscope, etc.; an output device 1008 including, for example, a liquid crystal display (LCD: Liquid Crystal Display), a speaker, a vibrator, etc.; a storage device 1003 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 1009. The communication device 1009 can allow the medical data quality assessment device to communicate with other devices wirelessly or by wire to exchange data. Although the figure shows a medical data quality assessment device with various systems, it should be understood that it is not required to implement or have all the systems shown. More or fewer systems can be implemented or have alternatively.

[0149] In particular, according to the embodiments disclosed in the present application, the process described above with reference to the flowchart can be implemented as a computer software program. For example, the embodiments disclosed in the present application include a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network through a communication device, or installed from a storage device 1003, or installed from a ROM 1002. When the computer program is executed by the processing device 1001, the above-mentioned functions defined in the method of the embodiment disclosed in the present application are executed.

[0150] The medical data quality assessment device provided by the present application adopts the medical data quality assessment method in the above embodiment, which can solve the technical problems of medical data quality assessment. Compared with the prior art, the beneficial effects of the medical data quality assessment device provided by the present application are the same as the beneficial effects of the medical data quality assessment method provided by the above embodiment, and the other technical features in the medical data quality assessment device are the same as the features disclosed in the method of the previous embodiment, which will not be repeated here.

[0151] It should be understood that the various parts disclosed in this application can be implemented by hardware, software, firmware or a combination thereof. In the description of the above embodiments, specific features, structures, materials or characteristics can be combined in any one or more embodiments or examples in a suitable manner.

[0152] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

[0153] The present application provides a computer-readable storage medium having computer-readable program instructions (ie, computer programs) stored thereon, and the computer-readable program instructions are used to execute the medical data quality assessment method in the above-mentioned embodiment.

[0154] The computer-readable storage medium provided in the present application may be, for example, a USB flash drive, but is not limited to electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, systems or devices, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In this embodiment, the computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, system or device. The program code contained on the computer-readable storage medium may be transmitted using any appropriate medium, including but not limited to: wires, optical cables, RF (Radio Frequency), etc., or any suitable combination of the above.

[0155] The computer-readable storage medium may be included in the medical data quality assessment device; or may exist independently without being assembled into the medical data quality assessment device.

[0156] The above-mentioned computer-readable storage medium carries one or more programs. When the above-mentioned one or more programs are executed by the medical data quality assessment device, the medical data quality assessment device: determines the dimension verification rules corresponding to the medical data quality assessment dimensions; verifies the medical data based on the dimension verification rules to obtain data verification results; evaluates the value of the medical data through the value assessment dimension to obtain a value assessment result, wherein the value assessment dimension is determined based on user needs; and generates a data quality assessment result corresponding to the medical data based on the data verification results and the value assessment results.

[0157] Computer program code for performing the operations of the present application may be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0158] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present application. In this regard, each square box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two square boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0159] The modules involved in the embodiments described in this application may be implemented by software or hardware, wherein the name of the module does not constitute a limitation on the unit itself in some cases.

[0160] The readable storage medium provided by the present application is a computer-readable storage medium, which stores computer-readable program instructions (i.e., computer programs) for executing the above-mentioned medical data quality assessment method, which can solve the technical problem that the medical data quality assessment method in the prior art usually adopts a unified quality evaluation system and cannot fully consider the special needs and application scenarios of different user roles in the process of data use, resulting in low practicality. Compared with the prior art, the beneficial effects of the computer-readable storage medium provided by the present application are the same as the beneficial effects of the medical data quality assessment method provided by the above-mentioned embodiment, which will not be repeated here.

[0161] The above descriptions are only some embodiments of the present application, and are not intended to limit the patent scope of the present application. All equivalent structural changes made using the contents of the present application specification and drawings under the technical concept of the present application, or direct / indirect applications in other related technical fields are included in the patent protection scope of the present application.

Claims

1. A method for assessing the quality of medical data, characterized in that: The method includes: Determine the dimension verification rules corresponding to the medical data quality assessment dimensions; Verify the medical data based on the dimension verification rule to obtain a data verification result; Evaluating the value of the medical data through value evaluation dimensions to obtain a value evaluation result, wherein the value evaluation dimensions are determined based on user needs; A data quality assessment result corresponding to the medical data is generated based on the data verification result and the value assessment result.

2. The method according to claim 1, characterized in that The medical data quality assessment dimension includes: an accuracy dimension; the step of determining the dimension verification rule corresponding to the medical data quality assessment dimension includes: If the medical data quality assessment dimension is an accuracy dimension, determining the dimension verification rule corresponding to the accuracy dimension as the accuracy verification rule; The step of verifying the medical data based on the dimension verification rule to obtain the data verification result includes: Determine data source constraints, data uniqueness constraints, enumeration value range limitation constraints and data verification rules based on the accuracy verification rules; Verify the medical data through the data source constraint, the data uniqueness constraint, the enumeration value range limitation constraint and the data verification rule to obtain a data verification result; Among them, the data source constraint is provided with an identity authentication system, and the identity authentication system is used to score the medical data; the data uniqueness constraint is provided with a number of uniqueness fields, and the uniqueness fields are used to perform uniqueness detection on the medical data; the enumeration value domain limitation constraint is provided with a number of enumeration value domains, and the enumeration value domains are used to perform enumeration value detection on the medical data; the data verification rule is used to determine the mean and standard deviation corresponding to the medical data, and judge whether the medical data has abnormalities based on the mean and the standard deviation.

3. The method according to claim 1, characterized in that The medical data quality assessment dimension includes: an integrity dimension; the step of determining the dimension verification rule corresponding to the medical data quality assessment dimension includes: If the medical data quality assessment dimension is an integrity dimension, determining the dimension verification rule corresponding to the integrity dimension as the integrity verification rule; The step of verifying the medical data based on the dimension verification rule to obtain the data verification result includes: Determine the attribute non-empty constraint and the conditional non-empty constraint based on the integrity check rule; Verifying the medical data through the attribute non-empty constraint and the conditional non-empty constraint to obtain a data verification result; Among them, the attribute non-empty constraint is used to detect in real time whether there are abnormal values ​​when data is inserted and / or updated in the medical data, and the abnormal values ​​include null values ​​and missing values; the conditional non-empty constraint is used to perform non-empty constraints on non-empty medical data fields, and the non-empty medical data fields include: patient identifier, diagnosis code, treatment date and drug dosage.

4. The method according to claim 1, characterized in that The medical data quality assessment dimension includes: a timeliness dimension; the step of determining a dimension verification rule corresponding to the medical data quality assessment dimension includes: If the medical data quality assessment dimension is a timeliness dimension, then the dimension verification rule corresponding to the timeliness dimension is determined as the timeliness verification rule; The step of verifying the medical data based on the dimension verification rule to obtain the data verification result includes: Timely processing of medical data based on timeliness verification rules, the timeliness processing includes: timely data upload processing; When the processing is completed, the time series records corresponding to the medical data are verified based on the event occurrence sequence corresponding to the medical data to obtain a data verification result.

5. The method according to claim 1, characterized in that The medical data quality assessment dimension includes: a normative dimension; the step of determining the dimension verification rule corresponding to the medical data quality assessment dimension includes: If the medical data quality assessment dimension is a normative dimension, determining the dimension verification rule corresponding to the normative dimension as the normative verification rule; The step of verifying the medical data based on the dimension verification rule to obtain the data verification result includes: Obtain the data storage format, data encoding standard and data transmission protocol corresponding to medical data; Based on the data storage format, the data encoding standard and the data transmission protocol, the medical data is subjected to a normative verification through the normative verification rules to obtain a data verification result.

6. The method according to claim 1, characterized in that The medical data quality assessment dimension includes: a consistency dimension; the step of determining the dimension verification rule corresponding to the medical data quality assessment dimension includes: If the medical data quality assessment dimension is a consistency dimension, determining the dimension verification rule corresponding to the consistency dimension as the consistency verification rule; The step of verifying the medical data based on the dimension verification rule to obtain the data verification result includes: Determine equivalent consistency constraints, logical consistency constraints, diagnosis and treatment consistency constraints, and distributed data consistency constraints based on the consistency verification rules; Verifying the medical data through the equivalent consistency constraint, the logical consistency constraint, the diagnosis and treatment consistency constraint, and the distributed data consistency constraint to obtain a data verification result; Among them, the equivalence consistency constraint is used to verify the numerical equivalence between the first data items in the medical data; the logical consistency constraint is used to verify the logical dependencies between the second data items in the medical data; the diagnosis and treatment consistency constraint is used to verify the logical consistency between the user diagnosis information and the treatment plan, and the correspondence between the diagnosis code in the diagnosis information and the treatment measures in the treatment plan is mapped through a knowledge graph; the distributed data consistency constraint is used to verify the consistency between the storage location and application of the third data item in the medical data.

7. The method according to claim 1, characterized in that The medical data quality assessment dimension includes: a validity dimension; the step of determining the dimension verification rule corresponding to the medical data quality assessment dimension includes: If the medical data quality assessment dimension is a validity dimension, determining the dimension verification rule corresponding to the validity dimension as the validity verification rule; The step of verifying the medical data based on the dimension verification rule to obtain the data verification result includes: Determine the data type, structured degree and data format corresponding to medical data; Based on the data type, the degree of structuring and the data format, the medical data is verified using the validity verification rules to obtain a data verification result.

8. A medical data quality assessment device, characterized in that: The device comprises: A verification rule determination module is used to determine the dimension verification rules corresponding to the medical data quality assessment dimension; A verification result acquisition module, used to verify the medical data based on the dimension verification rule to obtain a data verification result; A value assessment module, used to assess the value of the medical data through value assessment dimensions to obtain a value assessment result, wherein the value assessment dimensions are determined based on user needs; An evaluation result generating module is used to generate a data quality evaluation result corresponding to the medical data based on the data verification result and the value evaluation result.

9. A medical data quality assessment device, characterized in that: The device comprises: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program is configured to implement the steps of the medical data quality assessment method according to any one of claims 1 to 7.

10. A storage medium, characterized in that: The storage medium is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by a processor, the steps of the medical data quality assessment method according to any one of claims 1 to 7 are implemented.

Images