Multi-source heterogeneous diagnosis and treatment data quality evaluation method and device and computer equipment

Abstract

The invention discloses a multi-source heterogeneous diagnosis and treatment data quality evaluation method and device and computer equipment. The method comprises the following steps: acquiring multi-source heterogeneous diagnosis and treatment data of a hospital; converting and integrating the multi-source heterogeneous diagnosis and treatment data into a data intermediate pool, and generating a first index; extracting data from the data intermediate pool, and evaluating data quality by adopting a pre-constructed multi-source heterogeneous data quality evaluation model to obtain an evaluation result; monitoring data quality in the data intermediate pool, and when an evaluation result corresponding to the data meets a requirement, loading the data as infection monitoring data into a hospital infection monitoring multi-source heterogeneous database, and generating a second index; and performing data tracing according to the first index and the second index. By implementing the method provided by the invention, the problems of low efficiency and lack of an effective quality control and early warning mechanism in the traditional method for manually processing the multi-source heterogeneous diagnosis and treatment data can be solved.

Description

Technical Field

[0001] The present invention relates to a medical data processing method, and more specifically to a multi-source heterogeneous diagnosis and treatment data quality assessment method, device and computer equipment. Background Art

[0002] In the modern medical environment, hospitals are faced with heterogeneous data from multiple systems and devices, including medical records, laboratory results, and imaging data. Effective integration and management of this data is crucial to improving the quality of diagnosis and treatment and patient safety; However, due to the diversity and complexity of data sources, ensuring the accuracy and consistency of data has become a major challenge. At present, the data collected by medical institutions usually have problems with non-traceability and insufficient quality control. Traditional methods rely on on-site personnel to use open source tools (such as Kettle, DataX, SSIS, etc.) to perform manual data conversion and extract data through scheduled tasks, which requires manual intervention when problems arise with the data. This method not only fails to efficiently integrate multi-source heterogeneous data from different medical institutions, but also lacks an effective early warning mechanism.

[0003] Therefore, it is necessary to design a new method to solve the problems of low efficiency and lack of effective quality control and early warning mechanism in traditional manual processing of multi-source heterogeneous diagnosis and treatment data. Summary of the invention

[0004] The purpose of the present invention is to overcome the defects of the prior art and provide a method, device and computer equipment for evaluating the quality of multi-source heterogeneous diagnosis and treatment data.

[0005] To achieve the above objectives, the present invention adopts the following technical solution: a method for evaluating the quality of multi-source heterogeneous diagnosis and treatment data, comprising: Obtain multi-source heterogeneous diagnosis and treatment data of the hospital; Converting and integrating the multi-source heterogeneous diagnosis and treatment data into an intermediate data pool, and generating a first index; Extract data from the data intermediate pool and use the pre-built multi-source heterogeneous data quality evaluation model to evaluate the data quality to obtain the evaluation results; Monitoring the data quality in the data intermediate pool, and when the evaluation result corresponding to the data meets the requirements, loading the data into the hospital infection monitoring multi-source heterogeneous database as infection monitoring data, and generating a second index; Data tracing is performed according to the first index and the second index.

[0006] A further technical solution thereof is: before performing data tracing according to the first index and the second index, the method further includes: When the infection monitoring data or the number of collection times in the data intermediate pool meets the set warning requirements, a warning message is generated.

[0007] The further technical solution is: the acquisition of multi-source heterogeneous diagnosis and treatment data of the hospital includes: Acquire multi-source heterogeneous diagnosis and treatment data of the hospital collected by the data middleware tool based on the data standardized interface developed by the data view; The data view is a view formed by identifying and analyzing the data sources and key fields of multiple monitoring elements in different information system databases based on the basic data set of hospital infection monitoring.

[0008] A further technical solution is: the conversion and integration of the multi-source heterogeneous diagnosis and treatment data in the data intermediate pool and the generation of the first index include: Converting and integrating the multi-source heterogeneous diagnosis and treatment data into an intermediate data pool; A data model for recording data flow related fields is set in the data intermediate pool; The data model is used to define a data index field to obtain a first index.

[0009] A further technical solution is: extracting data from the data intermediate pool and using a pre-built multi-source heterogeneous data quality evaluation model to evaluate the data quality to obtain an evaluation result, including: Extract data from the data intermediate pool; A pre-built multi-source heterogeneous data quality evaluation model is used to calculate the comprehensive scores of each dimension of the accuracy, completeness and consistency of the data, and the final comprehensive score is calculated using a weighted average method to obtain the evaluation result.

[0010] The further technical solution is: the pre-built multi-source heterogeneous data quality evaluation model is used to calculate the comprehensive scores of each dimension of the accuracy, completeness and consistency of the data, and the final comprehensive score is calculated by weighted average to obtain the evaluation results, including: A pre-built multi-source heterogeneous data quality evaluation model is used to calculate the comprehensive scores of each dimension of the accuracy, completeness and consistency of the data; The comprehensive weight is determined by combining the G1 method with the anti-entropy weight method; The final comprehensive score is calculated by weighted average based on the comprehensive weight and the comprehensive scores of each dimension to obtain the evaluation result.

[0011] A further technical solution is: the data quality in the data intermediate pool is monitored, and when the evaluation result corresponding to the data meets the requirements, the data is loaded into the hospital infection monitoring multi-source heterogeneous database as infection monitoring data, and a second index is generated, including: Configure the quality assessment frequency based on data collection time; Monitoring the data quality in the data intermediate pool according to a quality assessment frequency; When the evaluation result corresponding to the data meets the requirements, the data is loaded into the hospital infection monitoring multi-source heterogeneous database as infection monitoring data, and a second index is generated.

[0012] The present invention also provides a multi-source heterogeneous diagnosis and treatment data quality assessment device, comprising: A data acquisition unit, used to acquire multi-source heterogeneous diagnosis and treatment data of the hospital; An integration unit, used for converting and integrating the multi-source heterogeneous diagnosis and treatment data into a data intermediate pool, and generating a first index; An evaluation unit is used to extract data from the data intermediate pool and evaluate the data quality using a pre-built multi-source heterogeneous data quality evaluation model to obtain an evaluation result; A monitoring unit, used to monitor the data quality in the data intermediate pool, and when the evaluation result corresponding to the data meets the requirements, load the data into the hospital infection monitoring multi-source heterogeneous database as infection monitoring data, and generate a second index; A tracing unit is used to perform data tracing according to the first index and the second index.

[0013] The present invention further provides a computer device, which includes a memory and a processor. The memory stores a computer program, and the processor implements the above method when executing the computer program.

[0014] The present invention also provides a storage medium, wherein the storage medium stores a computer program, and the computer program implements the above method when executed by a processor.

[0015] Compared with the prior art, the beneficial effects of the present invention are as follows: the present invention obtains multi-source heterogeneous diagnosis and treatment data of the hospital, converts and integrates them into the data intermediate pool, and generates an index. Subsequently, the data quality is evaluated using a pre-built data quality evaluation model, and qualified data will be loaded into the infection monitoring database. Finally, data traceability is performed through the index, and early warning information is generated when necessary to monitor data quality; through automated data conversion and integration processes, processing efficiency is greatly improved and manual intervention is reduced; the introduction of a data quality evaluation model realizes real-time quality monitoring to ensure the accuracy and reliability of data; by setting an early warning mechanism, abnormal situations are identified in a timely manner, thereby enhancing the effectiveness and responsiveness of data management, so as to solve the problems of low efficiency and lack of effective quality control and early warning mechanisms in traditional manual methods of processing multi-source heterogeneous diagnosis and treatment data.

[0016] The present invention is further described below in conjunction with the accompanying drawings and specific embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 A schematic diagram of an application scenario of the multi-source heterogeneous diagnosis and treatment data quality assessment method provided by an embodiment of the present invention; Figure 2 A flowchart of a method for evaluating the quality of multi-source heterogeneous medical data provided by an embodiment of the present invention; Figure 3 A schematic diagram of a sub-process of a method for evaluating quality of multi-source heterogeneous medical data provided by an embodiment of the present invention; Figure 4 A schematic diagram of a sub-process of a method for evaluating quality of multi-source heterogeneous medical data provided by an embodiment of the present invention; Figure 5 A schematic diagram of a sub-process of a method for evaluating quality of multi-source heterogeneous medical data provided by an embodiment of the present invention; Figure 6 A schematic diagram of a sub-process of a method for evaluating quality of multi-source heterogeneous medical data provided by an embodiment of the present invention; Figure 7 A schematic block diagram of a multi-source heterogeneous medical data quality assessment device provided by an embodiment of the present invention; Figure 8 A schematic block diagram of an integrated unit of a multi-source heterogeneous diagnosis and treatment data quality assessment device provided by an embodiment of the present invention; Fig. 9 A schematic block diagram of an evaluation unit of a multi-source heterogeneous diagnosis and treatment data quality evaluation device provided by an embodiment of the present invention; Fig.10 A schematic block diagram of a dimension assessment subunit of a multi-source heterogeneous diagnosis and treatment data quality assessment device provided by an embodiment of the present invention; Fig.11 A schematic block diagram of a monitoring unit of a multi-source heterogeneous diagnosis and treatment data quality assessment device provided by an embodiment of the present invention; Fig.12 A schematic block diagram of a computer device provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0018] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0019] See also Figure 1 and Figure 2 , Figure 1 A schematic diagram of an application scenario of the multi-source heterogeneous medical data quality assessment method provided in an embodiment of the present invention. Figure 2 A schematic flow chart of a multi-source heterogeneous diagnosis and treatment data quality assessment method provided for an embodiment of the present invention. The multi-source heterogeneous diagnosis and treatment data quality assessment method is applied to a server. The server interacts with a terminal, and the terminal refers to a computer or mobile phone that integrates multiple hospital information systems. By analyzing hospital infection monitoring data, a data standardization interface is developed, and multi-source heterogeneous diagnosis and treatment data is integrated into an intermediate pool, and a data index is generated, and a three-layer quality evaluation model is constructed to evaluate the accuracy, completeness and consistency of the data to ensure data quality. The data quality is monitored according to the evaluation results. If it meets the requirements, the data is loaded into the hospital infection monitoring database, and a second index is generated to track the data flow. Finally, a data display module is established to provide historical evaluation results and early warning functions, support data export and management, so as to solve the problem that the traditional manual processing method of multi-source heterogeneous diagnosis and treatment data is inefficient and lacks effective quality control and early warning mechanisms.

[0020] Figure 2 FIG. 1 is a flow chart of a method for evaluating the quality of multi-source heterogeneous medical data provided by an embodiment of the present invention. Figure 2 As shown, the method includes the following steps S110 to S160.

[0021] S110. Obtain the hospital's multi-source heterogeneous diagnosis and treatment data.

[0022] In this embodiment, the multi-source heterogeneous diagnosis and treatment data include but are not limited to basic patient information, clinical signs data, laboratory test and bacterial culture data, historical case data, and imaging examination data.

[0023] In this embodiment, the multi-source heterogeneous diagnosis and treatment data of the hospital collected by the data middleware tool based on the data standardization interface developed by the data view is obtained; The data view is a view formed by identifying and analyzing the data sources and key fields of multiple monitoring elements in different information system databases based on the basic data set of hospital infection monitoring.

[0024] Specifically, first, more than 70 monitoring elements were extracted from the basic data set of hospital infection monitoring, which covered important indicators related to hospital infection. Through in-depth analysis of these monitoring elements, the data sources and key fields in various information system databases can be identified. This process involves the following steps: Data element identification: The basic data set of hospital infection monitoring was analyzed to identify more than 70 key monitoring elements, including basic patient information, clinical signs, laboratory test results, bacterial culture results, historical cases and imaging examinations.

[0025] Data source and field arrangement: On the basis of ensuring that all monitoring elements are fully covered, investigate the data sources in various information systems within the hospital (such as hospital information system, laboratory information management system, imaging information system, electronic medical record system), and identify the corresponding key fields of each monitoring element in different systems. Arrange this information into a unified data view to facilitate subsequent data processing and analysis.

[0026] Based on the organized data view, the next step is to develop a data standardization interface. The specific process is as follows: Use of data middleware tools: Use data middleware tools to extract relevant data from multiple information systems. This tool can effectively connect different systems and support the conversion and integration of multiple data formats.

[0027] Data conversion and integration: The extracted data is standardized to ensure that data from different sources are compatible and in a unified format. The converted data will be integrated into an intermediate data pool.

[0028] Generate the first index: In the data intermediate pool, establish the first index of the data to facilitate subsequent data query and management. This index not only helps improve data access efficiency, but also lays the foundation for subsequent data analysis and application.

[0029] The composition of hospital information system Specifically, the multiple hospital information systems include but are not limited to: Hospital Information System (HIS): responsible for managing patients' basic information, hospitalization records, outpatient records, etc. Laboratory Information Management System (LIMS): used to process laboratory-related test data, such as blood tests, urine analysis, etc. Picture Information System (PACS): stores and manages medical imaging data, such as X-rays, CT scans, etc. Electronic Medical Record System (EMR): centrally manages patients' medical records, including medical history, treatment plans, and doctors' diagnosis information. Multi-source heterogeneous database for hospital infection monitoring. Ultimately, the integrated data will form a multi-source heterogeneous database for hospital infection monitoring, which contains the following data types: Patient basic information: including name, age, gender, address, etc. Patient clinical signs data: such as vital signs such as body temperature, pulse, respiratory rate, etc. Patient laboratory test and bacterial culture data: covers various laboratory test results and microbial culture results. Patient historical case data: records previous disease history and treatment. Patient imaging examination data: includes the results and reports of various imaging examinations.

[0030] Through the above steps, efficient integration and management of hospital infection monitoring data can be achieved, providing strong data support for hospital-related decision-making.

[0031] S120, converting and integrating the multi-source heterogeneous diagnosis and treatment data into an intermediate data pool, and generating a first index.

[0032] In this embodiment, the first index refers to an index that can indicate the data flow direction.

[0033] In one embodiment, see Figure 3 , the above-mentioned step S120 may include steps S121~S123.

[0034] S121. Convert and integrate the multi-source heterogeneous diagnosis and treatment data into an intermediate data pool.

[0035] In the data intermediate pool, the conversion and integration process of multi-source heterogeneous diagnosis and treatment data can be divided into the following steps: Extract data from multiple information systems of the hospital (such as hospital information system, laboratory information management system, imaging information system, electronic medical record system). This is done through data middleware tools to ensure that the required monitoring elements can be obtained from each system.

[0036] Standardize the extracted data, including format conversion, data cleaning, and missing value filling. Ensure that the data in different systems can be unified to the same standard to facilitate subsequent integration.

[0037] When data flows into the data intermediate pool, corresponding flow records are generated. This includes recording key information such as data source ID, processing steps, transmission path, and timestamp. Design appropriate data models and data tables to store these flow records to support subsequent queries and analysis.

[0038] Store the standardized data in the data intermediate pool, and record the flow and status of each piece of data (source_id, processing_step, destination_id, etc.) in the index data table to ensure that every change in the data is updated in the index.

[0039] Configure message queues to implement persistent storage of data indexes to ensure that data is not lost in the event of a system failure.

[0040] Integrate the standardized and processed data from the data intermediate pool into the multi-source heterogeneous database of hospital infection monitoring.

[0041] In this embodiment, raw data is extracted from multiple sources (such as hospital information systems, laboratory information management systems, etc.). Data in different formats (such as JSON, XML, CSV, etc.) are converted into a unified format for subsequent processing. The extracted data is cleaned to remove duplicate, incomplete or erroneous data records.

[0042] S122: Setting a data model for recording data flow related fields in the data intermediate pool.

[0043] In this embodiment, a data model containing fields related to recording data flow is designed in the data intermediate pool. The model includes the following fields: source_id: Identifies the data source, such as the ID of a hospital information system. processing_step: Records each step of the data processing process. destination_id: Identifies the destination of the data flow. timestamp: Records the timestamp of data processing to track the modification history of the data.

[0044] S123. Define a data index field using the data model to obtain a first index.

[0045] Determine the fields and create an index data table in the data intermediate pool specifically for storing data flow. The structure of this table should match the designed data model to ensure that the information of all the above fields can be recorded. Generate records when extracting data: When data is extracted from different information systems to the data intermediate pool, a flow record is immediately generated, filling in information such as source_id, processing_step, destination_id and timestamp. Update records during data processing: When the data goes through each processing step, update the processing_step field of the record to ensure that the latest processing status is reflected. Insert the generated flow record into the index data table for persistent storage. Each record should have a unique identifier to facilitate subsequent queries. Configure an update mechanism for the index record to ensure that the index record can be automatically updated whenever the data state changes (such as moving from one processing step to another). This mechanism can be implemented using triggers or application layer logic. Set up a message queue to achieve persistent storage of data flow. Whenever a flow record is generated or updated, this information is transmitted to the persistent storage layer through the message queue to ensure that important flow information is not lost in the event of a system failure.

[0046] In this embodiment, data index fields are defined based on the data model. These fields are used to record the data flow path and status, ensuring that the source and destination of each piece of data can be tracked.

[0047] When data is loaded into the intermediate pool, data flow records are generated and stored in the index data table. This process ensures that each piece of data has a corresponding flow record for subsequent auditing and tracking. Set up an update mechanism to record each change of data from one processing step to another. This can maintain the consistency and accuracy of the data state and ensure that key steps are not missed during data processing. Provide a query interface so that users can easily retrieve and view data flow records. This function provides data managers with an intuitive monitoring tool to track data processing in real time. Use visualization tools to display data flow to help users understand the source and processing history of data. Through graphical methods, users can more intuitively grasp the data flow path. Configure the data middleware message queue to achieve persistent storage of messages to ensure that logs are not lost in the event of system failure. This mechanism not only improves the reliability of data, but also ensures the accuracy and verifiability of data. Through a unified data conversion and integration process, the efficiency of data processing can be greatly improved. Data between different systems can be quickly coordinated, reducing the need for manual intervention. The process of data cleaning and standardization can improve the accuracy and completeness of data and ensure the reliability of analysis results. By clearly recording the data flow and processing steps, users can fully understand the life cycle of data, thereby improving the transparency of data management. Recording every processing step and change of data helps hospitals meet compliance requirements and provide audit support when necessary. Once a data problem occurs, the root cause of the problem can be quickly located through flow records, speeding up troubleshooting and repair. Visual tools are used to display data flows to help management better understand data and support scientific decision-making. Message queue configuration is used to ensure that data remains secure in the event of a system failure, enhancing the reliability and recovery capabilities of the data management system.

[0048] Through the detailed explanation of the above working principles and benefits, it can be seen that data conversion and integration are of great significance in hospital information management. It not only improves the efficiency of data processing, but also provides strong support for hospital decision-making.

[0049] S130, extracting data from the data intermediate pool, and using a pre-built multi-source heterogeneous data quality evaluation model to evaluate the data quality to obtain an evaluation result.

[0050] In this embodiment, the evaluation result refers to the score obtained after the integrity, accuracy and consistency of the data are evaluated.

[0051] In one embodiment, see Figure 4 , the above-mentioned step S130 may include steps S131~S132.

[0052] S131, extracting data from the data intermediate pool; S132. Use a pre-built multi-source heterogeneous data quality evaluation model to calculate the comprehensive scores of each dimension of the accuracy, completeness and consistency of the data, and use a weighted average method to calculate the final comprehensive score to obtain an evaluation result.

[0053] In this embodiment, the multi-source heterogeneous data quality evaluation model is divided into a three-layer structure, which is suitable for the quality evaluation of hospital infection monitoring data.

[0054] First level: quality dimension; According to the characteristics of hospital infection data, the following three quality dimensions are selected for evaluation: Accuracy: Whether the data truly reflects the patient's clinical condition and basic information.

[0055] Completeness: Whether the data record is complete and includes all necessary information.

[0056] Consistency: Whether the same data item in different data sources remains consistent.

[0057] Second level: quality characteristics; According to the selected quality dimension, it is further refined into specific quality characteristics: Accuracy characteristics: how well the data matches the actual situation; the number and type of erroneous records; Completeness characteristics: the proportion of missing values; the completion status of each data item; Consistency features: contradictions and inconsistencies between data; cross-validation results of multi-source data; The third layer: quality indicators; For each quality characteristic, define specific quality indicators. Accuracy quality indicators can be used ,in, = the accuracy of attribute j, = the number of records with correct attribute j, =Total number of records of attribute j, where j represents an attribute in the single-dimensional data attribute, i.e. {number of hospitalizations, hospitalization medical record number, patient ID number, patient ID category code, gender, date of birth...}, which represents the number of samples in the evaluation sample that meet the accuracy requirements among the j attributes. The Node attribute type data performs a separate data operation, and the accuracy only calculates the data contained in the intermediate pool table, and null values ​​are not included.

[0058] Hospital infection surveillance data mainly includes two types of data: Basic data (such as name, gender, age): usually a string.

[0059] Clinical data (such as hospitalization records, transfer records, test and examination results): usually contains numbers and strings.

[0060] These data types can be further classified into three types: Number: used to represent quantity or numerical data. String: used to represent text data. Node: a composite data type that usually contains information of other data types, such as case association information.

[0061] When evaluating hospital infection surveillance data, the relationship between accuracy and completeness needs to be considered. Specifically, when data are missing, completeness is first affected, leading to bias in accuracy assessment.

[0062] Since node-type data contains multiple types of data, its missing or incorrect data will affect both accuracy and completeness.

[0063] Therefore, during the evaluation process, the relationship between the two must be considered comprehensively to ensure the comprehensiveness and accuracy of data quality assessment.

[0064] In one embodiment, see Figure 5 , the above-mentioned step S132 may include steps S1321~S1323.

[0065] S1321. Calculate the comprehensive scores of the accuracy, completeness and consistency of the data using a pre-built multi-source heterogeneous data quality evaluation model; S1322. Determine the comprehensive weight by combining the G1 method with the anti-entropy weight method; S1323. Calculate the final comprehensive score by weighted average based on the comprehensive weight and the comprehensive scores of each dimension to obtain an evaluation result.

[0066] Specifically, accuracy is composed of the accuracy of multiple attribute dimensions: The quality is the weighted average of the quality of multi-attribute dimensional data, that is, a weight value is assigned to each evaluation indicator in the quality judgment process of data accuracy. The weight value can be determined comprehensively by the G1 method and the anti-entropy weight method.

[0067] Accurate qualitative indicators: (1), in formula (1), = the accuracy of attribute j, = the number of records with correct attribute j, =Total number of records of attribute j, j represents an attribute in the single-dimensional data attribute, that is, {number of hospitalizations, hospitalization medical record number, patient ID number, patient ID category code, gender, date of birth, etc.), which means the number of samples that meet the accuracy requirements in the evaluation sample among the j attributes. The Node attribute type data performs a separate data operation, and the accuracy only calculates the data contained in the intermediate pool table, and null values ​​are not included. Accuracy is composed of the accuracy of multiple attribute dimensions. Therefore, quality is the weighted average of the quality of multi-attribute dimensional data, that is, in the quality determination process of data accuracy, a weight value is assigned to each evaluation indicator. The weight value can be determined by the G1 method and the anti-entropy weight method. The accuracy model of multi-attribute data is: .in, is the weight of attribute j.

[0068] Integrity indicators: ;in, = completeness of attribute j; = the number of complete records for attribute j (the number of records without missing values); =Total number of records of attribute j; The integrity assessment model of multi-attribute data is: ; Consistency indicators: ;in, = consistency of attribute j; = Number of inconsistent records of attribute j; =Total number of records of attribute j; The consistency evaluation model of multi-attribute data is: .

[0069] The above G1 method and anti-entropy weight method are used to determine the weights, analyze the past infection monitoring data, and divide the collected data into training sets and test sets on a daily basis. The data set contains multi-source data, and its data type and length are used as influencing factors for sub-item analysis.

[0070] Using the G1 weighting method, experts are invited to rate the importance of each dimension and attribute. The value of each attribute is standardized to obtain the standardized data matrix X. The standardization formula is: ;in, represents the original value of the jth attribute of the i-th sample, is the standardized value.

[0071] Assuming that the standardized evaluation matrix X has been obtained, calculate the mean of each attribute : ;in, is the mean of the jth attribute, m is the total number of attributes, and n is the number of samples.

[0072] Calculate the weight of each attribute : .

[0073] Use the anti-entropy weight method to calculate the weight and the entropy value of each attribute : ;in, is the proportion of the jth attribute of the i-th sample: ; Calculate the anti-entropy of each attribute , reflecting the importance of the attribute: ; Normalize the anti-entropy value to get the final weight : ; Calculate G1 weight and anti-entropy weight: Get the G1 weight of each attribute and anti-entropy weights ; The two weights are combined by weighted average method to obtain the comprehensive weight : ; Where α is the weighting factor and its value is 0.5.

[0074] After confirming the data quality assessment indicators, it is necessary to build the assessment framework hierarchy and establish a model for the scoring indicators of each dimension, and finally calculate the comprehensive weighted comprehensive score of all indicators in the three dimensions: weighted comprehensive score for each dimension. Assuming that the weights of each dimension are α (accuracy), β (completeness), and γ (consistency), and α+ β +γ=1, calculate the comprehensive score through the following steps: Attribute-level comprehensive score, for each attribute j, the comprehensive score is: ; The data source level comprehensive score is obtained by weighted average of the comprehensive scores of all attributes. For example, the weight of attribute j is , the comprehensive score is: ; Multi-source comprehensive scoring: multiple data sources, the comprehensive scores of all data sources are weighted averaged to get the final multi-source comprehensive score. Assume that the weight of data source k is ,but: ; When data quality abnormalities occur, you can switch the above three comprehensive scores for re-evaluation, or adjust the α (accuracy), β (completeness), and γ (consistency) parameters.

[0075] Through the evaluation of the three dimensions of accuracy, completeness and consistency, all aspects of data quality can be fully reflected, avoiding the one-sidedness that may be caused by a single indicator. The pre-built multi-source heterogeneous data quality evaluation model makes the evaluation process more scientific and systematic, reducing the influence of human factors. By combining the G1 method with the anti-entropy weight method to determine the comprehensive weight, the weight can be dynamically adjusted according to different scenarios and needs, so as to more accurately reflect the actual situation. This method provides a clear data extraction and evaluation process, which makes it easy for hospitals to implement in actual operations and reduces the difficulty of operation. By improving data quality, it helps to provide a reliable basis for medical decision-making, thereby improving diagnosis and treatment efficiency and patient safety. The evaluation results can be used for subsequent data management and quality improvement, forming a virtuous circle and continuously improving data quality. In summary, this method not only improves the accuracy and reliability of data quality evaluation, but also provides important support for subsequent data management and decision-making.

[0076] S140, monitoring the data quality in the data intermediate pool, and when the evaluation result corresponding to the data meets the requirements, loading the data into the hospital infection monitoring multi-source heterogeneous database as infection monitoring data, and generating a second index.

[0077] In this embodiment, the second index refers to an index indicating the flow direction of infection monitoring data. The purpose of generating the second index is to track the flow path of data in the multi-source heterogeneous database of hospital infection monitoring to ensure the integrity and accuracy of the data. The following is the specific content contained in the second index: Index identifier index_id: a unique identifier used to identify each index record. Data source information source_id: an identifier of the original data source, indicating which information system the data comes from. Target table information target_table: the name of the target table, indicating the database table to which the data is written. Operation type operation_type: records the type of this operation, such as "insert", "update" or "delete". Processing steps processing_step: describes the processing steps that the current data has gone through, such as "data loading", "data cleaning", etc. Field mapping field_mapping: records the mapping relationship between the source table fields and the target table fields, so as to understand how the data is transformed. Timestamp timestamp: records the time of the operation for time series tracking. Status information status: records the status of the data in the target table, such as "success", "failure", etc., for subsequent monitoring and maintenance. Historical records previous_data: record snapshots of historical data in the target table to facilitate comparison during updates. Exception handling records error_message: If the operation fails, record the error message to help quickly locate the problem. Data integrity check results integrity_check: record the results of the data integrity check to ensure that the data is not lost or damaged during the loading process. Manual adjustment records manual_adjustments: If the manual adjustment stage is entered, record the relevant adjustment information and operations. User feedback user_feedback: record any feedback or comments from the user to facilitate the improvement of the data processing process. Through these contents, the second index can effectively support the addition, deletion, modification, and query of data, and provide the necessary tracking and auditing capabilities to ensure the high quality and manageability of data in the hospital infection monitoring system.

[0078] In one embodiment, see Figure 6 , the above-mentioned step S140 may include steps S141~S143.

[0079] S141, configuring the quality assessment frequency according to the data collection time; S142, monitoring the data quality in the data intermediate pool according to the quality assessment frequency; S143. When the evaluation result corresponding to the data meets the requirements, the data is loaded into the hospital infection monitoring multi-source heterogeneous database as infection monitoring data, and a second index is generated.

[0080] Configure the corresponding quality evaluation frequency according to the data collection time (scheduled collection or real-time collection). Monitor the data quality in the data intermediate pool. If the data quality meets the requirements (lower than the warning threshold), continue to build a multi-source heterogeneous database for hospital infection monitoring. Load the integrated infection data into the multi-source heterogeneous database for hospital infection monitoring and store it in the hospital infection monitoring server. In order to facilitate subsequent data management, return the second index of the data in the data intermediate pool. The purpose of the second index of the data is to track the data load-out path and improve the integrity and accuracy of the data. This enables the problem to be quickly located when the evaluation rules are adjusted later, and facilitates the addition, deletion, modification and query operations. Read the data quality assessment results. If the result meets the loading requirements, enter the write process of the multi-source heterogeneous database for hospital infection monitoring. If it does not meet the requirements, enter the step of repeated collection of hospital infection data. If the repeated collection reaches a certain number of times, an early warning is issued and the manual adjustment stage is entered. Extract the source table and target table data from the data intermediate pool, and set the comparison rules based on the collection time. Compare the fields in the source table with the key fields in the target table in order: if there is a historical record, overwrite the duplicate data; add data that exists in the source table but not in the target table; retain the data that exists in the target table but not in the source table. Scheduled collection (taking daily collection as an example): compare according to the key fields: if there is a historical record, overwrite the duplicate data; add data that exists in the source table but not in the target table; delete data that does not exist in the source table but exists in the target table. After writing is completed, generate the second index of the data and return it to the data intermediate pool for subsequent use. By monitoring data quality regularly and in real time, ensure that only data that meets the standards is included in the final database, thereby improving the accuracy and reliability of the overall data. The real-time collection mechanism can respond to changes quickly, ensure that the data always reflects the latest infection situation, and enhance the hospital's responsiveness. The generation of the second index of the data allows for flexible query and adjustment of the data in the future, which is convenient for tracking and correcting potential problems. By setting the threshold for duplicate collection and issuing early warnings in time, the accumulation of erroneous data can be prevented and the stability of the data environment can be guaranteed. The automated data processing process reduces the need for manual intervention, saves human resources, and improves work efficiency. High-quality multi-source heterogeneous databases provide a solid foundation for decision-making and help hospital management formulate more scientific infection control strategies. Accurate, complete and timely data can help hospitals better monitor and control infections, ultimately improving patient safety and treatment outcomes.

[0081] S150: When the infection monitoring data or the number of collection times in the data intermediate pool meets the set warning requirements, generate warning information.

[0082] In this embodiment, the data display module is mainly used to visualize the historical data evaluation results and warning information, so that users can intuitively understand the data quality. The core functions of this module include: Display of historical data evaluation results: Displays the flow path of each data field, including data source, data processing steps and timestamps. Provides quality evaluation indicators for each field, such as completeness, accuracy and consistency.

[0083] Early warning mechanism: When the infection monitoring data in the data intermediate pool meets the following two conditions at the same time: The data quality assessment results are higher than the assessment threshold of multi-source heterogeneous databases.

[0084] The number of repeated data collections exceeds the preset limit.

[0085] The system automatically issues early warnings and generates quality reports, pointing out major problems and their root causes.

[0086] User adjustment suggestions: In the quality report, specific adjustment suggestions are provided for the problems found to help users optimize the data integration process.

[0087] Data flow path display: Data traceability: By displaying the flow path of data, users can track the source of each piece of data and its flow within the system to ensure transparency.

[0088] Time management: Recording the processing time of each step of the data helps identify potential delays or bottlenecks and optimize data processing efficiency.

[0089] Quality report generation: Report content: The quality report will summarize the current data quality status, list the main problems (such as missing data, inconsistency, etc.) and root cause analysis (such as incorrect collection rules, improper data processing, etc.).

[0090] Chart display: Use charts and data visualization tools to make reports easier to understand and help users quickly understand the data quality status.

[0091] Users can clearly understand the source and processing of data, thereby enhancing their trust in the data. The early warning mechanism can quickly identify and feedback data quality issues, reducing decision-making risks caused by data errors. By analyzing key issues in quality reports, users can adjust data collection and processing processes in a targeted manner to improve overall data quality. Through visual quality assessment results, management can make more scientific and reasonable decisions based on data. Automated early warning and report generation reduces the need for manual monitoring and makes the workflow more efficient. Clear reports and suggestions can effectively promote communication and cooperation between different departments and jointly improve data governance. Timely early warnings and accurate data analysis can help hospitals better monitor and control infections, improve patient safety and treatment outcomes.

[0092] By establishing a data display module, hospitals can not only effectively manage and improve data quality, but also provide strong data support for clinical decision-making, thereby better responding to the challenges of infection monitoring and control.

[0093] S160: Perform data tracing according to the first index and the second index.

[0094] The process of data tracing based on the first index and the second index can be divided into the following key steps: First of all, it is necessary to clarify the type and scope of the data to be traced, such as data on a specific patient, infection monitoring data within a certain period of time, etc.

[0095] Use the first index to track the data source, and query the first index data table to obtain source data records related to the traceability target, including data source ID, processing steps, transmission path, timestamp, etc. According to the flow records of the source data, understand the processing process of data from various information systems (such as hospital information systems, laboratory information management systems, etc.) to the intermediate pool, and identify all related processing steps and changes.

[0096] Use the second index to track data changes. According to the traceability target, query the second index data table to obtain the flow information of data in multi-source heterogeneous databases, including operation type (such as insert, update, delete), target table information and field mapping. Check the timestamp and status of each operation to understand the data changes in a specific time period. For example, confirm when the data was updated, overwritten or deleted, and the user or system that performed these operations.

[0097] Combine the index information for complete tracing and trace back from the target table: Through the target table information in the second index, trace how the data is imported from the data intermediate pool to the hospital infection monitoring multi-source heterogeneous database to ensure a clear tracing path. Combine the history record field to view the original data status before the data update to understand the impact of the modification.

[0098] Generate a traceability report. Generate a detailed traceability report based on the information obtained from the first index and the second index, including the source of the data, processing process, change records and current status.

[0099] Troubleshooting and analysis: Identify any unexpected data changes through traceability information and analyze the causes, such as data loss, duplicate collection, etc. Based on the traceability results, propose improvement suggestions for data quality or processing flow to improve the overall performance of the system.

[0100] In one embodiment, a data packet of the hospital infection monitoring and treatment process containing a data index is exported from the data intermediate pool. This data packet will support operations such as tracing, updating, adding and deleting to ensure the integrity and manageability of the data. Data export includes: Data format: supports multiple export formats, such as CSV, Excel, JSON, etc., so that users can choose a suitable format for subsequent analysis. Data content: The exported data packet will contain the following information: Basic patient information: such as name, gender, age, hospitalization number, etc. Infection monitoring data: such as infection type, diagnosis time, treatment plan, drug usage, etc. Data index: Each record will be accompanied by a unique identifier (ID) to facilitate subsequent tracing and management. Data tracing includes: History: Through data indexing, the creation time, last update time and related operation logs (such as addition, modification, and deletion) of each record can be traced. Change log: The system will record each data modification, including data comparison before and after the modification, to ensure data transparency. Update functions include: Batch update: Supports batch update of selected records. Users can quickly update the data in the intermediate pool by uploading new data files. Version management: Each update will generate a new version record for subsequent comparison and backtracking. Add functions include: Data addition: Users can manually add new data or import data files through the interface, and the system will automatically generate the corresponding data index. Verification mechanism: When adding new data, the system will perform data integrity and consistency verification to ensure data accuracy. Deletion functions include: Safe deletion: Users can choose to delete specific records, and the system will ask for confirmation to prevent accidental deletion. Soft deletion mechanism: To protect data, deleted records will be marked as "deleted" instead of being completely deleted, which is convenient for subsequent recovery and auditing. User interface design includes: Simple and easy to use: The interface design should be intuitive, and users can easily find export, trace, update, add and delete functions. Search and filter: Provides powerful search functions so that users can quickly locate the required records and perform corresponding operations. Operation feedback: After each operation, the system will provide feedback information to inform users whether the operation is successful and the results of the operation. Application scenarios include: Clinical decision support: Doctors can develop more accurate treatment plans based on the exported infection monitoring data. Data analysis and research: Researchers can use the exported data packages to conduct epidemiological studies and evaluate the effectiveness of infection control. Quality management: Hospital management can continuously monitor and improve hospital infection management processes through traceability and update functions.

[0101] Through the perfect data export function, hospitals can effectively manage various types of data in the infection monitoring and treatment process, improve data utilization efficiency, and thus enhance the hospital's infection management capabilities and clinical decision support.

[0102] The above-mentioned multi-source heterogeneous diagnosis and treatment data quality assessment method obtains the hospital's multi-source heterogeneous diagnosis and treatment data, converts and integrates it into the data intermediate pool, and generates an index. Subsequently, the data quality is assessed using a pre-built data quality assessment model, and qualified data will be loaded into the infection monitoring database. Finally, data traceability is performed through the index, and early warning information is generated when necessary to monitor data quality. Through automated data conversion and integration processes, processing efficiency is greatly improved and manual intervention is reduced. The introduction of a data quality evaluation model realizes real-time quality monitoring to ensure the accuracy and reliability of data. By setting an early warning mechanism, abnormal situations are identified in a timely manner, thereby enhancing the effectiveness and responsiveness of data management, so as to solve the problems of low efficiency and lack of effective quality control and early warning mechanisms in traditional manual processing of multi-source heterogeneous diagnosis and treatment data.

[0103] Figure 7 is a schematic block diagram of a multi-source heterogeneous medical data quality assessment device 300 provided in an embodiment of the present invention. Figure 7 As shown, corresponding to the above multi-source heterogeneous medical data quality assessment method, the present invention also provides a multi-source heterogeneous medical data quality assessment device 300. The multi-source heterogeneous medical data quality assessment device 300 includes a unit for executing the above multi-source heterogeneous medical data quality assessment method, and the device can be configured in a server. Figure 7 The multi-source heterogeneous diagnosis and treatment data quality assessment device 300 includes a data acquisition unit 301, an integration unit 302, an assessment unit 303, a monitoring unit 304, an early warning unit 305 and a tracing unit 306.

[0104] The data acquisition unit 301 is used to acquire the hospital's multi-source heterogeneous diagnosis and treatment data; the integration unit 302 is used to convert and integrate the multi-source heterogeneous diagnosis and treatment data in the data intermediate pool, and generate a first index; the evaluation unit 303 is used to extract data from the data intermediate pool, and use a pre-built multi-source heterogeneous data quality evaluation model to evaluate the data quality to obtain an evaluation result; the monitoring unit 304 is used to monitor the data quality in the data intermediate pool, and when the evaluation result corresponding to the data meets the requirements, the data is loaded as infection monitoring data into the hospital infection monitoring multi-source heterogeneous database, and a second index is generated; the early warning unit 305 is used to generate early warning information when the infection monitoring data or the number of collection times in the data intermediate pool meets the set early warning requirements; the tracing unit 306 is used to trace the data according to the first index and the second index. In one embodiment, the data acquisition unit 301 is used to acquire multi-source heterogeneous diagnosis and treatment data of a hospital collected by a data middleware tool based on a data standardization interface developed by a data view; wherein the data view is a view formed by identifying and analyzing the data sources and key fields of multiple monitoring elements in different information system databases based on the basic data set of hospital infection monitoring. In one embodiment, if Figure 8 As shown, the integration unit 302 includes a conversion integration subunit 3021, a setting subunit 3022, and a definition subunit 3033. The conversion integration subunit 3021 is used to convert and integrate the multi-source heterogeneous diagnosis and treatment data in the data intermediate pool; the setting subunit 3022 is used to set a data model for recording data flow related fields in the data intermediate pool; the definition subunit 3033 is used to define a data index field using the data model to obtain a first index. In one embodiment, Fig. 9 As shown, the evaluation unit 303 includes a data extraction subunit 3031 and a dimension evaluation subunit 3032. The data extraction subunit 3031 is used to extract data from the data intermediate pool; the dimension evaluation subunit 3032 is used to use a pre-built multi-source heterogeneous data quality evaluation model to calculate the comprehensive score of each dimension of the accuracy, completeness and consistency of the data, and calculate the final comprehensive score by weighted average to obtain the evaluation result. In one embodiment, Fig.10As shown, the dimension evaluation subunit 3032 includes a score calculation module 30321, a weight determination module 30322 and a weighted average module 30323. The score calculation module 30321 is used to calculate the comprehensive score of each dimension for the accuracy, completeness and consistency of the data using a pre-built multi-source heterogeneous data quality evaluation model; the weight determination module 30322 is used to determine the comprehensive weight by combining the G1 method with the anti-entropy weight method; the weighted average module 30323 is used to calculate the final comprehensive score by weighted average according to the comprehensive weight and the comprehensive score of each dimension to obtain the evaluation result.

[0105] In one embodiment, if Fig.11 As shown, the monitoring unit 304 includes a frequency configuration subunit 3041 , a quality monitoring subunit 3042 , and a second index generation subunit 3043 .

[0106] The frequency configuration subunit 3041 is used to configure the quality assessment frequency according to the data collection time; the quality monitoring subunit 3042 is used to monitor the data quality in the data intermediate pool according to the quality assessment frequency; the second index generation subunit 3043 is used to load the data as infection monitoring data into the hospital infection monitoring multi-source heterogeneous database when the evaluation result corresponding to the data meets the requirements, and generate a second index.

[0107] It should be noted that technical personnel in the relevant field can clearly understand that the specific implementation process of the above-mentioned multi-source heterogeneous medical data quality assessment device 300 and each unit can refer to the corresponding description in the aforementioned method embodiment, and for the convenience and conciseness of the description, it will not be repeated here.

[0108] The multi-source heterogeneous diagnosis and treatment data quality assessment device 300 can be implemented in the form of a computer program. The computer program can be used in Fig.12 See Fig.12 , Fig.12 5 is a schematic block diagram of a computer device provided in an embodiment of the present application. The computer device 500 may be a terminal or a server, wherein the terminal may be an electronic device with communication functions such as a smart phone, a tablet computer, a laptop computer, a desktop computer, a personal digital assistant, and a wearable device. The server may be an independent server or a server cluster composed of multiple servers.

[0109] See also Fig.12 The computer device 500 includes a processor 502 , a memory and a network interface 505 connected via a system bus 501 , wherein the memory may include a non-volatile storage medium 503 and an internal memory 504 .

[0110] The non-volatile storage medium 503 can store an operating system 5031 and a computer program 5032. The computer program 5032 includes program instructions, and when the program instructions are executed, the processor 502 can execute a multi-source heterogeneous diagnosis and treatment data quality assessment method.

[0111] The processor 502 is used to provide computing and control capabilities to support the operation of the entire computer device 500 .

[0112] The internal memory 504 provides an environment for the operation of the computer program 5032 in the non-volatile storage medium 503. When the computer program 5032 is executed by the processor 502, the processor 502 can execute a multi-source heterogeneous diagnosis and treatment data quality assessment method.

[0113] The network interface 505 is used to communicate with other devices over the network. Fig.12 The structure shown in the figure is merely a block diagram of a portion of the structure related to the solution of the present application, and does not constitute a limitation on the computer device 500 to which the solution of the present application is applied. The specific computer device 500 may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0114] The processor 502 is used to run the computer program 5032 stored in the memory to implement the following steps: Acquire the hospital's multi-source heterogeneous diagnosis and treatment data; convert and integrate the multi-source heterogeneous diagnosis and treatment data in a data intermediate pool, and generate a first index; extract data from the data intermediate pool, and use a pre-built multi-source heterogeneous data quality evaluation model to evaluate the data quality to obtain an evaluation result; monitor the data quality in the data intermediate pool, and when the evaluation result corresponding to the data meets the requirements, load the data as infection monitoring data into a hospital infection monitoring multi-source heterogeneous database, and generate a second index; perform data tracing according to the first index and the second index.

[0115] In one embodiment, before implementing the step of tracing data according to the first index and the second index, the processor 502 further implements the following steps: When the infection monitoring data or the number of collection times in the data intermediate pool meets the set warning requirements, a warning message is generated.

[0116] In one embodiment, when the processor 502 implements the step of acquiring the multi-source heterogeneous medical treatment data of the hospital, the processor 502 specifically implements the following steps: Acquire multi-source heterogeneous diagnosis and treatment data of the hospital collected by the data middleware tool based on the data standardized interface developed by the data view; The data view is a view formed by identifying and analyzing the data sources and key fields of multiple monitoring elements in different information system databases based on the basic data set of hospital infection monitoring.

[0117] In one embodiment, when the processor 502 implements the step of converting and integrating the multi-source heterogeneous medical data into the data intermediate pool and generating the first index, the processor 502 specifically implements the following steps: The multi-source heterogeneous diagnosis and treatment data are converted and integrated in a data intermediate pool; a data model for recording data flow to related fields is set in the data intermediate pool; and a data index field is defined using the data model to obtain a first index.

[0118] In one embodiment, when the processor 502 implements the step of extracting data from the data intermediate pool and evaluating the data quality using a pre-built multi-source heterogeneous data quality evaluation model to obtain an evaluation result, the processor 502 specifically implements the following steps: Extract data from the data intermediate pool; use a pre-built multi-source heterogeneous data quality evaluation model to calculate the comprehensive score of each dimension of the accuracy, completeness and consistency of the data, and use a weighted average method to calculate the final comprehensive score to obtain the evaluation result.

[0119] In one embodiment, when the processor 502 implements the step of using the pre-built multi-source heterogeneous data quality evaluation model to calculate the comprehensive scores of the dimensions of accuracy, completeness and consistency of the data, and using the weighted average method to calculate the final comprehensive score to obtain the evaluation result, the following steps are specifically implemented: A pre-built multi-source heterogeneous data quality evaluation model is used to calculate the comprehensive scores of each dimension of the accuracy, completeness and consistency of the data; the G1 method is combined with the anti-entropy weight method to determine the comprehensive weight; the final comprehensive score is calculated by weighted average based on the comprehensive weight and the comprehensive score of each dimension to obtain the evaluation result.

[0120] In one embodiment, the processor 502 implements the following steps when implementing the step of monitoring the data quality in the data intermediate pool and when the evaluation result corresponding to the data meets the requirements, the data is loaded into the hospital infection monitoring multi-source heterogeneous database as infection monitoring data and generating a second index: The quality assessment frequency is configured according to the data collection time; the data quality in the data intermediate pool is monitored according to the quality assessment frequency; when the assessment result corresponding to the data meets the requirements, the data is loaded into the hospital infection monitoring multi-source heterogeneous database as infection monitoring data, and a second index is generated.

[0121] It should be understood that in the embodiment of the present application, the processor 502 may be a central processing unit (CPU), and the processor 502 may also be other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. Among them, the general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0122] It can be understood by those skilled in the art that all or part of the processes in the method for implementing the above embodiment can be completed by instructing the relevant hardware through a computer program. The computer program includes program instructions, and the computer program can be stored in a storage medium, which is a computer-readable storage medium. The program instructions are executed by at least one processor in the computer system to implement the process steps of the embodiment of the above method.

[0123] Therefore, the present invention also provides a storage medium. The storage medium may be a computer-readable storage medium. The storage medium stores a computer program, wherein when the computer program is executed by a processor, the processor executes the following steps: Acquire the hospital's multi-source heterogeneous diagnosis and treatment data; convert and integrate the multi-source heterogeneous diagnosis and treatment data in a data intermediate pool, and generate a first index; extract data from the data intermediate pool, and use a pre-built multi-source heterogeneous data quality evaluation model to evaluate the data quality to obtain an evaluation result; monitor the data quality in the data intermediate pool, and when the evaluation result corresponding to the data meets the requirements, load the data as infection monitoring data into a hospital infection monitoring multi-source heterogeneous database, and generate a second index; perform data tracing according to the first index and the second index.

[0124] In one embodiment, before executing the computer program to implement the step of tracing data according to the first index and the second index, the processor further implements the following steps: When the infection monitoring data or the number of collection times in the data intermediate pool meets the set warning requirements, a warning message is generated.

[0125] In one embodiment, when the processor executes the computer program to implement the step of obtaining multi-source heterogeneous medical data of a hospital, the processor specifically implements the following steps: Acquire multi-source heterogeneous diagnosis and treatment data of the hospital collected by the data middleware tool based on the data standardized interface developed by the data view; The data view is a view formed by identifying and analyzing the data sources and key fields of multiple monitoring elements in different information system databases based on the basic data set of hospital infection monitoring.

[0126] In one embodiment, when the processor executes the computer program to implement the step of converting and integrating the multi-source heterogeneous medical data into the data intermediate pool and generating the first index, the processor specifically implements the following steps: The multi-source heterogeneous diagnosis and treatment data are converted and integrated in a data intermediate pool; a data model for recording data flow to related fields is set in the data intermediate pool; and a data index field is defined using the data model to obtain a first index.

[0127] In one embodiment, when the processor executes the computer program to implement the step of extracting data from the data intermediate pool and evaluating the data quality using a pre-built multi-source heterogeneous data quality evaluation model to obtain an evaluation result, the processor specifically implements the following steps: Extract data from the data intermediate pool; use a pre-built multi-source heterogeneous data quality evaluation model to calculate the comprehensive score of each dimension of the accuracy, completeness and consistency of the data, and use a weighted average method to calculate the final comprehensive score to obtain the evaluation result.

[0128] In one embodiment, when the processor executes the computer program to implement the step of using a pre-built multi-source heterogeneous data quality evaluation model to calculate the comprehensive scores of each dimension of the accuracy, completeness and consistency of the data, and using a weighted average method to calculate the final comprehensive score to obtain an evaluation result, the following steps are specifically implemented: A pre-built multi-source heterogeneous data quality evaluation model is used to calculate the comprehensive scores of each dimension of the accuracy, completeness and consistency of the data; the G1 method is combined with the anti-entropy weight method to determine the comprehensive weight; the final comprehensive score is calculated by weighted average based on the comprehensive weight and the comprehensive score of each dimension to obtain the evaluation result.

[0129] In one embodiment, the processor implements the following steps when executing the computer program to monitor the data quality in the data intermediate pool, and when the evaluation result corresponding to the data meets the requirements, the data is loaded into the hospital infection monitoring multi-source heterogeneous database as infection monitoring data, and a second index step is generated: The quality assessment frequency is configured according to the data collection time; the data quality in the data intermediate pool is monitored according to the quality assessment frequency; when the assessment result corresponding to the data meets the requirements, the data is loaded into the hospital infection monitoring multi-source heterogeneous database as infection monitoring data, and a second index is generated.

[0130] The storage medium may be a USB flash drive, a mobile hard disk, a read-only memory (ROM), a magnetic disk, or an optical disk, etc., which are computer-readable storage media that can store program codes.

[0131] The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any technician familiar with the technical field can easily think of various equivalent modifications or replacements within the technical scope disclosed by the present invention, and these modifications or replacements should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention shall be based on the protection scope of the claims.

Claims

1. A method for evaluating the quality of multi-source heterogeneous medical data, characterized in that: include: Obtain multi-source heterogeneous diagnosis and treatment data of the hospital; Converting and integrating the multi-source heterogeneous diagnosis and treatment data into an intermediate data pool, and generating a first index; Extract data from the data intermediate pool and use the pre-built multi-source heterogeneous data quality evaluation model to evaluate the data quality to obtain the evaluation results; Monitoring the data quality in the data intermediate pool, and when the evaluation result corresponding to the data meets the requirements, loading the data into the hospital infection monitoring multi-source heterogeneous database as infection monitoring data, and generating a second index; Data tracing is performed according to the first index and the second index.

2. The method for evaluating the quality of multi-source heterogeneous medical data according to claim 1, characterized in that: Before performing data tracing according to the first index and the second index, the method further includes: When the infection monitoring data or the number of collection times in the data intermediate pool meets the set warning requirements, a warning message is generated.

3. The multi-source heterogeneous medical data quality assessment method according to claim 1, characterized in that: The acquisition of multi-source heterogeneous diagnosis and treatment data of the hospital includes: Acquire multi-source heterogeneous diagnosis and treatment data of the hospital collected by the data middleware tool based on the data standardized interface developed by the data view; The data view is a view formed by identifying and analyzing the data sources and key fields of multiple monitoring elements in different information system databases based on the basic data set of hospital infection monitoring.

4. The multi-source heterogeneous diagnosis and treatment data quality assessment method according to claim 1, characterized in that: The converting and integrating the multi-source heterogeneous diagnosis and treatment data into a data intermediate pool and generating a first index includes: Converting and integrating the multi-source heterogeneous diagnosis and treatment data into an intermediate data pool; A data model for recording data flow related fields is set in the data intermediate pool; The data model is used to define a data index field to obtain a first index.

5. The multi-source heterogeneous medical data quality assessment method according to claim 1, characterized in that: The data is extracted from the data intermediate pool, and the data quality is evaluated using a pre-built multi-source heterogeneous data quality evaluation model to obtain an evaluation result, including: Extract data from the data intermediate pool; A pre-built multi-source heterogeneous data quality evaluation model is used to calculate the comprehensive scores of each dimension of the accuracy, completeness and consistency of the data, and the final comprehensive score is calculated using a weighted average method to obtain the evaluation result.

6. The method for evaluating the quality of multi-source heterogeneous medical data according to claim 5, characterized in that: The pre-built multi-source heterogeneous data quality evaluation model is used to calculate the comprehensive scores of each dimension of the accuracy, completeness and consistency of the data, and the final comprehensive score is calculated by weighted average to obtain the evaluation results, including: A pre-built multi-source heterogeneous data quality evaluation model is used to calculate the comprehensive scores of each dimension of the accuracy, completeness and consistency of the data; The comprehensive weight is determined by combining the G1 method with the anti-entropy weight method; The final comprehensive score is calculated by weighted average based on the comprehensive weight and the comprehensive scores of each dimension to obtain the evaluation result.

7. The multi-source heterogeneous medical data quality assessment method according to claim 1, characterized in that: The data quality in the data intermediate pool is monitored, and when the evaluation result corresponding to the data meets the requirements, the data is loaded into the hospital infection monitoring multi-source heterogeneous database as infection monitoring data, and a second index is generated, including: Configure the quality assessment frequency based on data collection time; Monitoring the data quality in the data intermediate pool according to a quality assessment frequency; When the evaluation result corresponding to the data meets the requirements, the data is loaded into the hospital infection monitoring multi-source heterogeneous database as infection monitoring data, and a second index is generated.

8. A device for evaluating the quality of multi-source heterogeneous medical data, characterized in that: include: A data acquisition unit, used to acquire multi-source heterogeneous diagnosis and treatment data of the hospital; An integration unit, used for converting and integrating the multi-source heterogeneous diagnosis and treatment data into a data intermediate pool, and generating a first index; An evaluation unit is used to extract data from the data intermediate pool and evaluate the data quality using a pre-built multi-source heterogeneous data quality evaluation model to obtain an evaluation result; A monitoring unit, used to monitor the data quality in the data intermediate pool, and when the evaluation result corresponding to the data meets the requirements, load the data into the hospital infection monitoring multi-source heterogeneous database as infection monitoring data, and generate a second index; A tracing unit is used to perform data tracing according to the first index and the second index.

9. A computer device, characterized in that: The computer device comprises a memory and a processor, wherein a computer program is stored in the memory, and when the processor executes the computer program, the method according to any one of claims 1 to 7 is implemented.

10. A storage medium, characterized in that: The storage medium stores a computer program, and when the computer program is executed by a processor, the method according to any one of claims 1 to 7 is implemented.

Images