A medical data evaluation method and device based on data application requirements

Abstract

The present invention discloses a medical data evaluation method and device based on data application requirements. The method includes: collecting source data composed of different types of data sets generated by various medical institutions, and storing the source data in a preset data warehouse; when the source data in the data warehouse needs to be evaluated for a single data set, obtaining an indicator weight vector calculated under the data application requirements, and performing data quality evaluation based on the indicator weight vector combined with a fuzzy comprehensive evaluation model to obtain a comprehensive evaluation vector for the single data set; when the source data in the data warehouse needs to be evaluated for multiple data sets, obtaining a data set weight vector for each data set set by the data application party according to its own requirements, and determining the evaluation results of the multiple data sets based on the data set weight vector and the comprehensive evaluation vector of the single data set. This solves the problem in the prior art that when performing data quality evaluation, the requirements of specific data applications for different emphasis on the data quality of different data sets cannot be met.

Description

Technical Field

[0001] The present invention relates to the technical field of data management, and in particular to a medical data evaluation method and device based on data application requirements. Background Art

[0002] Currently, the regional medical data quality assessment approach includes the following steps: First, data is integrated into a data warehouse using ETL tools. Next, all incrementally extracted data sets are evaluated for completeness, consistency, validity, and timeliness. The results are then compiled into a report. Finally, data quality issues identified in the report are used to guide data correction. Once corrected, the data is then pushed to the appropriate databases based on the needs of different data users.

[0003] However, data quality assessment is only focused on the data warehouse, without considering that the data sets and data quality requirements required by various data application parties are different, and cannot meet the needs of specific data applications for different data sets with different emphasis on data quality. Summary of the Invention

[0004] In view of this, the purpose of the present invention is to provide a medical data evaluation method and device based on data application requirements, aiming to solve the problem that the existing technology cannot meet the needs of specific data applications for different data sets when performing data quality evaluation.

[0005] The present invention is achieved in that:

[0006] A medical data evaluation method based on data application requirements, the method comprising:

[0007] Collecting source data composed of different types of data sets generated by various medical institutions and storing the source data in a preset data warehouse;

[0008] When the source data in the data warehouse needs to be evaluated for a single data set, the indicator weight vector calculated under the data application requirements is obtained, and the data quality evaluation is performed based on the indicator weight vector combined with the fuzzy comprehensive evaluation model to obtain a comprehensive evaluation vector for the single data set;

[0009] When the source data in the data warehouse needs to be evaluated for multiple datasets, the dataset weight vector of each dataset set by the data application party according to its own needs is obtained, and the multi-dataset evaluation result is determined based on the dataset weight vector and the comprehensive evaluation vector of the single dataset.

[0010] Furthermore, in the above-mentioned medical data evaluation method based on data application requirements, the step of obtaining the indicator weight vector calculated under the data application requirements includes:

[0011] Obtaining the standard deviation of each indicator under the data application requirements and the correlation coefficient between the indicators, and constructing a quantitative indicator representing the conflict between the indicators based on the correlation coefficient;

[0012] Calculating the amount of information contained in each indicator based on the quantitative indicator and the standard deviation, and calculating the objective indicator based on the information amount;

[0013] The indicator weight vector of each indicator is determined according to the amount of information contained in each indicator and the objective indicator.

[0014] Furthermore, in the above-mentioned medical data evaluation method based on data application requirements, the calculation formula of the standard deviation is:

[0015] ;

[0016] The calculation formula of the correlation coefficient is:

[0017] ;

[0018] in, represents the standard matrix, m represents the number of columns of the standard matrix, n represents the number of rows of the standard matrix, represents the mean of the i-th indicator, represents the covariance of the i-th row and j-th column of the standard matrix.

[0019] Furthermore, in the above-mentioned medical data evaluation method based on data application requirements, the calculation formula of the information volume is:

[0020] ;

[0021] The calculation formula of the objective indicator is:

[0022] ;

[0023] in, A quantitative indicator representing the conflict between the i-th indicator and other indicators, Indicates the standard deviation of each indicator.

[0024] Furthermore, in the above-mentioned medical data evaluation method based on data application requirements, the step of performing data quality evaluation based on the indicator weight vector in combination with the fuzzy comprehensive evaluation model to obtain a comprehensive evaluation vector of a single data set includes:

[0025] Constructing a comment set according to the scoring criteria, and constructing a membership function of the indicator weight vector corresponding to the comment set, wherein the comment set is a collection of all evaluation results made by the evaluator on the evaluation object;

[0026] The membership of the indicator weight vector to different levels in the review set is calculated respectively to determine the evaluation matrix of the data set, and a comprehensive evaluation matrix representing the comprehensive evaluation vectors of all data sets is determined based on the evaluation matrix of the data set.

[0027] Furthermore, in the above-mentioned medical data evaluation method based on data application requirements, the step of determining the evaluation results of multiple data sets based on the data set weight vector and the comprehensive evaluation vector of the single data set includes:

[0028] The data set weight vector is multiplied by the comprehensive evaluation vector of the single data set to obtain the multi-data set evaluation result.

[0029] Another object of the present invention is to provide a medical data evaluation device based on data application requirements, the device comprising:

[0030] A source data acquisition module is used to collect source data generated by various medical institutions and composed of different types of data sets, and store the source data in a preset data warehouse;

[0031] A single data evaluation module is used to obtain the indicator weight vector calculated under the data application requirements when the source data in the data warehouse needs to be evaluated for a single data set, and to perform data quality evaluation based on the indicator weight vector in combination with the fuzzy comprehensive evaluation model to obtain a comprehensive evaluation vector for the single data set;

[0032] The multi-data evaluation module is used to obtain the dataset weight vector of each dataset set by the data application party according to its own needs when the source data in the data warehouse needs to be evaluated for multiple datasets, and determine the multi-dataset evaluation result based on the dataset weight vector and the comprehensive evaluation vector of the single dataset.

[0033] Another object of the present invention is to provide a readable storage medium having a computer program stored thereon, wherein the program implements the steps of the above method when executed by a processor.

[0034] Another object of the present invention is to provide an electronic device, comprising a memory, a processor, and a computer program stored in the memory and running on the processor, wherein the processor implements the steps of the above method when executing the program.

[0035] The present invention collects source data composed of different types of data sets generated by various medical institutions and stores the source data in a preset data warehouse; when the source data in the data warehouse needs to be evaluated for a single data set, the indicator weight vector calculated under the data application requirements is obtained, and the data quality is evaluated according to the indicator weight vector combined with the fuzzy comprehensive evaluation model to obtain a comprehensive evaluation vector of the single data set; when the source data in the data warehouse needs to be evaluated for multiple data sets, the data set weight vector of each data set set by the data application party according to its own needs is obtained, and the multi-data set evaluation result is determined according to the data set weight vector and the comprehensive evaluation vector of the single data set. The data application party can set the indicator weight vector and the data set weight vector according to its own application needs, taking into account the relative importance factors of different data sets, and solving the problem in the existing technology that when performing data quality assessment, the specific data application cannot meet the different emphasis on the data quality of different data sets. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] Figure 1 Flowchart of a medical data evaluation method based on data application requirements in a first embodiment of the present invention;

[0037] Figure 2 Schematic diagram of a scoring standard in a medical data evaluation method based on data application requirements in one embodiment of the present invention;

[0038] Figure 3 Schematic diagram of a data quality evaluation index system in a medical data evaluation method based on data application requirements in one embodiment of the present invention;

[0039] Figure 4 This is a schematic diagram of the results of calculating the indicator weight coefficient using the CRITIC method in the medical data evaluation method based on data application requirements in one embodiment of the present invention;

[0040] Figure 5 FIG. 4 is a structural block diagram of a medical data evaluation device based on data application requirements in a third embodiment of the present invention.

[0041] The following specific embodiments will further illustrate the present invention in conjunction with the above-mentioned drawings. DETAILED DESCRIPTION

[0042] To facilitate understanding of the present invention, the present invention will be described more fully below with reference to the accompanying drawings. The drawings illustrate several embodiments of the present invention. However, the present invention may be implemented in many different forms and is not limited to the embodiments described herein. Rather, these embodiments are provided to provide a more thorough and comprehensive understanding of the present invention.

[0043] It should be noted that when an element is referred to as being "fixed to" another element, it may be directly on the other element or there may be an intermediate element. When an element is referred to as being "connected to" another element, it may be directly connected to the other element or there may be an intermediate element. The terms "vertical," "horizontal," "left," "right," and similar expressions used herein are for illustrative purposes only.

[0044] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one skilled in the art to which this invention pertains. The terms used in this specification of the present invention are for the purpose of describing specific embodiments only and are not intended to limit the present invention. The term "and / or" as used herein includes any and all combinations of one or more of the associated listed types.

[0045] The following will describe in detail how to adapt to the different data quality priorities of different data sets when performing data quality assessment, with reference to specific embodiments and accompanying drawings.

[0046] Example 1

[0047] See also Figure 1 , shown is a medical data evaluation method based on data application requirements in the first embodiment of the present invention, the method includes steps S10 to S12.

[0048] Step S10: collecting source data generated by various medical institutions and consisting of different types of data sets, and storing the source data in a preset data warehouse.

[0049] Among them, the source system data of each medical institution is collected, including but not limited to the inpatient medical record homepage, admission record, admission medical record, examination and inspection record, hospitalization medical order, surgical treatment record, medical record, cost information, etc., and stored in the data warehouse. In the specific implementation, in order to ensure the accuracy of the data, the data can also be cleaned before storage.

[0050] Step S11: When the source data in the data warehouse needs to be evaluated for a single data set, the indicator weight vector calculated under the data application requirements is obtained, and the data quality evaluation is performed based on the indicator weight vector combined with the fuzzy comprehensive evaluation model to obtain a comprehensive evaluation vector of the single data set.

[0051] Specifically, the comprehensive evaluation of a single dataset uses a fuzzy comprehensive evaluation model combined with indicator weights calculated for specific data application requirements to evaluate data quality. The final evaluation result is a comprehensive evaluation vector of the single dataset against the comment set. If the largest element in the evaluation vector is less than the required value, technical processing is required to eliminate low-quality data until the requirements are met.

[0052] In some optional embodiments of the present invention, the step of performing data quality evaluation based on the indicator weight vector in combination with a fuzzy comprehensive evaluation model to obtain a comprehensive evaluation vector of a single data set includes:

[0053] Constructing a comment set according to the scoring criteria, and constructing a membership function of the indicator weight vector corresponding to the comment set, wherein the comment set is a collection of all evaluation results made by the evaluator on the evaluation object;

[0054] The membership of the indicator weight vector to different levels in the review set is calculated respectively to determine the evaluation matrix of the data set, and a comprehensive evaluation matrix representing the comprehensive evaluation vectors of all data sets is determined based on the evaluation matrix of the data set.

[0055] Among them, the fuzzy comprehensive evaluation method is used to evaluate the quality of regional medical data under specific data application requirements. The first step is to construct a comment set and membership function. The comment set refers to the set of all evaluation results made by the evaluator on the evaluation object, represented by V. For example, three evaluation levels are selected to establish the comment set, that is, V = {normal, caution, abnormal}. The scoring criteria are as follows Figure 2 shown.

[0056] In specific implementations, the value of the indicator vector is automatically calculated by the system according to the quality verification rules. The embodiment of the present invention uses a trapezoidal distribution function to establish the indicator membership function. The closer the value is to 1, the higher the quality satisfaction. The membership function of the indicator corresponding to the three states of the review set is as follows:

[0057] ;

[0058] in, x As the score value, fuzzy comprehensive evaluation is performed on the single data set, and their evaluation on the comment set is calculated respectively. Different levels of membership , from this we can conclude that Evaluation matrix of the dataset , we can get the comprehensive evaluation matrix of all data sets under specific data application requirements:

[0059] .

[0060] Step S12: When the source data in the data warehouse needs to be evaluated for multiple datasets, the dataset weight vector of each dataset set by the data application party according to its own needs is obtained, and the evaluation result of the multiple datasets is determined based on the dataset weight vector and the comprehensive evaluation vector of the single dataset.

[0061] For datasets involved in specific data application requirements, data users can set the weights for each dataset based on their own needs. This creates a personalized dataset requirement weight vector. This is then combined with the evaluation matrix formed by the comprehensive evaluation of the individual datasets to produce the final evaluation result.

[0062] Specifically, based on the comprehensive evaluation of a single dataset, the weight vector of the dataset is combined to obtain the comprehensive evaluation result of multiple datasets, that is, the membership vector of all datasets in the current scene to the comment set. , the calculation formula is as follows:

[0063] ;

[0064] Among them, A is the weight vector of the data set, and R is the comprehensive evaluation matrix of all data sets.

[0065] In summary, the medical data evaluation based on data application requirements in the above-mentioned embodiments of the present invention is a medical data evaluation method based on data application requirements, which collects source data composed of different types of data sets generated by various medical institutions and stores the source data in a preset data warehouse; when the source data in the data warehouse needs to be evaluated on a single data set, the indicator weight vector calculated under the data application requirements is obtained, and the data quality is evaluated based on the indicator weight vector combined with the fuzzy comprehensive evaluation model to obtain a comprehensive evaluation vector of the single data set; when the source data in the data warehouse needs to be evaluated on multiple data sets, the data set weight vector of each data set set by the data application party according to its own needs is obtained, and the multi-data set evaluation results are determined based on the data set weight vector and the comprehensive evaluation vector of the single data set. The data application party can set the indicator weight vector and the data set weight vector according to its own application needs, taking into account the relative importance factors of different data sets, and solving the problem in the existing technology that when performing data quality evaluation, the specific data application cannot meet the different emphasis on the data quality of different data sets.

[0066] Example 2

[0067] This embodiment of the present invention also provides a medical data evaluation method based on data application requirements. The difference between this medical data evaluation method based on data application requirements and the medical data evaluation method based on data application requirements proposed in the first embodiment of the present invention is that:

[0068] The step of obtaining the calculated indicator weight vector under the data application requirements includes:

[0069] Obtaining the standard deviation of each indicator under the data application requirements and the correlation coefficient between the indicators, and constructing a quantitative indicator representing the conflict between the indicators based on the correlation coefficient;

[0070] Calculating the amount of information contained in each indicator based on the quantitative indicator and the standard deviation, and calculating the objective indicator based on the information amount;

[0071] The indicator weight vector of each indicator is determined according to the amount of information contained in each indicator and the objective indicator.

[0072] Among them, first, a relevant indicator system for regional medical data quality evaluation can be constructed according to actual needs. For example, in the embodiment of the present invention, the relevant indicator system for regional medical data quality evaluation includes 4 indicator dimensions and 10 specific indicators of the 4 indicator dimensions. Among them, the data quality evaluation indicator system is as follows: Figure 3 shown.

[0073] Specifically, the indicator weight vector is determined using the CRITIC analysis method, which comprehensively determines the objective weight of an indicator by analyzing the magnitude of changes within the indicator and the conflicts between indicators. Objective indicator values can be collected for all 10 secondary indicators selected in this embodiment of the present invention, and there is a certain degree of volatility and correlation between the indicators. The indicator weights for a specific scenario are calculated using the following steps.

[0074] Based on the correlation coefficients between indicators, a quantitative expression is constructed to represent the conflict to express the conflict between indicators. The standard deviation of each indicator can be obtained The correlation coefficient between the Where represents the mean of the i-th indicator, Represents a standard matrix Covariance of row i and column j:

[0075] ;

[0076] ;

[0077] Calculate the amount of information contained in each indicator according to the CRITIC method Where A quantitative indicator that represents the conflict between the i-th indicator and other indicators. The larger it is, the more information is contained in the i-th indicator, and the greater the weight of the indicator is:

[0078] The calculation formula for the amount of information is:

[0079] ;

[0080] The calculation formula of objective indicators is:

[0081] ;

[0082] The indicator weight vector of each indicator is determined according to the amount of information contained in each indicator and the objective indicator.

[0083] To further describe the embodiment process of the present invention in detail, a regional medical research scenario is selected for example for example analysis. First, the data quality verification index calculation results of 6 data sets involved in the 60-day research scenario (inpatient medical record homepage, admission record, admission medical record, examination and testing record, hospitalization medical order, and surgical treatment record) are selected to perform indicator weight calculation. Secondly, the data to be evaluated on a certain day is selected and a single data set evaluation is performed on these 6 data sets. Then, a comprehensive evaluation is performed on multiple data sets to obtain the membership matrix of all data sets in the research scenario to the comment set. Finally, the data quality evaluation result of this day is determined according to the maximum membership principle.

[0084] Due to the different dimensions of the indicators, the indicators are first standardized, and then the indicator weight coefficients are calculated using the CRITIC method. Figure 4 shown.

[0085] By combining the collected daily index calculation results with the membership function, the fuzzy comprehensive evaluation of the six data sets was performed, and the membership matrix of the single data set to the comment set was obtained. as follows:

[0086] ;

[0087] Based on the comprehensive evaluation of a single dataset, the weight vector of the dataset is combined Calculate the membership vector of all data sets in the scientific research scene to the comment set In this example, the dataset weight vector is specified by the user as ,The process of calculating the membership matrix of all data sets to the comment set in the scenario of scientific research data application requirements is as follows:

[0088] ;

[0089] After calculation, we get ,According to the membership range of the above evaluation levels, the ,data quality evaluation results in the scientific research scenario of this ,example are at the “abnormal” level.

[0090] The medical data evaluation based on data application requirements in the above-mentioned embodiment of the present invention is a medical data evaluation method based on data application requirements, which collects source data composed of different types of data sets generated by various medical institutions and stores the source data in a preset data warehouse; when the source data in the data warehouse needs to be evaluated for a single data set, the indicator weight vector calculated under the data application requirements is obtained, and the data quality is evaluated according to the indicator weight vector combined with the fuzzy comprehensive evaluation model to obtain a comprehensive evaluation vector of the single data set; when the source data in the data warehouse needs to be evaluated for multiple data sets, the data set weight vector of each data set set by the data application party according to its own needs is obtained, and the multi-data set evaluation results are determined according to the data set weight vector and the comprehensive evaluation vector of the single data set. The data application party can set the indicator weight vector and the data set weight vector according to its own application needs, taking into account the relative importance factors of different data sets, and solving the problem in the existing technology that when performing data quality evaluation, the specific data application cannot meet the different emphasis on the data quality of different data sets.

[0091] In addition, data users can set the weights of data quality evaluation indicators according to their own application needs, which enhances the flexibility of the evaluation method and the accuracy of the evaluation results;

[0092] A comprehensive evaluation of multiple data sets is conducted based on the data sets involved by the data users, taking into account the relative importance factors of different data sets, so that the evaluation results are more in line with actual needs.

[0093] Example 3

[0094] See also Figure 5 , shown is a medical data evaluation device based on data application requirements proposed in the third embodiment of the present invention, the device comprising:

[0095] The source data collection module 100 is used to collect source data generated by various medical institutions and composed of different types of data sets, and store the source data in a preset data warehouse;

[0096] The single data evaluation module 200 is used to obtain the indicator weight vector calculated based on the data application requirements when the source data in the data warehouse needs to be evaluated for a single data set, and to perform data quality evaluation based on the indicator weight vector in combination with the fuzzy comprehensive evaluation model to obtain a comprehensive evaluation vector for the single data set;

[0097] The multi-data evaluation module 300 is used to obtain the data set weight vector of each data set set by the data application party according to its own needs when the source data in the data warehouse needs to be evaluated for multiple data sets, and determine the multi-data set evaluation result based on the data set weight vector and the comprehensive evaluation vector of the single data set.

[0098] Furthermore, in some optional embodiments of the present invention, the single data evaluation module includes:

[0099] an acquisition unit, configured to acquire the standard deviation of each indicator under the data application requirement and the correlation coefficient between the indicators, and construct a quantitative indicator representing the conflict between the indicators based on the correlation coefficient;

[0100] a calculation unit, configured to calculate the amount of information contained in each indicator based on the quantitative indicator and the standard deviation, and calculate the objective indicator based on the information amount;

[0101] A determination unit is used to determine the indicator weight vector of each indicator according to the amount of information contained in each indicator and the objective indicator.

[0102] Furthermore, in some optional embodiments of the present invention, the calculation formula of the standard deviation is:

[0103] ;

[0104] The calculation formula of the correlation coefficient is:

[0105] ;

[0106] in, represents the standard matrix, m represents the number of columns of the standard matrix, n represents the number of rows of the standard matrix, represents the mean of the i-th indicator, represents the covariance of the i-th row and j-th column of the standard matrix.

[0107] Furthermore, in some optional embodiments of the present invention, the calculation formula of the information amount is:

[0108] ;

[0109] The calculation formula of the objective indicator is:

[0110] ;

[0111] in, A quantitative indicator representing the conflict between the i-th indicator and other indicators, Indicates the standard deviation of each indicator.

[0112] Furthermore, in some optional embodiments of the present invention, the single data evaluation module further includes:

[0113] A construction unit, configured to construct a comment set according to a scoring standard, and to construct a membership function of the indicator weight vector corresponding to the comment set, wherein the comment set is a collection of all evaluation results made by the evaluator on the evaluation object;

[0114] The membership of the indicator weight vector to different levels in the review set is calculated respectively to determine the evaluation matrix of the data set, and a comprehensive evaluation matrix representing the comprehensive evaluation vectors of all data sets is determined based on the evaluation matrix of the data set.

[0115] Furthermore, in some optional embodiments of the present invention, the multi-data evaluation module is specifically configured to:

[0116] The data set weight vector is multiplied by the comprehensive evaluation vector of the single data set to obtain the multi-data set evaluation result.

[0117] The functions or operation steps implemented when the above modules are executed are substantially the same as those in the above method embodiments and will not be repeated here.

[0118] Example 4

[0119] Another aspect of the present invention further provides a readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the method described in any one of the above-mentioned embodiments 1 to 2.

[0120] Example 5

[0121] On the other hand, the present invention also provides an electronic device, which includes a memory, a processor, and a computer program stored in the memory and running on the processor. When the processor executes the program, the steps of the method described in any one of the above-mentioned embodiments 1 to 2 are implemented.

[0122] The technical features of the above embodiments can be combined arbitrarily. In order to make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0123] Those skilled in the art will appreciate that the logic and / or steps represented in the flowcharts or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by an instruction execution system, apparatus, or device (e.g., a computer-based system, a system including a processor, or other system that can fetch and execute instructions from an instruction execution system, apparatus, or device), or in conjunction with such instruction execution system, apparatus, or device. For purposes of this specification, "computer-readable medium" can be any device that can contain, store, communicate, propagate, or transport a program for use by an instruction execution system, apparatus, or device, or in conjunction with such instruction execution system, apparatus, or device.

[0124] More specific examples (a non-exhaustive list) of computer-readable media include the following: an electrical connection with one or more wires (electronic devices), a portable computer disk cartridge (magnetic devices), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), a fiber optic device, and a portable compact disc read-only memory (CDROM). In addition, the computer-readable medium may even be paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium and then editing, interpreting, or processing it in another suitable manner as necessary, and then storing it in a computer memory.

[0125] It should be understood that various components of the present invention may be implemented using hardware, software, firmware, or a combination thereof. In the aforementioned embodiments, multiple steps or methods may be implemented using software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented using hardware, as in another embodiment, any one or a combination of the following technologies known in the art may be used: a discrete logic circuit having logic gate circuits for implementing logic functions on data signals, an application-specific integrated circuit having suitable combinational logic gate circuits, a programmable gate array (PGA), a field-programmable gate array (FPGA), etc.

[0126] Throughout this specification, reference to terms such as "one embodiment," "some embodiments," "examples," "specific examples," or "some examples" means that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of the present invention. In this specification, schematic representations of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.

[0127] The above-described embodiments merely illustrate several implementations of the present invention, and while their descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the present invention. It should be noted that a person skilled in the art would be able to make numerous variations and improvements without departing from the spirit of the present invention, all of which fall within the scope of protection of the present invention. Therefore, the scope of protection of the present invention shall be determined by the appended claims.

Claims

1. A medical data evaluation method based on data application requirements, characterized in that: The method comprises: Collect source data composed of different types of data sets generated by various medical institutions and store the source data in a preset data warehouse, where the source data includes inpatient medical record homepage, admission record, admission course record, examination and testing record, hospitalization doctor's order, surgical treatment record, medical record, and cost information; When the source data in the data warehouse needs to be evaluated for a single data set, the indicator weight vector calculated under the data application requirements is obtained, and the data quality evaluation is performed based on the indicator weight vector combined with the fuzzy comprehensive evaluation model to obtain a comprehensive evaluation vector for the single data set; When the source data in the data warehouse needs to be evaluated for multiple datasets, a dataset weight vector of each dataset set by the data application party according to its own needs is obtained, and a multi-dataset evaluation result is determined based on the dataset weight vector and the comprehensive evaluation vector of the single dataset; The step of performing data quality evaluation based on the indicator weight vector in combination with the fuzzy comprehensive evaluation model to obtain a comprehensive evaluation vector for a single data set includes: Constructing a comment set according to the scoring criteria, and constructing a membership function of the indicator weight vector corresponding to the comment set, wherein the comment set is a collection of all evaluation results made by the evaluator on the evaluation object; Calculating the membership of the indicator weight vector to different levels in the review set respectively to determine the evaluation matrix of the data set, and determining a comprehensive evaluation matrix representing the comprehensive evaluation vectors of all data sets based on the evaluation matrix of the data set; The step of obtaining the calculated indicator weight vector under the data application requirements includes: Obtaining the standard deviation of each indicator under the data application requirements and the correlation coefficient between the indicators, and constructing a quantitative indicator representing the conflict between the indicators based on the correlation coefficient; Calculating the amount of information contained in each indicator based on the quantitative indicator and the standard deviation, and calculating the objective indicator based on the information amount; The indicator weight vector of each indicator is determined according to the amount of information contained in each indicator and the objective indicator.

2. The medical data evaluation method based on data application requirements according to claim 1, characterized in that: The standard deviation is calculated as follows: ； The calculation formula of the correlation coefficient is: ； in, represents the standard matrix, m represents the number of columns of the standard matrix, n represents the number of rows of the standard matrix, represents the mean of the i-th indicator, represents the covariance of the i-th row and j-th column of the standard matrix.

3. The medical data evaluation method based on data application requirements according to claim 2, characterized in that: The calculation formula of the information amount is: ； The calculation formula of the objective indicator is: ； in, A quantitative indicator representing the conflict between the i-th indicator and other indicators, Indicates the standard deviation of each indicator.

4. The medical data evaluation method based on data application requirements according to claim 1, characterized in that: The step of determining the multi-dataset evaluation result according to the data set weight vector and the comprehensive evaluation vector of the single data set includes: The data set weight vector is multiplied by the comprehensive evaluation vector of the single data set to obtain the multi-data set evaluation result.

5. A medical data evaluation device based on data application requirements, characterized in that: A device for implementing the medical data evaluation method based on data application requirements as described in any one of claims 1 to 4, comprising: A source data acquisition module is used to collect source data generated by various medical institutions and composed of different types of data sets, and store the source data in a preset data warehouse; A single data evaluation module is used to obtain the indicator weight vector calculated under the data application requirements when the source data in the data warehouse needs to be evaluated for a single data set, and to perform data quality evaluation based on the indicator weight vector in combination with the fuzzy comprehensive evaluation model to obtain a comprehensive evaluation vector for the single data set; The multi-data evaluation module is used to obtain the dataset weight vector of each dataset set by the data application party according to its own needs when the source data in the data warehouse needs to be evaluated for multiple datasets, and determine the multi-dataset evaluation result based on the dataset weight vector and the comprehensive evaluation vector of the single dataset.

6. A readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the steps of the method according to any one of claims 1 to 4 are implemented.

7. An electronic device, characterized in that: The method comprises a memory, a processor, and a computer program stored in the memory and running on the processor, wherein the steps of the method according to any one of claims 1 to 4 are implemented when the processor executes the program.

Images