A method and system for quality control of antimicrobial drugs based on data analysis

Abstract

The present invention discloses a method and system for quality control of antimicrobial drugs based on data analysis, and belongs to the technical field of data analysis. The medical cases of patients are imported into a data warehouse and data is stratified, and a quality control sample matrix is ​​constructed to characterize quality control estimation value information and quality control feature set information; the quality control estimation value is quantified by the quality control feature set, and its use compliance rate is evaluated; based on the use compliance rate, the quality control sample matrix is ​​converted into a Boolean matrix, the medical order correlation between patients is analyzed, and the patient information corresponding to the maximum correlation value is output to the medical staff port; the present invention can realize effective stratification and feature characterization of medical cases, can improve the accuracy of quantifying quality control estimation values ​​and evaluating use compliance rates, and can efficiently analyze the medical order correlation between patients, provide scientific and effective quality control information and auxiliary decision support for medical staff, and help optimize the use strategy of antimicrobial drugs and reduce irrational drug use.

Description

Technical Field

[0001] The present invention relates to the technical field of data analysis, and in particular to an antimicrobial drug quality control method and system based on data analysis. Background Art

[0002] In current medical practice, the use and management of antibiotics is an important part of medical quality control; however, due to the wide variety of antibiotics, different medication habits and the complexity of disease types, the rational use of antibiotics has become an extremely challenging task.

[0003] Traditional quality control methods for antibiotics mostly rely on review and statistics by medical staff. This method is not only inefficient, but also easily affected by human factors, resulting in low accuracy and reliability of quality control results. In recent years, with the rapid development of medical informatization and big data technology, quality control methods can be improved through big data analysis technology, but existing technologies often lack effective data stratification and feature characterization methods, resulting in a cumbersome quality control process and difficulty in accurately capturing key information, and failing to fully consider the complexity and diversity of antibiotic use. Summary of the invention

[0004] The object of the present invention is to provide an antimicrobial drug quality control method and system based on data analysis to solve the problems raised in the above background technology.

[0005] In order to solve the above technical problems, the present invention provides the following technical solutions:

[0006] An antimicrobial drug quality control system based on data analysis, the system comprises: a data warehouse module, a feature characterization module, a data analysis module and a quality control association module;

[0007] The data warehouse module is used to import the patient's medical case into the data warehouse after the patient's authorization. The data warehouse performs data stratification based on disease type, antimicrobial drug type and medication habit data, including first sample stratification, second sample stratification and third sample stratification;

[0008] The feature characterization module constructs a quality control sample matrix based on the first sample stratification and the second sample stratification, and characterizes the quality control estimation value information and the quality control feature set information through the quality control sample matrix;

[0009] The data analysis module is used to quantify the quality control estimation value through the quality control feature set and evaluate the usage compliance rate of the quality control estimation value;

[0010] The quality control association module converts the quality control sample matrix into a Boolean matrix based on the usage compliance rate, analyzes the medical order correlation between patients through the Boolean matrix, and outputs the patient information corresponding to the maximum medical order correlation to the medical staff port.

[0011] Further, the data warehouse module includes a data import unit and a data stratification unit;

[0012] The data import unit is used to import medical cases into the data warehouse, and the data warehouse adds coding marks to the imported medical cases; it is used to identify medical record information in the medical cases, and the medical record information includes patient information, disease type, antimicrobial drug type and medication habit data, and the medication habit data includes medication date and medication dosage within the medication date;

[0013] The data stratification unit is used to establish sample stratification, including a first sample stratification, a second sample stratification and a third sample stratification. The first sample stratification records various disease types and uniformly encodes the disease types. The second sample stratification records the types of antimicrobial drugs and uniformly encodes the antimicrobial drug types. The third sample stratification records all medical cases of the same patient and uniformly encodes the patients.

[0014] Further, the feature characterization module includes a quality control sample matrix model unit and a quality control feature collection unit;

[0015] The quality control sample matrix model unit constructs a quality control sample matrix based on the first sample stratification and the second sample stratification, wherein the row number of the quality control sample matrix corresponds to the code number of the disease type in the first sample stratification, and the column number of the quality control sample matrix corresponds to the code number of the antimicrobial drug type in the second sample stratification, and the matrix element at the xth row and the yth column in the quality control sample matrix is ​​recorded as the quality control estimation value;

[0016] The quality control feature collection unit generates a quality control feature set through the third sample stratification based on the quality control sample matrix.

[0017] Further, the data analysis module includes a data quantification unit and a data evaluation unit;

[0018] The data quantification unit is used to extract medication habit data in medical cases, identify medication dates in the medication habit data, collect the minimum medication date and the maximum medication date of the medical case records in the quality control feature set, and form the medication time range of the quality control feature set; within the medication time range, the total amount of limited daily doses of antibiotics purchased from different manufacturers is counted, and the total amount of medication doses of antibiotics in the quality control feature set is counted, and the quality control estimate is obtained by the ratio of the total amount of medication doses to the total amount of limited daily doses;

[0019] The data evaluation unit evaluates the usage compliance rate of the quality control estimation value based on the quality control sample matrix.

[0020] Further, the quality control association module includes an association analysis unit and an association screening unit;

[0021] The association analysis unit is used to preset a usage compliance rate threshold, and if the usage compliance rate is greater than or equal to the usage compliance rate threshold, the quality control estimation value is set to a value of 1, otherwise the quality control estimation value is set to a value of 0, and the quality control matrix is ​​converted into a Boolean matrix;

[0022] The association screening unit analyzes the medical order associations between patients based on the Boolean matrix, and screens out the patient information corresponding to the maximum medical order association to send to the medical staff port.

[0023] A method for quality control of antimicrobial drugs based on data analysis, the method comprising the following steps:

[0024] Step S1: Import the patient's medical records into the data warehouse, and the data warehouse performs data stratification based on disease type, antimicrobial drug type, and medication habit data, including first sample stratification, second sample stratification, and third sample stratification;

[0025] Step S2: constructing a quality control sample matrix based on the first sample stratification and the second sample stratification, and representing the quality control estimation value information and the quality control feature set information through the quality control sample matrix;

[0026] Step S3: quantifying the quality control estimation value through the quality control feature set, and evaluating the usage compliance rate of the quality control estimation value;

[0027] Step S4: Based on the usage compliance rate, the quality control sample matrix is ​​converted into a Boolean matrix. Through the Boolean matrix, the correlation between the medical orders of the patients is analyzed, and the patient information corresponding to the maximum medical order correlation is output to the medical staff port.

[0028] Furthermore, the specific implementation process of step S1 includes:

[0029] After the patient's authorization, the medical case is imported into the data warehouse, and the data warehouse adds a coding mark to the imported medical case, which is recorded as M e ; Identify medical cases M e The medical record information includes patient information, disease type, antimicrobial drug type and medication habit data, and the medication habit data includes medication date and medication dosage within the medication date;

[0030] The data warehouse establishes sample stratification, including the first sample stratification, the second sample stratification and the third sample stratification. The first sample stratification records each disease type and uniformly codes the disease types. Any x-th disease type is recorded as D x The second sample stratification records the type of antimicrobial drugs, and uniformly codes the antimicrobial drug types. Any y-th antimicrobial drug type is recorded as Ay In the third sample stratification, all medical cases of the same patient are recorded, and the patients are uniformly coded. Any h-th patient is recorded as S h .

[0031] Furthermore, the specific implementation process of step S2 includes:

[0032] Based on the first sample stratification and the second sample stratification, a quality control sample matrix is ​​constructed, wherein the row number of the quality control sample matrix corresponds to the code number of the disease type in the first sample stratification, and the column number of the quality control sample matrix corresponds to the code number of the antimicrobial drug type in the second sample stratification. The matrix element of the xth row and the yth column in the quality control sample matrix is ​​recorded as the quality control estimate value r(D x , A y );

[0033] Based on the quality control sample matrix, the quality control feature set is generated through the third sample stratification, and the quality control estimation value r(D x , A y ) corresponds to the quality control feature set generated, denoted as f(D x , A y ), the quality control feature set is generated as follows:

[0034] Based on the quality control sample matrix, when the same patient S h Medical Cases e Disease type D x and antimicrobial type A y When the medical case M e Recorded in the quality control feature set f(D x , A y )middle;

[0035] The same patient S h After all medical cases of are mapped to the quality control feature set, the corresponding patient S h The quality control matrix is ​​denoted as R(S h ).

[0036] Furthermore, the specific implementation process of step S3 includes:

[0037] Through the quality control feature set f(D x , A y ) to quantify the quality control estimate r(D x , A y ), the quantization process is as follows:

[0038] Extract medical cases e The medication habit data in the medication habit data are identified, and the medication date in the medication habit data is collected, and the quality control feature set f(D x , A y) constitutes the quality control feature set f(D x , A y ) medication time range;

[0039] Within the medication time range, statistics on the types of antimicrobial drugs purchased from different manufacturers A y The total amount of the defined daily dose, statistical quality control feature set f(D x , A y ) Antimicrobial drug type A y The total amount of the dosage of the drug is calculated by comparing the total amount of the dosage to the total amount of the limited daily dose to obtain the quality control estimate value r(D x , A y );

[0040] Based on the quality control sample matrix, the quality control estimate r(D x , A y ) usage compliance rate:

[0041]

[0042] In the formula, UCR(D x , A y ) represents the quality control estimate r(D x , A y ) usage compliance rate, r(A y ) represents the mean of the quality control estimation value, and the yth column of the quality control sample matrix is ​​summed and averaged to obtain Among them, U represents the quality control sample matrix R(S h ), that is, the total number of disease types, σ represents the standard deviation of the quality control estimate, and

[0043] In the above method, the sum and average are calculated according to the characteristics of the columns, aiming to quantify the usage of the same antibiotic for different disease types. This usage can reflect the drug resistance of patients when using the same antibiotic to treat different diseases, and then study the compliance rate of usage under medical advice.

[0044] Furthermore, the specific implementation process of step S4 includes:

[0045] Preset usage match rate threshold, if using match rate UCR (D x , A y ) is greater than or equal to the compliance rate threshold, then the quality control estimate value r(D x , A y )=1, otherwise let the quality control estimate value r(D x , A y)=0, then the quality control matrix R(S h ) is converted into a Boolean matrix BR(S h );

[0046] Based on the Boolean matrix, analyze the correlation between patients' medical orders:

[0047]

[0048] In the formula, Q(S h , S l ) indicates patient S h and patient S l The degree of medical advice correlation between them, and h≠l, NUM[BR(S h )∩BR(S l )] represents the Boolean matrix BR(S h ) and the Boolean matrix BR(S l ) contains the number of 1s after the intersection logic operation, NUM[BR(S h )∪BR(S l )] represents the Boolean matrix BR(S h ) and the Boolean matrix BR(S l ) after the logical union operation;

[0049] Let l = l + 1, perform iterative analysis, and obtain patient S h Except for patients S h The medical order correlation between each patient outside the group is calculated, and the patient information corresponding to the maximum medical order correlation is output and sent to the medical staff port.

[0050] Compared with the prior art, the beneficial effects achieved by the present invention are as follows: in an antimicrobial drug quality control method and system based on data analysis provided by the present invention, the patient's medical cases are imported into a data warehouse and data is stratified, and a quality control sample matrix is ​​constructed to characterize quality control estimation value information and quality control feature set information; the quality control estimation value is quantified by the quality control feature set, and its usage compliance rate is evaluated; based on the usage compliance rate, the quality control sample matrix is ​​converted into a Boolean matrix, the medical order correlation between patients is analyzed, and the patient information corresponding to the maximum correlation value is output to the medical staff port; the present invention can realize effective stratification and feature characterization of medical cases, can improve the accuracy of quantifying quality control estimation values ​​and evaluating usage compliance rates, and can efficiently analyze the medical order correlation between patients, provide scientific and effective quality control information and auxiliary decision support for medical staff, and help optimize the use strategy of antimicrobial drugs and reduce irrational drug use. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] The accompanying drawings are used to provide further understanding of the present invention and constitute a part of the specification. They are used to explain the present invention together with the embodiments of the present invention and do not constitute a limitation of the present invention.

[0052] Figure 1 It is a schematic diagram of the steps of an antimicrobial drug quality control method based on data analysis of the present invention. DETAILED DESCRIPTION

[0053] 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 only 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.

[0054] In the first embodiment of the present invention, a data analysis-based antimicrobial drug quality control system is provided, the system comprising: a data warehouse module, a feature characterization module, a data analysis module and a quality control association module;

[0055] The data warehouse module is used to import the patient's medical case into the data warehouse after the patient's authorization. The data warehouse performs data stratification based on disease type, antimicrobial drug type and medication habit data, including first sample stratification, second sample stratification and third sample stratification;

[0056] Wherein, the data warehouse module includes a data import unit and a data stratification unit;

[0057] The data import unit is used to import medical cases into the data warehouse, and the data warehouse adds coding marks to the imported medical cases; it is used to identify medical record information in the medical cases, and the medical record information includes patient information, disease type, antimicrobial drug type and medication habit data, and the medication habit data includes medication date and medication dosage within the medication date;

[0058] The data stratification unit is used to establish sample stratification, including a first sample stratification, a second sample stratification and a third sample stratification, wherein the first sample stratification records various disease types and uniformly codes the disease types, the second sample stratification records the types of antimicrobial drugs and uniformly codes the types of antimicrobial drugs, and the third sample stratification records all medical cases of the same patient and uniformly codes the patient;

[0059] The feature characterization module constructs a quality control sample matrix based on the first sample stratification and the second sample stratification, and characterizes the quality control estimation value information and the quality control feature set information through the quality control sample matrix;

[0060] Wherein, the feature characterization module includes a quality control sample matrix model unit and a quality control feature collection unit;

[0061] The quality control sample matrix model unit constructs a quality control sample matrix based on the first sample stratification and the second sample stratification, wherein the row number of the quality control sample matrix corresponds to the code number of the disease type in the first sample stratification, and the column number of the quality control sample matrix corresponds to the code number of the antimicrobial drug type in the second sample stratification, and the matrix element at the xth row and the yth column in the quality control sample matrix is ​​recorded as the quality control estimation value;

[0062] The quality control feature collection unit generates a quality control feature set through the third sample stratification based on the quality control sample matrix;

[0063] The data analysis module is used to quantify the quality control estimation value through the quality control feature set and evaluate the usage compliance rate of the quality control estimation value;

[0064] Wherein, the data analysis module includes a data quantification unit and a data evaluation unit;

[0065] The data quantification unit is used to extract medication habit data in medical cases, identify medication dates in the medication habit data, collect the minimum medication date and the maximum medication date of the medical case records in the quality control feature set, and form the medication time range of the quality control feature set; within the medication time range, the total amount of limited daily doses of antibiotics purchased from different manufacturers is counted, and the total amount of medication doses of antibiotics in the quality control feature set is counted, and the quality control estimate is obtained by the ratio of the total amount of medication doses to the total amount of limited daily doses;

[0066] The data evaluation unit evaluates the usage compliance rate of the quality control estimation value based on the quality control sample matrix;

[0067] The quality control association module converts the quality control sample matrix into a Boolean matrix based on the usage compliance rate, analyzes the medical order association between patients through the Boolean matrix, and outputs the patient information corresponding to the maximum medical order association to the medical staff port;

[0068] Wherein, the quality control association module includes an association analysis unit and an association screening unit;

[0069] The association analysis unit is used to preset a usage compliance rate threshold, and if the usage compliance rate is greater than or equal to the usage compliance rate threshold, the quality control estimation value is set to a value of 1, otherwise the quality control estimation value is set to a value of 0, and the quality control matrix is ​​converted into a Boolean matrix;

[0070] The association screening unit analyzes the medical order associations between patients based on the Boolean matrix, and screens out the patient information corresponding to the maximum medical order association to send to the medical staff port.

[0071] See also Figure 1 In the second embodiment, a method for quality control of antimicrobial drugs based on data analysis is provided to cooperate with the execution of the system in the first embodiment. The method includes the following steps:

[0072] Step S1: Import the patient's medical records into the data warehouse, and the data warehouse performs data stratification based on disease type, antimicrobial drug type, and medication habit data, including first sample stratification, second sample stratification, and third sample stratification;

[0073] For example, after authorization by the patient, the medical case is imported into the data warehouse, and the data warehouse adds a coding mark to the imported medical case, which is recorded as M e ; Identify medical cases M e The medical record information includes patient information, disease type, antimicrobial drug type and medication habit data, and the medication habit data includes medication date and medication dosage within the medication date;

[0074] The data warehouse establishes sample stratification, including the first sample stratification, the second sample stratification and the third sample stratification. The first sample stratification records each disease type and uniformly codes the disease types. Any x-th disease type is recorded as D x The second sample stratification records the type of antimicrobial drugs, and uniformly codes the antimicrobial drug types. Any y-th antimicrobial drug type is recorded as A y In the third sample stratification, all medical cases of the same patient are recorded, and the patients are uniformly coded. Any h-th patient is recorded as S h ;

[0075] Step S2: constructing a quality control sample matrix based on the first sample stratification and the second sample stratification, and representing the quality control estimation value information and the quality control feature set information through the quality control sample matrix;

[0076] Exemplarily, based on the first sample stratification and the second sample stratification, a quality control sample matrix is ​​constructed, the row number of the quality control sample matrix corresponds to the code number of the disease type in the first sample stratification, and the column number of the quality control sample matrix corresponds to the code number of the antimicrobial drug type in the second sample stratification, then the matrix element of the xth row and yth column in the quality control sample matrix is ​​recorded as the quality control estimate value r(D x , A y );

[0077] Based on the quality control sample matrix, the quality control feature set is generated through the third sample stratification, and the quality control estimation value r(D x , A y ) corresponds to the quality control feature set generated, denoted as f(D x , A y), the quality control feature set is generated as follows:

[0078] Based on the quality control sample matrix, when the same patient S h Medical Cases e Disease type D x and antimicrobial type A y When the medical case M e Recorded in the quality control feature set f(D x , A y )middle;

[0079] The same patient S h After all medical cases of are mapped to the quality control feature set, the corresponding patient S h The quality control matrix is ​​denoted as R(S h );

[0080] Step S3: quantifying the quality control estimation value through the quality control feature set, and evaluating the usage compliance rate of the quality control estimation value;

[0081] For example, by using the quality control feature set f(D x , A y ) to quantify the quality control estimate r(D x , A y ), the quantization process is as follows:

[0082] Extract medical case M e The medication habit data in the medication habit data are identified, and the medication date in the medication habit data is collected, and the quality control feature set f(D x , A y ) constitutes the quality control feature set f(D x , A y ) medication time range;

[0083] Within the medication time range, statistics on the types of antimicrobial drugs purchased from different manufacturers A y The total amount of the defined daily dose, statistical quality control feature set f(D x , A y ) Antimicrobial drug type A y The total amount of the dosage of the drug is calculated by comparing the total amount of the dosage to the total amount of the limited daily dose to obtain the quality control estimate value r(D x , A y );

[0084] Based on the quality control sample matrix, the quality control estimate r(D x , A y ) usage compliance rate:

[0085]

[0086] In the formula, UCR(D x , A y ) represents the quality control estimate r(D x , A y ) usage compliance rate, r(A y ) represents the mean of the quality control estimation value, and the yth column of the quality control sample matrix is ​​summed and averaged to obtain Among them, U represents the quality control sample matrix R(S h ), that is, the total number of disease types, σ represents the standard deviation of the quality control estimate, and

[0087] Step S4: based on the usage compliance rate, the quality control sample matrix is ​​converted into a Boolean matrix, the correlation between the medical orders of the patients is analyzed through the Boolean matrix, and the patient information corresponding to the maximum medical order correlation is output to the medical staff port;

[0088] For example, the usage compliance rate threshold is preset. If the usage compliance rate UCR (D x , A y ) is greater than or equal to the compliance rate threshold, then the quality control estimate value r(D x , A y )=1, otherwise let the quality control estimate value r(D x , A y )=0, then the quality control matrix R(S h ) is converted into a Boolean matrix BR(S h );

[0089] Based on the Boolean matrix, analyze the correlation between patients' medical orders:

[0090]

[0091] In the formula, Q(S h , S l ) indicates patient S h and patient S l The degree of medical advice correlation between them, and h≠l, NUM[BR(S h )∩BR(S l )] represents the Boolean matrix BR(S h ) and the Boolean matrix BR(S l ) contains the number of 1s after the intersection logic operation, NUM[BR(S h )∪BR(S l )] represents the Boolean matrix BR(S h ) and the Boolean matrix BR(S l ) after the logical union operation;

[0092] Let l = l + 1, perform iterative analysis, and obtain patient S h Except for patients S h The medical order correlation between each patient outside the group is calculated, and the patient information corresponding to the maximum medical order correlation is output and sent to the medical staff port.

[0093] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device.

[0094] Finally, it should be noted that the above is only a preferred embodiment of the present invention and is not intended to limit the present invention. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art can still modify the technical solutions described in the aforementioned embodiments or replace some of the technical features therein by equivalents. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A method for quality control of antimicrobial drugs based on data analysis, characterized in that: The method comprises the following steps: Step S1: Import the patient's medical records into the data warehouse, and the data warehouse performs data stratification based on disease type, antimicrobial drug type, and medication habit data, including first sample stratification, second sample stratification, and third sample stratification; Step S2: constructing a quality control sample matrix based on the first sample stratification and the second sample stratification, and representing the quality control estimation value information and the quality control feature set information through the quality control sample matrix; Step S3: quantifying the quality control estimation value through the quality control feature set, and evaluating the usage compliance rate of the quality control estimation value; Step S4: Based on the usage compliance rate, the quality control sample matrix is ​​converted into a Boolean matrix. Through the Boolean matrix, the correlation between the medical orders of the patients is analyzed, and the patient information corresponding to the maximum medical order correlation is output to the medical staff port.

2. The method for quality control of antimicrobial drugs based on data analysis according to claim 1, characterized in that: The specific implementation process of step S1 includes: After the patient's authorization, the medical case is imported into the data warehouse, and the data warehouse adds a coding mark to the imported medical case, which is recorded as M e ; Identify medical cases M e The medical record information includes patient information, disease type, antimicrobial drug type and medication habit data, and the medication habit data includes medication date and medication dosage within the medication date; The data warehouse establishes sample stratification, including the first sample stratification, the second sample stratification and the third sample stratification. The first sample stratification records each disease type and uniformly codes the disease types. Any x-th disease type is recorded as D x The second sample stratification records the type of antimicrobial drugs, and uniformly codes the antimicrobial drug types. Any y-th antimicrobial drug type is recorded as A y In the third sample stratification, all medical cases of the same patient are recorded, and the patients are uniformly coded. Any h-th patient is recorded as S h .

3. The method for quality control of antimicrobial drugs based on data analysis according to claim 2, characterized in that: The specific implementation process of step S2 includes: Based on the first sample stratification and the second sample stratification, a quality control sample matrix is ​​constructed, wherein the row number of the quality control sample matrix corresponds to the code number of the disease type in the first sample stratification, and the column number of the quality control sample matrix corresponds to the code number of the antimicrobial drug type in the second sample stratification. The matrix element of the xth row and the yth column in the quality control sample matrix is ​​recorded as the quality control estimate value r(D x , A y ); Based on the quality control sample matrix, the quality control feature set is generated through the third sample stratification, and the quality control estimation value r(D x , A y ) corresponds to the quality control feature set generated, denoted as f(D x , A y ), the quality control feature set is generated as follows: Based on the quality control sample matrix, when the same patient S h Medical Cases e Disease type D x and antimicrobial type A y When the medical case M e Recorded in the quality control feature set f(D x , A y )middle; The same patient S h After all medical cases of are mapped to the quality control feature set, the corresponding patient S h The quality control matrix is ​​denoted as R(S h ).

4. The method for quality control of antimicrobial drugs based on data analysis according to claim 3, characterized in that: The specific implementation process of step S3 includes: Through the quality control feature set f(D x , A y ) to quantify the quality control estimate r(D x , A y ), the quantization process is as follows: Extract medical case M e The medication habit data in the medication habit data are identified, and the medication date in the medication habit data is collected, and the quality control feature set f(D x , A y ) constitutes the quality control feature set f(D x , A y ) medication time range; Within the medication time range, statistics on the types of antimicrobial drugs purchased from different manufacturers A y The total amount of the defined daily dose, statistical quality control feature set f(D x , A y ) Antimicrobial drug type A y The total amount of the dosage of the drug is calculated by comparing the total amount of the dosage of the drug to the total amount of the limited daily dose to obtain the quality control estimate value r(D x , A y ); Based on the quality control sample matrix, the quality control estimate r(D x , A y ) usage compliance rate: In the formula, UCR(D x , A y ) represents the quality control estimate r(D x , A y ) usage compliance rate, r(A y ) represents the mean of the quality control estimation value, and the yth column of the quality control sample matrix is ​​summed and averaged to obtain A y ), where U represents the quality control sample matrix R(S h ), that is, the total number of disease types, σ represents the standard deviation of the quality control estimate, and 5. The method for quality control of antimicrobial drugs based on data analysis according to claim 4, characterized in that: The specific implementation process of step S4 includes: Preset usage match rate threshold, if using match rate UCR (D x , A y ) is greater than or equal to the compliance rate threshold, then the quality control estimate value r(D x , A y )=1, otherwise let the quality control estimate value r(D x , A y )=0, then the quality control matrix R(S h ) is converted into a Boolean matrix BR(S h ); Based on the Boolean matrix, analyze the correlation between patients' medical orders: In the formula, Q(S h , S l ) indicates patient S h and patient S l The degree of medical advice correlation between them, and h≠l, NUM[BR(S h )∩BR(S l )] represents the Boolean matrix BR(S h ) and the Boolean matrix BR(S l ) contains the number of 1s after the intersection logic operation, NUM[BR(S h )∪BR(S l )] represents the Boolean matrix BR(S h ) and the Boolean matrix BR(S l ) after the logical union operation; Let l = l + 1, perform iterative analysis, and obtain patient S h Except for patients S h The medical order correlation between each patient outside the group is calculated, and the patient information corresponding to the maximum medical order correlation is output and sent to the medical staff port.

6. An antimicrobial drug quality control system based on data analysis, executing an antimicrobial drug quality control method based on data analysis as claimed in any one of claims 1 to 5, characterized in that: The system includes a data warehouse module, a feature characterization module, a data analysis module and a quality control association module; The data warehouse module is used to import the patient's medical case into the data warehouse after the patient's authorization. The data warehouse performs data stratification based on disease type, antimicrobial drug type and medication habit data, including first sample stratification, second sample stratification and third sample stratification; The feature characterization module constructs a quality control sample matrix based on the first sample stratification and the second sample stratification, and characterizes the quality control estimation value information and the quality control feature set information through the quality control sample matrix; The data analysis module is used to quantify the quality control estimation value through the quality control feature set and evaluate the usage compliance rate of the quality control estimation value; The quality control association module converts the quality control sample matrix into a Boolean matrix based on the usage compliance rate, analyzes the medical order correlation between patients through the Boolean matrix, and outputs the patient information corresponding to the maximum medical order correlation to the medical staff port.

7. The antimicrobial drug quality control system based on data analysis according to claim 6, characterized in that: The data warehouse module includes a data import unit and a data stratification unit; The data import unit is used to import medical cases into the data warehouse, and the data warehouse adds coding marks to the imported medical cases; it is used to identify medical record information in the medical cases, and the medical record information includes patient information, disease type, antimicrobial drug type and medication habit data, and the medication habit data includes medication date and medication dosage within the medication date; The data stratification unit is used to establish sample stratification, including a first sample stratification, a second sample stratification and a third sample stratification. The first sample stratification records various disease types and uniformly encodes the disease types. The second sample stratification records the types of antimicrobial drugs and uniformly encodes the antimicrobial drug types. The third sample stratification records all medical cases of the same patient and uniformly encodes the patients.

8. The antimicrobial drug quality control system based on data analysis according to claim 6, characterized in that: The feature characterization module includes a quality control sample matrix model unit and a quality control feature collection unit; The quality control sample matrix model unit constructs a quality control sample matrix based on the first sample stratification and the second sample stratification, wherein the row number of the quality control sample matrix corresponds to the code number of the disease type in the first sample stratification, and the column number of the quality control sample matrix corresponds to the code number of the antimicrobial drug type in the second sample stratification, and the matrix element at the xth row and the yth column in the quality control sample matrix is ​​recorded as the quality control estimation value; The quality control feature collection unit generates a quality control feature set through the third sample stratification based on the quality control sample matrix.

9. The antimicrobial drug quality control system based on data analysis according to claim 6, characterized in that: The data analysis module includes a data quantification unit and a data evaluation unit; The data quantification unit is used to extract medication habit data in medical cases, identify medication dates in the medication habit data, collect the minimum medication date and the maximum medication date of the medical case records in the quality control feature set, and form the medication time range of the quality control feature set; within the medication time range, the total amount of limited daily doses of antibiotics purchased from different manufacturers is counted, and the total amount of medication doses of antibiotics in the quality control feature set is counted, and the quality control estimate is obtained by the ratio of the total amount of medication doses to the total amount of limited daily doses; The data evaluation unit evaluates the usage compliance rate of the quality control estimation value based on the quality control sample matrix.

10. The antimicrobial drug quality control system based on data analysis according to claim 6, characterized in that: The quality control association module includes an association analysis unit and an association screening unit; The association analysis unit is used to preset a usage compliance rate threshold, and if the usage compliance rate is greater than or equal to the usage compliance rate threshold, the quality control estimation value is set to a value of 1, otherwise the quality control estimation value is set to a value of 0, and the quality control matrix is ​​converted into a Boolean matrix; The association screening unit analyzes the medical order associations between patients based on the Boolean matrix, and screens out the patient information corresponding to the maximum medical order association to send to the medical staff port.

Images