Finished product quality evaluation method and system for lung-heat-clearing and inflammation-diminishing pills

Abstract

The invention relates to a method and a system for evaluating the quality of a finished product of lung-heat-clearing and inflammation-diminishing pills. The method comprises the following steps: S1, acquiring near infrared spectrum data of drugs of a plurality of specified production batches; s2, preprocessing the near infrared spectrum data to obtain preprocessed spectrum data; s3, establishing a data dimensionality reduction model, and performing dimensionality reduction on the preprocessed spectral data by using the data dimensionality reduction model to obtain dimensionality reduction score data; and S4, obtaining a Hotelling T2 statistic based on the dimension reduction score data, and determining a warning line threshold value and a control line threshold value so as to evaluate the quality of drugs in a production batch. According to the invention, the near infrared spectrum technology and the chemometrics are combined, a rapid and lossless drug quality evaluation method is established, and the problems of sample waste and tedious detection process in the existing drug quality detection technology are solved.

Description

Technical Field

[0001] The present invention relates to the technical field of drug detection, and in particular to a method and system for evaluating the finished product quality of Qingfei Xiaoyan Pills. Background Art

[0002] Currently, the evaluation method for preparations is to measure the content of quality markers in the preparations by using HPLC method. This method has the disadvantages of long time consumption, complex method, and loss of the produced preparations. In the prior art, the method of precise evaluation and control of "quality - quantity" pointed out in the paper "Research Status of Traditional Chinese Medicine Quality Evaluation and Discussion on the 'Quality - Quantity' Dual - Standard Evaluation Method" is still based on using high - performance liquid chromatography to measure the fingerprint spectrum and quality markers of traditional Chinese medicine. The document with the patent number CN115293480A collects raw materials, intermediates, finished products, etc. of multiple batches of traditional Chinese medicine preparations for multi - dimensional index detection, reduces the multi - dimensional indexes to the same dimension, and screens out the indexes representing the quality of traditional Chinese medicine preparations by comparing the weights of different dimensions. However, in general, pharmaceutical enterprises use the content of active ingredients and moisture in the finished pills as the quality release standard. Measuring all the indexes of the pills is time - consuming. Moreover, this patent does not point out how to evaluate the production batches after screening important indexes. Summary of the Invention

[0003] To solve the above - mentioned technical problems, the present invention provides a method and system for evaluating the finished product quality of Qingfei Xiaoyan Pills. The method includes the following steps:

[0004] S1: Obtain the near - infrared spectral data of drugs of a specified number of production batches;

[0005] S2: Pre - process the near - infrared spectral data to obtain pre - processed spectral data;

[0006] S3: Establish a data dimensionality reduction model, and use the data dimensionality reduction model to reduce the dimension of the pre - processed spectral data to obtain dimensionality reduction score data;

[0007] S4: Obtain the Hotelling T2 statistic based on the dimensionality reduction score data, and use the Hotelling T2 statistics with different confidence levels as the warning line threshold and the control line threshold to evaluate the quality of drugs in the production batches.

[0008] In an embodiment of the present invention, the method for obtaining the pre - processed spectral data includes: pre - processing the near - infrared spectral data by using a method including standard normal variate transformation, linear detrending, multiplicative scatter correction, and Savitzky - Golay first - order derivative to obtain the pre - processed spectral data.

[0009] In an embodiment of the present invention, the specific method for obtaining the dimensionality reduction score data includes:

[0010] Form a matrix \(Z\) with \(n\) rows and \(m\) columns by arranging the preprocessed spectral data column by column;

[0011] Perform zero-mean normalization on each row of the matrix \(Z\) to obtain the matrix \(Z\) after zero-mean normalization;

[0012] According to the matrix \(Z\) after zero-mean normalization, calculate the covariance matrix \(C\) to obtain the eigenvalues and corresponding eigenvectors of the covariance matrix \(C\);

[0013] Arrange the eigenvectors in a matrix in descending order of the corresponding eigenvalues row by row, and take the first \(k\) rows to form the matrix \(P\);

[0014] Based on the matrix \(P\), obtain the data after dimensionality reduction to \(k\) dimensions and the dimensionality reduction score data.

[0015] In an embodiment of the present invention, the calculation formula of the covariance matrix \(C\) is:

[0016]

[0017] where \((\cdot)^T\) T represents the transpose of the matrix.

[0018] In an embodiment of the present invention, the calculation method of the Hotelling \(T^2\) 2 statistic is:

[0019] \(T^2\) 2 \(=X^T\) T \(C^{-1}\) -1 \(X\)

[0020] where \(X^T\) T represents the transpose of the \(k\)-th component in the matrix \(Z\), and \(C^{-1}\) -1 represents the inverse of the covariance matrix \(C\).

[0021] In an embodiment of the present invention, the warning line threshold is the Hotelling \(T^2\) 2 statistic with a confidence level of 0.95, and the control line threshold is the Hotelling \(T^2\) 2 statistic with a confidence level of 0.99; the calculation formula of the warning line threshold or the control line threshold is:

[0022]

[0023] where \(\alpha\) represents the preset probability value, \(1 - \alpha\) is the confidence level, \(n\) represents the number of drug samples, and \(F\) α (k, n - k) represents the value of the \(F\)-distribution with the first degree of freedom \(k\) and the second degree of freedom \(n - k\).

[0024] In an embodiment of the present invention, the method for evaluating the quality of drugs in a production batch includes:

[0025] Warn against the drugs in the production batches that exceed the warning line threshold but do not exceed the control line threshold, and determine that the drugs in the production batches that exceed the control line threshold are unqualified.

[0026] Based on the same inventive concept as the method, the present invention also provides a finished product quality evaluation system for Qingfei Xiaoyan Pills, which system includes the following modules:

[0027] A spectral data acquisition module, configured to obtain near-infrared spectral data of drugs in a specified number of production batches;

[0028] A data preprocessing module, configured to preprocess the near-infrared spectral data to obtain preprocessed spectral data;

[0029] A data dimensionality reduction module, configured to establish a data dimensionality reduction model, and use the data dimensionality reduction model to reduce the dimensionality of the preprocessed spectral data to obtain dimensionality reduction score data;

[0030] A drug batch quality evaluation module, configured to use the Hotelling T 2 statistic obtained based on the dimensionality reduction score data, and use the Hotelling T 2 statistics with different confidence levels as the warning line threshold and the control line threshold to evaluate the quality of drugs in production batches.

[0031] The present invention also provides an electronic device, which includes a processor, a memory, and a bus system. The processor and the memory are connected through the bus system. The memory is used to store instructions, and the processor is used to execute the instructions stored in the memory to implement any one of the finished product quality evaluation methods for Qingfei Xiaoyan Pills.

[0032] The present invention also provides a computer storage medium, which stores a computer software product. The computer software product includes several instructions for causing a computer device to execute any one of the finished product quality evaluation methods for Qingfei Xiaoyan Pills.

[0033] The above technical solutions of the present invention have the following advantages compared with the prior art:

[0034] The present invention combines near-infrared spectroscopy technology with chemometrics to establish a fast and non-destructive evaluation method, which reduces costs and increases efficiency, saving time and moisture. Moreover, through near-infrared spectroscopy technology, a large amount of information contained in the finished product can be extracted to identify the production effects other than the components detected by conventional methods. Description of the Drawings

[0035] In order to make the content of the present invention easier to be clearly understood, the following further details the present invention according to specific embodiments of the present invention in conjunction with the drawings, where

[0036] Figure 1 It is a flow chart of a method for evaluating the finished product quality of Qingfei Xiaoyan Pills provided in an embodiment of the present invention;

[0037] Figure 2 It is the Hotelling T 2 value, warning line threshold and control line threshold obtained based on the constructed data dimensionality reduction PCA model in an embodiment of the present invention;

[0038] Figure 3 It is a schematic diagram of the experimental results of predicting sample data using the constructed PCA model in an embodiment of the present invention;

[0039] Figure 4 It is a structural diagram of a system for evaluating the finished product quality of Qingfei Xiaoyan Pills provided in an embodiment of the present invention;

[0040] Explanation of reference numerals in the specification drawings:

[0041] 100, spectral data acquisition module; 200, data preprocessing module; 300, data dimensionality reduction module; 400, drug batch quality evaluation module. Detailed implementation manners

[0042] The present invention will be further described below in conjunction with the accompanying drawings and specific embodiments, so that those skilled in the art can better understand the present invention and be able to implement it, but the specific embodiments cited shall not be construed as limiting the present invention.

[0043] Embodiment 1

[0044] Refer to Figure 1 As shown, the present invention provides a method for evaluating the finished product quality of Qingfei Xiaoyan Pills, and the system includes the following steps:

[0045] S1: Obtain the near-infrared spectral data of drugs of a specified number of production batches;

[0046] S2: Preprocess the near-infrared spectral data by using a method including standard normal transformation, linear detrending, multiplicative scatter correction, and Savitzky-Golay first derivative to obtain the preprocessed spectral data;

[0047] S3: Establish a data dimensionality reduction model, and use the data dimensionality reduction model to reduce the dimension of the preprocessed spectral data to obtain the dimension reduction score data;

[0048] S4: Use the Hotelling T 2 statistic obtained based on the dimension reduction score data, and use the Hotelling T 2 statistics with different confidence levels as the warning line threshold and the control line threshold to evaluate the quality of drugs in the production batch.

[0049] In this embodiment, the specific method for obtaining the dimensionality reduction score data includes:

[0050] Form a matrix Z with n rows and m columns by arranging the preprocessed spectral data column by column;

[0051] Perform zero-mean normalization on each row of the matrix Z to obtain the matrix Z after zero-mean normalization;

[0052] According to the matrix Z after zero-mean normalization, calculate the covariance matrix C to obtain the eigenvalues and corresponding eigenvectors of the covariance matrix C; where the calculation formula of the covariance matrix C is:

[0053]

[0054] where (·) T represents the transpose of the matrix.

[0055] Arrange the eigenvectors in a matrix by rows from top to bottom according to the corresponding eigenvalue magnitudes, and take the first k rows to form a matrix P;

[0056] Based on the matrix P, obtain the data after dimensionality reduction to k dimensions and the dimensionality reduction score data.

[0057] The calculation method of the Hotelling T 2 statistic obtained based on the dimensionality reduction score data is:

[0058] T 2 = X T C -1 X

[0059] where, X T represents the transpose of the k-th component in the matrix Z, and C -1 represents the inverse of the covariance matrix C.

[0060] In this embodiment, the calculation formula of the warning line threshold or the control line threshold is:

[0061]

[0062] where, α represents the preset probability value, 1 - α is the confidence level, n represents the number of drug samples, and F α (k, n - k) represents the value of the F-distribution with the first degree of freedom being k and the second degree of freedom being n - k. Let α = 0.05, and the warning line threshold is the Hotelling T 2 statistic with a confidence level of 0.95. Let α = 0.01, and the control line threshold is the Hotelling T 2 statistic.

[0063] In step S4 of this embodiment, the method for evaluating the quality of the drugs in the production batch includes:

[0064] Warn about the drugs in the production batches that exceed the warning line threshold but do not exceed the control line threshold, and determine that the drugs in the production batches that exceed the control line threshold are unqualified.

[0065] The beneficial effects of the present invention are elaborated below through specific examples. The finished Qingfei Xiaoyan Pills are scanned spectroscopically using a near-infrared spectrometer at an interval of 10 s for 10 min, and 7 optimal batches of production are determined according to the production site of the pharmaceutical enterprise. The near-infrared spectral data of the drugs produced in the 7 optimal batches are imported into the Unscrambler software. The spectrum is preprocessed using methods including standard normal variate (SNV), linear detrending (Detrend), multiplicative scatter correction (MSC), and Savitzky-Golay first derivative, and the preprocessed data is subjected to principal component analysis (PCA) for dimensionality reduction analysis to establish a PCA model. The Hotelling T 2 value is obtained using the PCA dimensionality reduction data, and the warning line and control line are obtained. The warning line T 2 = 3.89, and the control line T 2 = 6.75, as Figure 2 shown.

[0066] The near-infrared spectral data of a new batch of drugs is collected, imported into the Unscrambler software, and the established PCA model is used to predict the new batch, obtaining the Hotelling T 2 value corresponding to each spectral point of the new batch. The new production batch of finished products is evaluated according to the known warning line and control line. As Figure 3 can be seen, the Hotelling T 2 value estimated by detecting the drugs in the batch to be detected through the constructed PCA model is between the warning line and the control line, indicating that the quality of the ingredients of this batch of drugs is qualified.

[0067] Example 2

[0068] Based on the same inventive concept as the method described in Example 1, the present invention also provides a comprehensive evaluation system based on the finished Qingfei Xiaoyan Pills. As Figure 4 shown, the system includes the following modules:

[0069] A spectral data acquisition module 100 for obtaining the near-infrared spectral data of drugs in a specified number of production batches;

[0070] A data preprocessing module 200 for preprocessing the near-infrared spectral data to obtain preprocessed spectral data;

[0071] A data dimensionality reduction module 300 for establishing a data dimensionality reduction model and using the data dimensionality reduction model to perform dimensionality reduction on the preprocessed spectral data to obtain dimensionality reduction score data;

[0072] The drug batch quality evaluation module 400 is used to obtain the Hotelling T2 statistic based on the dimensionality reduction score data, and use the Hotelling T2 statistics with different confidence levels as the warning line threshold and the control line threshold to evaluate the quality of the drugs in the production batch.

[0073] A comprehensive evaluation system for Qingfei Xiaoyan Pills finished products according to this embodiment is used to implement the aforementioned comprehensive evaluation method for Qingfei Xiaoyan Pills finished products. Therefore, the specific implementation manners in the comprehensive evaluation system for Qingfei Xiaoyan Pills finished products can be seen in the embodiment part of the aforementioned comprehensive evaluation method for Qingfei Xiaoyan Pills finished products. For example, the spectral data acquisition module 100, the data preprocessing module 200, the data dimensionality reduction module 300, and the drug batch quality evaluation module 400 are respectively used to correspondingly implement steps S1, S2, S3, and S4 in the aforementioned comprehensive evaluation method for Qingfei Xiaoyan Pills finished products. Therefore, the specific implementation manners can refer to the descriptions of the corresponding individual part embodiments. To avoid redundancy, they will not be elaborated here.

[0074] Embodiment III

[0075] The present invention also provides an electronic device, which includes a processor, a memory, and a bus system. The processor and the memory are connected through the bus system. The memory is used to store instructions, and the processor is used to execute the instructions stored in the memory to implement the quality evaluation method for Qingfei Xiaoyan Pills finished products according to any one of the first embodiments.

[0076] Embodiment IV

[0077] The present invention also provides a computer storage medium, which stores a computer software product. The computer software product includes several instructions for causing a computer device to execute the quality evaluation method for Qingfei Xiaoyan Pills finished products according to any one of the first embodiments.

[0078] Those skilled in the art should understand that the embodiments of the present application can be provided as a method, a system, or a computer program product. Therefore, the present application can adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present application can adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk memories, CD-ROMs, optical memories, etc.) containing computer-usable program codes.

[0079] This application is described with reference to the flowcharts and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the present application. It should be understood that each flow and / or block in the flowcharts and / or block diagrams, and the combination of flows and / or blocks in the flowcharts and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, such that the instructions executed by the processor of the computer or other programmable data processing device produce means for implementing the functions specified in one flow Figure 1 one flow or multiple flows and / or blocks Figure 1 or means for implementing the functions specified in multiple blocks.

[0080] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to work in a specific manner, such that the instructions stored in the computer-readable memory produce a manufactured article including instruction means that implement the functions specified in one flow Figure 1 one flow or multiple flows and / or blocks Figure 1 or means for implementing the functions specified in multiple blocks.

[0081] These computer program instructions can also be loaded onto a computer or other programmable data processing device, such that a series of operating steps are executed on the computer or other programmable device to generate a computer-implemented process, so that the instructions executed on the computer or other programmable device provide steps for implementing the functions specified in one flow Figure 1 one flow or multiple flows and / or blocks Figure 1 or means for implementing the functions specified in multiple blocks.

[0082] Obviously, the above embodiments are merely examples for clear illustration and are not limitations on the implementation manners. For those of ordinary skill in the art, other different forms of changes or modifications can be made based on the above description. It is not necessary and impossible to exhaustively list all implementation manners here. And the obvious changes or modifications derived therefrom are still within the protection scope of the present invention.

Claims

1. A method for evaluating the finished product quality of Qingfei Xiaoyan Pills, characterized in that, Including: S1: Obtain the near-infrared spectral data of drugs from specified multiple production batches; S2: Preprocess the near-infrared spectral data to obtain preprocessed spectral data; S3: Establish a data dimensionality reduction model, and use the data dimensionality reduction model to reduce the dimensionality of the preprocessed spectral data to obtain dimensionality reduction score data; S4: Obtain the Hotelling T statistic based on the dimensionality reduction score data, and determine the warning line threshold and the control line threshold to evaluate the quality of the drugs in the production batch. 2 statistic, and determine the warning line threshold and the control line threshold to evaluate the quality of the drugs in the production batch.

2. The quality assessment method for the finished Qingfei Xiaoyan Pills according to claim 1, wherein: The method for obtaining the preprocessed spectral data includes: preprocessing the near-infrared spectral data by using a method including standard normal transformation, linear detrending, multiplicative scatter correction, and Savitzky-Golay first derivative to obtain the preprocessed spectral data.

3. The finished product quality assessment method of Qingfei Xiaoyan Pills according to claim 1, characterized in that: The specific method for obtaining the dimensionality reduction score data includes: Form a matrix Z of n rows and m columns with the preprocessed spectral data by columns; Perform zero-mean normalization on each row of matrix Z to obtain matrix Z after zero-mean normalization; According to the matrix Z after zero-mean normalization, calculate the covariance matrix C to obtain the eigenvalues and corresponding eigenvectors of the covariance matrix C; Arrange the eigenvectors in a matrix by rows from top to bottom according to the corresponding eigenvalue magnitudes, and take the first k rows to form matrix P; Based on matrix P, obtain the data after dimensionality reduction to k dimensions and the dimensionality reduction score data.

4. The quality evaluation method of the finished Qingfei Xiaoyan Pills according to claim 3, characterized in that: The calculation formula for the covariance matrix C is: where (·) T represents the transpose of a matrix.

5. The finished product quality evaluation method of Qingfei Xiaoyan Pills according to claim 3, characterized in that: The Hotelling T 2 statistic is calculated as follows: T 2 = X T C -1 X Among them, X T represents the transpose of the k-th component in matrix Z, C -1 represents the inverse of the covariance matrix C.

6. The finished product quality evaluation method of Qingfei Xiaoyan Pills according to claim 1, characterized in that: The warning line threshold is the Hotelling T statistic with a confidence level of 0.95, and the control line threshold is the Hotelling T statistic with a confidence level of 0.99; the calculation formula for the warning line threshold or the control line threshold is as follows: 2 The warning line threshold is the Hotelling T statistic with a confidence level of 0.95, and the control line threshold is the Hotelling T statistic with a confidence level of 0.99; the calculation formula for the warning line threshold or the control line threshold is as follows: 2 The warning line threshold is the Hotelling T statistic with a confidence level of 0.95, and the control line threshold is the Hotelling T statistic with a confidence level of 0.99; the calculation formula for the warning line threshold or the control line threshold is as follows: where α represents a preset probability value, 1 - α is the confidence level, n represents the number of drug samples, and F α (k, n - k) represents the value taken by an F-distribution with the first degree of freedom being k and the second degree of freedom being n - k.

7. The finished product quality evaluation method of Qingfei Xiaoyan Pills according to claim 6, characterized in that: The method for evaluating the quality of drugs in production batches includes: Give a warning to drugs in production batches that exceed the warning line threshold and do not exceed the control line threshold, and determine that drugs in production batches that exceed the control line threshold are unqualified.

8. A finished product quality assessment system for Qingfei Xiaoyan Pills, characterized in that, The system is used to implement the method for evaluating the finished product quality of Qingfei Xiaoyan Pills described in any one of claims 1 to 7, and specifically includes: A spectral data acquisition module, used to obtain the near-infrared spectral data of drugs from specified multiple production batches; A data preprocessing module, used to preprocess the near-infrared spectral data to obtain preprocessed spectral data; A data dimensionality reduction module, used to establish a data dimensionality reduction model and use the data dimensionality reduction model to reduce the dimensionality of the preprocessed spectral data to obtain dimensionality reduction score data; Drug batch quality evaluation module, which is used to obtain the Hotelling T 2 statistic based on the dimensionality reduction score data, and use the Hotelling T 2 statistics with different confidence levels as the warning line threshold and the control line threshold to evaluate the quality of the drugs in the production batch.

9. An electronic device, characterized in that, The electronic device includes a processor, a memory, and a bus system. The processor and the memory are connected through the bus system. The memory is used to store instructions, and the processor is used to execute the instructions stored in the memory to implement the method for evaluating the finished product quality of Qingfei Xiaoyan Pills described in any one of claims 1 to 7.

10. A computer storage medium, characterized in that, The computer storage medium stores a computer software product. The computer software product includes several instructions for causing a computer device to execute the method for evaluating the finished product quality of Qingfei Xiaoyan Pills described in any one of claims 1 to 7.

Images