Model for evaluating drug production risk index and construction method and application thereof

By constructing a drug production risk index model, the problem of unquantified management of drug risk factors has been solved, enabling quantitative assessment and dynamic management of drug production risks, and improving the effectiveness of drug regulation and risk early warning capabilities.

CN118917668AActive Publication Date: 2024-11-08湖南省药品审评与不良反应监测中心
View PDF 3 Cites 0 Cited by

Patent Information

Application Number
CN202411012431.X
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-07-26
Publication Date
2024-11-08
Estimated Expiration
2044-07-26

AI Technical Summary

Technical Problem

Existing technologies fail to quantify and manage drug risk factors, resulting in insufficient drug regulatory effectiveness and making it difficult to achieve scientific and rigorous risk management and early warning mechanisms.

Method used

A drug production risk index model is constructed. The weight values ​​and risk coefficients of each indicator are determined by the pecking order graph method. The model comprehensively considers the inherent risks, production process risks, quality control and assurance risks, compliance risks and product complaint and recall risks in the drug production process, thus forming a TRI model.

Benefits of technology

It has achieved quantitative management of drug risk factors, and the assessment results are highly consistent with the expert evaluation results, which improves the pertinence and timeliness of drug supervision. It can dynamically assess production line risks and initiate risk disposal in a timely manner.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure BDA0004964772840000021
    Figure BDA0004964772840000021
  • Figure BDA0004964772840000031
    Figure BDA0004964772840000031
  • Figure BDA0004964772840000041
    Figure BDA0004964772840000041
Patent Text Reader

Abstract

The invention relates to the field of drug supervision artificial intelligence application, in particular to a model for evaluating drug production risk indexes and a construction method and application thereof. The model for evaluating the drug production risk index is TR1 = alphamax + beta1 + beta2 + gamma + delta, tRI in the formula is the sum of risk index values of a certain medicine production line; alpha max is the maximum value of inherent risk indexes in all online products of the production line; beta1 is a production process risk index value; beta2 is a quality control and quality assurance risk index value; gamma is a compliance risk index value; delta is a product complaint recall risk index value; the risk index value (RI) is equal to 100 * Wi * Kj; in the formula, RI is a single-index risk index value; wi is a single index weight value determined according to an optimal sequence diagram method; kj is a single index risk coefficient determined by an expert. According to the model constructed by the invention, the practice of quantitative management of drug risk factors is realized, the model is used for evaluating drug production risk indexes, an evaluation result and an expert evaluation result have relatively good consistency, and kappa = 0.697, plt is calculated by using SPSS26.0; and the consistency rate is 80%.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the field of artificial intelligence applications for drug supervision, and in particular to a model for evaluating a drug production risk index, and a construction method and application thereof. Background Art

[0002] The newly revised Drug Administration Law states that drug administration should be centered on people's health, adhere to the principles of risk management, full-process control, and social co-governance, establish a scientific and strict supervision and management system, comprehensively improve drug quality, and ensure the safety, effectiveness, and accessibility of drugs. So far, the risk management concept has been clearly introduced into the field of drug supervision in the regulations. In order to innovate drug supervision methods, explore ways to improve supervision efficiency, save administrative resources, and prevent and control drug production quality risks, this paper attempts to use information technology and risk management technology to establish a drug production risk index model, scientifically divide drug production risk levels, establish a risk warning mechanism, and implement a risk-based drug inspection plan, so as to improve the ability of drug regulatory authorities to prevent and control drug production quality risks.

[0003] The US FDA drug regulatory model is widely recognized by the pharmaceutical industry, government departments or international organizations around the world for its transparency and authority, and its practices are highly respected. From the perspective of drug inspection, some practices are worth learning from. For example, in 2005, facing the actual situation that the demand for drug inspection far exceeds the ability of regulatory authorities to complete, the US FDA began to implement a risk-based production site selection model in cGMP routine supervision and inspection to supervise and inspect production sites, prioritize and formulate inspection plans, namely the site surveillance inspection list; in 2012, the US FDA amended Section 510(h) of the Federal Food, Drug, and Cosmetic Act (FD&C Act for short), adjusting the frequency of production site supervision and inspection from the original fixed frequency of at least once every two years to a risk-based inspection plan formulation strategy. For example, in the on-site monitoring of clinical trials, 25-30% of the total cost of clinical trials and about 70% of the time are spent on source data verification and error correction, while its significance in improving the quality of clinical trials is questionable. In 2013, in response to the problems existing in the on-site verification of clinical trials, in order to reduce the cost of on-site monitoring and improve the efficiency of monitoring, the US FDA issued a new monitoring guideline for clinical trials - "Clinical Research Supervision - Risk-Based Regulatory Approach", which introduced risk management into the on-site monitoring of drug clinical trials. This change in inspection thinking has played an important role in improving inspection efficiency and saving resources and costs.

[0004] Since the implementation of the revised Drug Administration Law in 2019, the concept of drug risk management has gradually penetrated into all aspects of drug research, production, operation and use in my country. As a management tool, risk management plays an increasingly important role in drug production practice. Domestic scholars or regulatory authorities have conducted a series of studies, such as Zhu Jialiang et al. studied the ideas of building a national drug sampling data sharing platform from the perspective of big data; Lin Weiqiang et al. [Research on drug quality risk warning model based on inspection data [J]. International IT Media Brand, 2018, 39(12): 127-130.] conducted a study on drug quality risk warning model based on inspection data; Sun Lingling et al. [Current status and problems of China's post-marketing drug sampling model [J]. Chinese Modern Applied Pharmacy, 2012, 29(8): 762-765.] studied the current status and problems of China's post-marketing drug sampling model. However, in drug regulatory activities, the application of this tool is relatively lagging behind. Jiangsu Evaluation Center explored the mechanism for initiating drug GMP inspections based on risk management [Drug GMP inspection initiation mechanism based on risk management [J]. Pharmaceutical Management, 2020, 28(3), 229-232.] and explored the establishment of a drug production risk assessment model; Wang Guangping [Drug safety risk early warning big data decision model design and methodology research [J]. China Food and Drug Administration, 2022(9): 138-147.] and others studied the design and methodology of drug safety risk early warning big data decision model, and used the hierarchical analysis method to analyze the model design criteria of the drug safety risk early warning big data decision system. However, there is no practice of quantitative management of drug risk factors. Summary of the invention

[0005] In view of the deficiency of the prior art in failing to quantitatively manage drug risk factors, the present invention provides a model for evaluating drug production risk index and a construction method and application thereof.

[0006] The first aspect of the present invention provides a model for evaluating the drug production risk index:

[0007] The drug production risk index model:

[0008] TRI=α max +β1+β2+γ+δ;

[0009] Where TRI is the risk index value of a drug production line; α max is the maximum inherent risk index of all online products in the production line; β1 is the production process risk index value; β2 is the quality control and quality assurance risk index value; γ is the compliance risk index value; δ is the product complaint recall risk index value.

[0010] The risk index value = 100 × W i ×Kj ;

[0011] The risk index value, RI, is a single indicator risk index value; W i is the weight value of a single indicator determined by the priority diagram method; K j It is the risk factor of a single indicator determined by experts.

[0012] Calculate W based on the priority diagram method i value:

[0013] Experts evaluate the importance of each indicator. The higher the score, the more important it is. Calculate the average of the expert scores for each indicator (X1, X2, ..., X n );

[0014] Compare the average values ​​of the calculated expert scores in pairs. If the indicator X i Ratio index X j Important, then X i 1 point; if equally important, X i 0.5 points; if indicator X j Ratio index X i Important, then X i Get 0 points; get a score of ij (where i, j = 1, 2, ..., n);

[0015] After obtaining the scoring results through pairwise comparison, the scores of each indicator are accumulated and obtained. i (where i = 1, 2, ..., n);

[0016] Calculate the total score of all indicators using the following formula:

[0017]

[0018] Calculate the weight value W of each indicator i (where i = 1, 2, ..., n), the formula is as follows:

[0019]

[0020] K j Determination of:

[0021] Risk Factor K j It refers to the size of the risk level corresponding to the next-level indicator (i.e. the fourth-level indicator), which is determined by experts and set to five levels: A, B, C, D, and E. The corresponding risk coefficients are 1.0, 0.8, 0.6, 0.4, and 0.2.

[0022] The second aspect of the present invention provides a method for constructing the drug production risk index model:

[0023] S1. Establish risk indicators: Based on the practice of drug production supervision, establish indicators at all levels of drug production risks from five aspects: inherent attributes of products, production process elements, quality control and assurance, GMP compliance, complaints and recalls;

[0024] S2. Questionnaire survey: A questionnaire survey was designed to obtain the experts’ opinions on the importance of each indicator. The higher the score, the more important it is. The average of the expert scores for each indicator (X1, X2, ..., X n );

[0025] S3. Weight calculation: weight calculation is performed using the priority diagram method;

[0026] S4. Drug production risk index model:

[0027] TRI=α max +β1+β2+γ+δ;

[0028] Where TRI is the risk index value of a drug production line; α max is the maximum inherent risk index of all online products in the production line; β1 is the production process risk index value; β2 is the quality control and quality assurance risk index value; γ is the compliance risk index value; δ is the product complaint recall risk index value;

[0029] The risk index value = 100 × W i ×K j ;

[0030] The risk index value, RI, is a single indicator risk index value; W i is the weight value of a single indicator determined according to the priority diagram method; K j It is the risk factor of a single indicator determined by experts.

[0031] S5. Model validation: The model was validated using the production line of a pharmaceutical manufacturer. The kappa value was calculated by calculating the consistency between the risk level obtained by the model and the expert evaluation results. The kappa coefficient value was between 0.61 and 0.80, indicating that the results of the model evaluation were consistent with those of the expert evaluation.

[0032] Further,

[0033] The S1 establishes indicators at various levels for drug production risks, including 5 secondary indicators and 22 tertiary indicators. Under each tertiary indicator, experts establish 2 to 5 quaternary indicators in accordance with the principle of factor classification, and assign corresponding risk levels according to their risk sizes, such as A, B, C, D, and E, and their corresponding risk coefficients are 1, 0.8, 0.6, 0.4, and 0.2, respectively.

[0034] Furthermore, the S3 weight calculation is:

[0035] The average values ​​of the expert scores on the drug production risk indicators obtained through the S2 questionnaire survey are compared pairwise; if the indicator X i Ratio index X j Important, then X i 1 point; if equally important, X i 0.5 points; if indicator X j Ratio index X i Important, then X i Get 0 points; get a score of ij (where i, j = 1, 2, ..., n);

[0036] After obtaining the scoring results through pairwise comparison, the scores of each indicator are accumulated and obtained. i (where i = 1, 2, ..., n); calculate the total score of all indicators, the formula is as follows:

[0037]

[0038] Calculate the weight value W of each indicator i (where i = 1, 2, ..., n), the formula is as follows:

[0039]

[0040] The third aspect of the present invention: the application of the above-mentioned drug production risk index model or the model constructed by the above-mentioned drug production risk index model construction method in the evaluation of drug production risk index.

[0041] Compared with the prior art, the beneficial effects of the present invention are:

[0042] 1. The model constructed by the present invention realizes the practice of quantitative management of drug risk factors and is used for the evaluation of drug production risk index. The evaluation results are consistent with the expert evaluation results. SPSS26.0 calculated kappa=0.697, p<0.001, and the consistency rate is 80%.

[0043] 2. From the results of model verification, the drug production risk index is consistent with the expert evaluation results. The model can effectively integrate enterprise basic information, drug archive information, drug supervision information, inspection and monitoring information, human resources information and other resources, collect objective and quantifiable indicators, and dynamically evaluate the risks of drug production lines. According to drug supervision resources and laws and regulations, reasonable risk warning conditions can be set, and risk disposal procedures can be initiated in a timely manner for those who touch the risk warning conditions, so as to increase the pertinence and timeliness of drug supervision. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] none DETAILED DESCRIPTION

[0045] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be described clearly and completely below. It should be noted that if no specific conditions are specified in the examples, they are carried out under normal conditions. The following description is only some embodiments of the present application, which does not limit the present invention in any form. For those skilled in the art, several adjustments and improvements can be made without departing from the concept of the present invention. All technologies realized based on the above contents of the present invention belong to the protection scope of the present invention.

[0046] 1. A model for evaluating the risk index of drug production

[0047] The drug production risk index model:

[0048] TRI=α max +β1+β2+γ+δ

[0049] Where TRI is the risk index value of a drug production line; α max is the maximum inherent risk index of all online products in the production line; β1 is the production process risk index value; β2 is the quality control and quality assurance risk index value; γ is the compliance risk index value; δ is the product complaint recall risk index value.

[0050] Risk index value (RI) = 100 × W i ×K j

[0051] Where RI is the single indicator risk index value; W i is the weight value of a single indicator determined by the priority diagram method; K j It is the risk factor of a single indicator determined by experts.

[0052] W i Calculation:

[0053] Calculate W based on the priority diagram method i Experts evaluate the importance of each indicator. The higher the score, the more important it is. Calculate the average of the expert scores for each indicator (X1, X2, ..., X n ). Compare the calculated average values ​​of the expert scores in pairs. If the indicator X i Ratio index X j Important, then X i 1 point; if equally important, X i 0.5 points; if indicator X j Ratio index X i Important, then X iScore 0. Score a ij (where i, j = 1, 2, ..., n).

[0054] After obtaining the scoring results through pairwise comparison, the scores of each indicator are accumulated and obtained. i (where i = 1, 2, ..., n). The total score of all indicators is calculated as follows:

[0055]

[0056] Calculate the weight value W of each indicator i (where i = 1, 2, ..., n). The formula is as follows:

[0057]

[0058] K j Determination of:

[0059] Risk Factor K j It refers to the size of the risk level corresponding to the next-level indicator, which is determined by experts and set as five levels: A, B, C, D, and E. The corresponding risk coefficients are 1.0, 0.8, 0.6, 0.4, and 0.2.

[0060] 2. Research Methods

[0061] 2.1 Establish risk indicators

[0062] This study attempts to construct a drug production risk assessment index system. Based on my country's drug production supervision practice, 10 drug production experts and senior drug inspectors jointly recommended and established 5 major and 22 minor drug production risk indicators (i.e., the three-level indicators in Table 1) from five aspects: product inherent attributes, production process elements, quality control and assurance, GMP compliance, complaints and recalls.

[0063] Under each third-level indicator, according to the principle of factor classification, experts establish 2 to 5 fourth-level indicators and assign corresponding risk levels according to their risk size, such as A, B, C, D, and E, and their corresponding risk coefficients are 1, 0.8, 0.6, 0.4, and 0.2 respectively. See Table 1 for details.

[0064] Table 1 Level 3 and Level 4 indicators and their risk levels

[0065]

[0066]

[0067]

[0068]

[0069] 2.2 Determine the weight calculation method

[0070] At present, the commonly used weight calculation methods are: precedence diagram method, analytic hierarchy process (AHP), entropy method, etc. The precedence diagram method was first proposed by Muti in the United States. It is a method based on subjective judgment. It compares multiple indicators or goals in pairs and finally gives the order of importance or priority. If indicator A is more important than indicator B, A gets 1 point; if they are equally important, A gets 0.5 points; if indicator B is more important than indicator A, A gets 0 points. This method is suitable for the processing of qualitative and quantitative problems. This study uses the precedence diagram method for weight calculation.

[0071] 2.3 Model construction

[0072] 2.3.1 Questionnaire survey

[0073] Based on the contents of 5 major and 22 minor drug production risk indicators, an expert questionnaire was designed to collect experts' opinions on the importance of each indicator. The higher the score, the more important it is. The average value of the expert scores for each indicator was calculated (X1,

[0074] X2, ..., X n ).

[0075] 2.3.2 Weight calculation

[0076] Compare the average values ​​of the calculated expert scores in pairs. If the indicator X i Ratio index X j Important, then X i 1 point; if equally important, X i 0.5 points; if indicator X j Ratio index X i Important, then X i Score 0. Score a ij (where i, j = 1, 2, ..., n).

[0077] After obtaining the scoring results through pairwise comparison, the scores of each indicator are accumulated and obtained. i (where i = 1, 2, ..., n). Calculate the total score of all indicators using the following formula:

[0078]

[0079] Calculate the weight value W of each indicator i (where i = 1, 2, ..., n). The formula is as follows:

[0080]

[0081] 2.3.3 Model establishment

[0082] 2.3.3.1 Risk indicators at all levels. After being scored by experts and weighted by W i The formula calculates the weight values ​​of 22 sub-indicators (i.e., level 3 indicators), see Table 2. The risk coefficient refers to the size of the risk level corresponding to the level 4 indicator. Each level 3 indicator is divided into 2 to 5 level 4 indicators, and the corresponding risk level is set according to the risk size of the level 4 indicator, i.e., level A, B, C, D, and E, and the corresponding risk coefficients are 1.0, 0.8, 0.6, 0.4, and 0.2, see Table 1.

[0083] Table 2 Secondary and tertiary indicators and their weight distribution

[0084]

[0085] 2.3.3.2 The drug production risk index in this study is used to assess the risk of drug production lines. It is closely related to the properties of the corresponding products and their production quality management system. In this article, it refers to the drug production line risk index. The production line risk index is calculated as follows: ① Risk index (RI) = 100 × weight × risk coefficient; ② Production line risk index (TRI) = {Inherent risk index of co-line or dedicated line products} max +Production process risk index+Quality control and quality assurance risk index+Compliance risk index+Product complaint recall risk index.

[0086] 2.3.4 Model Validation

[0087] 2.3.4.1 Expert evaluation. 10 experts and senior drug inspectors familiar with the pharmaceutical production enterprises in the province were selected to conduct an overall evaluation of the GMP compliance of 12 pharmaceutical production enterprises. The evaluation levels were good, relatively good, general, and poor, and the scores were 4, 3, 2, and 1 respectively. The risk level of each production line was divided into high, relatively high, general, and low according to its process complexity and risk, and the scores were 4, 3, 2, and 1 respectively. The expert evaluation score of the production line was calculated as follows: Production line expert evaluation score = (4-GMP compliance average score) × production line risk level score. The higher the score, the higher the risk level. The 50 expert evaluation scores were divided into risk levels according to 3:3:4. "++" means high risk, accounting for 30%; "+" means medium risk, accounting for 30%; "-" means low risk, accounting for 40%. The evaluation results are shown in Table 3.

[0088] 2.3.4.2 Model evaluation. Data was entered online by 12 pharmaceutical manufacturers, and the risk index values ​​of 50 production lines were calculated using risk assessment model software. The risk levels were divided into 3:3:4, with "++" indicating high risk, accounting for 30%; "+" indicating medium risk, accounting for 30%; and "-" indicating low risk, accounting for 40%. The model evaluation results are shown in Table 3.

[0089] Table 3 Expert evaluation and model assessment risk level table

[0090]

[0091]

[0092] 2.3.4.3 Verification. 50 production lines from 12 pharmaceutical manufacturers were selected for verification, and the consistency between the risk level obtained by the calculation model and the expert evaluation results was calculated. The results are shown in Table 4.

[0093] Table 4. Validation results of risk level model

[0094]

[0095] SPSS26.0 calculated kappa = 0.697, p < 0.001, and a consistency rate of 80%. Statistically, the kappa coefficient value is between 0.61 and 0.80, indicating that the results of model evaluation and expert evaluation are highly consistent and statistically significant; in terms of conformity, the conformity rate of model evaluation and expert evaluation results is 80%. In summary, from the verification results, the risk level assessment results of the production line risk index model for 50 production lines of 12 pharmaceutical manufacturers are highly consistent with the expert evaluation results, and the model can be used to evaluate the risk index of pharmaceutical production.

[0096] 3. Application of results

[0097] From the results of model verification, the drug production risk index is consistent with the expert evaluation results. The model can effectively integrate enterprise basic information, drug archive information, drug supervision information, inspection and monitoring information, human resources information and other resources, collect objective and quantifiable indicators, and dynamically evaluate the risks of drug production lines. According to drug supervision resources and laws and regulations, reasonable risk warning conditions can be set, and risk disposal procedures can be initiated in a timely manner for those who touch the risk warning conditions, so as to increase the pertinence and timeliness of drug supervision.

Claims

1. A model for evaluating the risk index of drug production, characterized by: The drug production risk index model: TRI=a max +β1+β2+γ+δ; Where TRI is the risk index value of a drug production line; α max is the maximum inherent risk index of all online products in the production line; β1 is the production process risk index value; β2 is the quality control and quality assurance risk index value; γ is the compliance risk index value; δ is the product complaint recall risk index value.

2. A model for evaluating drug production risk index according to claim 1, characterized in that: The risk index value = 100 × W i ×K j ; The risk index value, RI, is a single indicator risk index value; W i is the weight value of a single indicator determined according to the priority diagram method; K j It is the risk factor of a single indicator determined by experts.

3. A model for evaluating drug production risk index according to claim 2, characterized in that: Experts evaluate the importance of each indicator. The higher the score, the more important it is. The average of the expert scores for each indicator (X1, X2, ..., X n ); Compare the average values ​​of the calculated expert scores in pairs. If the indicator X i Ratio index X j Important, then X i 1 point; if equally important, X i 0.5 points; if indicator X j Ratio index X i Important, then X i Get 0 points; get a score of ij (where i, j = 1, 2, ..., n); After obtaining the scoring results through pairwise comparison, the scores of each indicator are accumulated and obtained. i (where i = 1, 2, ..., n); Calculate the total score of all indicators using the following formula: Calculate the weight value W of each indicator i (where i = 1, 2, ..., n), the formula is as follows:

4. A model for evaluating drug production risk index according to claim 2, characterized in that: Risk Factor K j It refers to the size of the risk level corresponding to the next-level indicator (i.e. the fourth-level indicator), which is determined by experts and set to five levels: A, B, C, D, and E. The corresponding risk coefficients are 1.0, 0.8, 0.6, 0.4, and 0.

2.

5. A method for constructing a drug production risk index model according to any one of claims 1 to 4, characterized in that: S1. Establish risk indicators: Based on the practice of drug production supervision, establish indicators at all levels of drug production risks from five aspects: inherent attributes of products, production process elements, quality control and assurance, GMP compliance, complaints and recalls; S2. Questionnaire survey: A questionnaire survey was designed to obtain the experts’ opinions on the importance of each indicator. The higher the score, the more important it is. The average of the expert scores for each indicator (X1, X2, ..., X n ); S3. Weight calculation: weight calculation is performed using the priority diagram method; S4. Drug production risk index model: TRI=a max +β1+β2+γ+δ; Where TRI is the risk index value of a drug production line; α max is the maximum inherent risk index of all online products in the production line; β1 is the production process risk index value; β2 is the quality control and quality assurance risk index value; γ is the compliance risk index value; δ is the product complaint recall risk index value; The risk index value = 100 × W i ×K j ; The risk index value, RI, is a single indicator risk index value; W i is the weight value of a single indicator determined according to the priority diagram method; K j It is the risk factor of a single indicator determined by experts. S5. Model validation: The model was validated using the production line of a pharmaceutical manufacturer. The kappa value was calculated by calculating the consistency between the risk level obtained by the model and the expert evaluation results. The kappa coefficient value was between 0.61 and 0.80, indicating that the results of the model evaluation were consistent with those of the expert evaluation.

6. The method for constructing a drug production risk index model according to claim 5, characterized in that: The S1 establishes indicators at various levels for drug production risks, including 5 secondary indicators and 22 tertiary indicators. Under each tertiary indicator, experts establish 2 to 5 quaternary indicators in accordance with the principle of factor classification, and assign corresponding risk levels according to their risk sizes, such as A, B, C, D, and E, and their corresponding risk coefficients are 1, 0.8, 0.6, 0.4, and 0.2, respectively.

7. The method for constructing a drug production risk index model according to claim 6, characterized in that: The S3 weight calculation: The average values ​​of the expert scores on the drug production risk indicators obtained through the S2 questionnaire survey are compared pairwise; if the indicator X i Ratio index X j Important, then X i 1 point; if equally important, X i 0.5 points; if indicator X j Ratio index X i Important, then X i Get 0 points; get a score of ij (where i, j = 1, 2, ..., n); After obtaining the scoring results through pairwise comparison, the scores of each indicator are accumulated and obtained. i (where i = 1, 2, ..., n); calculate the total score of all indicators, the formula is as follows: Calculate the weight value W of each indicator i (where i = 1, 2, ..., n), the formula is as follows:

8. Application of the drug production risk index model as described in any one of claims 1 to 4 or the model constructed by the drug production risk index model construction method as described in any one of claims 5 to 7 in the evaluation of drug production risk index.

Citation Information

Patent Citations

  • Risk evaluation system for medicine production and management enterprises

    CN102339415A

  • Drug safety risk assessment method and system

    CN110276523A

  • Comprehensive evaluation method for market power of electricity market

    CN113627753A