Hospital research and development project approval evaluation method based on big data analysis

Abstract

The invention discloses a hospital research and development project approval evaluation method based on big data analysis, and the method is characterized in that the method comprises the specific steps: S1, obtaining data from a related data source of a target hospital, the data source comprises one or more of a hospital official website, a scientific research project declaration system, a medical resource management system and national and local scientific research project management platforms; s2, screening and determining evaluation indexes, and screening out key evaluation indexes from the obtained data; the invention belongs to the technical field of data processing, processes of data collection, preprocessing, analysis, calculation and the like are automatically completed through a big data analysis technology, and the approval period is greatly shortened, so that the approval efficiency is improved; based on a scientific evaluation model and a big data analysis technology, the potential and value of each application project are objectively and comprehensively evaluated, and human intervention and subjective judgment are reduced, so that the examination and approval accuracy is improved.

Description

Technical Field

[0001] The present invention relates to the field of data processing technology, and in particular to an evaluation method for hospital R&D project approval based on big data analysis. Background Art

[0002] At present, hospitals often rely on expert review panels to evaluate each application project during the R&D project approval process. This method is not only time-consuming and labor-intensive, but also highly subjective and difficult to fully and objectively reflect the potential and value of the project. With the continuous development of big data technology, how to effectively use big data analysis methods to improve the efficiency and accuracy of hospital R&D project approval has become an urgent problem to be solved. Summary of the invention

[0003] To this end, the present invention provides an evaluation method for hospital R&D project approval based on big data analysis to solve the above-mentioned problems in the prior art.

[0004] In order to achieve the above object, the present invention provides the following technical solutions:

[0005] The evaluation method for hospital R&D project approval based on big data analysis has the following specific steps:

[0006] S1 obtains data from relevant data sources of the target hospital, wherein the data sources include one or more of the hospital's official website, a scientific research project application system, a medical resource management system, and a national and local scientific research project management platform;

[0007] S2 Screen and determine the evaluation indicators, and select key evaluation indicators from the acquired data. The evaluation indicators include but are not limited to project innovation, technical feasibility, market demand, expected social benefits, research team strength, and rationality of fund use;

[0008] S3 establishes an evaluation model, and based on the selected evaluation indicators, establishes an evaluation model for hospital R&D project approval, wherein the evaluation model is a hierarchical analysis method model, and constructs a paired comparison matrix to calculate the weight value of each evaluation indicator;

[0009] S4 calculates the comprehensive score of the project, inputs the R&D project application data to be approved into the trained evaluation model, obtains the comprehensive score of each project, sorts the projects according to the comprehensive score, and provides a basis for approval decision-making for the hospital management;

[0010] S5 generates a hospital R&D project approval report based on the data analysis results. The report includes the comprehensive score, ranking, main advantages, potential risks and improvement suggestions of each application project. The hospital management department makes an approval decision based on the content of the report.

[0011] As a further optimization scheme of the present invention, the multi-dimensional data collected in the data source of step S1 includes but is not limited to: project application, scientific research background of the project leader and team members, project budget, expected results, previous research results, historical data of similar projects, hospital resource allocation, market demand and social benefits.

[0012] As a further optimized solution of the present invention, in step S2, the collected data is cleaned and preprocessed, including removing invalid data, filling missing values, and normalizing the data, so as to screen out the evaluation indicators.

[0013] As a further optimization scheme of the present invention, in step S3, the gradient boosting decision tree algorithm of the machine learning xgboost library is used to extract the features of each sample data, and classify, sort and group them. The softmax loss function plus regularization term calculation is performed on the input calculation index items, and the relative importance score of each index item is obtained one by one, and the average of the relative importance score of the index item and the preset corresponding index item proportion score is used as the final weight value of the index item.

[0014] As a further optimization scheme of the present invention, in step S4, the corresponding numerical value of any indicator item in each group of evaluation dimensions in the matrix is ​​matrix-dot multiplied with its corresponding final weight value to obtain the evaluation score of the corresponding indicator item, and according to the normal distribution characteristics, the score of each group of evaluation dimensions is converted to a 100-point system, and the result is used as the final evaluation score of the enterprise indicator item.

[0015] As a further optimization solution of the present invention, in step S5, the approval result and feedback are promptly notified to the application team to promote continuous improvement and optimization of the project.

[0016] The present invention has the following advantages:

[0017] (1) Through big data analysis technology, data collection, preprocessing, analysis and calculation processes are automatically completed, greatly shortening the approval cycle and thus improving approval efficiency;

[0018] (2) Based on scientific evaluation models and big data analysis technology, objectively and comprehensively evaluate the potential and value of each application project, reduce human intervention and subjective judgment, and thus improve the accuracy of approval;

[0019] (3) By comparing the comprehensive scores and rankings of different projects, hospitals can allocate scientific research resources more reasonably, improve resource utilization efficiency, and thus optimize resource allocation;

[0020] (4) By promptly informing the applicant team of the approval results and feedback, it helps them identify the strengths and weaknesses of the project and make continuous improvements and optimizations. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] Figure 1 A schematic diagram of the evaluation method for hospital R&D project approval based on big data analysis provided by the present invention. DETAILED DESCRIPTION

[0022] The following is a description of the implementation of the present invention by specific embodiments. People familiar with the art can easily understand other advantages and effects of the present invention from the contents disclosed in this specification. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0023] like Figure 1 As shown in the figure, the evaluation method for hospital R&D project approval based on big data analysis has the following specific steps:

[0024] S1 obtains data from relevant data sources of the target hospital, wherein the data sources include one or more of the hospital's official website, a scientific research project application system, a medical resource management system, and a national and local scientific research project management platform;

[0025] The multi-dimensional data collected include but are not limited to: project application, scientific research background of project leader and team members, project budget, expected results, previous research results, historical data of similar projects, hospital resource allocation, market demand and social benefits;

[0026] S2 Screen and determine the evaluation indicators, and select key evaluation indicators from the acquired data. The evaluation indicators include but are not limited to project innovation, technical feasibility, market demand, expected social benefits, research team strength, and rationality of fund use;

[0027] Cleaning and preprocessing the collected data, including removing invalid data, filling missing values, and normalizing data, in order to screen out the evaluation indicators;

[0028] S3 establishes an evaluation model, and based on the selected evaluation indicators, establishes an evaluation model for hospital R&D project approval, wherein the evaluation model is a hierarchical analysis method model, and constructs a paired comparison matrix to calculate the weight value of each evaluation indicator;

[0029] The gradient boosting decision tree algorithm of the machine learning xgboost library is used to extract the features of each sample data, and to classify, sort and group them. The softmax loss function plus the regularization term calculation is performed on the input calculation index items, and the relative importance score of each index item is obtained one by one. The relative importance score of the index item and the average of the preset corresponding index item proportion score and the average of the relative importance score of the index item are used as the final weight value of the index item.

[0030] Specifically, the GBDT algorithm in the xgboost library is used. During the training process, xgboost will receive all sample data and extract the features of each sample data. These features cover multiple dimensions such as the company's business, employees, qualifications, intellectual property rights, projects, financing loans, assets and R&D expenses. Then, the algorithm will classify, sort and group these features to prepare for subsequent weight calculations.

[0031] S4 calculates the comprehensive score of the project, inputs the R&D project application data to be approved into the trained evaluation model, obtains the comprehensive score of each project, sorts the projects according to the comprehensive score, and provides a basis for approval decision-making for the hospital management;

[0032] Perform matrix dot multiplication on the corresponding value of any indicator item in each group of evaluation dimensions in the matrix and its corresponding final weight value to obtain the evaluation score of the corresponding indicator item, and convert the score of each group of evaluation dimensions into a 100-point system according to the normal distribution characteristics, and the result is used as the final evaluation score of the enterprise indicator item;

[0033] S5 generates a hospital R&D project approval report based on the data analysis results. The report contains the comprehensive score, ranking, main advantages, potential risks and improvement suggestions of each application project. The hospital management department makes an approval decision based on the content of the report and promptly notifies the application team of the approval results and feedback to promote continuous improvement and optimization of the project.

[0034] The following are the specific implementation steps of the first embodiment of the present invention:

[0035] Data acquisition: Obtain application materials for each R&D project from the hospital's scientific research project application system, including project plans, budget sheets, team member resumes, etc.; obtain relevant policy guidance and market demand information from the hospital's official website and industry reports;

[0036] Evaluation index screening: The evaluation indexes are determined as innovation (20%), scientificity (30%), practicality (20%), feasibility (20%), and expected benefits (10%);

[0037] Establish a pairwise comparison matrix: Assuming the evaluation indicators are A (innovation), B (scientificity), C (practicality), D (feasibility), and E (expected benefits), construct a 5x5 pairwise comparison matrix;

[0038] Calculate weight value: Calculate the weight value of each evaluation index by eigenvector method, and perform normalization and verification;

[0039] Calculate the comprehensive score: Assume that the innovation score of a project is 80 (out of 100), the scientific score is 90, the practicality score is 75, the feasibility score is 85, and the expected benefit score is 60.

[0040] The comprehensive score calculated according to the weight value = 80 × 20% + 90 × 30% + 75 × 20% + 85 × 20% + 60 × 100% = 81 points;

[0041] Approval decision: The preset approval standard is that the comprehensive score is not less than 80 points, then the project will pass the project approval. If the comprehensive score is less than 80 points, an early warning reminder will be issued and the project team will be required to make supplements or modifications.

[0042] In summary, the hospital R&D project approval evaluation method based on big data analysis proposed in the present invention acquires data from multiple data sources, screens key evaluation indicators, establishes a pairwise comparison matrix, and calculates the weight values ​​of the evaluation indicators and the comprehensive score of the project, thereby realizing the intelligent and scientific approval of hospital R&D project. This method can significantly improve the approval efficiency, reduce human interference, and provide strong support for the scientific research development of the hospital.

Claims

1. An evaluation method for hospital R&D project approval based on big data analysis, characterized in that: The specific steps are as follows: S1 obtains data from relevant data sources of the target hospital, wherein the data sources include one or more of the hospital's official website, a scientific research project application system, a medical resource management system, and a national and local scientific research project management platform; S2 Screen and determine the evaluation indicators, and select key evaluation indicators from the acquired data. The evaluation indicators include but are not limited to project innovation, technical feasibility, market demand, expected social benefits, research team strength, and rationality of fund use; S3 establishes an evaluation model. Based on the selected evaluation indicators, an evaluation model for hospital R&D project approval is established. The evaluation model is a hierarchical analysis method model, and a pairwise comparison matrix is ​​constructed to calculate the weight value of each evaluation indicator; S4 calculates the comprehensive score of the project, inputs the R&D project application data to be approved into the trained evaluation model, obtains the comprehensive score of each project, and sorts the projects according to the comprehensive score to provide a basis for approval decision-making for the hospital management; S5 generates a hospital R&D project approval report based on the data analysis results. The report includes the comprehensive score, ranking, main advantages, potential risks and improvement suggestions of each application project. The hospital management department makes an approval decision based on the content of the report.

2. The evaluation method for hospital R&D project approval based on big data analysis according to claim 1 is characterized in that: The multi-dimensional data collected in step S1 data source include but are not limited to: project application, scientific research background of project leader and team members, project budget, expected results, previous research results, historical data of similar projects, hospital resource allocation, market demand and social benefits.

3. The evaluation method for hospital R&D project approval based on big data analysis according to claim 1 is characterized in that: In step S2, the collected data is cleaned and preprocessed, including removing invalid data, filling missing values, and normalizing data, so as to screen out the evaluation indicators.

4. The evaluation method for hospital R&D project approval based on big data analysis according to claim 1 is characterized in that: In step S3, the gradient boosting decision tree algorithm of the machine learning xgboost library is used to extract the features of each sample data, and classify, sort and group them. The softmax loss function plus the regularization term are calculated based on the input calculation index items, and the relative importance score of each index item is obtained one by one. The average of the relative importance score of the index item and the preset corresponding index item proportion score is used as the final weight value of the index item.

5. The evaluation method for hospital R&D project approval based on big data analysis according to claim 1 is characterized in that: In step S4, the corresponding numerical value of any indicator item in each group of evaluation dimensions in the matrix is ​​matrix-multiplied with its corresponding final weight value to obtain the evaluation score of the corresponding indicator item, and the score of each group of evaluation dimensions is converted to a 100-point system based on the normal distribution characteristics, and the result is used as the final evaluation score of the enterprise indicator item.

6. The evaluation method for hospital R&D project approval based on big data analysis according to claim 1 is characterized in that: In step S5, the approval results and feedback are promptly notified to the application team to promote continuous improvement and optimization of the project.

Images