Research On Clinical Pathway Optimization Diagnosis And Treatment Based On Big Data

The lack of medical resources in China and the uneven distribution of medical resources are evident in the fact that the top-three hospitals in the city are overcrowded,while the community hospitals and township hospitals are extremely small.With the complexity of the disease,the development of diversity,and the amount of medical insurance paid by the state is increasing each year,both the medical quality and the medical cost raise new requirements for the development of the medical industry.As a standardized single-disease diagnosis and treatment process,the clinical pathway has the characteristics of ensuring medical quality,shortening hospital stay,and reducing redundant treatment.However,due to the complex and varied nature of the disease,the clinical path diagnosis and treatment plan needs to be continuously improved during use.The continuous optimization of clinical pathways based on the use of data mining in medical big data becomes a new research direction for medical reform.The purpose of this research project is to expand the scope of application of the clinical pathway standard diagnosis and treatment program in the context of regional medical integration and mass medical data,so that it has a larger group of patients within the region,and enhance the community hospitals and township hospitals.The quality of medical care,so that the medical resources of hospitals at all levels are fully utilized,reducing the total cost of medical care for all people.This study focuses on the optimization needs of general clinical pathway standards that are applicable to a wide range of areas,particularly chronic diseases,in response to the regional medical environment.The object of optimization is the content of clinical path diagnosis and treatment standards,and the selected clinical path is chronic disease and conventional disease.Using data mining technology,a clinical path optimization diagnosis and treatment strategy based on diagnosis and treatment unit division was proposed.Moreover,the specific implementation of this optimization strategy isexplained using the clustering and correlation analysis methods.Finally,the diabetes-associated hypertension case was used as an example to test the performance of the proposed optimization strategy.The experimental results show that the optimized clinical strategy after the optimization strategy proposed in this paper is better than the original standard in ensuring the average length of stay and the average hospital stay.The main research contents and achievements of this paper are as follows:(1)Analyze the problems existing in the current clinical pathway standards and propose a clinical pathway optimization strategy.In the context of regional medical integration,the types of medical data are diverse,the data size is not the same,the naming conventions in the data table are not uniform,and so on.The pretreatment requirements and process specifications for diagnosis and treatment data are proposed.By analyzing the problems existing in the current clinical pathway standards,in the context of regional medical integration,it proposes to extract appropriate clinical behavior from the patient's diagnosis and treatment data,which is called the diagnosis and treatment unit.Through the optimization and combination of diagnosis and treatment units,the optimized clinical pathway is finally achieved.Standards apply to medical institutions at all levels in the region.(2)Using data mining technology to implement the proposed clinical path optimization strategy.In the division stage of diagnosis and treatment unit,two methods for realizing data attribute normalization and cluster integration based on K-means algorithm are proposed.At the stage of diagnosis and treatment unit optimization,the correlation between clinical behaviors was analyzed using the FP-growth algorithm and Apriori algorithm of association rules.For the overall optimization of the clinical path,serial and parallel diagnosis and treatment unit integration methods are proposed.Then taking the clinical path of diabetes and hypertension as an example,the degree of difficulty and the analysis effect of the comparison methods at each stage were verified by experiments.It was determined that the cluster integration method,FP-growth algorithm and parallel integration method are more suitable for optimizing the clinical path in the context of regional diagnosis and treatment.(3)Comprehensive evaluation of the clinical path optimization diagnosis and treatment effect through experiments.From the aspects of improving the quality of medical care and controlling the cost of medical care,four evaluation indicators forclinical pathway optimization were proposed,including the application rate,cure rate,average length of stay,and average medical costs.Experiments show that after the optimization strategy proposed in this paper,the clinical path diagnosis and treatment achieved a substantial increase in medical quality under the condition that the medical cost is basically flat.That is,when the cure rate remained at 89%,the application rate increased from 69% to 72.1%.