Research And Application Of Data Mining Technology In Diagnosis Of Tuberculosis Diseases

Tuberculosis has been a serious threat to the health of people all over the years.China is one of the world’s 22 high burden of tuberculosis.Information technology continues to evolve,the major hospitals are also using the medical management system for daily work,making its medical equipment and equipment in the digital,the amount of information is also growing growth.How to carry out data mining and data diagnosis of mass tuberculosis disease diagnosis data by efficient and intelligent computer algorithm is the research content of this paper.Through the collection of 8210 cases of tuberculosis patients in Beijing’s Changping District Tuberculosis Control Center,Beijing Institute of Tuberculosis Control,the application of database technology to build the electronic file based on SQL Server 2010,the use of data mining methods in the rough set and decision tree method,And optimize the algorithm to improve the establishment of intelligent diagnosis of tuberculosis disease model.Taking into account the medical data and sharing,this article set up hadoop large data platform to build a diagnosis of tuberculosis disease intelligent diagnosis of cloud systems to meet the needs of medical data.The research contents and main work of this paper include the following four points: 1,This paper preprocesses the data set,the data set is optimized to deal with the existence of noise in medical data,incomplete problems.In this paper,the clustering method in data mining is selected to preprocess the data of tuberculosis disease,and the consistency and uncertainty of the data are guaranteed and transformed into the form suitable for excavation.The operation,can be a good late high-quality data mining.2,Tuberculosis disease due to individual differences have shown the symptoms are different,many data attributes,resulting in mining efficiency is not high.In order to solve this problem,this paper uses rough set theory to carry out attribute reduction,and proposes an entropy calculation method which is suitable for SQL language condition information,and completes attribute reduction.To reduce the implementation of the method.Using the database-based rough set attribute reduction method,the redundant attributes in tuberculosis disease data are removed.3,In the model construction,this paper studies the construction of the model by combining the rough set and the decision tree in view of the low efficiency of single mining method.In this paper,we use a single decision tree method and rough set method.The optimization algorithm of rough set reduction and decision tree rule extraction proposed in this paper has good applicability and advantage,and it is effective to improve the objectivity of diagnosis.The accuracy of the diagnosis of tuberculosis disease.4,In order to meet the growing demand for medical large data,this paper builds a large cloud platform based on hadoop technology and builds the intelligent diagnosis system of tuberculosis disease based on the diagnosis model of tuberculosis disease.The cloud computing is applied to the medical system,Effectively handle medical data,and provide decision support for the diagnosis of tuberculosis disease.