The Study On The Cost Model Of Single Disease Treatment Based On Data Mining Methods

Lung malignant tumor is a kind of severe disease which has high morbidity and mortality, can cause excessive consumption of medical resources. On the other hand, the cost of different lung tumor inpatients is distinct. There is not a reasonable and feasible cost consultation system for inpatients of lung tumor, for current few studies about the cost of single-disease such as lung malignant tumor, or simple studies based on small samples, so it is hard to describe the difference of medical resources comsumption among different kinds of lung malignant tumor which is medicare advance payment and health economy specialists wanted, so the study on the cost of inpatients of lung tumor is necessary.Based on discussion of theory technology of data warehousing and data mining, this thesis adopts several data mining methods such as linear regression, decision tree, neural network to analyze and process the fee-for-service of single-case lung malignancy, using the fee-for-service data from managing information system of Nantong tumour hospital, then divides all lung-tumour cases into operation, non-operation and 15 sub-class cases, and finally makes use of cost model represented by the 3-level and 15-class decision tree to detailedly discuss the technology and method created by the above-mentioned model, and analyzes the mining out in detail. In addition, this thesis analyzes the advantages and disadvantages of building model with neural network.Experimental outs indicate that the single-case model discussed in this thesis reflect the knowledge and rules embedded in the historical data, also it is convenient to build other single-case model of fee-for-service, which will supply scientific standard for impersonally evaluating the output of medical treatment, compensating hospital from national hospitalization insurance.