26. Decision Tree Approach to Predict Lung Cancer the Data Mining Technology

The purposes of this research is using the Data Mining techniques, and explore the potential information from the National Health Insurance Research Database, analysis lung cancer patients which has the highest mortality in Taiwan, as a reference of the analysis of Bureau of National Health Insurance files and the clinical index of hospitals. By using statistical software, “SPSS Clementine 12.0”, this research merged “The detail file of hospital medical expenses inventory” and “The basic data file of medical institution” between 06’ and 09’ as the study data, then hospitalized lung cancer patients screened for the study sample, and using Two-Step clustering technique to produce the results that are effective. The hospitalized patients that with lung cancer and death patients, males have a higher percentage than females, lung cancer people are usually accompanied with comorbidities, especially for pneumonia; most lung cancer patients go to the center of medical, and most patients make booking as out-patient. The treatment of lung cancer patients should notice the factor that lead to pneumonia, and this research shows that most patients make booking as out-patient, therefore, taking drug treatment for patients can regarded as the main dependence for curing.