Analysis of the factors influencing lung cancer hospitalization expenses using data mining

BACKGROUND: Hospitalization expenses for the therapy of lung cancer are not only a direct economic burden on patients, but also the focus of medical insurance departments. Therefore, the method for classifying and analyzing lung cancer hospitalization expenses so as to predict reasonable medical cost has become an issue of common interest for both hospitals and insurance institutions. METHODS: A C5.0 algorithm is adopted to analyze factors influencing hospitalization expenses of 731 lung cancer patients. A C5.0 algorithm is a data mining method used to classify calculation. RESULTS: Increasing the number of input variables leads to variation in the importance of different variables, but length of stay (LOS), major therapy, and medicine cost are the three variables of greater importance. They are important factors that affect the hospitalization cost of lung cancer patients. In all three calculations, the classification accuracy rate of training and testing partition sets reached 84% and above. The classification accuracy rate reached over 95% after addition of the cost variables. CONCLUSION: The classification rules are proven to be in accordance with actual clinical practice. The model established by the research can also be applied to other diseases in the screening and analysis of disease hospitalization costs according to selected feature variables.