Evaluation of Classifiers Based on Decision Tree for Learning Medical Claim Process

Brazil has one of the largest private healthcare markets in the world. However, it appears that many medical procedures are being carried out without need, generating unnecessary costs on businesses and making the service offered more expensive. The medical claim process is a control mechanism used by health insurance companies to minimize the waste of resources through blockage of procedures that were requested wrongly. However, in order to realize an efficient medical claim process it needs a medical reviewer 24 hours a day and this generates a high cost. In this work, we followed the initial stages of the process of Knowledge Discovery Database in order to improve the quality of the data of a health insurance company. Then, we compared classification techniques based in Decision Tree in order to learn the medical reviewer behavior - professionals who assess if the medical requests should or not should be authorized. For the generation of knowledge, we used a database from a nonprofitable health insurance company containing records collected since the year 2007. Promising experimental results are present.