In recent years many successful machine learning applications have been developed, ranging from datamining programs to information-filtering systems that learn users' reading preferences. At the same time, there have been important advances in the theory and algorithms that can be used identify the diseases and treatment relations in a Bio-Science text. Imagine a computer learns from medical records which treatments are most effective for new diseases. Having the machine learning concept behind we have proposed a Machine Learning (ML) approach based on Naïve Bayes (NB) algorithm to improve the automatic disease identification in the medical field. And also we have improved text classification by using an integrated model. © Maxwell Scientific Organization, 2013.