Background: Tuberculosis is the second most common causes of death throughout the worldrnnext to HIV/AIDS. Ethiopia is also among the high burden countries. Though the disease hasrnbeen a cause of death for millions of people around the globe, it is curable. Prediction of rntreatment outcome of TB patients using data mining techniques help the effort to stop TB-rnhealth problem. rnObjective: The objective of this research was to prepare a predictive model for TB treatmentrnoutcomes that assist clinical decisions in connection with TB treatment. rnMethod: The six steps Ciso et al Hybrid Model were used. A total of 6332 instances wererncollected from five health centers of Addis Ababa City Government that provide tuberculosisrntreatment. A pre-processed the data was fed in to data mining tools with selected classificationrnalgorithms. These algorithms were J48, NaÃ¯ve Bayes, SMO and PART. Accuracy and Area under ROCrnwere the metrics used to compare models generated by the algorithms. rn Result: After successive experiments using the four algorithms, PART algorithm revealed bestrnperformance. An accuracy of 81.32% and area under ROC=0.89. The algorithm generated fivernrules for the three treatment outcomes and the rules were found to be interesting for experts.rnThe rules contain the following predictor variables for treatment outcome: HIV Status, Sex, Age,rnInitial Weight with second month weight and Patient Category. rnConclusion: The findings from the research indicated that for the tuberculosis dataset with classrnimbalance PART found to be the best learner algorithm and most importantly clinical decisionsrnsuch as diagnosis, prognosis and resource allocation can be supported by data miningrntechniques.