SUMMARY
OBJECTIVES: Predictive analysis can be used effectively to evaluate enormous data generated by health care industry to extract information and establish relationships amongst the variables. Unlike traditional statistical methods, it uses artificial intelligence to reveal associations which health care professionals would never even suspect. Tobacco cessation is clearly beneficial, however many tobacco users respond differently as it is based on multitude of factors. So our objectives to understand the data mining techniques using WEKA tool and its role in predictive analysis as well as to predict the quit status of patients using prediction algorithms in tobacco cessation. METHODS: WEKA a Data Mining Tool used to classify the data and evaluated using 10-fold cross-validations. The various algorithms used in this tool are Naïve Bayes, SMO, Random Forest, J-48 and Decision stump to further analyse its role in determining the quit status of patients. For this secondary data of 655 patients from Tobacco Cessation Clinic was utilized and described using 20 different attributes for prediction of quit status.RESULTS: The result showed that Decision stump and SMO was found to be having a best prediction and accuracy for prediction of quitting status. Out of 20 attributes, previous attempt of quitting, type of intervention, number of years since habit initiated were found to be associated with early quitting rate.CONCLUSION: This study concludes that Data mining & predictive analytics models like WEKA tool will not only improve patient outcomes but understand variables or combination of variables for effective interventions in tobacco cessation.