Background: Cancer surveillance data provide information on the incidence and trends of cancer in the population level. Analyzing cancer trends according to these characteristics plays an important role in cancer surveillance. Knowledge of the causes of cancer allow better prevent the appearance of it. A large number of epidemiological evidence supporting the effect of smoking on the causes of cancer there is strong evidence supporting a role for smoking in the etiology of cancers. Alcohol appears to interact with the tobacco significantly and can be considered a risk factor in the development of cancers. Obesity which is now well recognized as a public health problem increases the risk of developing cancers. All these factors are characterized by uncertainty, complexity and imprecision. Methods: In this study, we propose an analysis of these factors based on the principles of fuzzy logic inference system. The data were collected from WHO data. As this technique addresses the uncertain, its application in this area is perfectly adequate. Results: A database is established, after the analysis system is done, it will be possible to read the prevalence of cancer by introducing randomly the values in inputs variables. Conclusion: like cancer has become a national scourge, this application allows predicting the impact of it just from the introduction inputs variables such as BMI, degree of physical activity, tobacco and sex.