Background and Aim: Gastric cancer is one the most common gastrointestinal tract cancers in Iran, with East-Azerbaijan Province ranking second in the country. The objectives of this research were to determine the feasibility of using cure models in survival analysis and factors affecting short-term and long-term patient survival rates using the mixture cure cox model. Materials and Methods: We used the available information on 184 patients diagnosed with gastric cancer in East-Azerbaijan Province cities referring to medical centers during the period 2009-2010 and followed up for 5 years. Results: The median of survival time was 8.33 months (95% CI=5.9-10.6). Fitting the univariate and final cox cure models showed that in the short-term survival the effect of the chemotherapy factor was statistically significant (Hazard ratio=0.49, 95% CI=0.34, 0.69, p-value <0.001). Conclusion: If the population under study consists of two groups of susceptible and non-susceptible individuals for the intended incident, the mixture cure models can be used for the discrete analysis of long-term and short-term survival of patients diagnosed with gastric cancer and identification of variables affecting the two survival rates.