A comparison between Kaplan-Meier and weighted Kaplan-Meier methods of five-year survival estimation of patients with gastric cancer

The 5-year survival rate is a good prognostic indicator for patients with Gastric cancer that is usually estimated based on Kaplan-Meier. In situations where censored observations are too many, this method produces biased estimations. This study aimed to compare estimations of Kaplan-Meier and Weighted Kaplan-Meier as an alternative method to deal with the problem of heavy-censoring. Data from 330 patients with Gastric cancer who had undergone surgery at Iran Cancer Institute from 1995- 1999 were analyzed. The Survival Time of these patients was determined after surgery, and the 5-year survival rate for these patients was evaluated based on Kaplan-Meier and Weighted Kaplan-Meier methods. A total of 239 (72.4%) patients passed away by the end of the study and 91(27.6%) patients were censored. The mean and median of survival time for these patients were 24.86±23.73 and 16.33 months, respectively. The one-year, two-year, three-year, four-year, and five-year survival rates of these patients with standard error estimation based on Kaplan-Meier were 0.66 (0.0264), 0.42 (0.0284), 0.31 (0.0274), 0.26 (0.0264) and 0.21 (0.0256) months, respectively. The estimations of Weighted Kaplan-Meier for these patients were 0.62 (0.0251), 0.35 (0.0237), 0.24 (0.0211), 0.17 (0.0172), and 0.10 (0.0125) months, consecutively. In cases where censoring assumption is not made, and the study has many censored observations, estimations obtained from the Kaplan-Meier are biased and are estimated higher than its real amount. But Weighted Kaplan-Meier decreases bias of survival probabilities by providing appropriate weights and presents more accurate understanding.