We thank Singh et al 1 for their letter 2 commenting on our recent paper. 3 The authors briefly summarised current evidence regarding the chemopreventive effects of statins on hepatocellular carcinoma (HCC) and noted the lack of analyses on the role of statins in HCC in our study.We agree that the use of statins was found to be associated with a reduced risk of HCC according to previous studies. 3 However, not only statins but also nonsteroidal anti-inflammatory drugs (NSAIDs), aspirin, thiazolidinediones, antiviral agents, etc, were all reported to be associated with a lower risk of HCC. Sahasrabuddhe et al analysed the National Institutes of Health-AARP Diet and Health Study cohort and reported that aspirin users had significantly reduced risks of HCC (relative risk (RR)=0.59, 95% CI 0.45 to 0.77) and mortality (RR=0.55, 95% CI 0.45 to 0.67) due to chronic liver disease. 4 In the present study, we found that not only metformin but also thiazolidinedions were associated with a lower risk of HCC (HR=0.76, 95% CI 0.70 to 0.81). 1 In our other recent study focused on antiviral therapy and risk of hepatitis B virus (HBV)-related HCC, also based on Taiwan's National Health Insurance Research Database, we found that the use of nucleoside analogues was associated with a lower risk of HCC recurrence among patients with HBV-related HCC after liver resection (HR=0.67, 95% CI 0.55 to 0.81). The use of statins (HR=0.68, 95% CI 0.53 to 0.87) and NSAIDs or aspirin (HR=0.80, 95% CI 0.73 to 0.88) was also found to be an independent protective factor for HCC recurrence. 5 In the present study, we focused on antidiabetic agents because we already had many factors to be controlled, including age, gender, hepatitis B, hepatitis C, cirrhosis, end-stage renal failure, diabetic duration, control of diabetes, and use of other oral antidiabetic agents, thiazolidinediones and insulin. We did not intend to include other non-anti-diabetic agents, such as statins, NSAIDs or aspirin, and antiviral agents in the initial study design of the present study because analysing too many factors in the multivariate model will result in a trade-off with lower power to detect differences. We believe it is for the same reason that Singh et al did not intend to examine the chemopreventive effects of drugs other than statins in their meta-analysis. Even though the roles of metformin, thiazolidinedions, NSAIDs or aspirin, and antiviral agents are not included in their study, this does not hinder the merits of their meta-analysis. 3 REFERENCES 1. Singh S, Singh PP, Singh AG, et al. Statins are associated with a reduced risk of hepatocellular cancer: a systematic review and meta-analysis.