PostScript 41 cases along with their fivefold matched controls (as stated in the legend of figure 1, 774 cases and 3870 controls were used), and came out with a hazard rate ratio for CSCR of 1.61, with adjusted p value 0.009. Since a more sophisticated stratified Cox regression had already been applied on the strictly stratified case–control sample, here we chose to apply the KM analysis on the slightly larger sample. Nonetheless, the results are quite consistent. San-Ni Chen,1,2 Iebin Lian3 1

Department of Ophthalmology, Changhua Christian Hospital, Changhua, Taiwan 2 School of Medicine, Chung Shan Medical University, Taichung, Taiwan 3 Graduate Institute of Statistics and Information Science, National Changhua University of Education, Changhua, Taiwan Correspondence to Dr Lian Ie-bin, Graduate Institute of Statistics and Information Science, National Changhua University of Education, # 1 Jinde Rd, Changhua City, Changhua, Taiwan; [email protected]. edu.tw Acknowledgements We thank Rohit Ramesh Modi (MS, DNB, FICO) for the comment concerning the sample size in the analysis. Contributors IL: drafting. S-NC: discussion. Competing interests None. Provenance and peer review Not commissioned; internally peer reviewed.

To cite Chen S-N, Lian I. Br J Ophthalmol 2014;98:997. Received 24 February 2014 Accepted 6 March 2014 Published Online First 19 March 2014 Br J Ophthalmol 2014;98:997. doi:10.1136/bjophthalmol-2014-305148

Increased risk of coronary heart disease in male patients with central serous chorioretinopathy: results of a population-based cohort study

REFERENCE 1

Chen S, Chen Y, Lian L. Increased risk of coronary heart disease in male patients with central serous chorioretinopathy: results of a population-based cohort study. Br J Ophthalmol 2014;98:110–14.

Actually we used two survival analyses in the paper:1 a Kaplan–Meier (KM) plot with log-rank test (figure 1), and stratified Cox regression (table 2). Among the 815 cases and 4075 controls, 41 cases and 164 controls had pre-coronary heart disease (CHD). In the KM analysis, we excluded only those with pre-CHD, and the corresponding (unadjusted) p value from log-rank test for central serous chorioretinopathy (CSCR) is 0.002. However, in stratified Cox regression, we did exclude Br J Ophthalmol July 2014 Vol 98 No 7

997

Copyright of British Journal of Ophthalmology is the property of BMJ Publishing Group and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use.

Increased risk of coronary heart disease in male patients with central serous chorioretinopathy: results of a population-based cohort study.

Increased risk of coronary heart disease in male patients with central serous chorioretinopathy: results of a population-based cohort study. - PDF Download Free
344KB Sizes 2 Downloads 3 Views