Open Collections

Statistical analysis of survival data : an application to perhipheral vascular bypass surgery

University of British Columbia

A retrospective study was carried out on 535 patients who underwent bypass surgery for peripheral vascular disease. Survival data for 303 patients out of these 535 cases are subjected to quantitative analysis. The main interest is in survival of these patients in order to identify the risk factors. The importance of types of grafting technique in long-term survival is also considered. Statistical methods used to ascertain the important prognostic variables include Cox's proportional hazards model, stepwise regression and all subsets regression in proportional hazards model discussed by Kuk (1984). In descending order of significance, the most important variables are myocardial infarction, presence or absence of hypertension, sex and whether or not a revision operation was done. The variable, history of a previous coronary bypass graft is highly correlated with survival but the comparison of its significance to the other significant variables is not possible with Cox's model. Age is also related to survival in this data set. However, since there is no control group, one cannot make a strong conclusion about the effect of age on survival of the patients who have had surgery for peripheral vascular disease.

Text

2010-06-20

For non-commercial purposes only, such as research, private study and education. Additional conditions apply, see Terms of Use https://open.library.ubc.ca/terms_of_use.

http://hdl.handle.net/2429/25912

Statistics

University of British Columbia

Graduate