Rethinking traditional survival analysis: Modulated renewal analysis with competing risks regression

Reply from authors: A new shared vision on survival analysis: Good news from Baltimore

“…We read with interest the letter from Van den Eynde and colleagues. 1 We must admit that it is quite difficult to reply to such a beautiful explanation of the main concept of our article. Recently, an increasing number of groups have used competing risk regression analysis to determine the influence of competing events such as mortality.…”

“…Van den Eynde and colleagues 1 have clearly pointed out the most important advantages of this modeling technique when compared with classic Kaplan-Meier survival estimates and Cox regression analysis. Limiting the analysis to the first occurring event at follow-up results in failure to account for subsequent events and for the interactions of these with competing variables, particularly important when several events happen during the follow-up period.…”

“…It is with great enthusiasm that we welcome the words of Van den Eynde and colleagues. 1 A great deal of effort will be needed in the coming years to promote the evolution of statistical analysis to keep pace with increasing use of big data and the growth of medical technology. 5 Good news from Baltimore!…”

Reply: Using different statistical tools to see forests and trees

“…We read with interest the commentary provided by Van den Eynde and colleagues 1 regarding the article by Guariento and colleagues 2 and their examination of outcomes with a modulated renewal analysis in a group of truncus arteriosus patients at Boston Children's Hospital. Van den Eynde and colleagues 1 provide additional insight about the statistical question and answer the conundrum investigators face when analyzing complex clinical data.…”

“…We read with interest the commentary provided by Van den Eynde and colleagues 1 regarding the article by Guariento and colleagues 2 and their examination of outcomes with a modulated renewal analysis in a group of truncus arteriosus patients at Boston Children's Hospital. Van den Eynde and colleagues 1 provide additional insight about the statistical question and answer the conundrum investigators face when analyzing complex clinical data. Their discussion of major adverse cardiac events in patients with HIV makes clear that reliance on Kaplan-Meier methods and the accompanying log-rank testing can result in clinical events being overlooked when only examining the time to a first event.…”