Dear Editor:

I read Feng’s study [1] with great interest. In this study, the author aimed to investigate potential risk factors for emergence delirium (ED) in pediatric patients after tonsillectomy and adenoidectomy (T&A). Univariate and multivariate logistic regression analyses were performed to investigate risk factors for ED, and this study found that the preoperative NLR level and postoperative pain were independent risk factors for ED in pediatric patients undergoing T&A. Despite definite results, I mention that a great factor may be ignored that could greatly influence the result of risk factors in this study.

I noted that there are 19 ED patients for analyzing the risk factors associated with ED using the univariate and multivariate logistic regression analyses in Table 3. But there are 7 variables (age, height, MYPAs, postoperative pain, LYM#, NLR, MLR) in this table. Thus, this statistical analysis breaks the rule that 1 variable per 10 outcome events (i.e., ED in this study) in the univariate and multivariate analysis. However, there are only 19 ED patients in this study; then, the risk factors predictor model should have included at most 2 variables. Thus, 7 variables in only 19 ED patients may overfit this regression model. More ED patients should be included in this study, which could obtain reliable statistical results. However, despite these comments, I show great gratitude to Feng and colleagues’ outstanding work.