Concerns regarding cohort construction and selection bias in the study of PAP devices and cancer incidence

We read with great interest the recent article written by Kendzerska et al. [1] entitled "Association between a recalled positive airway pressure device and incident cancer: a population-based study," which was published recently in your esteemed journal. We are writing to express a few concerns regarding the methodology and data presentation, particularly as detailed in figure 1 of the article. While the study provides valuable insights, the cohort construction process could have resulted in potential biases that may impact the generalisability and validity of the findings.