We read with great interest the article by Aksay et al [1]. To our knowledge, this is the first study performed in an emergency department (ED) that suggested that cardiac troponin I (cTnI) could predict in-hospital complicated pulmonary embolism (PE). It is interesting because echocardiography is rarely available in most EDs. However, we have several concerns and comments about the method they used and their conclusions. First, it was a retrospective study (with all the methodological biases [2]) of patients admitted with a diagnosis of PE in the ED; we suggest that some PEs could have been missed in the ED and diagnosed later in the ward but not included in their study.