Following the publication and correction of this article [1, 2], questions were raised about the study design and reporting that prompted a full reassessment of the article. This post-publication evaluation involved three senior staff editors, a statistical reviewer, and a member of PLOS ONE’s Editorial Board, and identified the following concerns:

The PLOS ONE Editors and the consulted Academic Editor reviewed the information and additional methodological details provided by authors in response to each of these issues. The Editors determined that the additional information provided did not fully address the above concerns, which call into question the reproducibility of the study, the scientific validity and rigor of the study design, and whether conclusions are adequately supported by the results. For these reasons, the PLOS ONE Editors retract this article. We regret that these issues were not identified and addressed prior to the article’s publication.

During the post-publication assessment, questions were also raised about whether the 6-week duration of the study and fixed dosing regimen for fluoxetine treatment were sufficient to allow an assessment as to the efficacy of fluoxetine where it was prescribed. The consulted Academic Editor noted that other randomized clinical trials using fluoxetine allow for increasing dosage in case of nonresponse. The Academic Editor also noted that per clinical practice guidelines, trials of antidepressants should generally last 8–12 weeks [4] and it generally requires 4–8 weeks of treatment to determine whether a patient is responsive to a particular intervention [5]. The authors noted that trials identified in published systematic reviews [6, 7, 8] used the same duration of fluoxetine treatment as was applied in [1]. The authors further commented that the fluoxetine dose used aligns with starting doses applied in clinical practice [4].

EdCM-C, LL-G, LA-F, and JA-B did not agree with retraction.