"The Effects of Cognitive Behavioral Therapy as an Anti-Depressive Treatment is Falling: A Meta-Analysis": Correction to Johnsen and Friborg (2015)

Abstract

Reports an error in "The effects of cognitive behavioral therapy as an anti-depressive treatment is falling: A meta-analysis" by Tom J. Johnsen and Oddgeir Friborg (Psychological Bulletin, 2015[Jul], Vol 141[4], 747-768). There are several numerical errors in the flowchart summarizing the selection and exclusion of studies as contained in Figure 1. The correct number of titles not further investigated should be 27,381; abstracts rejected should be 1,181; Excluded, different treatment form should be (94). The errors do not affect the results or conclusions of the study as the final number of meta-analysable studies are the same as originally reported. (The following abstract of the original article appeared in record 2015-20361-001.) A meta-analysis examining temporal changes (time trends) in the effects of cognitive behavioral therapy (CBT) as a treatment for unipolar depression was conducted. A comprehensive search of psychotherapy trials yielded 70 eligible studies from 1977 to 2014. Effect sizes (ES) were quantified as Hedge's g based on the Beck Depression Inventory (BDI) and the Hamilton Rating Scale for Depression (HRSD). Rates of remission were also registered. The publication year of each study was examined as a linear metaregression predictor of ES, and as part of a 2-way interaction with other moderators (Year × Moderator). The average ES of the BDI was 1.58 (95% CI [1.43, 1.74]), and 1.69 for the HRSD (95% CI [1.48, 1.89]). Subgroup analyses revealed that women profited more from therapy than did men (p < .05). Experienced psychologists (g = 1.55) achieved better results (p < .01) than less experienced student therapists (g = 0.98). The metaregressions examining the temporal trends indicated that the effects of CBT have declined linearly and steadily since its introduction, as measured by patients' self-reports (the BDI, p < .001), clinicians' ratings (the HRSD, p < .01) and rates of remission (p < .01). Subgroup analyses confirmed that the declining trend was present in both within-group (pre/post) designs (p < .01) and controlled trial designs (p = .02). Thus, modern CBT clinical trials seemingly provided less relief from depressive symptoms as compared with the seminal trials. Potential causes and possible implications for future studies are discussed.