Adverse effects of psychotherapy: protocol for a systematic review and meta-analysis

Background: While it is well known that psychotherapy is efficacious in the treatment of mental disorders, much less is known about the adverse effects of psychotherapeutic interventions. The aim of this systematic review is to examine the definition, frequency, nature, and severity of adverse effects occurring parallel to or following psychotherapeutic treatment and to compare it against control groups. Methods: All registered randomised controlled trials published since 2004 (publication year of harm-reporting extension of the CONSORT statement) with adult patients fulfilling clinical criteria of defined mental disorders, which compare individual or group psychotherapy against a control group, will be included. First, a search through international trial registers as well as a search in literature databases (e.g. MEDLINE) and in relevant journals (e.g. Trials) for study protocols will be conducted to identify eligible trials. In a second step, we will search for respective publications of the results of the eligible studies. Publications will be retrieved and screened for eligibility. Two previously trained, independent raters will extract the data in duplicate. Reporting of adverse effects will be descriptively analysed regarding frequency, heterogeneity, and longitudinal course. We will further compare the adverse effects of psychotherapeutic interventions against various control groups. For each categorical outcome, we will calculate relative risks (RR) together with 95% confidence intervals. For continuous outcomes, standardised mean differences (Hedges' g) with a 95% confidence interval will be computed. Between-study heterogeneity will be tested with the Q statistic and quantified using I-2. Discussion: Preselecting studies with regard to randomised controlled trials might induce bias due to dropout before the beginning of treatment or end of treatment. However, we will thoroughly assess the negative effects of randomisation, e.g. reasons for non-randomisation, if reported. Even if delayed adverse effects might be overlooked in randomised controlled trials, these are the only sources of causal evidence.