Mindfulness-based interventions for psychiatric disorders: A systematic review and meta-analysis

Abstract

Despite widespread scientific and popular interest in mindfulness-based interventions, questions regarding the empirical status of these treatments remain. We sought to examine the efficacy of mindfulness-based interventions for clinical populations on disorder-specific symptoms. To address the question of relative efficacy, we coded the strength of the comparison group into five categories: no treatment, minimal treatment, non-specific active control, specific active control, and evidence-based treatment. A total of 142 non-overlapping samples and 12,005 participants were included. At post-treatment, mindfulness-based interventions were superior to no treatment (d=0.55), minimal treatment (d=0.37), non-specific active controls (d=0.35), and specific active controls (d=0.23). Mindfulness conditions did not differ from evidence-based treatments (d=-0.004). At follow-up, mindfulness-based interventions were superior to no treatment conditions (d=0.50), non-specific active controls (d=0.52), and specific active controls (d=0.29). Mindfulness conditions did not differ from minimal treatment conditions (d=0.38) and evidence-based treatments (d=0.09). Effects on specific disorder subgroups showed the most consistent evidence in support of mindfulness for depression, pain conditions, smoking, and addictive disorders. Results support the notion that mindfulness-based interventions hold promise as evidence-based treatments.

Keywords: Evidence-based treatments; Meditation; Meta-analysis; Mindfulness; Psychiatric disorders; Relative efficacy.

Figure 1

PRISMA Flow Diagram

Figure 2

Post-treatment effects by comparison group type. k = number of disorder-specific comparisons; Tx n = mindfulness condition sample size; Cont n = comparison group sample size (note that total n is larger than the full sample size as some samples are represented in multiple comparisons); d = Cohen’s d effect size; Q = Q-statistic; Q_p = p-value for Q-statistic; I² = heterogeneity; k_imp = number of imputed studies based on trim-and-fill analyses; d_adj = adjusted d based on trim-and-fill analyses; No tx = no treatment; Min tx = minimal treatment; Non-spec = non-specific active control condition; Spec = Specific active control condition; EBT = evidence-based treatment.

Figure 3

Post-treatment effects on disorder-specific symptoms by comparison group and disorder. Comp = comparison group; k = number of disorder-specific comparisons; Tx n = mindfulness condition sample size; Cont n = comparison group sample size (note that total n is larger than the full sample size as some samples are represented in multiple comparisons); d = Cohen’s d effect size; Q = Q-statistic; Q_p = p-value for Q-statistic; I² = heterogeneity; k_imp = number of imputed studies based on trim-and-fill analyses; d_adj = adjusted d based on trim-and-fill analyses; No tx = no treatment; Min tx = minimal treatment; Non-spec = non-specific active control condition; Spec = Specific active control condition; EBT = evidence-based treatment.

Figure 4

Follow-up effects by comparison type. k = number of disorder-specific comparisons; Tx n = mindfulness condition sample size; Cont n = comparison group sample size (note that total n is larger than the full sample size as some samples are represented in multiple comparisons); d = Cohen’s d effect size; Q = Q-statistic; Q_p = p-value for Q-statistic; I² = heterogeneity; k_imp = number of imputed studies based on trim-and-fill analyses; d_adj = adjusted d based on trim-and-fill analyses; No tx = no treatment; Min tx = minimal treatment; Non-spec = non-specific active control condition; Spec = Specific active control condition; EBT = evidence-based treatment.

Figure 5

Follow-up effects by comparison type and disorder. Comp = comparison group; k = number of disorder-specific comparisons; Tx n = mindfulness condition sample size; Cont n = comparison group sample size (note that total n is larger than the full sample size as some samples are represented in multiple comparisons); d = Cohen’s d effect size; Q = Q-statistic; Q_p = p-value for Q-statistic; I² = heterogeneity; k_imp = number of imputed studies based on trim-and-fill analyses; d_adj = adjusted d based on trim-and- fill analyses; No tx = no treatment; Min tx = minimal treatment; Non-spec = non-specific active control condition; Spec = Specific active control condition; EBT = evidence-based treatment.