Can We Reduce the Duration of Untreated Psychosis? A Systematic Review and Meta-Analysis of Controlled Interventional Studies

Abstract

Reduction of duration of untreated psychosis (DUP) is the key strategy of early interventions for improving the outcomes of first-episode psychosis. Although several controlled interventional studies have been conducted with the aim of reducing DUP, the results are highly inconsistent and conflicting. The current study systematically searches Web of Science and Ovid for English original articles investigating interventions adopted to reduce DUP, compared to a control intervention, up to April 6, 2017. Sixteen controlled interventional studies were retrieved, including 1964 patients in the intervention arm and 1358 in the control arm. The controlled intervention studies were characterized by standalone first episode psychosis services, standalone clinical high risk services, community interventions, healthcare professional training, and multifocus interventions. Random effects meta-analyses were conducted. There was no summary evidence that available interventions are successful in reducing DUP during the first episode of psychosis (Hedges' g = -0.12, 95% CI = -0.25 to 0.01). Subgroup analyses showed no differences within each subgroup, with the exception of clinical high risk services (Hedges' g = -0.386, 95% CI = -0.726 to -0.045). These negative findings may reflect a parceled research base in the area, lack of prospective randomized controlled trials (only 2 randomized cluster designed studies were present) and small sample sizes. There was substantial heterogeneity (I2 = 66.4%), most of which was accounted by different definitions of DUP onset (R2 = .88). Psychometric standardization of DUP definition, improvement of study design, and implementation of preventative strategies seem the most promising avenues for reducing DUP and improving outcomes of first-episode psychosis.

Fig. 1.

PRISMA flow chart.

Fig. 2.

Forest plot showing results of random effects within-subgroup analysis and overall summary effect.

Fig. 3.

Meta-regression analyses. Effect of controlled intervention on the DUP (Hedges’ g) by length of intervention (months).

Fig. 4.

Meta-regression analyses. Effect of controlled intervention on the DUP (Hedges’ g) by control DUP (days).

Fig. 5.

Meta-regression analyses. Effect of controlled intervention on the DUP (Hedges’ g) by DUP onset definition.