Effectiveness of Implementing a Collaborative Chronic Care Model for Clinician Teams on Patient Outcomes and Health Status in Mental Health: A Randomized Clinical Trial

Abstract

Importance: Collaborative chronic care models (CCMs) have extensive randomized clinical trial evidence for effectiveness in serious mental illnesses, but little evidence exists regarding their feasibility or effect in typical practice conditions.

Objective: To determine the effectiveness of implementation facilitation in establishing the CCM in mental health teams and the impact on health outcomes of team-treated individuals.

Design, setting, and participants: This quasi-experimental, randomized stepped-wedge implementation trial was conducted from February 2016 through February 2018, in partnership with the US Department of Veterans Affairs (VA) Office of Mental Health and Suicide Prevention. Nine facilities were enrolled from all VA facilities in the United States to receive CCM implementation support. All veterans (n = 5596) treated by designated outpatient general mental health teams were included for hospitalization analyses, and a randomly selected sample (n = 1050) was identified for health status interviews. Individuals with dementia were excluded. Clinicians (n = 62) at the facilities were surveyed, and site process summaries were rated for concordance with the CCM process. The CCM implementation start time was randomly assigned across 3 waves. Data analysis of this evaluable population was performed from June to September 2018.

Interventions: Internal-external facilitation, combining a study-funded external facilitator and a facility-funded internal facilitator working with a designated team for 1 year.

Main outcomes and measures: Facilitation was hypothesized to be associated with improvements in both implementation and intervention outcomes (hybrid type II trial). Implementation outcomes included the clinician Team Development Measure (TDM) and proportion of CCM-concordant team care processes. The study was powered for the primary health outcome, mental component score (MCS). Hospitalization rate was derived from administrative data.

Results: The veteran population (n = 5596) included 881 women (15.7%), and the mean (SD) age was 52.2 (14.5) years. The interviewed sample (n = 1050) was similar but was oversampled for women (n = 210 [20.0%]). Facilitation was associated with improvements in TDM subscales for role clarity (53.4%-68.6%; δ = 15.3; 95% CI, 4.4-26.2; P = .01) and team primacy (50.0%-68.6%; δ = 18.6; 95% CI, 8.3-28.9; P = .001). The percentage of CCM-concordant processes achieved varied, ranging from 44% to 89%. No improvement was seen in veteran self-ratings, including the primary outcome. In post hoc analyses, MCS improved in veterans with 3 or more treated mental health diagnoses compared with others (β = 5.03; 95% CI, 2.24-7.82; P < .001). Mental health hospitalizations demonstrated a robust decrease during facilitation (β = -0.12; 95% CI, -0.16 to -0.07; P < .001); this finding withstood 4 internal validity tests.

Conclusions and relevance: Implementation facilitation that engages clinicians under typical practice conditions can enhance evidence-based team processes; its effect on self-reported overall population health status was negligible, although health status improved for individuals with complex conditions and hospitalization rate declined.

Trial registration: ClinicalTrials.gov Identifier: NCT02543840.

Figure 1.. CONSORT Diagram for Facilities, Veteran Participants, and Clinicians

Providers are mental health clinicians on the teams that received implementation support. The parenthetical t₀ represents baseline prior to implementation of support; t₆, the 6-month midpoint of implementation support; t₁₂, postimplementation support after 12 months.

Figure 2.. Protocol Structure: Implementation and Evaluation

The implementation and evaluation protocol is illustrated for 3 facilities across 3 waves. Implementation consisted of 6 months of intensive facilitation followed by 6 months of step-down support (shaded rows). Facilities were assigned staggered start times for implementation, beginning at approximately 4-month intervals. The evaluative activities are illustrated beneath the implementation activities for each site (unshaded rows). Specifically, population-level hospitalization data were gathered on a quarterly basis from 12 months prior to the start of implementation (PreQ4-PreQ1) and for the 12 months of implementation (Q1-Q4). The veteran interview sample was assessed at the beginning of implementation, after 6 months, and after 12 months of implementation (black dots). Clinician assessment with the Team Development Measure took place at the beginning of facilitation and during step-down support. Thus, all evaluation activities were anchored to the start time of implementation support, considered protocol time zero (t₀) for each site. Q indicates quarter of the year.

Figure 3.. Mental Health Hospitalization Rates

The x-axis displays protocol time, with implementation support occurring from Q1 through Q4. The blue line represents hospitalization rate for veterans treated by collaborative chronic care model (CCM)–enhanced teams, and the orange line represents veterans from the same clinics who were not treated by the CCM-enhanced teams (see text for details). Error bars represent SEs. Q indicates quarter of the year.