Cognitive behavioral therapy skills via a smartphone app for subthreshold depression among adults in the community: the RESiLIENT randomized controlled trial

Abstract

Subthreshold depression, defined as a depressive status falling short of the diagnostic threshold for major depression, is common, disabling and constitutes a risk factor for future depressive episodes. Cognitive behavioral therapies (CBT) have been shown to be effective but are usually provided as packages of various skills. Little research has been done to investigate whether all their components are beneficial and contributory to mental health promotion. We addressed this issue by developing a smartphone CBT app that implements five representative CBT skills (behavioral activation, cognitive restructuring, problem solving, assertion training and behavior therapy for insomnia), and conducting a master randomized study that included four 2 × 2 factorial trials to enable precise estimation of skill-specific efficacies. Between September 2022 and February 2024, we recruited 3,936 adult participants with subthreshold depression. Among those randomized, the follow-up rate was 97% at week 6 and adherence to the app was 84%. The study showed that all included CBT skills and their combinations differentially beat all three control conditions of delayed treatment, health information or self-check, with effect sizes ranging between -0.67 (95% confidence interval: -0.81 to -0.53) and -0.16 (-0.30 to -0.02) for changes in depressive symptom severity from baseline to week 6, as measured with the Patient Health Questionnaire-9 scores. Knowledge of the active ingredients of CBT can better inform the design of more effective and scalable psychotherapies in the future. (UMIN Clinical Trials Registry UMIN000047124 ).

Fig. 1. Consolidated Standards of Reporting Trials (CONSORT) diagram.

The BA arm and control arm were common across the four 2 × 2 trials and are shown by the dotted squares in trials 2 to 4. The prespecified control condition was the delayed treatment. We conducted sensitivity analyses by replacing the delayed treatment with the health information arm and the self-check arm (Methods). ^aParticipants working on a three-shift schedule were excluded in the primary and sensitivity analyses for trial 4 (199 (5.1%) of the total sample were shift workers). AT, assertion training; BA, behavioral activation; BI, behavior therapy for insomnia; CR, cognitive restructuring; PHQ-9, Patient Health Questionnaire-9; PS, problem solving.

Extended Data Fig. 1. Contents of the interventions and controls.

The intervention arms #1 through #10 (BA through Self-check) filled in the PHQ-9 every week and received weekly encouragement emails from the clinical research coordinators at the central office. #11 (Health information) and #12 (Delayed treatment) were asked to fill in the PHQ-9 at weeks 3 and 6 only, and did not receive encouragement emails. AT: Assertion training, BA: Behavioural activation, BI: Behaviour therapy for insomnia CR: Cognitive restructuring, PS: Problem solving.

Extended Data Fig. 2. PHQ-9 change from baseline up to week 26.

Data represent least squares mean changes of the PHQ-9 scores estimated by the combined MMRM model. The regression model included fixed effects of treatment, visit (as categorical), and treatment-by-visit interactions, adjusted for baseline PHQ-9 scores employment status, age and gender. The error bars at weeks 6 and 26 represent SEMs. For more information, see Table 4, Extended Data Table 8, and Supplementary Table 2. AT: Assertion training, BA: Behavioural activation, BI: Behaviour therapy for insomnia, CR: Cognitive restructuring, PHQ-9: Patient Health Questionnaire-9, PS: Problem solving.