Reduction of Depression in People With Disabilities Through Dual Treatment: Digital CBT & NBHWC Coaching

Change in Evaluator-Administered Hamilton Depression Rating Scale (HAM-D) from Baseline to Week 8.

The analysis of the primary endpoint, i.e., change in HAM-D @ Week 8, will be based on a MMRM (mixed model of repeated measures) in the enrolled population, where site \& participant are random effects \& assessment (Week 4 versus Week 8) \& randomization arm (Toivoa-002 vs Sham) \& the assessment-by-arm interaction are fixed effects. Additionally, the baseline assessment will be included as a fixed effect covariate. The model will include up to 2 outcomes per participant (change @ Week 4 \& change @ Week 8). The hypothesis of equal mean change will be evaluated based on the t-test corresponding to the difference in least square means at Week 8, where both the point estimate \& the variance of the difference in least square means will be estimated using multiple imputation. Details regarding the number of multiple imputation datasets, the method of obtaining a combined point estimate and variance from the MMRM evaluations of the multiple imputation datasets will be pre-specified in the plan

Changes in Hamilton Depression Rating Scale (HAM-D) at Week 12, Clinical Global Impression for Improvement (CGI- I) at Week 8 and Week 12, and proportion of participants achieving clinically meaningful response at Week 8 on HAM-D.

(1) Change in Evaluator-administered Hamilton Depression Rating Scale (HAM-D) at Week 12 (4 weeks after completion of Toivoa modules) (2) Evaluator Administered Clinical Global Impression for Improvement (CGI-I) at end of therapy at Week 8. (3) Evaluator Administered Clinical Global Impression for Improvement (CGI-I) at Week 12 (4 weeks after completion of therapy). (4) Proportion achieving a clinically meaningful HAM-D reduction at Week 8. All secondary endpoints will be evaluated using the enrolled population. The durability of the HAM-D effect will be analyzed with an MMRM that is identical to the model in the primary analysis with the exception that it will include the change at Week 12, such that there are up to 3 observations per participant. The hypothesis will be tested based on the t-test for the difference in least squares means at Week 12 rather than Week 8.

Changes in Hamilton Anxiety Rating Scale (HAM-A) and Patient Health Questionnaire-9 (PHQ-9) Baseline to Week 8

1\) Change in Evaluator-administered Hamilton Anxiety Rating Scale (HAM-A) from baseline to Week 8. (2) Patient Health Questionnaire-9 (PHQ-9) from baseline to Week 8. The analysis of change in anxiety will be evaluated with an MMRM that is identical to the primary analysis, with the exception that the outcome will be change in HAM-A rather than change in HAM-D. Similarly, the analysis of change in PHQ-9 will be evaluated with an MMRM that is identical to the primary analysis, with the exception that the outcome will be change in PHQ-9 rather than change in HAM-D.