Community Mental Health Service Digital Phenotyping Alert Fatigue and Crisis Team Response Latency in South African Community Teams: A Target-Trial Emulation of Surveillance Exposure

Digital phenotyping systems that stream continuous behavioural and physiological signals from community mental health service users generate alerts for crisis teams, but the density of those alerts may itself degrade the timeliness of clinical response. the present analysis characterises the operating characteristics of a target-trial emulation designed to estimate the effect of sustained surveillance exposure on crisis team response latency in South African community teams, using a before-after-control-impact (BACI) estimator under a declared variance structure. No observational data are used or claimed. The analysis specified between-cluster standard deviation 6.0, residual standard deviation 4.5 and intraclass correlation 0.64, and evaluated power across 2000 replications per design cell for cluster counts of 8, 16, 24 and 32 and effect sizes of 3, 5 and 8 percentage points. Power was estimated for the BACI interaction, and the minimum detectable effect at 80% power was derived for each cluster count. Fifty-six clusters were required to detect a 5 percentage point effect at 80% power. The results establish the design conditions under which alert-fatigue effects on response latency can be distinguished from between-team heterogeneity, and they identify the cluster counts at which the estimator becomes informative. The contribution is a design specification for causal inference on surveillance exposure in low-resource community mental health systems, not a report of observed latency.