Artificial Intelligence Distributionally Robust Optimisation of Community Pharmacy Antiretroviral Regimen Substitution Under Variable Viral Load Assay Turnaround Telemetry: A computed Healthcare Resistance-Safety Evaluation

Community pharmacies in resource-limited settings increasingly substitute antiretroviral regimens when viral load assay turnaround telemetry is delayed or unreliable, yet the resistance-safety consequences of such substitution rules are rarely quantified before deployment. the present analysis formulates regimen substitution as a distributionally robust optimisation problem over an ambiguity set of turnaround-time distributions, couples it to a stochastic within-host resistance model, and evaluates the resulting policies in a computed healthcare environment. The design is a before-after-control-impact (BACI) evaluation of the estimator that would be used to detect a policy's effect on resistance-safety outcomes, characterised under a declared variance structure with between-cluster SD = 6.0, residual SD = 4.5 and intraclass correlation = 0.64. Power was estimated 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.52 clusters are required to detect a 5-percentage-point effect at 80% power, that the minimum detectable effect falls steeply between 8 and 24 clusters, and that the BACI interaction estimator remains approximately nominal in coverage across the grid. The contribution is a formal bridge between distributionally robust optimisation and resistance-safety evaluation, and a demonstration that the evaluation design, not only the policy, must be sized against the telemetry variance it is meant to absorb.