Artificial Intelligence Causal Inference of Community Clinic Insulin Cold-Chain Viability Under Unmeasured Solar Refrigerator Duty-Cycle Confounding: A Healthcare Instrumental Variable Spoilage Evaluation

Solar direct-drive refrigerators are the backbone of insulin cold-chain maintenance in off-grid community clinics, yet their duty-cycle behaviour is rarely instrumented, leaving a latent confounder that biases naive estimates of spoilage risk. The framework is formalised as a structural causal model with explicit assumptions, and the before-after-control-impact (BACI) estimator is characterised through a replication-based power analysis under a declared variance structure (between-cluster SD = 6.0, residual SD = 4.5, intraclass correlation = 0.64). Across 2000 replications per design cell, power was estimated for cluster counts of 8, 16, 24 and 32 and effect sizes of 3, 5 and 8 percentage points; 54 clusters were required for 80% power at a 5-percentage-point effect. The analysis is methodological: it does not report observational findings but specifies the identification conditions, the estimator, and the design parameters under which a field evaluation would be credible. The contribution is a reusable template for instrumental-variable spoilage evaluation in resource-constrained cold chains, together with a transparent account of the design's operating characteristics.