Artificial Intelligence Distributionally Robust Optimisation of Surgical Consumable Kitting Under Variable Sterilisation Autoclave Cycle Failure Logging: A Healthcare Shortage Resilience Evaluation

Surgical consumable kitting is vulnerable to sterilisation autoclave failures whose logging is inconsistent, creating ambiguity about the true failure rate and the risk of shortage. The framework is evaluated through a replication-based design study that characterises the operating characteristics of a before-after-control-impact estimator under a declared variance structure (between-cluster SD = 6.0, residual SD = 4.5, intraclass correlation = 0.64). Power was estimated across 2000 design cells for cluster counts of 8, 16, 24 and 32 and effect sizes of 3, 5 and 8 percentage points. The analysis indicates that 52 clusters are required to detect a 5 percentage point effect at 80% power. The results show that ignoring logging variability leads to systematic underestimation of required safety stock, and that the distributionally robust approach yields kitting policies that are resilient to plausible perturbations in failure-rate estimates.