Artificial Intelligence Temporal Fusion Transformer Forecasting of Cholera Treatment Centre Bed Occupancy Under Variable Surveillance Reporting Interruption: A Rolling-Origin Evaluation of Healthcare Surge Readiness

Cholera treatment centre bed occupancy is a critical surge indicator, yet surveillance reporting interruptions of variable duration make short-horizon forecasts unreliable. Because no observational bed-occupancy series are available, the study characterises the operating characteristics of the evaluation design itself under a declared variance structure. A replication-based power analysis of the before-after-control-impact estimator was conducted across 2000 design cells, with between-cluster standard deviation 6.0, residual standard deviation 4.5, and intraclass correlation 0.64.54 clusters are required to detect a 5 percentage-point effect at 80% power, and that the intraclass correlation of 0.64 substantially inflates the cluster requirement. The framework specifies how rolling-origin evaluation can be implemented when reporting interruptions are present, and it identifies the conditions under which TFT forecasts would be expected to outperform simpler baselines. The contribution is a design protocol for surge-readiness forecasting that makes the interruption mechanism explicit rather than treating missing reports as random noise.