Artificial Intelligence Constrained Multi-Objective Optimisation of Neonatal Phototherapy Device Allocation Under Variable Irradiance Degradation Telemetry: A computed Evaluation of Healthcare Jaundice Treatment Equity

Neonatal jaundice remains a leading cause of preventable neurodevelopmental harm in low-resource settings, where phototherapy device allocation is complicated by irradiance degradation that varies across devices and over time. the present analysis formulates device allocation as a constrained multi-objective optimisation problem that trades off population-level treatment efficacy against inter-infant equity, subject to telemetry-driven irradiance constraints. Because no field data are available, the study is framed as a design and power analysis: a before-after-control-impact estimator is characterised under a declared variance structure (between-cluster SD = 6.0, residual SD = 4.5, intraclass correlation = 0.64), with power 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, and that the minimum detectable effect falls steeply as cluster count rises from 8 to 32. A constrained Pareto formulation is proposed in which irradiance telemetry defines the feasible allocation set and an equity penalty governs the trade-off between mean effective dose and the worst-served device. The contribution is a design-stage framework that makes the equity consequences of telemetry-driven allocation explicit before deployment, together with the sample-size requirements that any field evaluation of such a framework must meet.