Artificial Intelligence replication of District Hospital Neonatal Kangaroo Care Transfer Scheduling Under Unmeasured Maternal Postpartum Ambulation Variability: A Healthcare Robustness-Constrained Evaluation

Kangaroo care transfer scheduling in district hospitals requires the repeated movement of neonates between incubators and maternal chest positions, yet the timing of maternal postpartum ambulation is rarely recorded and cannot be measured reliably in low-resource wards. The framework is evaluated through a replication-based replication study: 600 data sets of N = 500 were drawn from a declared data-generating process (intercept 12.0, exposure 0.42, group -3.1, severity 1.35, error SD 4.2), and the behaviour of the ordinary least squares estimator was characterised under the stated process. Across the 600 replications, the estimated bias for the intercept was 0.02888 and for the exposure coefficient -0.00052; the root mean squared error was 0.86695 for the intercept and 0.01594 for the exposure coefficient; empirical coverage of the nominal 95% confidence intervals was 1.0 for both parameters. The results indicate that the estimator is approximately unbiased and that nominal coverage is achieved under the declared process, which establishes a baseline against which robustness-constrained scheduling rules can be compared. The contribution is a formalisation of ambulation variability as a bounded adversarial input and a demonstration that the resulting scheduling problem admits a tractable robust counterpart.