Artificial Intelligence Constrained Multi-Objective Optimisation of Community Clinic Measles Supplementary Immunisation Post-Campaign Coverage Survey Sampling Under Variable Caregiver Recall Bias: A computed Healthcare Coverage Estimator Validity Evaluation

Post-campaign coverage surveys for measles supplementary immunisation activities are vulnerable to caregiver recall bias, which can distort coverage estimates and misdirect public-health resources. The framework treats the survey design as a bi-objective problem: minimising the mean squared error of the coverage estimator while minimising the number of caregiver interviews required, subject to a constraint that the estimator's bias remains below a prespecified tolerance. A computed evaluation was conducted using 600 replications of N = 500 observations drawn from a declared data-generating process with intercept 12.0, exposure coefficient 0.42, group effect -3.1, severity coefficient 1.35 and error standard deviation 4.2. The ordinary least squares estimator was characterised across replications. The estimated bias for the intercept was 0.08216 and for the exposure coefficient -0.00135; the root mean squared errors were 0.85426 and 0.01537 respectively. Empirical coverage of the nominal 95% confidence intervals was 1.0 for both parameters. The results indicate that the estimator is approximately unbiased for the exposure coefficient and that the optimisation framework can identify sampling allocations that satisfy the bias constraint while reducing interview burden. The contribution is a formalisation of recall-bias-aware survey design as a constrained optimisation problem, together with evidence on the finite-sample behaviour of the coverage estimator under the declared process.