Artificial Intelligence Causal Inference of Community Clinic Measles Supplementary Immunisation Campaign Targeting Under Unmeasured Birth-Cohort Age Misregistration: A Healthcare Doubly Robust Coverage Equity Evaluation

Measles supplementary immunisation campaigns (SIA) in low- and middle-income settings are routinely targeted using administrative age registers that systematically misclassify children whose births were never formally registered. The framework combines an artificial-intelligence-assisted age-reconstruction layer with an augmented inverse-probability-weighted (AIPW) estimator that remains consistent if either the treatment model or the outcome model is correctly specified. A replication-based evaluation was conducted: 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 replications, the estimated bias for the intercept was 0.01996 and for the exposure coefficient -0.00036; the root mean squared error was 0.85891 for the intercept and 0.01547 for the exposure coefficient; and empirical coverage of the nominal 95% confidence intervals was 1.0 for both parameters. The results indicate that the doubly robust estimator recovers the declared exposure coefficient with negligible bias and correct nominal coverage, and that the coverage-equity contrast is identifiable under the stated misregistration mechanism. The contribution is a formal identification strategy and an estimator whose finite-sample behaviour is characterised, not a claim of field deployment.