Artificial Intelligence replication of District Hospital Pulmonary Tuberculosis Contact Tracing Allocation Under Unmeasured Cough Acoustics Sensor Placement Bias: A Healthcare Fairness-Constrained Evaluation

Cough acoustics sensing has been proposed as a triage aid for pulmonary tuberculosis contact tracing in district hospitals, but the placement of acoustic sensors introduces unmeasured heterogeneity that can distort allocation decisions. The framework couples a latent bias process to a constrained optimisation rule that penalises allocation disparities across sensor-placement strata. A replication-based evaluation of the ['Intercept', 'exposure', 'group', 'severity'] estimator 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). The study characterises the behaviour of the ordinary least squares estimator under the stated process. Across the 600 replications, the estimated bias for the intercept was 0.05984 and for the exposure coefficient -0.00086; the root mean squared error was 0.86457 for the intercept and 0.01585 for the exposure coefficient. Empirical coverage of the nominal 95% confidence intervals was 1.0 for both parameters. The results indicate that under the declared process the estimator is approximately unbiased for the exposure coefficient and that nominal coverage is achieved, which provides a baseline against which fairness-constrained allocation rules can be assessed. Sensor placement bias should be treated as a structural feature of the allocation problem rather than as measurement noise, and it derives conditions under which a fairness constraint remains binding.