Artificial Intelligence Causal Effect Estimation of Intermittent Preventive Treatment in Pregnancy Dosing Under Variable Antenatal Card Transcription Lag: A Target Trial Emulation Evaluation of Healthcare Birth-Weight Equity

Intermittent preventive treatment in pregnancy with sulfadoxine-pyrimethamine reduces low birth weight in malaria-endemic settings, but antenatal card transcription lag — the interval between the clinical encounter and the digitisation of the dosing record — threatens the validity of any causal estimate drawn from routine health information systems. No observational data are used or claimed. The analysis is a design and power evaluation conducted under a declared variance structure: between-cluster standard deviation 6.0, residual standard deviation 4.5, and intraclass correlation 0.64. Power was 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. Fifty-six clusters are required to detect a 5 percentage point effect at 80 per cent power under this variance structure. The framework formalises transcription lag as a time-varying misclassification process, shows that lag induces differential exposure misclassification when it correlates with gestational age at first antenatal visit, and specifies the target trial that a before-after-control-impact design can credibly emulate. The contribution is a design-level argument: causal claims about intermittent preventive treatment dosing and birth-weight equity require designs whose power is adequate to the variance induced by clustered antenatal care, and whose identification strategy explicitly models the lag process rather than treating the digitised record as a faithful proxy for the clinical encounter.