The accuracy of a risk prediction depends first on data quality, not model complexity. Missing encounters, inconsistent lab units and duplicate registrations across systems are all amplified in the model output.
In practice we start with a completeness assessment of the key fields: which measures have the highest missing rate, and whether missingness concentrates in particular sites or populations.
Missingness can itself carry information. A test that is consistently not performed may relate to access or adherence and should be treated as a separate signal rather than simply imputed.
