Excess mortality is not self-interpreting: Baseline choice as a governance issue in public health analytics

Interpretation of excess mortality depends critically on baseline choice. This commentary examines the recent debate on all-cause mortality in Norway in 2024 and argues that it reflects a conflation of two distinct purposes: real-time surveillance using updated baselines and assessment of whether mortality has returned to the pre-pandemic improvement trajectory. These correspond to different estimands and are not interchangeable. Baseline redefinition has predictable inferential and communicative consequences, particularly in public-facing outputs. I argue that the main risk lies not in modeling choices themselves, but in insufficiently explicit communication. Transparent reporting with clearly labeled baselines is essential to avoid interpretive drift.