Impact of diagnosis code grouping method on clinical prediction model performance: A multi-site retrospective observational study

•Methods for incorporating diagnosis codes in modelling are inconsistent.•AHRQ-Elixhauser is unable to map the vast majority of raw ICD codes.•Single-level CCS performs on par with raw codes and is clinically meaningful.•Single-level CCS serves as a good baseline as features in clinical prediction tasks.•Source code of analyses of MIMIC dataset are available to ensure reproducibility.