Introduction: Neonatal sepsis remains an important clinical syndrome despite advances in neonatology. Current hematology analyzers can determine cell volume (V), conductivity for internal composition of cell (C) and light scatter for cytoplasmic granularity and nuclear structure (S), and standard deviations which are effective in the diagnosis of sepsis. Statistical models can be used to strengthen the diagnosis. Effective modeling of molecular activity (EMMA) uses combinatorial algorithm of the selection parameters for regression equation based on modified stepwise procedure. It allows obtaining different regression models with different combinations of parameters.