This invention discloses a method and
system for early warning of pediatric
sepsis risk based on leukocyte dynamic trajectory. The method includes: acquiring time-series leukocyte count data of a target
pediatric patient for N consecutive days after admission or diagnosis of
sepsis, forming a
raw data sequence; preprocessing the
raw data sequence to eliminate baseline differences between individuals; inputting the preprocessed data sequence into a pre-trained leukocyte dynamic trajectory classification model to output the probability of the target
pediatric patient belonging to each category, and determining the category with the highest probability as the current trajectory category of the target
pediatric patient; mapping the current trajectory category to the corresponding
sepsis risk level according to a preset trajectory category-
risk level mapping rule; and determining whether to generate early warning information based on the sepsis
risk level. This invention can automatically analyze continuous leukocyte count data after patient admission, identify its characteristic dynamic change trajectory, automatically determine the risk level based on the
trajectory pattern, and issue timely early warnings.