Abstract: Machine learning algorithms are algorithms that study and analyze data to obtain regularities among the data and use the regularities to predict unknown data. Electronic medical records contain a large amount of data information about patients' diseases,which provides the data basis for the practice of machine learning in the field of medical and nursing. This article reviewed the application status of machine learning in the early identification and nursing of neonatal sepsis,including obtaining data such as demographic characteristics,vital signs,antibiotic use,etiological characteristics and treatment of the entire hospitalization period from the electronic medical record database,and developing predictive models through machine learning algorithms,in order to provide reference for clinic nurses to realize early identification of neonatal sepsis,implement nursing plans as early as possible,and provide nursing interventions. Machine learning modeling can be used for early identification and diagnosis of neonatal sepsis. Its accuracy and wide adaptability need to be further confirmed by prospective studies based on multi-center large-scale data.

Key words: Machine Learning, Neonatal Sepsis, Prediction Model, Critical Care Nursing