Abstract: Objective To investigate the risk factors of neonatal nosocomial infection and effect of cluster nursing intervention, and to provide reference for clinical treatment. Methods A total of 826 cases of neonates were selected from Hainan maternal and child health care hospital. They were divided into hospital infection group (52 cases) and non hospital infection group (774 cases) according to the occurrence of hospital infection. Univariate and multivariate Logistic regression analysis were used to analyze the risk factors of nosocomial infection in neonates. Fifty-two cases of hospital infection were randomly divided into the control group and the observation group, with 26 cases in each group. The control group was given routine care, the observation group was treated by cluster nursing on the basis of routine care, and the intervention effect between the two groups was compared. Results There were 52 cases of nosocomial infection in 826 neonates, the infection rate was 6.30%, and the main infection site was respiratory tract, accounting for 53.85%. A total of 58 strains of pathogenic bacteria were isolated from 52 children with nosocomial infection, mainly Gram negative bacteria (65.52%) and gram positive bacteria (31.03%). Univariate and multivariate Logistic regression analysis showed that birth weight (OR=2.704, P=0.021), invasive operation (OR=5.206, P<0.001), Apgar score (OR=1.947, P=0.036) and antimicrobial use time (OR=3.126, P<0.001) were neonatal nosocomial infection independent risk factors. The hospitalization time, hospitalization expenses, mechanical ventilation time, white blood cell count, ventilator use rate and complication rate of the observation group were significantly lower than those in the control group(P<0.05). The effective rate of observation group was significantly higher than that of the control group (P<0.05). Conclusion The pathogens of neonatal infection are quite extensive, and the risk factors of nosocomial infection are varied. Cluster nursing intervention can improve the treatment effect among children.