Objective:To clarify the applicability of the Chinese version of Cornell Assessment of Pediatric Delirium Scale (CAPD) for neonatal delirium screening in Neonatal Intensive Care Units (NICU) .Methods:From March 2021 to May 2022, convenience sampling was used to select 210 newborns admitted to NICU at Zhuji Maternal and Child Health Care Hospital in Zhejiang Province as the study subject. This study used the American Diagnostic and Statistical Manual of Mental Disorders-V (DSM-V) as the gold standard to test the diagnostic validity of the Chinese version of CAPD in the assessment of neonatal delirium in NICU.Results:This study ultimately included 189 newborns. A total of 43 newborns with delirium were diagnosed by DSM-V, with an incidence rate of 22.75% (43/189). There was no statistically significant difference in the incidence of neonatal delirium among newborns with different gestational age, day age, gender, and disease diagnosis ( P>0.05). Compared with DSM-V, the consistency Kappa value between two results of scales was 0.72 ( P<0.01). When the CAPD diagnostic threshold was set at 15, the sensitivity of the Chinese version of CAPD was 86.01%, the specificity was 86.30%, and the maximum Youden index obtained was 0.723. Conclusions:The diagnostic validity of the Chinese version of CAPD for neonatal delirium assessment in NICU is good, and it can provide reliable tool support for neonatal delirium assessment.