Objectives The COVID-19 pandemic instigated multiple societal and healthcare interventions with potential to affect perinatal practice. We evaluated population-level changes in preterm and full-term admissions to neonatal units, care processes and outcomes. Design Observational cohort study using the UK National Neonatal Research Database. Setting England and Wales. Participants Admissions to National Health Service neonatal units from 2012 to 2020. Main outcome measures Admissions by gestational age, ethnicity and Index of Multiple Deprivation, and key care processes and outcomes. Methods We calculated differences in numbers and rates between April and June 2020 (spring), the first 3 months of national lockdown (COVID-19 period), and December 2019–February 2020 (winter), prior to introduction of mitigation measures, and compared them with the corresponding differences in the previous 7 years. We considered the COVID-19 period highly unusual if the spring–winter difference was smaller or larger than all previous corresponding differences, and calculated the level of confidence in this conclusion. Results Marked fluctuations occurred in all measures over the 8 years with several highly unusual changes during the COVID-19 period. Total admissions fell, having risen over all previous years (COVID-19 difference: −1492; previous 7-year difference range: +100, +1617; p<0.001); full-term black admissions rose (+66; −64, +35; p<0.001) whereas Asian (−137; −14, +101; p<0.001) and white (−319; −235, +643: p<0.001) admissions fell. Transfers to higher and lower designation neonatal units increased (+129; −4, +88; p<0.001) and decreased (−47; −25, +12; p<0.001), respectively. Total preterm admissions decreased (−350; −26, +479; p<0.001). The fall in extremely preterm admissions was most marked in the two lowest socioeconomic quintiles. Conclusions Our findings indicate substantial changes occurred in care pathways and clinical thresholds, with disproportionate effects on black ethnic groups, during the immediate COVID-19 period, and raise the intriguing possibility that non-healthcare interventions may reduce extremely preterm births.