We analyzed data from 15,846 live-born infants to assess the effect of electronic fetal monitoring on neonatal death rates. The crude neonatal death rate was 1.7 times higher in unmonitored infants than in those monitored. Adjusting for inherent risk and changes in mortality rates and monitoring rates during the years of the study lowered the relative risk to 1.4 (95 per cent confidence interval, 0.85 to 2.45). The estimated yield from monitoring decreased as the inherent risk of the baby declined. Thus, in the highest-risk group 109 lives might be saved for every thousand babies monitored. In the lowest risk group (babies at term with no risk factors) the neonatal death rate is around one per thousand. The absolute benefit for this large group could therefore not exceed one life saved for every thousand babies monitored.