Objective To determine the accuracy of intrapartum fetal heart rate (FHR) abnormalities as defined by National Institute of Health and Care Excellence guidelines for the prediction of moderate-severe hypoxic-ischemic neonatal encephalopathy (HIE). Design Case-control study Setting Rotunda Hospital, Dublin, Ireland. Population or Sample Eligible babies were born between September 2006 and November 2017 at ≥35+0 weeks’ gestational age. Cases were eligible babies with moderate-severe HIE. Controls were eligible babies born before and after each case with normal Apgar scores. Methods Blinded manual marking of FHR trace features followed by automated categorisation of each 15-minute segment. Main Exposure Measures FHR pattern features: baseline, variability, accelerations, early, variable, deep/prolonged variable, late or prolonged decelerations, bradycardia, sinusoidal pattern FHR pattern categories: normal, suspicious, or pathological Results Adequate FHR traces results were available in 52 of 88 cases and 118 of 176 controls. The FHR pattern feature with the largest area under the receiving operator characteristic curve (AUROCC) was the maximum number of consecutive segments with the baseline >160bpm (0.71 [95% confidence interval {CI}: 0.62-0.80]). The FHR category variable with the highest AUROCC was the number of suspicious segments (0.76 [95% CI: 0.67-0.84]). A multivariate model incorporating the number of segments and the percentage of segments classed suspicious/pathological achieved an AUROCC of 0.782 (95% CI: 0.704-0.861). Conclusions The power of FHR analysis to predict HIE is hampered by poor sensitivity for the rarity of the outcome. When analysing a suspicious FHR trace, it is beneficial to consider the overall duration of the suspicious patterns