Utilization of Therapeutic Hypothermia and Neurological Injury in Neonates with Mild Hypoxic-Ischemic Encephalopathy: A Report from Children's Hospital Neonatal Consortium

Growth trajectories and need for oral feeding support among infants with neonatal encephalopathy treated with therapeutic hypothermia

OBJECTIVE

Identify feeding supports required among infants with neonatal encephalopathy and determine growth trajectories to 3 years.

STUDY DESIGN

Single-center retrospective cohort study of 120 infants undergoing therapeutic hypothermia. Logistic regression and stratified analyses identified whether clinical factors, EEG-determined encephalopathy severity, and MRI-based brain injury predict feeding supports (nasogastric tube, oral feeding compensations) and growth.

RESULTS

50.8% of infants required feeding supports in the hospital, decreasing to 14% at discharge. Moderate-to-severe encephalopathy and basal ganglia injury predicted feeding support needs. Yet, 35% of mildly encephalopathic infants required gavage tubes. Growth trajectories approximated expected growth of healthy infants.

CONCLUSION

Infants with neonatal encephalopathy-even if mild-frequently experience feeding difficulties during initial hospitalization. With support, most achieve full oral feeds by discharge and adequate early childhood growth. Clinical factors may help identify infants requiring feeding support, but do not detect all at-risk infants, supporting routine screening of this high-risk population.

Whole-body hypothermia in mild neonatal encephalopathy: protocol for a multicentre phase III randomised controlled trial

BACKGROUND

Mild hypoxic ischemic encephalopathy is associated with sub optimal cognition and learning difficulties at school age. Although whole-body hypothermia reduces death and disability after moderate or severe encephalopathy in high-income countries, the safety and efficacy of hypothermia in mild encephalopathy is not known. The cooling in mild encephalopathy (COMET) trial will examine if whole-body hypothermia improves cognitive development of neonates with mild encephalopathy.

METHODS

The COMET trial is a phase III multicentre open label two-arm randomised controlled trial with masked outcome assessments. A total of 426 neonates with mild encephalopathy will be recruited from 50 to 60 NHS hospitals over 2 ½ years following parental consent. The neonates will be randomised to 72 h of whole-body hypothermia (33.5 ± 0.5 C) or normothermia (37.0 ± 0.5 C) within six hours or age. Prior to the recruitment front line clinical staff will be trained and certified on expanded modified Sarnat staging for encephalopathy. The neurological assessment of all screened and recruited cases will be video recorded and centrally assessed for quality assurance. If recruitment occurs at a non-cooling centre, neonates in both arms will be transferred to a cooling centre for continued care, after randomisation. All neonates will have continuous amplitude integrated electroencephalography (aEEG) at least for the first 48 h to monitor for seizures. Predefined safety outcomes will be documented, and data collected to assess resource utilization of health care. A central team masked to trial group allocation will assess neurodevelopmental outcomes at 2 years of age. The primary outcome is mean difference in composite cognitive scores on Bayley scales of Infant and Toddler development 4th Edition.

DISCUSSION

The COMET trial will establish the safety and efficacy of whole-body hypothermia for mild hypoxic ischaemic encephalopathy and inform national and international guidelines in high income countries. It will also provide an economic assessment of whole-body hypothermia therapy for mild encephalopathy in the NHS on cost-effectiveness grounds.

TRIAL REGISTRATION NUMBER

NCT05889507 June 5, 2023.

Whole-Body Hypothermia vs Targeted Normothermia for Neonates With Mild Encephalopathy: A Multicenter Pilot Randomized Clinical Trial

Importance

Although whole-body hypothermia is widely used after mild neonatal hypoxic-ischemic encephalopathy (HIE), safety and efficacy have not been evaluated in randomized clinical trials (RCTs), to our knowledge.

Objective

To examine the effect of 48 and 72 hours of whole-body hypothermia after mild HIE on cerebral magnetic resonance (MR) biomarkers.

Design, Setting, and Participants

This open-label, 3-arm RCT was conducted between October 31, 2019, and April 28, 2023, with masked outcome analysis. Participants were neonates at 6 tertiary neonatal intensive care units in the UK and Italy born at or after 36 weeks' gestation with severe birth acidosis, requiring continued resuscitation, or with an Apgar score less than 6 at 10 minutes after birth and with evidence of mild HIE on modified Sarnat staging. Statistical analysis was per intention to treat.

Interventions

Random allocation to 1 of 3 groups (1:1:1) based on age: neonates younger than 6 hours were randomized to normothermia or 72-hour hypothermia (33.5 °C), and those 6 hours or older and already receiving whole-body hypothermia were randomized to rewarming after 48 or 72 hours of hypothermia.

Main Outcomes and Measures

Thalamic N-acetyl aspartate (NAA) concentration (mmol/kg wet weight), assessed by cerebral MR imaging and thalamic spectroscopy between 4 and 7 days after birth using harmonized sequences.

Results

Of 225 eligible neonates, 101 were recruited (54 males [53.5%]); 48 (47.5%) were younger than 6 hours and 53 (52.5%) were 6 hours or older at randomization. Mean (SD) gestational age and birth weight were 39.5 (1.1) weeks and 3378 (380) grams in the normothermia group (n = 34), 38.7 (0.5) weeks and 3017 (338) grams in the 48-hour hypothermia group (n = 31), and 39.0 (1.1) weeks and 3293 (252) grams in the 72-hour hypothermia group (n = 36). More neonates in the 48-hour (14 of 31 [45.2%]) and 72-hour (13 of 36 [36.1%]) groups required intubation at birth than in the normothermic group (3 of 34 [8.8%]). Ninety-nine neonates (98.0%) had MR imaging data and 87 (86.1%), NAA data. Injury scores on conventional MR biomarkers were similar across groups. The mean (SD) NAA level in the normothermia group was 10.98 (0.92) mmol/kg wet weight vs 8.36 (1.23) mmol/kg wet weight (mean difference [MD], -2.62 [95% CI, -3.34 to -1.89] mmol/kg wet weight) in the 48-hour and 9.02 (1.79) mmol/kg wet weight (MD, -1.96 [95% CI, -2.66 to -1.26] mmol/kg wet weight) in the 72-hour hypothermia group. Seizures occurred beyond 6 hours after birth in 4 neonates: 1 (2.9%) in the normothermia group, 1 (3.2%) in the 48-hour hypothermia group, and 2 (5.6%) in the 72-hour hypothermia group.

Conclusions and Relevance

In this pilot RCT, whole-body hypothermia did not improve cerebral MR biomarkers after mild HIE, although neonates in the hypothermia groups were sicker at baseline. Safety and efficacy of whole-body hypothermia should be evaluated in RCTs.

Trial Registration

ClinicalTrials.gov Identifier: NCT03409770.

Regional variability in therapeutic hypothermia eligibility criteria for neonatal hypoxic-ischemic encephalopathy

Early induced therapeutic hypothermia represents the cornerstone treatment in neonates with probable hypoxic-ischemic encephalopathy. The selection of patients for treatment usually involves meeting criteria indicating evidence of perinatal hypoxia-ischemia and the presence of moderate or severe encephalopathy. In this review, we highlight the variability that exists between some of the different regional and national eligibility guidelines. Determining the potential presence of perinatal hypoxia-ischemia may require either one, two or three signs amongst history of acute perinatal event, prolonged resuscitation at delivery, abnormal blood gases and low Apgar score, with a range of cutoff values. Clinical neurological exams often define the severity of encephalopathy differently, with varying number of domains required for determining eligibility and blurred interpretation of findings assigned to different severity grades in different systems. The role of early electrophysiological assessment is weighted differently. A clinical implication is that infants may receive different care depending on the location in which they are born. This could also impact epidemiological data, as inference of rates of moderate-severe encephalopathy based on therapeutic hypothermia rates are misleading and influenced by different eligibility methods used. We would advocate that a universally endorsed single severity staging of encephalopathy is vital for standardizing management and neonatal outcome. IMPACT: Variability exists between regional and national therapeutic hypothermia eligibility guidelines for neonates with probable hypoxic-ischemic encephalopathy. Differences are common in both criteria indicating perinatal hypoxia-ischemia and criteria defining moderate or severe encephalopathy. The role of early electrophysiological assessment is also weighted unequally. This reflects in different individual care and impacts research data. A universally endorsed single severity staging of encephalopathy would be crucial for standardizing management.

Growth and developmental outcomes of infants with hypoxic ischemic encephalopathy

Despite advances in obstetric care, hypoxic ischemic encephalopathy (HIE) remains a significant disease burden. We determined the national trends of HIE prevalence, therapeutic hypothermia (TH) use, mortality, and outcomes from 2012 to 2019. This study included term infants diagnosed with HIE between 2012 and 2019 from the National Health Insurance Service database. The prevalence of HIE was 2.4 per 1000 births without significant change during the period. TH was performed in approximately 6.7% of infants with HIE, and the annual variation ranged from 2.4 to 12.5%. The mortality among all term infants with HIE was 4.6%. The mortality rate among infants with HIE and TH significantly declined from 40 to 16.9% during the eight years. Infants with TH had higher mortality, increased use of inhaled nitric oxide, and more invasive ventilator use, indicating greater disease severity in the TH group. Infants with TH also showed significantly poorer outcomes, including delayed development, cerebral palsy, sensorineural hearing loss, and seizure, compared to infants without TH (p < 0.0001). With the increasing application of TH, mortality and developmental outcomes among infants with HIE have been improving in the past eight years in Korea. Further efforts to improve outcomes should be needed.

Reduced Hippocampal Volumes in Children with History of Hypoxic Ischemic Encephalopathy after Therapeutic Hypothermia

Hypoxic ischemic encephalopathy (HIE) remains a significant cause of disability despite treatment with therapeutic hypothermia (TH). Many survive with more subtle deficits that affect daily functioning and school performance. We have previously shown an early indication of hippocampal changes in infants with HIE despite TH. The aim of this study was to evaluate the hippocampal volume via MRI and memory function at 5 years of age. A cohort of children followed from birth returned for a 5-year follow-up (n = 10 HIE treated with TH, n = 8 healthy controls). The children underwent brain MRI and neurodevelopmental testing to assess their brain volume, general development, and memory function. Children with HIE had smaller hippocampal volumes than the controls despite no differences in the total brain volume (p = 0.02). Children with HIE generally scored within the average range on developmental testing. Though there was no difference in the memory scores between these groups, there was a positive within-group correlation between the hippocampal volume and memory scores in children with HIE (sentence recall r = 0.66, p = 0.038). There was no relationship between newborn memory function and 5-year hippocampal size. Children with HIE treated with TH experienced significant and lasting changes to the hippocampus despite improvements in survival and severe disability. Future studies should target diminishing injury to the hippocampus to improve overall outcomes.

Brain Injury in Infants Evaluated for, But Not Treated with, Therapeutic Hypothermia

Defining neonatal encephalopathy clinically to qualify for therapeutic hypothermia is challenging. This study examines magnetic resonance imaging outcomes of 39 infants who were evaluated and not cooled using criteria inclusive of mild encephalopathy. Infants evaluated for therapeutic hypothermia are at risk for brain injury and may benefit from neuroimaging and follow-up.

The influence of late prematurity on the encephalopathy exam of infants with neonatal encephalopathy

BACKGROUND

Late preterm (LPT) infants are increasingly treated for hypoxic-ischemic encephalopathy (HIE). However, neurodevelopmental differences of LPT infants may independently influence the neurologic exam and confound care.

METHODS

Perinatal and outcome characteristics were extracted along with the worst autonomic and state/neuromuscular/reflex Sarnat components in a cross-section of infants with moderate/severe HIE. Infants were classified as late preterm (LPT, 34-36 weeks) or term (>36 weeks).

RESULTS

250 infants were identified, 55 were late preterm. LPT infants had lower mean gestational age and birthweight and greater length of stay (LOS). LPT infants had higher median scores for the Moro and respiratory autonomic components, but no difference in total score.

CONCLUSIONS

LPT infants had increased LOS, worse Moro reflex, and respiratory status, but no clinically or statistically significant differences in total Sarnat scores. Although it is important to note the impact of immaturity on the exam, it is unlikely to independently alter management.

Brain injury following mild hypoxic-ischemic encephalopathy in neonates-Ten-year experience in a tertiary perinatal center

OBJECTIVE

We aimed to evaluate abnormal magnetic resonance imaging (MRI) findings in neonates with mild hypoxic-ischemic encephalopathy (HIE).

STUDY DESIGN

This was a single-center, retrospective study of mild HIE conducted from 2011 to 2020. Almost all neonates with mild HIE received management targeted to a temperature of 36 ± 0.5°C for 72 h and underwent MRI (135 of 145). We evaluated medical records and assessed amplitude-integrated electroencephalography (aEEG).

RESULT

All participants survived until discharge. Abnormal MRI findings were present in 23/135 (17%) neonates. The normal versus abnormal MRI-finding groups had similar characteristics, except discontinuous aEEG patterns (p = 0.002) and inotropic drugs (p = 0.035). Regression analyses showed discontinuous aEEG patterns (odds ratio = 19.3, 95% confidence interval=1.88-197, p = 0.013) being associated with higher odds of abnormal MRI findings.

CONCLUSION

Our study suggests that a discontinuous aEEG pattern is associated with abnormal MRI findings and can be used to discuss the definition of mild HIE.

Mild hypoxic-ischemic encephalopathy (HIE): timing and pattern of MRI brain injury

BACKGROUND

Mild hypoxic-ischemic encephalopathy (HIE) is increasingly recognized as a risk factor for neonatal brain injury. We examined the timing and pattern of brain injury in mild HIE.

METHODS

This retrospective cohort study includes infants with mild HIE treated at 9 hospitals. Neonatal brain MRIs were scored by 2 reviewers using a validated classification system, with discrepancies resolved by consensus. Severity and timing of MRI brain injury (i.e., acute, subacute, chronic) was scored on the subset of MRIs that were performed at or before 8 days of age.

RESULTS

Of 142 infants with mild HIE, 87 (61%) had injury on MRI at median age 5 (IQR 4-6) days. Watershed (23%), deep gray (20%) and punctate white matter (18%) injury were most common. Among the 125 (88%) infants who received a brain MRI at ≤8 days, mild (44%) injury was more common than moderate (11%) or severe (4%) injury. Subacute (37%) lesions were more commonly observed than acute (32%) or chronic lesions (1%).

CONCLUSION

Subacute brain injury is common in newborn infants with mild HIE. Novel neuroprotective treatments for mild HIE will ideally target both subacute and acute injury mechanisms.

IMPACT

Almost two-thirds of infants with mild HIE have evidence of brain injury on MRI obtained in the early neonatal period. Subacute brain injury was seen in 37% of infants with mild HIE. Neuroprotective treatments for mild HIE will ideally target both acute and subacute injury mechanisms.

Association Between Early EEG Background and Outcomes in Infants With Mild HIE Undergoing Therapeutic Hypothermia

BACKGROUND

Hypoxic-ischemic encephalopathy (HIE) occurs in 1-4:1000 live births. Although neonates with moderate-severe HIE have been studied over several decades, newborns with mild HIE remain understudied, including seizure occurrence, electroencephalography (EEG) characteristics, and outcome.

METHODS

We conducted a retrospective cohort study of neonates ≥35 weeks of gestation with mild HIE who underwent therapeutic hypothermia to correlate the early EEG background pattern with clinical course and outcomes.

RESULTS

Of the included 29 neonates, 10 infants had a moderately to severely abnormal EEG background and 19 had either a normal or a mildly abnormal background. Those with moderately to severely abnormal background also had more multiorgan dysfunction (90% vs 42%, P = 0.02) and a higher incidence of subdural and intraventricular hemorrhages (80% vs 26%, P = 0.02). The overall seizure incidence was 20.7% and was significantly higher in newborns with more severely abnormal background compared to neonates with less abnormal background (50% vs 5%; P = 0.01; relative risk, 9.5; 95% confidence interval, 1.28-70.6). Seizure onset was between 11 and 63 hours of life. Regardless of the EEG background pattern, seizures were brief with an overall low seizure burden. None of the newborns with normal or mildly abnormal background had a new onset of seizures after 24 hours of recording or developed epilepsy during infancy.

CONCLUSIONS

In neonates with mild HIE, early moderately to severely abnormal EEG background is common and strongly associated with an increased risk for seizures.

Differences in standardized neonatal encephalopathy exam criteria may impact therapeutic hypothermia eligibility

BACKGROUND

Therapeutic hypothermia (TH) is routinely provided to those with moderate or severe neonatal encephalopathy (NE). Subtle differences exist in the standardized exams used to define NE severity. We aimed to assess if an infant's TH eligibility status differed if they were evaluated using either the NICHD/Neonatal Research Network's (NICHD-NRN) or TOBY/British Association of Perinatal Medicine's (TOBY-BAPM) neurological exam.

METHODS

Encephalopathic infants ≥36 weeks with evidence of perinatal asphyxia and complete documentation of the neurological exam &lt;6 h of age were included. TH eligibility using the NICHD-NRN and TOBY-BAPM criteria was determined based upon the documented exams.

RESULTS

Ninety-one encephalopathic infants were included. Despite good agreement between the two exams (κ = 0.715, p &lt; 0.001), TH eligibility differed between them (p &lt; 0.001). A total of 47 infants were deemed eligible by at least one method-46 using NICHD-NRN and 35 using TOBY-BAPM. Of the 12 infants eligible per NICHD-NRN, but ineligible per TOBY-BAPM, two developed electrographic seizures and seven demonstrated hypoxic-ischemic cerebral injury.

CONCLUSIONS

Both the NICHD-NRN and TOBY-BAPM exams are evidence-based. Despite this, there is a significant difference in the number of infants eligible for TH depending on which exam is used. The NICHD-NRN exam identifies a greater proportion as eligible.

IMPACT

There are subtle differences in the NICHD-NRN and TOBY-BAPM's encephalopathy exams used to determine eligibility for TH. This results in a significant difference in the proportion of infants determined to be eligible for TH depending on which encephalopathy exam is used. The NICHD-NRN encephalopathy exam identifies more infants as being eligible for TH than the TOBY-BAPM encephalopathy exam. This may result in different rates of cooling depending on which evidence-based neurological exam for evaluation of encephalopathy a center uses.

Impact of Hypoxia-Ischemia on Neurogenesis and Structural and Functional Outcomes in a Mild-Moderate Neonatal Hypoxia-Ischemia Brain Injury Model

Hypoxic-ischemic encephalopathy (HIE) is a common type of brain injury caused by a lack of oxygen and blood flow to the brain during the perinatal period. The incidence of HIE is approximately 2−3 cases per 1000 live births in high-income settings; while in low- and middle-income countries, the incidence is 3−10-fold higher. Therapeutic hypothermia (TH) is the current standard treatment for neonates affected by moderate−severe HIE. However, more than 50% of all infants with suspected HIE have mild encephalopathy, and these infants are not treated with TH because of their lower risk of adverse outcomes. Despite this, several analyses of pooled data provide increasing evidence that infants who initially have mild encephalopathy may present signs of more significant brain injury later in life. The purpose of this study was to expand our knowledge about the effect of mild−moderate hypoxia-ischemia (HI) at the cellular, structural, and functional levels. An established rat model of mild−moderate HI was used, where postnatal day (P) 7 rats were exposed to unilateral permanent occlusion of the left carotid artery and 90 min of 8% hypoxia, followed by TH or normothermia (NT) treatment. The extent of injury was assessed using histology (P14 and P42) and MRI (P11 and P32), as well as with short-term and long-term behavioral tests. Neurogenesis was assessed by BrdU staining. We showed that mild−moderate HI leads to a progressive loss of brain tissue, pathological changes in MRI scans, as well as an impairment of long-term motor function. At P14, the median area loss assessed by histology for HI animals was 20% (p < 0.05), corresponding to mild−moderate brain injury, increasing to 55% (p < 0.05) at P42. The data assessed by MRI corroborated our results. HI led to a decrease in neurogenesis, especially in the hippocampus and the lateral ventricle at early time points, with a delayed partial recovery. TH was not neuroprotective at early time points following mild−moderate HI, but prevented the increase in brain damage over time. Additionally, rats treated with TH showed better long-term motor function. Altogether, our results bring more light to the understanding of pathophysiology following mild-moderate HI. We showed that, in the context of mild-moderate HI, TH failed to be significantly neuroprotective. However, animals treated with TH showed a significant improvement in motor, but not cognitive long-term function. These results are in line with what is observed in some cases where neonates with mild HIE are at risk of neurodevelopmental deficits in infancy or childhood. Whether TH should be used as a preventive treatment to reduce adverse outcomes in mild-HIE remains of active interest, and more research has to be carried out in order to address this question.

Outcome of non-cooled asphyxiated infants with under-recognised or delayed-onset encephalopathy

OBJECTIVE

To describe the clinical characteristics, MRI findings and neurodevelopmental outcome of infants with documented perinatal asphyxia and seizure onset within 24 hours after birth who were not selected for therapeutic hypothermia (TH).

DESIGN

Retrospective cohort study.

SETTING AND PATIENTS

(Near-)term infants with documented perinatal asphyxia referred to two Dutch level III neonatal units with neonatal encephalopathy (NE) and seizures <24 hours after birth not treated with TH. Infants with a diagnosis other than NE following perinatal asphyxia causing the seizures were excluded.

MAIN OUTCOME MEASURES

Clinical characteristics, findings on cranial MRI performed within 8 days after birth and neurodevelopmental outcome assessed using the Griffiths Mental Development Scales at 18 months or Bayley Scales of Infant and Toddler Development-Third Edition at 2 years of age.

RESULTS

39 infants were included. All had abnormalities on MRI. Predominant white matter/watershed injury was the most common pattern of injury, 23 (59%). 7 (18%) infants had predominant basal ganglia/thalamus injury, 3 (8%) near total brain injury, 5 (13%) arterial ischaemic stroke, 1 (3%) an intraventricular haemorrhage. Adverse outcome was seen in 51%: 6 died, 11 developed cerebral palsy (spastic n=8, dyskinetic n=3), 2 had neurodevelopmental delay, 1 had severe hearing impairment.

CONCLUSIONS

All infants with documented perinatal asphyxia and seizure onset within 24 hours after birth who did not receive TH had abnormalities on MRI. 51% had an adverse outcome. Better methods for recognition of infants who might benefit from TH and careful neurodevelopmental follow-up are urgently needed.

Neonates with mild hypoxic-ischaemic encephalopathy receiving supportive care versus therapeutic hypothermia in California

OBJECTIVE

The use of therapeutic hypothermia (TH) for mild hypoxic-ischaemic encephalopathy (HIE) remains controversial and inconsistent. We analysed trends in TH and maternal and infant characteristics associated with short-term outcomes of infants with mild HIE.

DESIGN

Retrospective cohort analysis of the California Perinatal Quality Care Collaborative database 2010-2018. E-value analysis was conducted to determine the potential impact of unmeasured confounding.

SETTING

California neonatal intensive care units.

PATIENTS

1364 neonates with mild HIE.

INTERVENTIONS

Supportive care versus TH.

MAIN OUTCOME MEASURES

Factors associated with TH and mortality.

RESULTS

The proportion of infants receiving TH increased from 46% in 2010 to 79% in 2018. TH was more likely in the setting of singleton birth (OR 2.69, 95% CI 1.21 to 5.39), no major birth defects (OR 2.18, 95% CI 1.42 to 3.30), operative vaginal delivery (OR 3.04, 95% CI 1.80 to 5.10) and 5-minute Apgar score ≤5 (OR 3.17, 95% CI 2.43 to 4.13). Mortality was associated with small for gestational age (OR 5.79, 95% CI 1.90 to 18.48), <38 weeks' gestation (OR 7.31 95% CI 2.39 to 24.93), major birth defects (OR 11.62, 95% CI 3.97 to 38.00), inhaled nitric oxide (OR 12.73, 95% CI 4.00 to 44.53) and nosocomial infection (OR 7.98, 95% CI 1.15 to 47.03). E-value analyses suggest that unmeasured confounding may have contributed to some of the observed effects.

CONCLUSIONS

Variation in management of mild HIE persists, but therapeutic drift has become more prevalent over time. Further studies are needed to assess long-term outcomes alongside resource utilisation to inform evidence-based practice.

Predictive modelling of hypoxic ischaemic encephalopathy risk following perinatal asphyxia

Hypoxic Ischemic Encephalopathy (HIE) remains a major cause of neurological disability. Early intervention with therapeutic hypothermia improves outcome, but prediction of HIE is difficult and no single clinical marker is reliable. Machine learning algorithms may allow identification of patterns in clinical data to improve prognostic power. Here we examine the use of a Random Forest machine learning algorithm and five-fold cross-validation to predict the occurrence of HIE in a prospective cohort of infants with perinatal asphyxia. Infants with perinatal asphyxia were recruited at birth and neonatal course was followed for the development of HIE. Clinical variables were recorded for each infant including maternal demographics, delivery details and infant's condition at birth. We found that the strongest predictors of HIE were the infant's condition at birth (as expressed by Apgar score), need for resuscitation, and the first postnatal measures of pH, lactate, and base deficit. Random Forest models combining features including Apgar score, most intensive resuscitation, maternal age and infant birth weight both with and without biochemical markers of pH, lactate, and base deficit resulted in a sensitivity of 56-100% and a specificity of 78-99%. This study presents a dynamic method of rapid classification that has the potential to be easily adapted and implemented in a clinical setting, with and without the availability of blood gas analysis. Our results demonstrate that applying machine learning algorithms to readily available clinical data may support clinicians in the early and accurate identification of infants who will develop HIE. We anticipate our models to be a starting point for the development of a more sophisticated clinical decision support system to help identify which infants will benefit from early therapeutic hypothermia.