The use of machine learning in paediatric nutrition.

PURPOSE OF REVIEW: In recent years, there has been a burgeoning interest in using machine learning methods. This has been accompanied by an expansion in the availability and ease of use of machine learning tools and an increase in the number of large, complex datasets which are suited to machine learning approaches. This review summarizes recent work in the field and sets expectations for its impact in the future. RECENT FINDINGS: Much work has focused on establishing good practices and ethical frameworks to guide the use of machine learning in research. Machine learning has an established role in identifying features in 'omics' research and is emerging as a tool to generate predictive models to identify people at risk of disease and patients at risk of complications. They have been used to identify risks for malnutrition and obesity. Machine learning techniques have also been used to develop smartphone apps to track behaviour and provide healthcare advice. SUMMARY: Machine learning techniques are reaching maturity and their impact on observational data analysis and behaviour change will come to fruition in the next 5 years. A set of standards and best practices are emerging and should be implemented by researchers and publishers.

The Development of a Communication Tool to Aid Parent-Centered Communication between Parents and Healthcare Professionals: A Quality Improvement Project.

Good communication is central to good healthcare. As a result of poor communication between parents and healthcare professionals (HCPs) in clinical settings, this study aimed to address this problem by developing a communication tool to empower parents and act as a prompt for HCPs to talk about the child's care and gather information at the point of admission to hospital about what is important to families, therefore supporting patient-centered communication. A design thinking process was used to develop a physical copy of Chloe's card and evaluate its use. Design thinking is a problem-solving approach, which uses an empathetic lens to integrate viewpoints of different stakeholders throughout the process of creating solutions. Design thinking involves five processes: (1) empathise-including a literature review and data synthesis, (2) define-by completing semi-structured interviews with parents about their experience of communication and HCPs perceptions of parent's experience of communication, (3) ideate-iterate the design of Chloe's card with parents and HCPs, (4) prototype-develop the design of Chloe's card, and (5) test-pilot test in clinical practice. Results from this initial study suggest that a small hand-held card, with emoticons and a place to write concerns, was acceptable to parents and feasible to use in clinical practice. Parents do not always feel heard by HCPs and a tool such as Chloe's card may help facilitate sharing of information about matters important to them and their child. However, some HCPs felt the need for a communication tool undermined their clinical skills. Feedback from HCP participants suggests that the idea of Chloe's card was acceptable and perceived as potentially being useful in clinical practice. Further work is required, as part of a larger study, to further refine this communication tool, identify those parents who would benefit most from Chloe's card, as well as to further refine the HCP process prior to implementing it into clinical settings. It was noted future iterations would benefit from a digital version linked with a child's electronic record, as well as multi-language versions and information for parents.

Longitudinal pilot study of oxygen saturation indices in healthy preterm infants.

BACKGROUND: This study aimed to determine patterns of nocturnal pulse oximetry indices in moderate to late preterm infants, and investigate the relationship between oxygen desaturations, the apnoea hypopnoea index, and both corrected gestational and postnatal age. METHODS: 21 healthy infants born at 32 + 0 - 36 + 6 weeks gestation underwent serial nocturnal pulse oximetry studies and respiratory polygraphy studies until 40 weeks corrected gestational age (CGA). The main outcome measures were number of >3% oxygen desaturations/hour (ODI3), mean oxygen saturations, and number of apnoeas and hypopnoeas/hour. RESULTS: Median ODI3 increased between weeks 1 and 3 from 49.9 to 85.4/hour (p = 0.017). Mean oxygen saturations reached a corresponding nadir of 96.0% in week 3, then increased to 96.8% in week 6 (p = 0.019). Mixed effects modelling demonstrated that ODI3 and mean saturations were influenced by postnatal age but not CGA (p < 0.05). Desaturations frequently occurred without an apnoea or hypopnoea. CONCLUSION: ODI3 rises then falls during the first 8 weeks of life in moderate to late preterm infants, independently of CGA. These interesting preliminary results highlight the importance of further serial data collection to generate age-specific normal ranges, and develop a better understanding of respiratory control in preterm infants. IMPACT: The frequency of >3% oxygen desaturations (ODI3) in healthy moderate to late preterm infants rises then falls after birth, peaking in postnatal week 3. There is a corresponding nadir in mean saturations. There were significant non-linear relationships between ODI3/mean saturations and postnatal age, but not corrected gestational age. The majority of brief oxygen desaturations occurred without an apnoea or hypopnoea. Normal ranges for oxygen saturation indices are not known in this population. These results demonstrate the need for further serial data collection to generate age-specific normal ranges and inform oxygen prescribing guidelines.

Enteral Nutrition in Preterm Infants (2022): A Position Paper From the ESPGHAN Committee on Nutrition and Invited Experts.

OBJECTIVES: To review the current literature and develop consensus conclusions and recommendations on nutrient intakes and nutritional practice in preterm infants with birthweight <1800 g. METHODS: The European Society of Pediatric Gastroenterology, Hepatology and Nutrition (ESPGHAN) Committee of Nutrition (CoN) led a process that included CoN members and invited experts. Invited experts with specific expertise were chosen to represent as broad a geographical spread as possible. A list of topics was developed, and individual leads were assigned to topics along with other members, who reviewed the current literature. A single face-to-face meeting was held in February 2020. Provisional conclusions and recommendations were developed between 2020 and 2021, and these were voted on electronically by all members of the working group between 2021 and 2022. Where >90% consensus was not achieved, online discussion meetings were held, along with further voting until agreement was reached. RESULTS: In general, there is a lack of strong evidence for most nutrients and topics. The summary paper is supported by additional supplementary digital content that provide a fuller explanation of the literature and relevant physiology: introduction and overview; human milk reference data; intakes of water, protein, energy, lipid, carbohydrate, electrolytes, minerals, trace elements, water soluble vitamins, and fat soluble vitamins; feeding mode including mineral enteral feeding, feed advancement, management of gastric residuals, gastric tube placement and bolus or continuous feeding; growth; breastmilk buccal colostrum, donor human milk, and risks of cytomegalovirus infection; hydrolyzed protein and osmolality; supplemental bionutrients; and use of breastmilk fortifier. CONCLUSIONS: We provide updated ESPGHAN CoN consensus-based conclusions and recommendations on nutrient intakes and nutritional management for preterm infants.

A scoping review: urinary markers of metabolic maturation in infants with CHD and the relationship to growth.

BACKGROUND: Growth failure in infants born with CHD is a persistent problem, even in those provided with adequate nutrition. OBJECTIVE: To summarise the published data describing the change in urinary metabolites during metabolic maturation in infants with CHD and identify pathways amenable to therapeutic intervention. DESIGN: Scoping review. ELIGIBILITY CRITERIA: Studies using qualitative or quantitative methods to describe urinary metabolites pre- and post-cardiac surgery and the relationship with growth in infants with CHD. SOURCES OF EVIDENCE: NICE Healthcare Databases website was used as a tool for multiple searches. RESULTS: 347 records were identified, of which 37 were duplicates. Following the removal of duplicate records, 310 record abstracts and titles were screened for inclusion. The full texts of eight articles were reviewed for eligibility, of which only two related to infants with CHD. The studies included in the scoping review described urinary metabolites in 42 infants. A content analysis identified two overarching themes of metabolic variation predictive of neurodevelopmental abnormalities associated with anaerobic metabolism and metabolic signature associated with the impact on gut microbiota, inflammation, energy, and lipid digestion. CONCLUSION: The results of this scoping review suggest that there are considerable gaps in our knowledge relating to metabolic maturation of infants with CHD, especially with respect to growth. Surgery is a key early life feature for CHD infants and has an impact on the developing biochemical phenotype with implications for metabolic pathways involved in immunomodulation, energy, gut microbial, and lipid metabolism. These early life fingerprints may predict those individuals at risk for neurodevelopmental abnormalities.

Using machine learning to impact on long-term clinical care: principles, challenges, and practicalities.

The rise of machine learning in healthcare has significant implications for paediatrics. Long-term conditions with significant disease heterogeneity comprise large portions of the routine work performed by paediatricians. Improving outcomes through discovery of disease and treatment prediction models, alongside novel subgroup clustering of patients, are some of the areas in which machine learning holds significant promise. While artificial intelligence has percolated into routine use in our day to day lives through advertising algorithms, song or movie selections and sifting of spam emails, the ability of machine learning to utilise highly complex and dimensional data has not yet reached its full potential in healthcare. In this review article, we discuss some of the foundations of machine learning, including some of the basic algorithms. We emphasise the importance of correct utilisation of machine learning, including adequate data preparation and external validation. Using nutrition in preterm infants and paediatric inflammatory bowel disease as examples, we discuss the evidence and potential utility of machine learning in paediatrics. Finally, we review some of the future applications, alongside challenges and ethical considerations related to application of artificial intelligence. IMPACT: Machine learning is a widely used term; however, understanding of the process and application to healthcare is lacking. This article uses clinical examples to explore complex machine learning terms and algorithms. We discuss limitations and potential future applications within paediatrics and neonatal medicine.

A Scoping Review: Urinary Markers of Metabolic Maturation in Preterm Infants and Future Interventions to Improve Growth.

Background: Growth failure in infants born preterm is a significant issue, increasing the risk of poorer neurodevelopmental outcomes and metabolic syndrome later in life. During the first 1000 days of life biological systems mature rapidly involving developmental programming, cellular senescence, and metabolic maturation, regulating normal growth and development. However, little is known about metabolic maturation in infants born preterm and the relationship with growth. Objective: To examine the available evidence on urinary markers of metabolic maturation and their relationship with growth in infants born preterm. Eligibility criteria: Studies including in this scoping review using qualitative or quantitative methods to describe urinary markers of metabolic maturation and the relationship with growth in infants born preterm. Results: After a screening process 15 titles were included in this review, from 1998-2021 drawing from China (n = 1), Italy (n = 3), Germany (n = 3), Greece (n = 1), Japan (n = 2), Norway (n = 1), Portugal (n = 1), Spain (n = 2) and USA (n = 1). The included studies examined urinary metabolites in 1131 infants. A content analysis identified 4 overarching themes relating to; (i) metabolic maturation relative to gestational age, (ii) metabolic signature and changes in urinary metabolites over time, (iii) nutrition and (iv) growth. Conclusion: The results of this scoping review suggest there are considerable gaps in our knowledge relating to factors associated with metabolic instability, what constitutes normal maturation of preterm infants, and how the development of reference phenome age z scores for metabolites of interest could improve nutritional and growth outcomes.

The nutritional needs of moderate-late preterm infants.

This article discusses the nutritional needs of moderate and late preterm infants (born between 32+0weeks and 36+6weeks' gestation) and makes recommendations for best practice both while these infants are in hospital and when they are discharged into the community. These recommendations were derived following a roundtable meeting of a group comprising two neonatologists, three paediatric dietitians, a health visitor/paediatric nurse and a midwife practitioner. The meeting and medical writing assistance was sponsored by Nutricia. None of the participants accepted honoraria for their contributions to the discussion.

The FEED1 trial: protocol for a randomised controlled trial of full milk feeds versus intravenous fluids with gradual feeding for preterm infants (30-33 weeks gestational age).

BACKGROUND: In the UK, approximately 8% of live births are preterm (before 37 weeks gestation), more than 90% of whom are born between 30 and 36 weeks, forming the largest proportion of a neonatal units' workload. Neonatologists are cautious in initiating full milk feeds for preterm infants due to fears of necrotising enterocolitis (NEC). There is now evidence to dispute this fear. Small studies have shown that feeding preterm infants full milk feeds enterally from birth could result in a shorter length of hospital stay, which is important to parents, clinicians and NHS services without increasing the risk of NEC. This trial aims to investigate whether full milk feeds initiated in the first 24 h after birth reduces the length of hospital stay in comparison to introduction of gradual milk feeding with IV fluids or parenteral nutrition. METHODS: FEED1 is a multi-centre, open, parallel group, randomised, controlled superiority trial of full milk feeds initiated on the day of birth versus gradual milk feeds for infants born at 30+0 to 32+6 (inclusive) weeks gestation. Recruitment will take place in around 40 UK neonatal units. Mothers will be randomised 1:1 to full milk feeds, starting at 60 ml/kg day, or gradual feeds, as per usual local practice. Mother's expressed breast milk will always be the first choice of milk, though will likely be supplemented with formula or donor breast milk in the first few days. Feeding data will be collected until full milk feeds are achieved (≥ 140 ml/kg/day for 3 consecutive days). The primary outcome is length of infant hospital stay. Additional data will be collected 6 weeks post-discharge. Follow-up at 2 years (corrected gestational age) is planned. The sample size is 2088 infants to detect a between group difference in length of stay of 2 days. Accounting for multiple births, this requires 1700 women to be recruited. Primary analysis will compare the length of hospital stay between groups, adjusting for minimisation variables and accounting for multiple births. DISCUSSION: This trial will provide high-quality evidence on feeding practices for preterm infants. Full milk feeds from day of birth could result in infants being discharged sooner. TRIAL REGISTRATION: ISRCTN ISRCTN89654042 . Prospectively registered on 23 September 2019: ISRCTN is a primary registry of the WHO ICTRP network, and all items from the WHO Trial Registration dataset are included.

Research priorities in pediatric parenteral nutrition: a consensus and perspective from ESPGHAN/ESPEN/ESPR/CSPEN.

Parenteral nutrition is used to treat children that cannot be fully fed by the enteral route. While the revised ESPGHAN/ESPEN/ESPR/CSPEN pediatric parenteral nutrition guidelines provide clear guidance on the use of parenteral nutrition in neonates, infants, and children based on current available evidence, they have helped to crystallize areas where research is lacking or more studies are needed in order to refine recommendations. This paper collates and discusses the research gaps identified by the authors of each section of the guidelines and considers each nutrient or group of nutrients in turn, together with aspects around delivery and organization. The 99 research priorities identified were then ranked in order of importance by clinicians and researchers working in the field using a survey methodology. The highest ranked priority was the need to understand the relationship between total energy intake, rapid catch-up growth, later metabolic function, and neurocognitive outcomes. Research into the optimal intakes of macronutrients needed in order to achieve optimal outcomes also featured prominently. Identifying research priorities in PN should enable research to be focussed on addressing key issues. Multicentre trials, better definition of exposure and outcome variables, and long-term metabolic and developmental follow-up will be key to achieving this. IMPACT: The recent ESPGHAN/ESPEN/ESPR/CSPEN guidelines for pediatric parenteral nutrition provided updated guidance for providing parenteral nutrition to infants and children, including recommendations for practice. However, in several areas there was a lack of evidence to guide practice, or research questions that remained unanswered. This paper summarizes the key priorities for research in pediatric parenteral nutrition, and ranks them in order of importance according to expert opinion.

Toy story: A cross-sectional survey of toy populations in tertiary neonatal units.

Thousands of babies are given toys for their zeroth birthday … But what happens if that baby is admitted to neonatal intensive care? In a global first, we describe the population of toys found in incubators on neonatal intensive care unit.

A systematic review of the definitions and prevalence of feeding intolerance in preterm infants.

BACKGROUND & AIMS: Feeding intolerance (FI) is a common phenomenon experienced in preterm infants in neonatal intensive care units, as well as being a focus of many research studies into feeding methods, particularly in relation to comorbidities. There is no widely accepted definition of FI. This systematic review aimed to explore the range of definitions used for FI and provide an estimate of the prevalence amongst preterm infants. METHODS: Searches were completed on MEDLINE (includes the Cochrane library), Embase, PsycInfo, CINAHL, NHS Evidence and Web of Science. Inclusion criteria; preterm infants in neonatal units, a clear definition of FI, >10 patients and be available in English language. Case reports were excluded. RESULTS: One hundred studies were included. Definitions of FI were inconsistent. Studies were grouped according to definition used into: Group A - measuring gastric residual volume (GRV) only; group B - GRV and abdominal distension (AD); group C - GRV, AD and gastrointestinal symptoms (GI) which included any of vomiting, bilious vomiting and blood in stool; group D- GRV and GI; group E - AD and GI; group F - GI only and group G - any other elements used. Meta-analysis demonstrated that prevalence of FI between groups varied from 15 to 30% with an overall prevalence of 27% (95% confidence interval 23-31%). Group A had the highest prevalence. Review of time to full enteral feed was performed (37 studies) which demonstrated a range of 11.3-18.3 days depending on which FI definition used. DISCUSSION: Definitions of FI in research are inconsistent, a similar finding to that seen in studies in both paediatric and adult critical care populations. The difficulty of defining FI in the preterm population is the concern regarding necrotising enterocolitis, with some studies using an overlap in their definitions, despite differing pathophysiology and management. Due to the heterogeneity of data obtained in this review regarding definitions used, further robust research is required in order to conclude which elements which should be used to define FI in this population. PROSPERO NUMBER: CRD42019155596. Registered November 2019.

Bioelectrical spectroscopy impedance phase angle is not associated with nutritional status in a stable cohort of paediatric inflammatory bowel disease patients.

BACKGROUND & AIMS: Nutritional assessment in paediatric inflammatory bowel disease (IBD) is key to supporting growth whilst minimising adiposity. Bedside assessment using bioelectrical impedance spectroscopy (BIS) has previous identified patients with declining cellular and nutritional health. We aimed to assess BIS measures in stable paediatric IBD patient. METHODS: Stable IBD patients were recruited at routine hospital visits. All patients underwent BIS, anthropometry and disease activity assessment. Multivariable regression and receiver operator curve (ROC) analyses were undertaken to assess the utility of BIS phase angle 50 KHz (PA-50) and 200/5 KHz impedance ratio (IR) in nutritional assessment. RESULTS: There were 140 study visits from 97 patients, mean age 14.49 years, 62.9% Crohn's disease. Mean BMI Z-score (BMIZ) was 0.31 (range -2.97 to 3.99), 33% of patients were overweight (BMIZ>1) and 13.8% of patients were underweight (BMIZ < -1). Crohn's disease patients had a lower mean BMIZ score 0.14, compared to ulcerative colitis, 0.68, p = 0.007. There was no relationship between PA-50 and BMIZ or disease activity. IR was not related to disease activity but was negatively related to BMIZ in a multivariable regression, accounting for age, sex and disease subtype (beta -0.331, p = 0.001). ROC analyses did not identify a clinically useful cut off for either PA-50 or IR to identify patients with active disease, biologic use or BMIZ>1 or < -1. CONCLUSION: BIS appears to have limited added value in nutritional assessment of stable paediatric IBD patients. Nearly 1/3 patients were overweight and personalised approach to supplementation is vital to avoid overnutrition.

Routine abdominal magnetic resonance imaging can determine psoas muscle area in paediatric Crohn's disease and correlates with bioelectrical impedance spectroscopy measures of lean mass.

BACKGROUND: Paediatric Crohn's disease (CD) has been associated with undernutrition. Accurate and accessible measures of body composition would provide data to personalise nutritional therapy. We assessed feasibility of MRI-derived measures of psoas cross-sectional area (PCSA) in paediatric CD and correlated with anthropometric and bioelectrical impedance spectroscopy (BIS) measures. METHODS: MRI small bowel/pelvis images of patients with CD, aged <18 years, were retrieved. Patients with concurrent anthropometric and BIS measurements were eligible for inclusion. The PCSA at L3 was calculated by two assessors and combined. To assess reproducibility of measures we calculated the coefficient of variation (CoV). Age, height-Z-scores, weight-Z-scores and BIS measures were correlated with PCSA. Using normal paediatric data from CT-scans we derived psoas area Z-scores for our cohort. RESULTS: 10 patients were included. Mean age at MRI scan was 14.6 years (11.7-16.3). PCSA was calculated for all MRI scans. There was high reproducibility between measurers, mean CoV 0.099. There was a significant positive correlation between PCSA and BIA-derived fat free mass, Pearson correlation coefficient (PCC) 0.831, p = 0.003. Correlation coefficients for PCSA and Height-for-age Z-score, weight-for-age -Z-score and age were PCC 0.343- p = 0.33, PCC = 0.222- p = 0.54, and PCC 0.6034- p = 0.065, respectively. The mean PCSA Z-score was -1.81, with 70% of the patients having a Z-score < -2.0. CONCLUSIONS: These data demonstrate the feasibility of deriving measures of body composition from routine MRI imagine. There was significant positive correlation between PCSA and BIS-derived lean mass. Further studies are required to confirm applicability of normal ranges prior to routine clinical implementation.

Impact of Computer Calculation Program on Quality of Individualized Parenteral Nutrition and Selected Clinical Parameters of Extremely Low-Birth-Weight Infants.

BACKGROUND: The aim of the study was to assess the effects of computerized provider order entry (CPOE) for parenteral nutrition (PN) on selected clinical parameters of extremely low-birth-weight (ELBW) neonates in a tertiary neonatal intensive care unit. METHODS: This study was a retrospective data analysis of preterm infants born over a 1-year period before and after introduction of CPOE. PN composition during the first 2 weeks of life, change in weight, head circumference and body length z-scores were assessed. Duration of PN and selected neonatal complications were compared. Logistic regression was used to adjust for confounding variables (sex, birth weight, and birth-gestational age). RESULTS: Ninety-four patients in 2 equal groups were analyzed. Birth weight (median 810 vs 825 g) and gestational age (27 vs 27 weeks) were comparable. After adjustment for confounding variables, on the first and seventh day of life, significantly more energy (P < .001), protein (P < .001), lipid (P < .03), and carbohydrate (P < .02) were administered in the CPOE group than in the manually calculated (MC) prescriptions group. The CPOE group had lower weight loss (P < .001), a significant improvement in linear growth, and faster regain of birth weight (P < .01) compared with the MC group. CONCLUSION: The CPOE positively influences the quality of PN in ELBW infants. It also significantly reduced initial weight loss, time to regain birth weight, and linear growth. It may also have beneficial effects on selected clinical outcomes, which requires further study.

Growth failure is rare in a contemporary cohort of paediatric inflammatory bowel disease patients.

AIM: We assessed growth in a paediatric inflammatory bowel disease (PIBD) cohort. METHODS: Paediatric inflammatory bowel disease patients were eligible if they were diagnosed at Southampton Children's Hospital from 2011 to 2018. Weight and height standard deviation scores (SDS) were retrieved. Mean SDS values, SDS change and anti-TNF status were analysed at diagnosis and during follow-up. RESULTS: Four hundred and ninety patients were included, 313 with Crohn's disease (CD). CD patients presented with mean height SDS -0.13, -0.1 at 1-year, -0.11 at 2-years and -0.03 at 5 years, reflecting preserved linear growth. There was no significant height-SDS change from diagnosis to 5-year follow-up, +0.12, 95%-CI: 0.48 to -0.24. Mean weight-SDS at diagnosis was -0.39, driven by CD patients (-0.65). Mean weight-SDS approached 0 after 1 year and remained at the 50th centile throughout follow-up. Growth in ulcerative colitis was maintained. In multivariable regression males had worse height growth from diagnosis to transition (P = .036). Anti-TNF treatment (P = .013) and surgical resection (P = .005) were also associated with poorer linear growth. Patients treated with anti-TNF therapy had lower height-SDS compared to those never treated with anti-TNF at 1 year (-0.2 vs -0.01, P = .22), 2-years (-0.27 vs -0.01, P = .07) and 5 years (-0.21 vs 0.25, P = .051). CONCLUSION: Height was generally maintained in Crohn's disease, and impaired linear growth was rare in this cohort.

Weaning oxygen in infants with bronchopulmonary dysplasia.

Bronchopulmonary dysplasia (BPD) is a form of chronic lung disease commonly seen in preterm infants as the sequelae following respiratory distress syndrome. The management of evolving BPD aims to minimise lung injury and prevent the impact of hypoxia and hyperoxia. Proposed morbidities include respiratory instability, pulmonary hypertension, suboptimal growth, altered cerebral oxygenation and long-term neurodevelopmental impairment. The ongoing management and associated morbidity present a significant burden for carers and healthcare systems. Long-term oxygen therapy may be required for variable duration, though there is a lack of consensus and wide variation in practise when weaning supplemental oxygen. Furthermore, a shift in care towards earlier discharge and community care underlines the importance of a structured discharge and weaning process that eliminates the potential risks associated with hypoxia and hyperoxia. This review article describes recent evidence outlining oxygen saturation reference ranges in young infants, on which structured guidance can be based.

Systematic review: long-term cognitive and behavioural outcomes of neonatal hypoxic-ischaemic encephalopathy in children without cerebral palsy.

AIM: To evaluate long-term cognitive and behavioural outcomes of children with neonatal hypoxic-ischaemic encephalopathy (HIE) in the absence of cerebral palsy (CP). METHODS: A systematic search was performed on five databases (EMBASE, Medline, PubMed, Web of Science, PsycInfo). Randomised controlled trials, non-randomised controlled trials, or observational studies, published between 1990 and 2017, that reported long-term (age greater than or equal to four years) cognitive and/or behavioural outcomes of neonatal HIE without CP were included. RESULTS: Seven articles met the inclusion criteria (n = 352 total participants, n = 53 treated with therapeutic hypothermia). Studies reporting cognitive outcome demonstrate impairment of general cognitive abilities in 25-63% of participants with HIE without CP. Specific cognitive difficulties were reported in two studies for attention, executive functioning, memory function and language. Results regarding behavioural outcome possibly indicate a higher risk of difficulties. CONCLUSION: A substantial proportion of children with neonatal HIE who survive without CP are at increased risk of general and/or specific cognitive impairments. Behavioural problems may be more common, but evidence is limited. Results highlight the importance of comprehensive long-term follow-up to identity difficulties and enable intervention to optimise educational achievement and behavioural adjustment.