Non-invasive ventilation (NIV) is a key form of respiratory support in neonatal intensive care units (NICU). Non-invasive ventilation failure, however, can lead to adverse outcomes in preterm infants. This narrative review explores the potential of using artificial intelligence (AI) to improve the prediction of NIV failure, potentially reducing the mortality and morbidity within this population.

Optimizing neonatal nutrition and diagnosing serious gastrointestinal diseases remains a challenge, as traditional guideline-based approaches often fail to address the individualized needs of preterm and term infants. Advances in artificial intelligence and machine learning provide opportunities for precision diagnostics and therapeutics by incorporating multiomic data and clustering infants based on risk factors and metabolic profiles. For example, machine learning is redefining necrotizing enterocolitis as a spectrum of intestinal injuries rather than a single disease, while digital twin models offer the potential for real-time personalized nutrition optimization. Moreover, integration of advanced gastrointestinal monitoring methods using novel biomarkers and sensor technologies may further enhance early detection and intervention strategies. Altogether, these digital technological advancements may lead to identification of early predictors of nutritional deficiencies and prompt recognition of gastrointestinal pathologies, thereby allowing for proactive interventions and potentially improved outcomes in the neonatal population.

Neonatal sepsis remains a major cause of neonatal deaths globally. Despite advances, accurate and timely diagnosis is hindered by the limited performance of the current clinical approaches, imperfect laboratory biomarkers, and long turnaround time of blood cultures. Artificial intelligence (AI), with its ability to identify patterns and learn continuously (machine learning), seems promising. Basic steps in model development include data filtration, train: test split, feature selection, choosing appropriate algorithms, and evaluating performance using a reference standard. In neonatal sepsis, the role of AI spans from predicting sepsis and related outcomes to formulating an individualized treatment approach for the neonate. Existing models, largely from high-income countries, report encouraging diagnostic accuracy but face methodological limitations, lack external validation, and remain somewhat distant from bedside application. Additional barriers to their generalizability include lack of uniform definition of sepsis, variations in disease and pathogen profiles in different settings (particularly in developing countries), availability of electronic health data, tweaks in feature selection, and ethical and legal challenges. This review synthesizes current evidence, highlights gaps, and outlines priorities for future research. We call for a collaborative effort from AI and neonatal experts to devise robust, context-specific solutions.

Non-invasive ventilation (NIV) is a key form of respiratory support in neonatal intensive care units (NICU). Non-invasive ventilation failure, however, can lead to adverse outcomes in preterm infants. This narrative review explores the potential of using artificial intelligence (AI) to improve the prediction of NIV failure, potentially reducing the mortality and morbidity within this population.

Mortality remains a key indicator for the assessment of care quality in medicine. In neonatology, mortality rates are highly variable, both across units and over time. Comparison of crude mortality rates, however, are insufficient for benchmarking, as they fail to account for differences in population case mix and severity of illness. Risk adjustment using artificial intelligence (AI) and machine learning (ML) has emerged as a promising tool to facilitate meaningful comparisons and drive improvement. This review seeks to examine the state of the current literature on the use of AI/ML-based models to predict mortality in the neonatal intensive care unit (NICU). We identified 37 studies describing 242 models. Most studies developed models using single-center data and frequently lacked external validation. Similarly, reporting of performance metrics was heterogenous, limiting evaluation. As a result, further work is necessary before AI/ML-enabled risk adjustment is feasible.

To explore the applicability of artificial intelligence (AI) in neonatal intensive care units (NICUs), identifying key trends in AI-driven technologies and their roles in the prognosis, classification, monitoring and forecasting of neonatal conditions.

The use of Artificial Intelligence (AI) has the potential to transform healthcare in part by enhancing the accuracy of drug dosing and improving patient safety. However, its use in neonatology and pediatrics has just been started, with limited research exploring its full potential. This scoping review systematically maps the literature on AI applications in pediatric and neonatal pharmacology, analyzing studies published between 2004 and 2024. Searches in databases including MEDLINE, Scopus, and IEEE Xplore identified 412 records, of which 33 met the inclusion criteria. These included neonates (n = 8) and older pediatric patients (n = 25), encompassing 58,864 patients and utilizing various Machine-Learning techniques. The use of AI has demonstrated significant potential for precision dosing, predicting drug efficacy, and decreasing the occurrence of adverse events. Despite these promising findings, however, more rigorous, large-scale studies are essential to validate the results. Future research should prioritize real-world applications and address integration barriers, ensuring safe and effective use of AI in neonatal and pediatric clinical practice.

Maternal vaccination during pregnancy is emerging as a powerful strategy in protecting newborns from infectious diseases, improving neonatal outcomes, and potentially reducing antimicrobial use and resistance. Maternal immunisation works by eliciting protective antibodies in the mother that are transferred to the fetus transplacentally and through breastmilk postnatally to provide the infant with passive immunity during the first vulnerable months of life. There is sufficient evidence to support the role of maternal vaccination in averting many neonatal infections that would otherwise require medical intervention. By preventing infections in mothers and their newborn, maternal vaccination also holds significant potential for reducing antimicrobial use and antimicrobial resistance. Fewer neonatal infections translate to a reduced need for antimicrobial use in the neonatal period and in postpartum women, therefore lowering the selective pressure for drug-resistant bacteria. Routine maternal vaccines (tetanus, diphtheria, acellular pertussis (Tdap), influenza, COVID-19, respiratory syncytial virus) already confer measurable antibiotic-sparing benefits by preventing infections that typically trigger antimicrobial therapy in mothers and neonates. Pipeline candidates (Group B Streptococcus, Klebsiella pneumoniae, Escherichia coli) could further lower neonatal sepsis burden, reducing broad-spectrum antimicrobial use in neonatal intensive care units to help slow antimicrobial resistance. Integrated with antibiotic stewardship and infection-prevention measures, maternal immunisation offers a practical, scalable practice to limit perinatal antibiotic exposure.

In the past decades more infants of lower gestational ages (GAs) have developed invasive Candida infection (ICI) from nonmodifiable risk factors of immature immunity and underdeveloped immune barriers (skin, gastrointestinal and respiratory tracts). Rates of ICI vary secondary to modifiable clinical practices, resuscitation practices and the nonmodifiable factor of the number of infants cared for at the lowest GAs of 22-24 weeks. Standardization of ICI definitions and reporting by each GA are needed to optimally elucidate actual rates, outcomes and differences across units, countries and regions. In extremely low birth weight (ELBW, <1000 g at birth) infants with ICI, mortality and neurodevelopmental impairment (NDI) have remained high despite appropriate antifungal therapy and (if candidemia) prompt removal of central venous catheters (CVC). Targeted fluconazole prophylaxis (3 or 6 mg/kg) twice a week in high-risk ELBW infants has been shown to be effective in preventing ICI and is safe without the emergence of azole resistance. Compared to nystatin, fluconazole prophylaxis for ELBW infants is more effective in preventing ICI and since it can be given intravenously, it is not dependent on enteral feeding status. Risk factors (e.g., receiving treatment with antibiotics or parenteral nutrition, presence of a CVC, vaginal delivery) can be used to both identify high-risk patients and define the time period when antifungal prophylaxis is beneficial. Independently of GA, high-risk infants also include those receiving third and fourth generation cephalosporins or carbapenems and those with complex gastrointestinal conditions (e.g. necrotizing enterocolitis, bowel perforation, gastroschisis).

The neonatal skin is central to early survival and immune development. Far from being a passive mechanical barrier, it integrates physical, chemical, and microbial defences that together protect the infant in the immediate postnatal period. In preterm infants, structural immaturity, reduced antimicrobial capacity, and altered microbial colonisation confer heightened vulnerability to infection and inflammation. At the same time, the neonatal period represents a critical window during which skin-microbe interactions shape tolerance and long-term immune trajectories. This review summarises recent advances in understanding the development of the skin barrier, antimicrobial and innate immune defences, and the role of commensals in immune programming. Translational opportunities for neonatal care are discussed, including skin protective practices, antisepsis, and emollient use that may reduce infection risk in the neonatal intensive care unit. Finally, we consider future directions in microbiome-informed and skin-centred strategies.

Congenital diaphragmatic hernia (CDH) remains one of the most challenging conditions to manage in neonatal intensive care, with outcomes determined by the complex interplay between pulmonary hypoplasia, pulmonary vascular remodeling, and ventricular dysfunction. Traditional treatment strategies, including high-frequency ventilation, inhaled nitric oxide, and vasopressor use, fail to account for the dynamic heterogeneity of CDH physiology and may contribute to persistently high mortality. Emerging evidence delineates three principal hemodynamic phenotypes: (1) preserved biventricular function with mild/no pulmonary hypertension (PH), (2) pre-capillary PH with or without right ventricular dysfunction, and (3) post-capillary PH with primary left ventricular (LV) dysfunction. Each phenotype demands distinct ventilatory and pharmacologic strategies, ranging from cautious respiratory support to targeted pulmonary vasodilators, inodilators, or LV-directed therapies. Ventilation in CDH is further complicated by profound lung inhomogeneity, the "baby lung" phenomenon, and susceptibility to ventilator-induced lung injury. Advances in lung-protective strategies, including low driving pressure, permissive hypercapnia, synchrony-enhancing modes, and real-time functional monitoring with echocardiography, lung ultrasound, electrical impedance tomography, and use of circulating biomarkers enable tailored interventions. A precision medicine approach, grounded in multimodal monitoring and gentle cardiopulmonary support, holds promise to optimize hemodynamic balance, reduce iatrogenic injury, and improve survival and long-term outcomes in infants with CDH.

Late onset sepsis is a major cause of morbidity and mortality in the neonatal intensive care unit, and it is frequently acquired from the environment. Infant- and family-centered developmental care, which involves skin-to-skin contact, breastfeeding and continuous parental participation in the care, is an effective infection prevention strategy. Kangaroo mother care, including skin-to-skin contact supports the development of a diverse skin microbiome, distinct from that of the hospital environment. Breastmilk further contributes to infection prevention and immune system development through multiple mechanisms. Parental involvement may improve the safety and quality of care delivery by hospital staff. In summary, parents play an important role in infection prevention in the neonatal intensive care unit. The risks of not including parents in the care of their infants should be further considered both in research and clinical practice.

Probiotic supplementation in preterm infants is one of the most extensively studied interventions in neonatal medicine, with over 50 randomised controlled trials. This paper examines the relationship between probiotic supplementation and late onset sepsis (LOS), considering mechanistic pathways, clinical evidence, and safety profile. Multiple systematic reviews and meta-analyses consistently show that probiotics reduce necrotising enterocolitis (NEC) incidence and all-cause mortality in preterm infants, establishing them as one of the most beneficial interventions in neonatology. Current evidence suggests modest effects on LOS, with Cochrane systematic reviews reporting relative risk 0.89 (95 % CI 0.82-0.97) but with low certainty. Mechanisms supporting LOS reduction include competitive pathogen exclusion, enhanced epithelial barrier function, improved immune responses, and reduced time to full enteral feeding with decreased intravenous access requirements. The safety profile of probiotics is reassuring, with serious adverse events being exceptionally rare. Probiotic-induced sepsis probably occurs in less than 0.5 % of treated infants, representing a very low risk that must be weighed against the likely substantial benefits for NEC and mortality reduction. Product contamination and other quality issues exist but appear manageable with appropriate quality control. Given the robust evidence for NEC and mortality reduction, probiotics represent a valuable intervention for preterm infants but may have limited, if any impact on sepsis. While their specific role in LOS prevention and impacts on the resistome requires further investigation, the overall benefit-risk profile strongly favors their use. Future research will further refine understanding of optimal strain selection and implementation strategies for maximizing clinical benefits while maintaining safety.

Antimicrobial resistance is an evolving threat to infants admitted to the neonatal intensive care unit. Antibiotic-resistant organisms may colonize infants, cause infections, or contribute to nosocomial outbreaks, and are associated with infant morbidity and mortality. As microorganisms continue to acquire resistance to available antimicrobials, infants become at risk of therapeutic failure. One key strategy to prevent the development of antimicrobial resistance is through antimicrobial stewardship to optimize antimicrobial use. This review starts with an overview of neonatal sepsis and drivers of antimicrobial resistance. It subsequently discusses strategies to address and minimize the burden and transmission of antibiotic-resistance organisms as well as implement antimicrobial stewardship programs in the neonatal intensive care unit.

Congenital cytomegalovirus (CMV) infection is a large contributor to neurodevelopmental delay and non-genetic sensorineural hearing loss, which can often be delayed in onset. While a majority of CMV infections are asymptomatic in healthy children and adults, periconceptual and early in utero infection can cause clinically significant and potentially long-term sequelae. The complex relationship between congenital CMV infection and maternal immunity provides a challenging backdrop for CMV prevention. Increased awareness of the significance of congenital CMV is reflected in the proliferation of prevention strategies over the past 30 years, including education initiatives, behavioral modifications, and maternal antiviral prophylaxis. This review explores different levels of congenital CMV prevention and highlights a variety of prevention strategies, including the potential for development of effective vaccines for CMV.

Newborns, especially preterm infants, are vulnerable to invasive infections due to their developing immune system and frequent need for central venous catheters. Central line-associated bloodstream infections (CLABSI) are among the most common invasive infections in this population and represent the leading cause of neonatal bloodstream infection in many settings. Neonatal CLABSI is associated with substantial mortality, long-term morbidity, and increased healthcare costs. Most importantly, CLABSI is preventable. Bundles centered on rigorous hand hygiene combined with standardized practices for catheter insertion, maintenance and removal have proven effective in reducing infection rates in neonates. Benchmarking and quality improvement initiatives enable neonatal intensive care units (NICUs) to track progress and share best practices. While no novel prevention strategies with robust evidence have emerged, sustained declines in CLABSI rates in many NICUs and networks over the past decades highlight the importance of a comprehensive multidisciplinary approach to implement and maintain best practices.

Prevention of RSV lower respiratory tract infections (LRTI) in infants has been limited to general measures and palivizumab, a monoclonal antibody indicated for the highest risk groups. Recently developed RSV vaccines used during pregnancy generate antibodies that cross the placenta. Randomized controlled trials (RCT) and real-life monitoring have demonstrated their effectiveness in protecting newborns and infants during the first months of life. Likewise, novel extended half-life monoclonal antibodies, nirsevimab and the recently approved clesrovimab, opened the possibility of large-scale protection targeted to all infants born during the winter season and those <6 months at the beginning of it. Several RCTs and results from populations adopting nirsevimab prophylaxis demonstrated a large decrease in the incidence of RSV-LRTIs and a great impact in infant public health. Deployment of either strategies or in combination as part of immunization programs can be complement each other even as newer immunologic agents are being introduced.

Neonatal herpes simplex virus (HSV) infection remains a life-threatening condition with high morbidity and mortality despite advances in diagnostics and therapy. Transmission occurs predominantly during delivery and the three main clinical phenotypes; skin-eye-mouth disease, central nervous system disease, and disseminated disease, carry distinct prognoses. This state-of-the-art review focuses on prevention and consideration of empirical treatment. Maternal antiviral prophylaxis in late pregnancy has shown to reduce the frequency of active HSV outbreaks at delivery. Decisions on empirical acyclovir therapy must balance early recognition against overtreatment, guided by the number needed to treat, which in European settings among term and near-term infants ranges from over 1,000 for early-onset sepsis to ∼150 for late-onset sepsis. Ongoing research focuses on preventive strategies, including vaccine development and novel biomarkers on dried blood spot samples to improve outcomes.

Preterm infants, who represent around 10 % of births worldwide, are at markedly increased risk of infections due to their immunological immaturity and reduced maternal antibody transfer. Although international guidelines recommend immunization based on chronological age, vaccination in this population is frequently delayed or incomplete. This review summarizes the current evidence on vaccine safety, efficacy, and timing in preterm infants, with particular emphasis on primary immunizations and vaccines administered during the first year of life. Distinct immunological characteristics-including impaired T- and B-cell responses as well as altered microbiome development-contribute to reduced vaccine responsiveness. Emerging approaches such as mRNA vaccine technologies, novel adjuvants, maternal immunization, and microbiome modulation hold promise for enhancing vaccine efficacy. Ensuring timely immunization and adherence to vaccination recommendations in preterm infants is essential to reduce preventable morbidity and mortality in this highly vulnerable group.

Vertical transmission of HIV to newborns and infants during pregnancy, labour and delivery, and breastfeeding ranges from 15 % to 45 % without intervention. The most important risk factor for transmission is a high maternal viral load. Prevention guidelines for low- and middle-income (high-burden) countries differ from those for high-income (lower-burden) settings, with a key differences in provision of caesarean section, post delivery antiretroviral care of the baby and infant feeding practice. This review will focus on a comprehensive approach to the elimination of paediatric HIV. We will discuss aspects of prevention of HIV and the current standards of care in the prevention of vertical transmission. We highlight the differences between well-resourced and lower-resourced settings including approaches to caesarean section and breastfeeding and infant prophylaxis. We also touch on the potential of emerging strategies to further reduce vertical transmission of HIV. Lastly, despite progress in prevention, challenges persist, particularly in sub-Saharan Africa due to structural health system gaps and loss to care. The recent reduction in donor funding threatens the progress made in transmission prevention.