Pediatric delirium has emerged as a common and clinically meaningful complication of critical illness, with growing recognition of its association with adverse short-term and long-term outcomes. This review is timely given increasing guideline recommendations for routine delirium screening in pediatric critical care settings and the expanding use of validated bedside tools by multidisciplinary teams. Recent literature demonstrates that delirium affects a substantial proportion of critically ill children, particularly those in pediatric ICUs (PICUs) and pediatric cardiac ICUs (PCICUs). The development and validation of pediatric-specific delirium screening instruments have enabled reliable, real-time detection without exclusive reliance on psychiatric consultation. Studies highlight the clinical impact of delirium on morbidity, mortality, length of stay, discharge disposition, and post-intensive care sequelae. However, persistent challenges include variable implementation across units, limited data in certain subpopulations, and gaps in evidence linking screening to targeted interventions and improved outcomes. Routine delirium screening represents an important advance in pediatric critical care, positioning delirium as a modifiable adverse outcome. Future research should focus on optimizing implementation strategies, addressing special populations, and integrating screening into effective prevention and management pathways to improve patient-centered outcomes.

Artificial intelligence has been integrated in nearly all aspects of clinical care to improve patient outcomes, augment human capabilities and improve efficiency. Particularly in the field of radiology and medical imaging, artificial intelligence could revolutionize how care is delivered. In this review, we review the recent literature and provide an assessment of the advantages (pros) and limitations (cons) of artificial intelligence in point-of-care ultrasonography (POCUS). Emerging literature suggests that artificial intelligence assisted diagnostic models offer a performance advantage over standard imaging modalities with regards to image acquisition and diagnostic accuracy particularly with less experienced users. In pediatric POCUS, artificial intelligence has been shown to improve image acquisition and augment education, which is remarkably helpful in areas where ultrasound experts are limited. Nevertheless, integration of artificial intelligence in the growing field of POCUS requires careful assessment of its drawbacks, biases and limitations. Models that are trained primarily on adult populations should be assessed and validated before utilization in the pediatric population to ensure generalizability. Furthermore, the use of artificial intelligence should integrate with and not replace existing educational models and credentialing processes to preserve ultrasound skills. Finally, at the institutional and global levels, hospitals and organizations will need to weigh in on policies, data governance and oversight in this vulnerable population. The use of artificial intelligence in POCUS in the fields of emergency medicine and critical care is promising but should be viewed with a lens of caution. It holds promise for improving accessibility, reducing variability in care and transforming care in resource-limited settings, but integration of this evolving technology should be thoughtful to address its potential limitations.

Single cell technologies are quickly becoming more affordable and widespread throughout academic research. We review the application of single cell and multi-omic technologies to study neonatal health and disease, as well as their potential to further impact translational discoveries in the future. Pediatric and neonatal development and disease have been largely understudied compared to their adult counterparts. This difference can be partially attributed to limited sample access and small sample volumes. Single cell and multi-omic approaches have drastically altered the landscape of neonatal research, as they allow for the acquisition of large volumes of data from small and limited samples. When profiled individually, even a few hundred cells contain a wealth of information that was previously inaccessible with prior techniques. Single cell technologies have revealed profound cellular heterogeneity, dynamic regulation over time and across tissues, disease activity, and many other factors. The use of single-cell technologies has rapidly advanced our understanding of baseline immune development and pathologies of early-life, however, there is a pressing need for development and benchmarking of multi-modal platforms that measure parameters beyond mRNA transcripts, and the analytical tools required to integrate these complex datasets.

Near-infrared spectroscopy (NIRS) is increasingly used in pediatric cardiac intensive care to monitor regional tissue oxygenation. Despite its widespread adoption, its clinical utility remains uncertain. This review examines the physiological rationale, accuracy, potential benefits, and limitations of NIRS as a monitoring tool in critically ill children, emphasizing whether it improves outcomes or meaningfully guides management. NIRS provides continuous, noninvasive regional oxygenation data, but measurements are affected by technical and physiological confounders and correlate only moderately with validated markers of systemic perfusion. Although low values may prompt interventions, no randomized trials have demonstrated improved mortality, neurological outcomes, or organ function with NIRS-guided care. Thresholds for intervention vary widely, and most centers lack standardized response protocols. NIRS use may increase unnecessary interventions, contribute to alarm fatigue, and impose substantial financial costs without demonstrated benefit. Current evidence suggests that NIRS should serve as an adjunct rather than a primary driver of clinical decision-making in pediatric cardiac intensive care. Established modalities such as venous oxygen saturation, lactate trends, echocardiography, and functional hemodynamic assessments provide more actionable information. Further trials are required to define whether NIRS improves outcomes.

The literature review is pertinent because diagnosing pediatric tuberculosis (PdTB) remains quite challenging, especially in areas with limited resources, due to complications caused by variable generalized symptoms, paucibacillary characteristics, vague clinical manifestations, and challenges associated with pediatric sputum sample production. Recent developments in artificial intelligence have the potential to enhance the accuracy of diagnoses and the effectiveness of treatments. Nineteen published studies between January 2024 and July 2025 were examined, which focused on artificial intelligence driven chest X-ray (CXR) examination and medical prediction. The reviewed studies utilized convolutional neural networks (CNN), transfer learning, and stacked ensemble machine learning (SEML) to achieve sensitivity values ranging from 76.0 to 98.2%, specificity of 70.0 to 98.0%, and area under the curve (AUC) values of as high as 0.98 in AI-CXR diagnosis for the detection of PdTB. Through continuous experiments and use of the AI-CXR triage in Ethiopia (2025), successfully identifying over 30% of patients, while prediction models indicate 82% hepatotoxicity concerns in Nigerian cohorts. Plasma proteomics and exhaled breath analysis are emerging methodologies that exhibit potential; however, pediatric datasets are limited, necessitating multicenter validation. Artificial intelligence enhances the diagnosis and treatment prediction of PdTB in resource-constrained settings. The integration of artificial intelligence with existing diagnostic tools like GeneXpert and telemedicine strategies can significantly improve the efficiency of screening processes. Future research efforts should prioritize the expansion of pediatric datasets and the evaluation of multimodal AI-PdTB approaches.

Pediatric trigger thumb is a common problem in children accounting for 1 in 2000 visits to the pediatric hand clinic. Misdiagnosis as a fracture or dislocation is common, so proper identification is key. The ideal treatment strategy remains a subject of debate, and there are studies documenting successful outcomes with both nonoperative and surgical treatment. Recent literature highlights that observation is reasonable, as spontaneous resolution can occur in 30-50% of cases over a several-year period, with those having an interphalangeal angle of less than 30° being more likely to resolve. Surgical release of the A1 pulley remains the definitive treatment, with consistently excellent outcomes and minimal complications, particularly for children older than 2 years or those with more severe contractures or failed conservative management. Recent studies have identified certain congenital malformations that occur at a higher rate in children with trigger thumbs. This developmental condition is common with spontaneous resolution being frequent. Proper diagnosis includes findings on examination of the volar nodule and flexion at the interphalangeal joint of the thumb. Minimizing misdiagnosis and appropriate observation in mild cases for a certain time frame is acceptable. Awareness of the potential need for surgical intervention, which is highly effective for persistent or severe trigger thumb in children, is important. The choice of management should be individualized based on age, severity, and parental preference, with recent studies supporting both approaches depending on clinical context.

To provide pediatric clinicians with an overview of current research on leucovorin use in children with autism spectrum disorder (ASD) and a guide to patient evaluation and treatment. An association between cerebral folate deficiency (CFD) and ASD has been suggested in some studies. Autoantibodies that block folate entry into the brain are a cause of CFD and have been detected in 71% of patients with ASD. Leucovorin is a synthetic drug that increases folate concentrations in the brain despite the presence of autoantibodies. Certain studies have indicated reductions in communication deficits in nonverbal children with ASD, particularly those with these autoantibodies, following consistent leucovorin use. However, other studies have found no change in symptoms despite leucovorin intake. The American Academy of Pediatrics (AAP) currently does not recommend use of leucovorin in children with ASD. Due to recent popularity among policymakers and on social media, many pediatricians have reported increased requests by families for leucovorin prescriptions to treat ASD in pediatric patients. This review provides clinicians with an overview of the biological rationale, clinical evidence, and potential benefits and limitations of leucovorin use in children with ASD.

Mothers in the United States are unwell, with high rates of maternal stress and death. Maternal health matters in its own right, and it is more difficult for children to be well if their parents are not. Improving mothers' economic status and social connectedness to improve maternal and child health has received increased attention. New data build on previous findings that economic (e.g., financial strain, lost health insurance) and social [e.g., adverse childhood experiences (ACEs), structural racism] stressors are associated with poorer maternal and child health. Conversely, economic and social supports (e.g., cash transfers, paid family and medical leave, social connectedness) improve aspects of maternal and child health. Evidence on whether pandemic-era cash transfers impact maternal and child health is mixed. Addressing social and economic stressors can improve maternal and child health, but the details matter. Incremental economic interventions are insufficient. Social factors such as isolation and structural racism must also be addressed. Policy implementation is equally important; families cannot benefit if they cannot access resources. Policy changes such as universal paid family and medical leave are needed. The field of pediatrics should update practice guidelines and advocate for policy changes.