Artificial intelligence in the neonatal intensive care unit: the time is now

Artificial intelligence (AI) has the potential to revolutionize the neonatal intensive care unit (NICU) care by leveraging the large-scale, high-dimensional data that are generated by NICU patients. There is an emerging recognition that the confluence of technological progress, commercialization pathways, and rich data sets provides a unique opportunity for AI to make a lasting impact on the NICU. In this perspective article, we discuss four broad categories of AI applications in the NICU: imaging interpretation, prediction modeling of electronic health record data, integration of real-time monitoring data, and documentation and billing. By enhancing decision-making, streamlining processes, and improving patient outcomes, AI holds the potential to transform the quality of care for vulnerable newborns, making the excitement surrounding AI advancements well-founded and the potential for significant positive change stronger than ever before.

Transforming neonatal care with artificial intelligence: challenges, ethical consideration, and opportunities

Artificial intelligence (AI) offers tremendous potential to transform neonatology through improved diagnostics, personalized treatments, and earlier prevention of complications. However, there are many challenges to address before AI is ready for clinical practice. This review defines key AI concepts and discusses ethical considerations and implicit biases associated with AI. Next we will review literature examples of AI already being explored in neonatology research and we will suggest future potentials for AI work. Examples discussed in this article include predicting outcomes such as sepsis, optimizing oxygen therapy, and image analysis to detect brain injury and retinopathy of prematurity. Realizing AI's potential necessitates collaboration between diverse stakeholders across the entire process of incorporating AI tools in the NICU to address testability, usability, bias, and transparency. With multi-center and multi-disciplinary collaboration, AI holds tremendous potential to transform the future of neonatology.

Health-Related Qualities of Life in School-Aged Children with Bronchopulmonary Dysplasia

OBJECTIVE

To determine health-related quality of life (HRQOL) of school-aged children with bronchopulmonary dysplasia (BPD) using the standardized Patient-Reported Outcomes Measurement Information System (PROMIS) assessment tools.

STUDY DESIGN

The Indoor Air Quality and Respiratory Morbidity in Children with BPD Study is an ongoing observational study of school-aged children with BPD. HRQOL is assessed at enrollment by 3 PROMIS questionnaires, Parent Proxy Scale-Global Health 7, Parent Proxy Psychological Stress Experiences-Short Form, and the Parent Proxy Profile-Profile-25. PROMIS data were tested for significant deviation from the standardized T-Score references for normative populations of children.

RESULTS

Eighty-nine subjects enrolled in the AERO-BPD study had complete outcome data for HRQOL. The mean age was 9 (±2) years and 43% were female. Mean days on respiratory support totaled 96 (±40). Across all domains, school-aged children with BPD reported similar or slightly better outcomes than the reference sample. Statistically significant findings of lower depression (P < .0001), fatigue (P < .0001), and pain (P < .0001) scores were found; there was no difference in psychological stress experiences (P = .87), global health (P = .06), anxiety (P = .08), relationships (P = .80), and mobility (P = .59) domains.

CONCLUSIONS

This study demonstrated that children with BPD may have less depression, fatigue, and pain HRQL than the general population. Once validated, these findings may offer reassurance to parents and providers caring for children with BPD.

Performance of a Large Language Model on Practice Questions for the Neonatal Board Examination

This Diagnostic/Prognostic Study evaluates the performance of a large language model in generating answers to practice questions for the neonatal-perinatal board examination.

National Needs Assessment of Utilization of Common Newborn Clinical Decision Support Tools

OBJECTIVE

Clinical decision support tools (CDSTs) are common in neonatology, but utilization is rarely examined. We examined the utilization of four CDSTs in newborn care.   Study Design: A 72-field needs assessment was developed. It was distributed to listservs encompassing trainees, nurse practitioners, hospitalists, and attendings. At the conclusion of data collection, responses were downloaded and analyzed.        Results: We received 339 fully completed questionnaires. BiliTool and the EOS tool were used by > 90% of respondents, the BPD tool by 39%, and the EPB tool by 72%. Common reasons CDSTs did not impact clinical care included lack of electronic health record (EHR) integration, lack of confidence in prediction accuracy, and unhelpful predictions.   Conclusion: From a national sample of neonatal care providers, there is frequent but variable use of four CDSTs. Understanding the factors that contribute to tool utility is vital prior to development and implementation.

Early postnatal illness severity scores predict neurodevelopmental impairments at 10 years of age in children born extremely preterm

OBJECTIVE

A neonatal illness severity score, The Score for Neonatal Acute Physiology-II (SNAP-II), predicts neurodevelopmental impairments at two years of age among children born extremely preterm. We sought to evaluate to what extent SNAP-II is predictive of cognitive and other neurodevelopmental impairments at 10 years of age.

STUDY DESIGN

In a cohort of 874 children born before 28 weeks of gestation, we prospectively collected clinical, physiologic and laboratory data to calculate SNAP-II for each infant. When the children were 10 years old, examiners who were unaware of the child's medical history assessed neurodevelopmental outcomes, including neurocognitive, gross motor, social and communication functions, diagnosis and treatment of seizures or attention deficit hyperactivity disorder (ADHD), academic achievement, and quality of life. We used logistic regression to adjust for potential confounders.

RESULTS

An undesirably high SNAP-II (⩾30), present in 23% of participants, was associated with an increased risk of cognitive impairment (IQ, executive function, language ability), adverse neurological outcomes (epilepsy, impaired gross motor function), behavioral abnormalities (attention deficit disorder and hyperactivity), social dysfunction (autistic spectrum disorder) and education-related adversities (school achievement and need for educational supports. In analyses that adjusted for potential confounders, Z-scores ⩽-1 on 11 of 18 cognitive outcomes were associated with SNAP-II in the highest category, and 6 of 18 were associated with SNAP-II in the intermediate category. Odds ratios and 95% confidence intervals ranged from 1.4 (1.01, 2.1) to 2.1 (1.4, 3.1). Similarly, 2 of the 8 social dysfunctions were associated with SNAP-II in the highest category, and 3 of 8 were associated with SNAP-II in the intermediate category. Odds ratios and 95% confidence intervals were slightly higher for these assessments, ranging from 1.6 (1.1, 2.4) to 2.3 (1.2, 4.6).

CONCLUSION

Among very preterm newborns, physiologic derangements present in the first 12 postnatal hours are associated with dysfunctions in several neurodevelopmental domains at 10 years of age. We are unable to make inferences about causality.

Transplacental toxoplasmosis in a reindeer (Rangifer tarandus) fetus

Toxoplasma gondii infection was diagnosed in a full term stillborn reindeer (Rangifer tarandus) fetus. The fetus had encephalitis and placentitis associated with T. gondii. Tissue cysts were identified histologically in sections of brain and tachyzoites were present in placenta and the myocardium. Protozoa in the brain, heart, and placenta stained positively with T. gondii antibodies, but not with Neospora caninum antibodies in an immunohistochemical test. The dam of the fetus had a 1:12,800 titer to T. gondii in the modified agglutination test employing whole tachyzoites and mercaptoethanol. This is the first confirmed report of T. gondii infection in reindeer.