Equitable Artificial Intelligence in Obstetrics, Maternal-Fetal Medicine, and Neonatology.

Artificial intelligence (AI) offers potential benefits in the interconnected fields of obstetrics, maternal-fetal medicine, and neonatology to bridge disciplinary silos for a unified approach. Artificial intelligence has the capacity to improve diagnostic accuracy and clinical decision making for the birthing parent-neonate dyad. There is an inherent risk of ingrained biases in AI that perpetuate existing inequalities; thus, care must be taken to include diverse data sets with interdisciplinary collaboration that centers equitable AI implementation. As AI plays an increasingly important role in perinatal care, we advocate for its cautious, equity-focused application to benefit the perinatal dyad while avoiding the intensification of health care disparities and disciplinary silos.

The Current State of Neonatal Neurodevelopmental Follow-up Programs in North America: A Children's Hospitals Neonatal Consortium Report.

OBJECTIVE: This study aimed to determine neonatal neurodevelopmental follow-up (NDFU) practices across academic centers. STUDY DESIGN: This study was a cross-sectional survey that addressed center-specific neonatal NDFU practices within the Children's Hospitals Neonatal Consortium (CHNC). RESULTS: Survey response rate was 76%, and 97% of respondents had a formal NDFU program. Programs were commonly staffed by neonatologists (80%), physical therapists (77%), and nurse practitioners (74%). Median gestational age at birth identified for follow-up was ≤32 weeks (range 26-36). Median duration was 3 years (range 2-18). Ninety-seven percent of sites used Bayley Scales of Infant and Toddler Development, but instruments used varied across ages. Scores were recorded in discrete electronic data fields at 43% of sites. Social determinants of health data were collected by 63%. Care coordination and telehealth services were not universally available. CONCLUSION: NDFU clinics are almost universal within CHNC centers. Commonalities and variances in practice highlight opportunities for data sharing and development of best practices. KEY POINTS: · Neonatal NDFU clinics help transition high-risk infants home.. · Interdisciplinary neonatal intensive care unit follow-up brings together previously separated outpatient service lines.. · This study reviews the current state of neonatal NDFU in North America..

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.

Fatigue and fallibility: the perils of prolonged shifts for neonatologists.

Sleep deprivation is a major challenge for neonatologists, who face increasing demands in the complex healthcare system. Current neonatal intensive care unit (NICU) schedule models often include extended shifts and overnight call, which can lead to sleep deprivation. This lack of sufficient sleep poses adverse health risks to neonatologists and can impair cognitive function, which increases the risk of medical errors and compromises patient safety. This paper proposes reducing shift durations and implementing policies and interventions to reduce fatigue among neonatologists and improve patient safety. The paper also offers policymakers, healthcare leaders, and NICU physicians valuable insights on potential ways to promote the health of the neonatologist workforce and safety in the NICU.

A global perspective of delayed cord clamping in infants.

Delayed umbilical cord clamping, DCC, a practice in which the umbilical cord is not clamped immediately after birth, promotes placental transfusion to preterm and term neonates. DCC may improve outcomes in preterm neonates by reducing mortality and blood transfusion requirements and increasing iron stores. Despite the recommendations from multiple governing bodies, including the World Health Organization, research on DCC in LMICs remains limited. Given that iron deficiency is prevalent, and most neonatal deaths occur in LMICs, DCC has the potential to improve outcomes in these settings. This article aims to provide a global perspective on DCC in LMICs and to identify knowledge gaps that offer future research opportunities.

Predicting clinical outcomes using artificial intelligence and machine learning in neonatal intensive care units: a systematic review.

BACKGROUND: Advances in technology, data availability, and analytics have helped improve quality of care in the neonatal intensive care unit. OBJECTIVE: To provide an in-depth review of artificial intelligence (AI) and machine learning techniques being utilized to predict neonatal outcomes. METHODS: The PRISMA protocol was followed that considered articles from established digital repositories. Included articles were categorized based on predictions of: (a) major neonatal morbidities such as sepsis, bronchopulmonary dysplasia, intraventricular hemorrhage, necrotizing enterocolitis, and retinopathy of prematurity; (b) mortality; and (c) length of stay. RESULTS: A total of 366 studies were considered; 68 studies were eligible for inclusion in the review. The current set of predictor models are primarily built on supervised learning and mostly used regression models built on retrospective data. CONCLUSION: With the availability of EMR data and data-sharing of NICU outcomes across neonatal research networks, machine learning algorithms have shown breakthrough performance in predicting neonatal disease.

Study Protocol: Multimodal Longitudinal Assessment of Infant Brain Organization and Recovery in Perinatal Brain Injury.

PURPOSE: Perinatal brain injury is a primary cause of cerebral palsy, a condition resulting in lifelong motor impairment. Infancy is an important period of motor system development, including development of the corticospinal tract (CST), the primary pathway for cortical movement control. The interaction between perinatal stroke recovery, CST organization, and resultant motor outcome in infants is not well understood. METHODS: Here, we present a protocol for multimodal longitudinal assessment of brain development and motor function following perinatal brain injury using transcranial magnetic stimulation and magnetic resonance imaging to noninvasively measure CST functional and structural integrity across multiple time points in infants 3 to 24 months of age. We will further assess the association between cortical excitability, integrity, and motor function. DISCUSSION: This protocol will identify bioindicators of motor outcome and neuroplasticity and subsequently inform early detection, diagnosis, and intervention strategies for infants with perinatal stroke, brain bleeds, and related diagnoses.

Management of Placental Transfusion to Neonates After Delivery.

This review summarizes high-quality evidence supporting delayed umbilical cord clamping to promote placental transfusion to preterm and term neonates. In preterm neonates, delayed cord clamping may decrease mortality and the need for blood transfusions. Although robust data are lacking to guide cord management strategies in many clinical scenarios, emerging literature is reviewed on numerous topics including delivery mode, twin gestations, maternal comorbidities (eg, gestational diabetes, red blood cell alloimmunization, human immunodeficiency virus [HIV] infection, and severe acute respiratory syndrome coronavirus 2 [SARS-CoV-2] infection) and neonatal complications (eg, fetal growth restriction, congenital heart disease, and the depressed neonate). Umbilical cord milking is an alternate method of rapid placental transfusion, but has been associated with severe intraventricular hemorrhage in extremely preterm neonates. Data on long-term outcomes are discussed, as well as potential contraindications to delayed cord clamping. Overall, delayed cord clamping offers potential benefits to the estimated 140 million neonates born globally every year, emphasizing the importance of this simple and no-cost strategy.

Gaps in Palliative Care Education among Neonatology Fellowship Trainees.

Background: To provide proper care for infants at risk for death, neonatologists need expertise in many areas of palliative care. Although neonatology training programs have implemented a wide variety of palliative care educational programs, the impact of these programs on trainees' skills and effective communication regarding end-of-life issues remains unclear. Objective: To determine whether neonatology fellowship programs are providing formal palliative care education and assess whether this education is effective at increasing fellows' self-reported comfort with these important skills. Methods: An anonymous survey was sent to program directors (PDs) and fellows of ACGME accredited neonatology fellowship programs in the United States. Using a 5-point Likert scale, participants were asked about the palliative care education they received, and their comfort level with several key aspects of palliative care. Results: Twenty-four (26%) PDs and 66 (33%) fellows completed the survey. Fourteen PDs (58%) reported including palliative care education in their formal fellowship curriculum, whereas only 20 (30%) responding fellows reported receiving palliative care education. Of the responding fellows, most (80%) reported being uncomfortable or only somewhat comfortable with all assessed areas of palliative care. Fellows who received formal education were more comfortable than those without it in leading goals of care conversations (p = 0.001), breaking bad news (p = 0.048), discussing change in code status (p = 0.029), and grief and bereavement (p = 0.031). Conclusions: Most fellows report being uncomfortable or only somewhat comfortable with essential areas of palliative care. Formal palliative care education improves fellows' self-reported comfort with important aspects of end-of-life care. To promote a well-rounded neonatology fellowship curriculum, inclusion of formal palliative care education is recommended.

Caffeine Inhibits Choroidal Neovascularization Through Mitigation of Inflammatory and Angiogenesis Activities.

Adenosine receptors (AR) are widely expressed in a variety of tissues including the retina and brain. They are involved in adenosine-mediated immune responses underlying the onset and progression of neurodegenerative diseases. The expression of AR has been previously demonstrated in some retinal cells including endothelial cells and retinal pigment epithelial cells, but their expression in the choroid and choroidal cells remains unknown. Caffeine is a widely consumed AR antagonist that can influence inflammation and vascular cell function. It has established roles in the treatment of neonatal sleep apnea, acute migraine, and post lumbar puncture headache as well as the neurodegenerative diseases such as Parkinson and Alzheimer. More recently, AR antagonism with caffeine has been shown to protect preterm infants from ischemic retinopathy and retinal neovascularization. However, whether caffeine impacts the development and progression of ocular age-related diseases including neovascular age-related macular degermation remains unknown. Here, we examined the expression of AR in retinal and choroidal tissues and cells. We showed that antagonism of AR with caffeine or istradefylline decreased sprouting of thoracic aorta and choroid/retinal pigment epithelium explants in ex vivo cultures, consistent with caffeine's ability to inhibit endothelial cell migration in culture. In vivo studies also demonstrated the efficacy of caffeine in inhibition of choroidal neovascularization and mononuclear phagocyte recruitment to the laser lesion sites. Istradefylline, a specific AR 2A antagonist, also decreased choroidal neovascularization. Collectively, our studies demonstrate an important role for expression of AR in the choroid whose antagonism mitigate choroidal inflammatory and angiogenesis activities.

Cord blood DNA methylation modifications in infants are associated with white matter microstructure in the context of prenatal maternal depression and anxiety.

Maternal and environmental factors influence brain networks and architecture via both physiological pathways and epigenetic modifications. In particular, prenatal maternal depression and anxiety symptoms appear to impact infant white matter (WM) microstructure, leading us to investigate whether epigenetic modifications (i.e., DNA methylation) contribute to these WM differences. To determine if infants of women with depression and anxiety symptoms exhibit epigenetic modifications linked to neurodevelopmental changes, 52 umbilical cord bloods (CBs) were profiled. We observed 219 differentially methylated genomic positions (DMPs; FDR p < 0.05) in CB that were associated with magnetic resonance imaging measures of WM microstructure at 1 month of age and in regions previously described to be related to maternal depression and anxiety symptoms. Genomic characterization of these associated DMPs revealed 143 unique genes with significant relationships to processes involved in neurodevelopment, GTPase activity, or the canonical Wnt signaling pathway. Separate regression models for female (n = 24) and male (n = 28) infants found 142 associated DMPs in females and 116 associated DMPs in males (nominal p value < 0.001, R > 0.5), which were annotated to 98 and 81 genes, respectively. Together, these findings suggest that umbilical CB DNA methylation levels at birth are associated with 1-month WM microstructure.

Renal tissue oxygenation after caffeine administration in preterm neonates.

BACKGROUND: Caffeine has been associated with reduced rates of acute kidney injury (AKI) in preterm neonates. The effect of caffeine on preterm neonatal renal regional saturation of oxygen (RrSO2) is unknown. METHODS: RrSO2 was recorded continuously in neonates < 32 weeks' gestation until 7 days of age with INVOS™ neonatal near-infrared spectroscopy (NIRS) sensors. Baseline RrSO2 values were established by averaging the saturations in the 20 min prior to caffeine administration. Subgroup analysis was performed based on pre-caffeine RrSO2 averages. Change in RrSO2 was recorded at 0.5, 1, 2, 3, 4, 6, and 12 h after maintenance caffeine administration. RESULTS: Of 35 eligible neonates, 31 (median gestational age 28.4 weeks) received 156 caffeine doses (median 8 mg/kg). Analysis of combined doses showed no significant changes in RrSO2 after caffeine administration at any time. However, neonates with baseline 20-29.9% had significant increases from 1 to 12 h (range of increase 5.9-13.9%), and those with baseline 30-39.9 had significant increases at 1 h (8.06%, p < 0.05). CONCLUSIONS: Maintenance caffeine dosing increased RrSO2 in neonates with low RrSO2 in the first week. Further research is needed to determine the effect of loading doses of caffeine and if increases in RrSO2 correlate with improved clinical kidney outcomes. IMPACT: Caffeine administration is associated with increased renal tissue oxygenation in preterm neonates with low baseline values under 40%. The most significant renal tissue oxygenation changes occur in the first 3 h after IV caffeine administration. With recent studies suggesting low RrSO2 values in preterm neonates are associated with AKI, caffeine should be studied as a potential therapeutic for this common and complex morbidity in preterm neonates.

Mitigating the Impacts of COVID-19 on Global Child Health: a Call to Action.

PURPOSE OF REVIEW: Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2), the cause of coronavirus disease 2019 (COVID-19), continues to affect individuals, communities, and health systems worldwide. Here, we highlight how COVID-19 threatens to jeopardize the tremendous gains made over the last few decades on improving children's health globally. RECENT FINDINGS: In contrast to adults, children with COVID-19 are less likely to develop severe disease requiring hospitalization or die as a direct result of infection. However, the pandemic will likely have other important health impacts disproportionately affecting vulnerable children globally. Possible effects include worsening of poverty and food insecurity; disruption of already strained routine child health services; damage to already imperiled healthcare workforces; a wave of mental health challenges; interruption of education; and increased risks of violence, abuse, exploitation, and neglect. These challenges notwithstanding, the response to COVID-19 may also provide opportunities, such as for health system strengthening, that could improve child health after the pandemic. SUMMARY: The negative impacts of COVID-19 on global child health may be substantial. However, these are not foregone conclusions and much can be done to mitigate the worst outcomes. Child health providers should advocate for an equitable response to COVID-19 that prioritizes the health of vulnerable children and furthers the gains made in global child health.

Development and validation of high definition phenotype-based mortality prediction in critical care units.

OBJECTIVES: The objectives of this study are to construct the high definition phenotype (HDP), a novel time-series data structure composed of both primary and derived parameters, using heterogeneous clinical sources and to determine whether different predictive models can utilize the HDP in the neonatal intensive care unit (NICU) to improve neonatal mortality prediction in clinical settings. MATERIALS AND METHODS: A total of 49 primary data parameters were collected from July 2018 to May 2020 from eight level-III NICUs. From a total of 1546 patients, 757 patients were found to contain sufficient fixed, intermittent, and continuous data to create HDPs. Two different predictive models utilizing the HDP, one a logistic regression model (LRM) and the other a deep learning long-short-term memory (LSTM) model, were constructed to predict neonatal mortality at multiple time points during the patient hospitalization. The results were compared with previous illness severity scores, including SNAPPE, SNAPPE-II, CRIB, and CRIB-II. RESULTS: A HDP matrix, including 12 221 536 minutes of patient stay in NICU, was constructed. The LRM model and the LSTM model performed better than existing neonatal illness severity scores in predicting mortality using the area under the receiver operating characteristic curve (AUC) metric. An ablation study showed that utilizing continuous parameters alone results in an AUC score of >80% for both LRM and LSTM, but combining fixed, intermittent, and continuous parameters in the HDP results in scores >85%. The probability of mortality predictive score has recall and precision of 0.88 and 0.77 for the LRM and 0.97 and 0.85 for the LSTM. CONCLUSIONS AND RELEVANCE: The HDP data structure supports multiple analytic techniques, including the statistical LRM approach and the machine learning LSTM approach used in this study. LRM and LSTM predictive models of neonatal mortality utilizing the HDP performed better than existing neonatal illness severity scores. Further research is necessary to create HDP-based clinical decision tools to detect the early onset of neonatal morbidities.