A clinical informatics approach to bronchopulmonary dysplasia: current barriers and future possibilities.

Bronchopulmonary dysplasia (BPD) is a complex, multifactorial lung disease affecting preterm neonates that can result in long-term pulmonary and non-pulmonary complications. Current therapies mainly focus on symptom management after the development of BPD, indicating a need for innovative approaches to predict and identify neonates who would benefit most from targeted or earlier interventions. Clinical informatics, a subfield of biomedical informatics, is transforming healthcare by integrating computational methods with patient data to improve patient outcomes. The application of clinical informatics to develop and enhance clinical therapies for BPD presents opportunities by leveraging electronic health record data, applying machine learning algorithms, and implementing clinical decision support systems. This review highlights the current barriers and the future potential of clinical informatics in identifying clinically relevant BPD phenotypes and developing clinical decision support tools to improve the management of extremely preterm neonates developing or with established BPD. However, the full potential of clinical informatics in advancing our understanding of BPD with the goal of improving patient outcomes cannot be achieved unless we address current challenges such as data collection, storage, privacy, and inherent data bias.

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.

Clinician collaboration to improve clinical decision support: the Clickbusters initiative.

OBJECTIVE: We describe the Clickbusters initiative implemented at Vanderbilt University Medical Center (VUMC), which was designed to improve safety and quality and reduce burnout through the optimization of clinical decision support (CDS) alerts. MATERIALS AND METHODS: We developed a 10-step Clickbusting process and implemented a program that included a curriculum, CDS alert inventory, oversight process, and gamification. We carried out two 3-month rounds of the Clickbusters program at VUMC. We completed descriptive analyses of the changes made to alerts during the process, and of alert firing rates before and after the program. RESULTS: Prior to Clickbusters, VUMC had 419 CDS alerts in production, with 488 425 firings (42 982 interruptive) each week. After 2 rounds, the Clickbusters program resulted in detailed, comprehensive reviews of 84 CDS alerts and reduced the number of weekly alert firings by more than 70 000 (15.43%). In addition to the direct improvements in CDS, the initiative also increased user engagement and involvement in CDS. CONCLUSIONS: At VUMC, the Clickbusters program was successful in optimizing CDS alerts by reducing alert firings and resulting clicks. The program also involved more users in the process of evaluating and improving CDS and helped build a culture of continuous evaluation and improvement of clinical content in the electronic health record.

Factors associated with initial tidal volume selection during neonatal volume-targeted ventilation in two NICUs: a retrospective cohort study.

OBJECTIVE: To quantify initial tidal volume (VT) during neonatal volume-targeted ventilation (VTV) and to characterize the agreement of initial VT with the limited-evidence available. STUDY DESIGN: We performed a multi-center retrospective observational cohort study in two Neonatal Intensive Care Units evaluating 313 infants who received VTV as the initial ventilation modality prior to postnatal day 14. We generated descriptive statistics and performed multivariable logistic regression analysis to determine factors associated with initial VT use that agreed with available literature. RESULTS: 154 (49%) infants received an initial VT of 5.0 mL/kg (median 5.0 mL/kg, IQR 5.0-5.1). 45 (14%) infants received an initial VT that was congruent with available literature. A birth weight of 700 -<1250 g was significantly associated with an initial VT in agreement with VT literature (aOR 9.4, 95% CI 1.7-50.4). CONCLUSIONS: Most infants receive an initial VT of 5.0 mL/kg.

Optimizing the Use of Human Milk Cream Supplement in Very Preterm Infants: Growth and Cost Outcomes.

BACKGROUND: An exclusive human milk-based diet has been shown to decrease necrotizing enterocolitis and improve outcomes for infants ≤1250 g birth weight. Studies have shown that infants who received an exclusive human milk diet with a donor-human milk-derived cream supplement (cream) had improved weight and length velocity when the cream was added to mother's own milk or donor-human milk when energy was <20 kcal/oz using a human milk analyzer. Our objective was to compare growth and cost outcomes of infants ≤1250 g birth weight fed with an exclusive human milk diet, with and without human milk cream, without the use of a human milk analyzer. METHODS: Two cohorts of human milk-fed premature infants were compared from birth to 34 weeks postmenstrual age. Group 1 (2010-2011) received a donor-human milk fortifier, whereas Group 2 (2015-2016) received donor-human milk fortifier plus the commercial cream supplement, if weight gain was <15 g/kg/d. RESULTS: There was no difference in growth between the 2 groups for weight (P = 0.32) or head circumference (P = 0.90). Length velocity was greater for Group 1 (P = 0.03). The mean dose of donor-human milk fortifier was lower in Group 2 (P < 0.001). Group 2 saved an average of $2318 per patient on the cost of human milk products (P < 0.01). CONCLUSIONS: Infants receiving a human milk diet with cream supplementation for growth faltering achieve appropriate growth in a cost-effective feeding strategy.

Quality of EHR data extractions for studies of preterm birth in a tertiary care center: guidelines for obtaining reliable data.

BACKGROUND: The use of Electronic Health Records (EHR) has increased significantly in the past 15 years. This study compares electronic vs. manual data abstractions from an EHR for accuracy. While the dataset is limited to preterm birth data, our work is generally applicable. We enumerate challenges to reliable extraction, and state guidelines to maximize reliability. METHODS: An Epic™ EHR data extraction of structured data values from 1,772 neonatal records born between the years 2001-2011 was performed. The data were directly compared to a manually-abstracted database. Specific data values important to studies of perinatology were chosen to compare discrepancies between the two databases. RESULTS: Discrepancy rates between the EHR extraction and the manual database were calculated for gestational age in weeks (2.6 %), birthweight (9.7 %), first white blood cell count (3.2 %), initial hemoglobin (11.9 %), peak total and direct bilirubin (11.4 % and 4.9 %), and patent ductus arteriosus (PDA) diagnosis (12.8 %). Using the discrepancies, errors were quantified in both datasets using chart review. The EHR extraction errors were significantly fewer than manual abstraction errors for PDA and laboratory values excluding neonates transferred from outside hospitals, but significantly greater for birth weight. Reasons for the observed errors are discussed. CONCLUSIONS: We show that an EHR not modified specifically for research purposes had discrepancy ranges comparable to a manually created database. We offer guidelines to minimize EHR extraction errors in future study designs. As EHRs become more research-friendly, electronic chart extractions should be more efficient and have lower error rates compared to manual abstractions.

Genetic variation in CYB5R3 is associated with methemoglobin levels in preterm infants receiving nitric oxide therapy.

BACKGROUND: In recent years, increasing numbers of preterm infants have been exposed to inhaled nitric oxide (iNO). This population has decreased methemoglobin (MetHb) reductase activity in their erythrocytes, which may increase the risk of MetHb toxicity. We sought to determine if genetic factors are associated with the observed variance in MetHb levels. METHODS: A population of 127 preterm infants was genotyped for five single-nucleotide polymorphisms (SNPs) in the CYB5A and CYB5R3 genes. iNO dose and levels of MetHb were obtained by chart abstraction. ANOVA was performed to identify genetic associations with MetHb levels. RESULTS: An association was found between the heterozygous genotype (GA) of rs916321 in the CYB5R3 gene and the mean of the first recorded MetHb levels in Caucasian infants (P = 0.01). This result remained significant after adjustment for the iNO dose (P = 0.009), gender (P = 0.03), multiple gestation (P = 0.03), birth weight (P = 0.02), and gestational age (P = 0.02). No significant associations were found with the other SNPs. CONCLUSION: We demonstrate a novel genetic association with neonatal MetHb levels. Identification of genetic risk factors may be useful in determining which preterm infants are most at risk of developing MetHb toxicity with the use of iNO.