Automated prioritization of sick newborns for whole genome sequencing using clinical natural language processing and machine learning.

BACKGROUND: Rapidly and efficiently identifying critically ill infants for whole genome sequencing (WGS) is a costly and challenging task currently performed by scarce, highly trained experts and is a major bottleneck for application of WGS in the NICU. There is a dire need for automated means to prioritize patients for WGS. METHODS: Institutional databases of electronic health records (EHRs) are logical starting points for identifying patients with undiagnosed Mendelian diseases. We have developed automated means to prioritize patients for rapid and whole genome sequencing (rWGS and WGS) directly from clinical notes. Our approach combines a clinical natural language processing (CNLP) workflow with a machine learning-based prioritization tool named Mendelian Phenotype Search Engine (MPSE). RESULTS: MPSE accurately and robustly identified NICU patients selected for WGS by clinical experts from Rady Children's Hospital in San Diego (AUC 0.86) and the University of Utah (AUC 0.85). In addition to effectively identifying patients for WGS, MPSE scores also strongly prioritize diagnostic cases over non-diagnostic cases, with projected diagnostic yields exceeding 50% throughout the first and second quartiles of score-ranked patients. CONCLUSIONS: Our results indicate that an automated pipeline for selecting acutely ill infants in neonatal intensive care units (NICU) for WGS can meet or exceed diagnostic yields obtained through current selection procedures, which require time-consuming manual review of clinical notes and histories by specialized personnel.

Omega-3 Fatty Acid Supplementation, Pro-Resolving Mediators, and Clinical Outcomes in Maternal-Infant Pairs.

Omega (n)-3 fatty acids are vital to neonatal maturation, and recent investigations reveal n-3 fatty acids serve as substrates for the biosynthesis of specialized pro-resolving lipid mediators (SPM) that have anti-inflammatory and immune-stimulating effects. The role SPM play in the protection against negative maternal-fetal health outcomes is unclear, and there are no current biomarkers of n-3 fatty acid sufficiency. We sought to ascertain the relationships between n-3 fatty acid intake, SPM levels, and maternal-fetal health outcomes. We obtained n-3 fatty acid intake information from 136 mothers admitted for delivery using a food frequency questionnaire and measured docosahexaenoic acid (DHA)-derived SPMs resolvin D1 (RvD1) and RvD2 in maternal and cord plasma. We found significantly elevated SPM in maternal versus cord plasma, and increased SPM levels were associated with at-risk outcomes. We also identified that increased DHA intake was associated with elevated maternal plasma RvD1 (p = 0.03; R² = 0.18) and RvD2 (p = 0.04; R² = 0.20) in the setting of neonatal intensive care unit (NICU) admission. These findings indicate that increased n-3 fatty acid intake may provide increased substrate for the production of SPM during high-risk pregnancy/delivery conditions, and that increased maternal plasma SPM could serve as a biomarker for negative neonatal outcomes.