About

Edgar J. Hernandez, PhD, is a Research Assistant Professor in the Department of Biomedical Informatics at the University of Utah. He is a multidisciplinary researcher with a passion for bridging genomics and clinical outcomes. His expertise lies at the intersection of biostatistics, artificial intelligence (AI), and predictive tools. His research involves developing innovative methods that leverage electronic health record (EHR) data for personalized risk predictions, collaborating with consortia and industry partners to apply probabilistic graphical models and machine learning approaches to quantify risk and classify clinical outcomes. Hernandez contributes to cutting-edge tools for diagnosing rare genetic diseases using whole exome sequencing (WES) and whole genome sequencing (WGS), and is actively involved in multi-omics research, particularly transcriptomics and metagenomics analysis, to uncover molecular signatures during acute phases of multisystem inflammatory syndrome in children (MIS-C). His background includes a Bachelor's degree in Biology from Universidad Nacional de Colombia and a PhD in Ecology, Systematics, and Evolution from the University of Missouri, with extensive experience in statistical and bioinformatics skills, evolutionary biology, ecological models, and human genetics. His career goal is to utilize bioinformatics to improve the utilization of genomic and sequence information to enhance human health and disease therapy.

Research topics

• Computer Science
• Biology
• Medicine
• Pathology
• Artificial Intelligence
• Genetics
• Computational biology
• Internal medicine
• Psychiatry
• Database
• Environmental health
• Cell biology
• Data science
• Endocrinology
• Bioinformatics
• Biochemistry

Selected publications

• Quantifying lifetime risk for 1,401 infectious diseases across the diabetes spectrum using a Bayesian approach

  BMC Medicine · 2026-02-07

  articleOpen accessSenior author

  BACKGROUND: While diabetes-related complications have been widely investigated, the burden of infectious diseases across the diabetes spectrum remains relatively understudied. METHODS: We developed a Bayesian approach to compare infection risk across 9,476 patients with type 1 diabetes (T1D), 74,270 with type 2 diabetes (T2D), and 32,095 with prediabetes. RESULTS: Patients with T1D, T2D, and prediabetes had multifold increased risk for all organ system- and pathogen-based composite infection outcomes. We also quantified risk for 1,401 individual infection outcomes, finding increased risk for most infections among patients with either T1D, T2D, or prediabetes. Patients had increased risk for well-established diabetes-associated infections (e.g., mucormycosis) and less commonly associated infections (e.g., West Nile Virus encephalitis). Finally, we found disparities in risk across sociodemographic subgroups (i.e., age, sex, ethnicity, ancestry, and insurance status). CONCLUSIONS: Our comprehensive findings advance previous research by quantifying risk for wide-ranging infection outcomes across diverse patients with T1D, T2D, and prediabetes through an innovative Bayesian approach.

  PublisherDOI

• Global Footprint of the Multidrug Resistance Island Ec17R and Resistance Gene Co-Occurrence in Pathogenic <i>Escherichia coli</i> Isolates

  bioRxiv (Cold Spring Harbor Laboratory) · 2025-10-11

  preprintOpen access

  ABSTRACT Multidrug resistant (MDR) bacterial pathogens are a major threat to global health, limiting treatment options for common infections. Extraintestinal Pathogenic Escherichia coli (ExPEC), a leading cause of bloodstream and urinary tract infections (UTIs), are often resistant to one or more antibiotic classes. Previously, we identified a clonal group of ExPEC strains (P1A) that persisted over a 5-year period from 2012 to 2016 within a female patient who suffered from frequent recurrent UTIs. A subset of these isolates carried a plasmid-borne MDR island (Ec17R) harboring 17 resistance genes. Sampling of fecal and urine samples in 2019 indicated that the patient remained colonized with the P1A lineage, including Ec17R-positive strains, over 7 years after collection of the first P1A isolates in 2012. Highlighting the public health relevance and mobility of Ec17R, we found that Ec17R-like islands are globally distributed across diverse bacterial species from various environmental, agricultural, and clinical sources, including multiple ExPEC isolates from local pediatric patients. By applying clustering approaches and Bayesian network modeling to 267 pediatric ExPEC isolates, we found that functionally distinct classes of resistance genes (including several heavy metal resistance genes) have a high probability of co-occurrence, possibly reflecting carriage within MDR islands like Ec17R. Finally, we observed that strains within the P1A lineage are recalcitrant to antibiotics for which they have no known resistance mechanisms, suggesting that these pathogens have means beyond their formidable array of resistance genes to survive within a host for years despite the administration of numerous, robust antimicrobial treatments. SIGNIFICANCE Multidrug resistance (MDR) in bacteria is a growing global health crisis that compromises our ability to treat routine infections. In this study, we investigated a clonal lineage of pathogenic Escherichia coli that persisted for many years in a patient with recurrent urinary tract infections. A subset of the E. coli strains carried by this patient possessed a large genomic island encoding resistance to multiple antibiotic classes. This MDR island is globally distributed across diverse bacterial species and niches, from clinical samples to agricultural and environmental reservoirs. Using probabilistic modeling of nearly 300 clinical isolates, we identified networks of resistance gene co-occurrence that link antibiotic and heavy metal resistance, suggesting the potential for environmental pollutants to contribute to MDR dissemination. Notably, patient-derived isolates also survived certain clinically relevant antibiotic treatments despite lacking known resistance mechanisms, highlighting tolerance and persistence as important, often overlooked drivers of therapeutic failure.

  PublisherOA PDFDOI

• MPSE identifies newborns for whole genome sequencing within 48 h of NICU admission

  npj Genomic Medicine · 2025-06-12

  articleOpen access

  Identifying critically ill newborns who will benefit from whole genome sequencing (WGS) is difficult and time-consuming due to complex eligibility criteria and evolving clinical features. The Mendelian Phenotype Search Engine (MPSE) automates the prioritization of neonatal intensive care unit (NICU) patients for WGS. Using clinical data from 2885 NICU patients, we evaluated the utility of different machine learning (ML) classifiers, clinical natural language processing (CNLP) tools, and types of Electronic Health Record (EHR) data to identify sick newborns with genetic diseases. Our results show that MPSE can identify children most likely to benefit from WGS within the first 48 h after NICU admission, a critical window for maximally impactful care. Moreover, MPSE provided stable, robust means to identify these children using many combinations of classifiers, CNLP tools, and input data types-meaning MPSE can be used by diverse health systems despite differences in EHR contents and IT support.

  PublisherOA PDFDOI

• The Utah NeoSeq Project: a collaborative multidisciplinary program to facilitate genomic diagnostics in the neonatal intensive care unit

  npj Genomic Medicine · 2025-03-22 · 1 citations

  articleOpen access

  Rapid genomic diagnostics in the Neonatal Intensive Care Unit represents a paradigm shift in medicine with increasing evidence of the utility of early diagnosis, impacting management. The goal of the Utah NeoSeq Project was to implement and evaluate a multidisciplinary and longitudinal rapid sequencing program while transitioning to CLIA-certified sequencing. Enrollment of 65 infants resulted in 26 (40%) with a diagnostic variant(s) and 7 (11%) harboring a strong candidate. This includes re-analyses resulting in four additional diagnoses. Parental surveys indicated that 7% (4/59) of parents had a decisional conflict after consent, and 3% (2/59) experienced decisional regret after the results. Fifty-two provider surveys were conducted. Seventy-nine percent (41/52) of results and 86% (19/22) of diagnostic results were "very useful" or "useful" and associated with management changes. The NeoSeq Project demonstrates that a multidisciplinary collaborative approach to diagnosis is feasible. We have developed a generalizable, collaborative protocol that addresses the need for expedited genetic evaluation with emerging technologies.

  PublisherOA PDFDOI

• AI-based analysis of fetal growth restriction in a prospective obstetric cohort quantifies compound risks for perinatal morbidity and mortality and identifies previously unrecognized high risk clinical scenarios

  BMC Pregnancy and Childbirth · 2025-01-29 · 7 citations

  articleOpen access

  BACKGROUND: Fetal growth restriction (FGR) is a leading risk factor for stillbirth, yet the diagnosis of FGR confers considerable prognostic uncertainty, as most infants with FGR do not experience any morbidity. Our objective was to use data from a large, deeply phenotyped observational obstetric cohort to develop a probabilistic graphical model (PGM), a type of "explainable artificial intelligence (AI)", as a potential framework to better understand how interrelated variables contribute to perinatal morbidity risk in FGR. METHODS: Using data from 9,558 pregnancies delivered at ≥ 20 weeks with available outcome data, we derived and validated a PGM using randomly selected sub-cohorts of 80% (n = 7645) and 20% (n = 1,912), respectively, to discriminate cases of FGR resulting in composite perinatal morbidity from those that did not. We also sought to identify context-specific risk relationships among inter-related variables in FGR. Performance was assessed as area under the receiver-operating characteristics curve (AUC). RESULTS: Feature selection identified the 16 most informative variables, which yielded a PGM with good overall performance in the validation cohort (AUC 0.83, 95% CI 0.79-0.87), including among "N of 1" unique scenarios (AUC 0.81, 0.72-0.90). Using the PGM, we identified FGR scenarios with a risk of perinatal morbidity no different from that of the cohort background (e.g. female fetus, estimated fetal weight (EFW) 3-9th percentile, no preexisting diabetes, no progesterone use; RR 0.9, 95% CI 0.7-1.1) alongside others that conferred a nearly 10-fold higher risk (female fetus, EFW 3-9th percentile, maternal preexisting diabetes, progesterone use; RR 9.8, 7.5-11.6). This led to the recognition of a PGM-identified latent interaction of fetal sex with preexisting diabetes, wherein the typical protective effect of female fetal sex was reversed in the presence of maternal diabetes. CONCLUSIONS: PGMs are able to capture and quantify context-specific risk relationships in FGR and identify latent variable interactions that are associated with large differences in risk. FGR scenarios that are separated by nearly 10-fold perinatal morbidity risk would be managed similarly under current FGR clinical guidelines, highlighting the need for more precise approaches to risk estimation in FGR.

  PublisherOA PDFDOI

• Explainable artificial intelligence for stroke risk stratification in atrial fibrillation

  European Heart Journal - Digital Health · 2025-03-22 · 6 citations

  reviewOpen access

  Current risk stratification tools can limit the optimal implementation of new and emerging therapies for patients with heart rhythm disorders. For example, stroke prevention treatments have outpaced means for stroke risk stratification for patients with atrial fibrillation (AF). Artificial intelligence (AI) techniques have shown promise for improving various tasks in cardiovascular medicine. Here, we explain key concepts in AI that are central to using these technologies for better risk stratification, highlighting one approach particularly well suited to the task of portable, personalized risk stratification-probabilistic graphical models (PGMs). Probabilistic graphical models can empower physicians to ask and answer a variety of clinical questions, which we demonstrate using a preliminary model of AF-related stroke risk among 1.6 million patients within the University of Utah Health System. This example also highlights the ability of PGMs to combine social determinants of health and other non-traditional variables with standard clinical and demographic ones to improve personalized risk predictions and address risk factor interactions. When combined with electronic health data, these computational technologies hold great promise to empower personalized, explainable, and equitable risk assessment.

  PublisherOA PDFDOI

• Extracellular matrix and cytoskeletal reverse remodeling pathways are key drivers of myocardial recovery following left ventricular assist device therapy

  bioRxiv (Cold Spring Harbor Laboratory) · 2025-11-08

  preprintOpen access

  Abstract Transcriptomic changes in heart failure (HF) patients prior to and following left ventricular assist device (LVAD) support have been extensively studied. Recent studies focused on understanding DNA methylation changes in patients with cardiovascular diseases (CVD) and the role of circulating markers of DNA methylation as clinical predictors of the risk of CVD related morbidity and mortality. In this study, we used paired (pre- and post-LVAD) myocardial samples to examine changes in DNA methylation alongside RNA and protein expression. Our data suggests that patients with no improvement in cardiac function after LVAD therapy, despite showing an improvement in energy production (increased β-oxidation of fatty acid) exhibited persistent activation of profibrotic signaling, increased collagen deposition and cytoskeletal disarray evident from abnormal increase in sarcomeric distance following LVAD support. Contrarily, patients with improvement in cardiac function after LVAD therapy showed activation of pro-inflammatory signaling, collagen degradation and myogenesis. Both RNA sequencing and western blot data showed increased COL1A1 and decreased TPPP3 in post-NR thereby suggesting increased fibrosis and disrupted cytoskeletal signaling as potential barriers to myocardial recovery. Additionally, responders to LVAD therapy showed a significant reversal in myocardial interstitial fibrosis with a preserved sarcomeric architecture. Mice model of HF and recovery also confirmed our human findings, with reduced fibrotic signaling and improved cytoskeletal remodeling signaling observed in mice that showed improvement in cardiac function compared to mice with HF. Overall, our data suggests that altering extracellular matrix regulation and cytoskeletal signaling pathways may contribute to myocardial recovery. Further studies targeting these pathways are required to identify new HF therapeutic targets.

  PublisherOA PDFDOI

• Regional variation in parental stroke history between Jeju Island and mainland Korea

  medRxiv · 2025-09-12

  preprintOpen accessCorresponding

  Abstract Purpose Despite having one of the highest prevalences of hypertension in Korea, Jeju Island maintains the lowest rate of stroke mortality nationwide. This paradoxical cardiovascular health profile raises questions about the underlying factors contributing to differential stroke risk in the Jeju population. Methods We used health data from the Korea National Health and Nutrition Examination Survey (KNHANES) to investigate whether differences in regional stroke outcome can be explained by known environmental and behavioral contributors to increased cerebrovascular health risk. We applied logistic regression with backward feature selection and cross-validation to identify predictors of parental history of stroke. Results We found that individuals from Jeju Island were significantly less likely to report a parental history of stroke compared to individuals from Seoul. This finding persisted even after adjusting for known cerebrovascular risk factors, including age, sex, SBP, antihypertensive use, dietary sodium intake, BMI, and hematocrit. Conclusions Our results suggest that other hidden factors may contribute to protection against cerebrovascular disease. Given the unique population demographic history of the island, these findings prompt future analyses to explore whether the genetic variation of Jeju contributes meaningfully to stroke resilience at the population level.

  PublisherOA PDFDOI

• Sex Dependent Molecular Changes In Heart Failure Patients On Lvad Support: Implications On Myocardial Recovery

  Journal of Cardiac Failure · 2025-01-01

  article
  PublisherDOI

• Genome sequencing is critical for forecasting outcomes following congenital cardiac surgery

  Nature Communications · 2025-07-10 · 4 citations

  articleOpen access

  While exome and whole genome sequencing have transformed medicine by elucidating the genetic underpinnings of both rare and common complex disorders, its utility to predict clinical outcomes remains understudied. Here, we use artificial intelligence (AI) technologies to explore the predictive value of whole exome sequencing in forecasting clinical outcomes following surgery for congenital heart defects (CHD). We report results for a prospective observational cohort study of 2,253 CHD patients from the Pediatric Cardiac Genomics Consortium with a broad range of complex heart defects, pre- and post-operative clinical variables and exome sequencing. Damaging genotypes in chromatin-modifying and cilia-related genes are associated with an elevated risk of adverse post-operative outcomes, including mortality, cardiac arrest and prolonged mechanical ventilation. The impact of damaging genotypes is further amplified in the context of specific CHD phenotypes, surgical complexity and extra-cardiac anomalies. The absence of a damaging genotype in chromatin-modifying and cilia-related genes is also informative, reducing the risk for some adverse postoperative outcomes. Thus, genome sequencing enriches the ability to forecast outcomes following congenital cardiac surgery.

  PublisherOA PDFDOI

Frequent coauthors

• Mark Yandell

  University of Utah

  40 shared

• Martin Tristani‐Firouzi

  University of Utah

  17 shared

• Umang Swami

  University of Utah

  14 shared

• Roberto Nussenzveig

  Huntsman Cancer Institute

  14 shared

• Benjamin L. Maughan

  Huntsman Cancer Institute

  12 shared

• Barry Moore

  University of Utah

  12 shared

• Bushra Gorsi

  University of Utah

  10 shared

• Nicolas Sayegh

  Huntsman Cancer Institute

  10 shared

Education

• B.S., Biology

  Universidad Nacional de Colombia

• Ph.D., Ecology, Systematics, and Evolution

  University of Missouri