Provision and availability of genomic medicine services in Level IV neonatal intensive care units

NeoGx: Machine-Recommended Rapid Genome Sequencing for Neonates

Background

Genetic disease is common in the Level IV Neonatal Intensive Care Unit (NICU), but neonatology providers are not always able to identify the need for genetic evaluation. We trained a machine learning (ML) algorithm to predict the need for genetic testing within the first 18 months of life using health record phenotypes.

Methods

For a decade of NICU patients, we extracted Human Phenotype Ontology (HPO) terms from clinical text with Natural Language Processing tools. Considering multiple feature sets, classifier architectures, and hyperparameters, we selected a classifier and made predictions on a validation cohort of 2,241 Level IV NICU admits born 2020-2021.

Results

Our classifier had ROC AUC of 0.87 and PR AUC of 0.73 when making predictions during the first week in the Level IV NICU. We simulated testing policies under which subjects begin testing at the time of first ML prediction, estimating diagnostic odyssey length both with and without the additional benefit of pursuing rGS at this time. Just by using ML to accelerate initial genetic testing (without changing the tests ordered), the median time to first genetic test dropped from 10 days to 1 day, and the number of diagnostic odysseys resolved within 14 days of NICU admission increased by a factor of 1.8. By additionally requiring rGS at the time of positive ML prediction, the number of diagnostic odysseys resolved within 14 days was 3.8 times higher than the baseline.

Conclusions

ML predictions of genetic testing need, together with the application of the right rapid testing modality, can help providers accelerate genetics evaluation and bring about earlier and better outcomes for patients.

Implementation of rapid genomic sequencing in safety-net neonatal intensive care units: protocol for the VIrtual GenOme CenteR (VIGOR) proof-of-concept study

INTRODUCTION

Rapid genomic sequencing (rGS) in critically ill infants with suspected genetic disorders has high diagnostic and clinical utility. However, rGS has primarily been available at large referral centres with the resources and expertise to offer state-of-the-art genomic care. Critically ill infants from racial and ethnic minority and/or low-income populations disproportionately receive care in safety-net and/or community settings lacking access to state-of-the-art genomic care, contributing to unacceptable health equity gaps. VIrtual GenOme CenteR is a 'proof-of-concept' implementation science study of an innovative delivery model for genomic care in safety-net neonatal intensive care units (NICUs).

METHODS AND ANALYSIS

We developed a virtual genome centre at a referral centre to remotely support safety-net NICU sites predominantly serving racial and ethnic minority and/or low-income populations and have limited to no access to rGS. Neonatal providers at each site receive basic education about genomic medicine from the study team and identify eligible infants. The study team enrols eligible infants (goal n of 250) and their parents and follows families for 12 months. Enrolled infants receive rGS, the study team creates clinical interpretive reports to guide neonatal providers on interpreting results, and neonatal providers return results to families. Data is collected via (1) medical record abstraction, (2) surveys, interviews and focus groups with neonatal providers and (3) surveys and interviews with families. We aim to examine comprehensive implementation outcomes based on the Proctor Implementation Framework using a mixed methods approach.

ETHICS AND DISSEMINATION

This study is approved by the institutional review board of Boston Children's Hospital (IRB-P00040496) and participating sites. Participating families are required to provide electronic written informed consent and neonatal provider consent is implied through the completion of surveys. The results will be disseminated via peer-reviewed publications and data will be made accessible per National Institutes of Health (NIH) policies.

TRIAL REGISTRATION NUMBER

NCT05205356/clinicaltrials.gov.

Genomic medicine in neonatal care: progress and challenges

During the neonatal period, many genetic disorders present and contribute to neonatal morbidity and mortality. Genomic medicine-the use of genomic information in clinical care- has the potential to significantly reduce morbidity and mortality in the neonatal period and improve outcomes for this population. Diagnostic genomic testing for symptomatic newborns, especially rapid testing, has been shown to be feasible and have diagnostic and clinical utility, particularly in the short-term. Ongoing studies are assessing the feasibility and utility, including personal utility, of implementation in diverse populations. Genomic screening for asymptomatic newborns has also been studied, and the acceptability and feasibility of such an approach remains an active area of investigation. Emerging precision therapies, with examples even at the "n-of-1" level, highlight the promise of precision diagnostics to lead to early intervention and improve outcomes. To sustainably implement genomic medicine in neonatal care in an ethical, effective, and equitable manner, we need to ensure access to genetics and genomics knowledge, access to genomic tests, which is currently limited by payors, feasible processes for ordering these tests, and access to follow up in the clinical and research realms. Future studies will provide further insight into enablers and barriers to optimize implementation strategies.