314: Proactive Genomic Reanalysis at Boston Children’s: VS-NN, HPO NLP and DRAGEN find diagnoses in pediatric ES/GS

Rockowitz S et al., Human Genetics and Genomics Advances - Boston Children's Hospital used VS-NN, HPO NLP, and DRAGEN reprocessing in a proactive genomic reanalysis to identify candidate diagnoses in 2% of pediatric ES/GS cases. Key terms: genomic reanalysis, proactive reanalysis, VS-NN, HPO NLP, rare disease diagnostics. Study Highlights:The study deployed a centralized Proactive Genomic Reanalysis (PGR) workflow on a Boston Children’s Hospital pediatric ES/GS cohort integrated into the CRDC infrastructure. Key methods combined DRAGEN reprocessing, automated HPO extraction from EHR notes, CFA filtering on the GeneDx research platform and a VS-NN variant-scoring neural network followed by two-pass manual review. Applied to 2,144 previously unsolved cases, the pipeline flagged 310 variants, manual review prioritized 45 variants in 42 patients, and clinicians judged 33 variants to have high suspicion of disease causality, yielding ~2% candidate diagnostic rate. The work shows that institution-led, semi-automated reanalysis can produce clinically actionable findings while reducing reliance on clinician-initiated lab reanalysis, though it requires infrastructure for data transfer, confirmation and patient recontact. Conclusion:A centralized, semi-automated, clinically integrated Proactive Genomic Reanalysis workflow at Boston Children’s Hospital is feasible and identified candidate diagnostic variants in 2% of reviewed pediatric ES/GS cases, demonstrating a scalable model that can increase diagnoses while requiring institutional resources for confirmation and recontact. Music:Enjoy the music based on this article at the end of the episode. Article title:Scaling genomic reanalysis to unlock diagnoses and transform rare disease care First author:Rockowitz S Journal:Human Genetics and Genomics Advances DOI:10.1016/j.xhgg.2026.100582 Reference:Rockowitz S, Shao W, French C, Truong TK, Hagen J, McGonigle R, et al.; and Wendy K. Chung. Scaling genomic reanalysis to unlock diagnoses and transform rare disease care. Human Genetics and Genomics Advances. 2026;7:100582. https://doi.org/10.1016/j.xhgg.2026.100582. License:This episode is based on an open-access article published under the Creative Commons Attribution 4.0 International License (CC BY 4.0) - https://creativecommons.org/licenses/by/4.0/ Support:Base by Base – Stripe donations: https://donate.stripe.com/7sY4gz71B2sN3RWac5gEg00 Official website https://basebybase.com On PaperCast Base by Base you’ll discover the latest in genomics, functional genomics, structural genomics, and proteomics. Episode link: https://basebybase.com/episodes/proactive-genomic-reanalysis-bch QC:This episode was checked against the original article PDF and publication metadata for the episode release published on 2026-03-11. QC Scope:- article metadata and core scientific claims from the narration- excludes analogies, intro/outro, and music- transcript coverage: Audited the portion of the transcript describing the centralized Proactive Genomic Reanalysis (PGR) workflow, VS-NN AI scoring, NLP-based HPO extraction, CFA/DRAGEN pipelines, pilot results, and implementation challenges including data access and recontact.- transcript topics: Centralized Proactive Genomic Reanalysis (PGR) workflow; VS-NN variant scoring neural network; HPO NLP and phenotype matching; DRAGEN read mapping and CFA filtering; Two-pass manual review process; Pilot results: dataset size, variant counts, and diagnostic yield QC Summary:- factual score: 10/10- metadata score: 10/10- supported core claims: 6- claims flagged for review: 0- metadata checks passed: 4- metadata issues found: 0 Metadata Audited:- article_doi- article_title- article_journal- licens...