HeartVar: An LLM-Assisted Tool for Clinical Classification of Variants in Cardiovascular Disease Cohorts
- 1Victor Chang Cardiac Research Institute
Abstract
Manual clinical DNA variant classification is the bottleneck of every clinical and research rare disease workflow. The process typically requires a curator to assemble evidence from numerous databases, weigh 28 criteria, reconcile competing evidence, and produce a defensible case for the final classification. Additionally, the framework used to assess variants is not static and successive addenda have revised individual criteria. The most complete and current evidence aggregators available are commercial platforms, which can limit researcher access. We present HeartVar, an open-source web tool that automates the evidence-gathering and interpretation steps of variant classification associated with cardiovascular disease. Given a gene, a variant, and clinical context, HeartVar queries 20 public databases in parallel and assigns ACMG/AMP criteria through a hybrid rule-based/large language model (LLM) approach. Criteria that can be resolved from structured data are computed programmatically, and only those requiring interpretation of unstructured evidence are passed to the LLM. HeartVar returns a classification, point score, per-criterion breakdown, clinical-narrative summary, and database annotations. Benchmarking of 106 expert-curated ClinGen variants showed HeartVar outperformed other curation tools, assigning the correct ACMG tier in 72% of cases. HeartVar demonstrates that an LLM constrained by a domain-specific prompt and grounded in structured evidence can produce variant interpretations of first-pass quality for a cardiovascular disease cohort; however, it is not intended to replace manual assessment by a qualified variant curator. The tool is freely available to use and hosted at www.heartvar.victorchang.edu.au.
Related
- A translational pipeline for classification of variants of uncertain significance to support gene therapy clinical trial in OTOF-related deafness
- Nomenclature, classification, and in-silico structural analysis of MSP1a variants of Anaplasma marginale
- Whole genome similarity provides a rapid, robust framework for classification of fungal taxa from the genus rank to intraspecies variants
- DONSON-Associated MISSLA with Co-Occurring p.Arg442Ter and p.Lys489Thr Variants: Longitudinal Clinical and Genomic Characterization
- From Monogenic Variants to Polygenic Risk Scores in Inherited Cardiomyopathies: Clinical Utility, Ancestry Gaps, and Future Implementation in Arab Populations
BibTeX
@misc{thompson2026heartvar,
title = {{HeartVar: An LLM-Assisted Tool for Clinical Classification of Variants in Cardiovascular Disease Cohorts}},
author = {J.-L. Thompson and D. Das and S. L. Dunwoodie and E. Giannoulatou},
howpublished = {bioRxiv},
year = {2026},
month = sep,
doi = {10.64898/2026.09.10.750569},
url = {https://www.biorxiv.org/content/10.64898/2026.09.10.750569v1},
note = {CC BY-NC},
}
RIS
TY - UNPB
TI - HeartVar: An LLM-Assisted Tool for Clinical Classification of Variants in Cardiovascular Disease Cohorts
AU - J.-L. Thompson
AU - D. Das
AU - S. L. Dunwoodie
AU - E. Giannoulatou
PY - 2026
DA - 2026/09/10
PB - bioRxiv
DO - 10.64898/2026.09.10.750569
UR - https://www.biorxiv.org/content/10.64898/2026.09.10.750569v1
AB - Manual clinical DNA variant classification is the bottleneck of every clinical and research rare disease workflow. The process typically requires a curator to assemble evidence from numerous databases, weigh 28 criteria, reconcile competing evidence, and produce a defensible case for the final classification. Additionally, the framework used to assess variants is not static and successive addenda have revised individual criteria. The most complete and current evidence aggregators available are commercial platforms, which can limit researcher access. We present HeartVar, an open-source web tool that automates the evidence-gathering and interpretation steps of variant classification associated with cardiovascular disease. Given a gene, a variant, and clinical context, HeartVar queries 20 public databases in parallel and assigns ACMG/AMP criteria through a hybrid rule-based/large language model (LLM) approach. Criteria that can be resolved from structured data are computed programmatically, and only those requiring interpretation of unstructured evidence are passed to the LLM. HeartVar returns a classification, point score, per-criterion breakdown, clinical-narrative summary, and database annotations. Benchmarking of 106 expert-curated ClinGen variants showed HeartVar outperformed other curation tools, assigning the correct ACMG tier in 72% of cases. HeartVar demonstrates that an LLM constrained by a domain-specific prompt and grounded in structured evidence can produce variant interpretations of first-pass quality for a cardiovascular disease cohort; however, it is not intended to replace manual assessment by a qualified variant curator. The tool is freely available to use and hosted at www.heartvar.victorchang.edu.au.
ER -