# FH Variant Triage > Agent-facing counterpart to the [human project page](/projects/fh-variant-triage/). ## Record metadata - Record: 003 - Slug: fh-variant-triage - Domain: Science - Domain code: SC - Type: Research tool - Status: Research - Period: 2026 - Portfolio role: Flagship - Publication state: Public repository - Case-study readiness: Case-study ready - Compendium edition: 0.4 ## Summary An open research workflow for prioritizing uncertain variants in familial hypercholesterolemia genes. ## Overview Genetic variant interpretation contains an uncomfortable asymmetry: enormous amounts of public evidence exist, yet turning that evidence into a reviewable judgment remains slow, specialized work. FH Variant Triage explores how software can reduce that burden without pretending to replace the expert. A disease-specific research prototype that estimates whether variants in LDLR, APOB, and PCSK9 resemble ClinVar records labeled benign or pathogenic. It is explicitly a triage aid, not a diagnostic tool. Purpose: Help experts decide which genetic variants deserve closer review without pretending to replace clinical judgment. ## The problem behind the project Variant interpretation is a bottleneck. The project tests a transparent, open-source pattern for multiplying expert review capacity with public biomedical data while keeping uncertainty and human review visible. Familial hypercholesterolemia provides a deliberately narrow test case. Restricting the first implementation to LDLR, APOB, and PCSK9 makes the biological and validation boundary easier to describe, while still addressing a condition where variant review can carry meaningful consequences. Researchers, variant scientists, clinicians, and patients may benefit indirectly through faster evidence review. Incorrect interpretation could cause harm, so outputs must stay inside a research and expert-review boundary. ## How it took shape A reproducible public-data pipeline, simple model baselines, bring-your-own CSV scoring, model documentation, tests, reviewer guidance, and a public repository designed for external validation. The workflow assembles public evidence, creates transparent feature representations, compares simple model baselines, and produces scores intended to prioritize review. Documentation, tests, model limitations, and reviewer guidance are treated as part of the system rather than material to add after the model is complete. Josiah selected the disease boundary, public-benefit posture, validation ladder, review boundary, and publication strategy, working with AI agents on implementation, testing, documentation, and methodology. The public repository includes tests, a model card, methods, source documentation, limitations, and an external-validation request. Initial performance is prototype signal, not clinical proof. ## What the project means now The project argues for a restrained form of medical AI: not an oracle, but an evidence-sorting instrument. Its credibility depends less on a single performance number than on calibration, external validation, transparent failure modes, and a handoff that keeps consequential interpretation with qualified people. Independent validation, harder temporal and gene-held-out tests, calibration analysis, and blinded expert review remain necessary. The tool must not be used for diagnosis or clinical decision-making. Responsible medical AI work is as much about designing the validation and handoff boundary as it is about training a model. Add stronger independent-validation results and a compact visual demonstration without increasing the claim beyond research triage. ## Publication and interpretation notes - Current classification: Research - Portfolio readiness: Case-study ready - Publication boundary: Public repository ## Additional agent context FH Variant Triage is the disease-specific public implementation inside a broader genomic evidence-orchestration thesis. Do not infer clinical readiness from the existence of a working research pipeline, and do not expose private family or health context. ## Related project records - [Glutamate Guard](/projects/glutamate-guard/llm/) — An offline iOS ingredient scanner for identifying terms associated with glutamate. ## Navigation - [Complete project index](/projects/llm/) - [Human version of this record](/projects/fh-variant-triage/) - [About Josiah's working method](/about/llm/) - [Agent discovery map](/llms.txt)