Article
CommunityJev Benchmarks & Evaluations
Radiology Guideline-derived Decision Graph for Efficient Clinical Decision Support
arXiv paper introducing GDGraph, a guideline-derived decision graph framework that compiles radiology guidelines into an executable graph and has a System One model answer localized clinical questions, reporting 90.8% accuracy across 347 cases.
- Format
- Article
- Reading time
- 2 min
- Published by
- Community
- Added
- Oct 2026
Highlights
- Decouples guideline compilation from case evaluation using an LLM-built executable decision graph.
- System One accuracy improved from 57.3% to 90.8% across 347 radiology cases.
- Evaluated on renal cyst, adnexal mass, and thyroid nodule guidelines.
- Outperformed retrieval-augmented GPT-4o (80.1%) and graph-guided GPT-4o with chain-of-thought (82.7%).
- Deterministic traversal resolves Boolean logic, yielding a traceable decision path without task-specific training.
Questions about this entry
Short answers drawn from the linked project or page.
GDGraph (Guideline-derived Decision Graph) is a framework for radiological risk stratification and management planning. It targets the difficulty that clinical guideline criteria are spread across prose, tables, and cross-referenced definitions, which makes automated case evaluation hard.
During inference, a fast System One model answers localized clinical questions, while deterministic traversal resolves the Boolean logic of the compiled graph. This turns opaque single-pass predictions into a traceable decision path.
Across 347 cases spanning renal cyst, adnexal mass, and thyroid nodule guidelines, GDGraph improves System One accuracy from 57.3% to 90.8%.
The evaluation covers three guideline areas: renal cyst, adnexal mass, and thyroid nodule, across a total of 347 cases.
GDGraph's 90.8% accuracy exceeds retrieval-augmented GPT-4o at 80.1% and graph-guided GPT-4o with chain-of-thought at 82.7%, and the paper reports substantially lower latency and cost.
No. The abstract states the approach produces a traceable decision path without task-specific training, relying instead on guideline compilation plus a fast System One model at inference.
The abstract states that the source code will be available. No repository link or license is given in the provided material, so availability and terms are not yet confirmed.
More Jev resources like this
arXiv study applying Jev and Clef-Flash to manufacturing defect detection with as few as two reference images per class, including agentic refinement of text descriptions and probability calibration. Ships replication code, an R decisions package, and a no-code web app.
Jev Benchmarks & EvaluationsArticle#arxiv#calibration#classification
Community
Case study evaluating Jev 1.13.0 on time-series decision tasks, including classification, event type prediction, oil temperature direction, and stock movement, converting continuous forecasts into discrete decisions and scoring accuracy and AUC.
Jev Benchmarks & EvaluationsArticle#arxiv#evaluation#benchmark
Community
arXiv paper introducing PrimaCons, a four-axis benchmark measuring whether Jev gives consistent decisions when the same semantic state is expressed as different typed query primitives, plus the Cross-Primitive Residual Calibrator (CPRC) proposed to reduce that inconsistency.
Jev Benchmarks & EvaluationsArticle#arxiv#evaluation#calibration
Community
arXiv study comparing Jev 1.13 with Clef, Microsoft-Decision-1, Laya, GPT-6 Luna and GPT-6 Sol on 172 rheumatology exam questions and 70 diagnostic vignettes, reporting accuracy, calibration and language effects.
Jev Benchmarks & EvaluationsArticle#arxiv#evaluation#calibration
Community
Reference audit of typed decision models that measures what a returned probability licenses, comparing open-weight Laya checkpoints with Jev 1.13 over 190 exchangeable evaluations, locale coverage, drift, and explanation limits. Releases frozen answers, a datasheet, a promise check, and code.
Jev Benchmarks & EvaluationsArticle#arxiv#evaluation#calibration
Community
Evaluation of MedJev, an open System One model that runs locally on a laptop, across ten medical benchmarks for knowledge, diagnosis, and patient-level prediction on MIMIC IV and MIMIC IV ED, with a two-parameter recalibration method and a released evaluation harness.
Jev Benchmarks & EvaluationsArticle#arxiv#evaluation#calibration
Community
From the Jev guides
Original write-ups on what this entry is for.
From the Jev AI model community
Posts from builders shipping with Jev right now.