Skip to content

RareDx: Controlled Knowledge Integration and Graph-Grounded Policy Optimization for Rare-Disease Diagnosis

Sep 2026 · 0 citations · 37 references
Computer Science

TL;DR

Results indicate that structured medical knowledge can turn a compact model into a competitive diagnostic ranker across heterogeneous long-tail settings in clinical practice.

Abstract

Rare-disease diagnosis is a long-tail reasoning problem: phenotypes are incomplete, individual disorders are sparsely documented, and relevant evidence is distributed across ontologies, gene annotations, and biomedical text. Language models consequently favor common conditions, miss rare candidates, or produce plausible but invalid names. We introduce RareDx, which couples controlled evidence use with knowledge-graph-grounded policy optimization. RareDx-Harness normalizes heterogeneous records into one ranked-diagnosis task and compares direct inference, static retrieval, adaptive tools, and structured phenotype-gene-disease reasoning over a shared knowledge layer. The training pipeline combines Top-10 post-training with RareDx-KGPO, our knowledge-graph-grounded policy optimization method. Its reward projects predictions into a canonical disease graph and integrates curated graded relevance, ontology proximity, biomedical similarity, and phenotype consistency. Vocabulary and output-budget constraints prevent dense partial credit from rewarding fabricated or overlong differentials. Across eight benchmarks, the complete RareDx system centered on Qwen3.5-9B reaches 38.34 macro Hit@10, 1.60 points above GPT-5.5 under the archived protocol; a disjoint validation-selection audit retains a 6.80-point routing gain over Direct on held-out cases. The 27B system reaches 23.53/36.56/40.76 at Hit@1/5/10. Controlled ablations show that retrieval is not uniformly helpful and that controlled routing is central to the gain. These results indicate that structured medical knowledge can turn a compact model into a competitive diagnostic ranker across heterogeneous long-tail settings in clinical practice.

View source

Similar papers

#natural language process... Preprint Aug 2026

Surgical Alignment in Knowledge Graph Training for Clinical Diagnosis with Large Language Models

A systematic study spanning five KG task formulations, three training paradigms, two KGs, and three base LLMs finds that at the task level, all paradigms improve over the non-finetuned baseline, but methods with comparable in-domain accuracy show substantially different knowledge transfer behavior.

Saksham Khatwani, He Cheng, M. Afshar et al. · 0 citations
Open access Sep 2026

An annotation-overlap-flagged rare-disease gene-prioritisation benchmark and PMC index recipe

Benchmarks for rare-disease gene prioritisation are assembled from published clinical cases. Those cases often come from the same publications used to build knowledge-base (“curated”) tools, so a curated tool can be scored on its own source literature. This resource makes that circularity measurable. We release a strat...

Johanna Angulo, Héctor Espinós-Morató, Víctor Yeste · 0 citations

Training-Free Clinical Reasoning through Medical Ontologies and Cognitive Mapping: A Symbolic-Probabilistic Knowledge Graph Framework

Most clinical prediction systems learn patient-variable-outcome associations; we investigate a training-free diagnostic paradigm mapping patient observations to explicit medical knowledge. CKG Reasoner integrates candidate-specific Evidence Feature Nodes, patient-reference matching, a bounded Information Gate, knowledg...

Surajit Das · 0 citations
#natural language process... Preprint Sep 2026

Learning to Fuse LLMs with Ontology Rankers for Rare-Disease Diagnosis

Ontology rankers remain useful for rare-disease diagnosis because each candidate can be traced to matched patient phenotypes. Large language models (LLMs) can generate differential diagnoses from the same patient description, but their predictions lack an equally clear evidence trail. Rather than asking which system sh...

Zhao-Yang Jiang, Zhizhong Fu, Yunsoo Kim et al. · 0 citations
Conference Open access Sep 2026

Structure-Aware Contrastive Learning for Biomedical Embeddings: Bridging the Gap Between HPO and Clinical Literature

A new embedding adaptation procedure is defined whose fine-tuning approach is guided by a novel "Disease-Overlap" similarity measure, which prioritizes clinical co-occurrence of phenotypes over taxonomic distance, and optimizes the embedding space using AnglE Loss to mitigate gradient saturation.

Jose L. Mellina Andreu, Alejandro Cisterna García, Juan A. Botía · 0 citations
Aug 2026

A Knowledge Graph–Driven Multimodal Framework for Drug–Disease Association Prediction

KGDDA is proposed, a multimodal framework designed for drug-disease association prediction that synergistically integrates KGs with medical ontologies, enabling the adaptive capture of intricate drug-disease interactions.

Qi-Chang Zhao, Qiao Ling, Muhammad Habibulla Alamin et al. · 0 citations

Related blog posts

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.