A specialized reasoning large language model for accelerating rare disease diagnosis: a randomized AI physician assistance trial

Source

• Source name: arXiv
• Source kind: paper
• Authors / organization: Haichao Chen, Songchi Zhou, Zhengyun Zhao, Shikai Hu, Xianghong Jin, Hongwei Ji, Li He, Shuli Li, Yiming Qin, Xin Tan, Runfeng Shi, Yih Chung Tham, Jiaye Zhu, Ye Li, Ye Jin, Longhao Cao, Dawei Li, Honghan Wu, Hongqiu Gu, Guanqiao Li, Tudor Groza, Chunying Li, Dian Zeng, Weihong Yu, Gareth Baynam, Saumya Shekhar Jamuar, Min Shen, Shuyang Zhang, Bin Sheng, Sheng Yu, Tien Yin Wong
• Venue: arXiv: cs.AI
• Published: 2026-06-23
• Collected: 2026-06-24
• URL: http://arxiv.org/abs/2606.24510v1
• PDF: https://arxiv.org/pdf/2606.24510v1
• DOI: UNKNOWN

Plain-Language Brief

A new open-source language model called RaDaR (Rare Disease navigatoR) has been developed to aid in the diagnosis of rare diseases. The model was trained on a combination of public free-text cases and synthetic cases, and it performed better than other evaluated models across various benchmarks and validation centers. In a retrospective cohort, RaDaR helped diagnose rare diseases before clinical suspicion in over 60% of cases, potentially reducing diagnosis time by about 1.87 months. In a randomized trial, using RaDaR improved physician's ability to diagnose rare diseases by approximately 21.44%.

What the Document Says

• RaDaR is an open-source language model for rare disease diagnosis.
• RaDaR was trained with 49,170 public free-text cases and 104,666 synthetic cases.
• RaDaR showed the best performance among evaluated models across various benchmarks and validation centers.
• In a retrospective cohort, RaDaR helped diagnose rare diseases before clinical suspicion in 61.06% of cases.
• Potential lead time for diagnosis with RaDaR is 1.87 months in the retrospective cohort.
• In a randomized physician-assistance trial, RaDaR improved physicians' rare-disease diagnostic accuracy by 21.44% compared to internet search alone.
• Synthetic-data ablations suggest that phenotype-anchored narratives provide useful training signal for long-tail rare diseases.

Key Concepts Mentioned

• Rare disease diagnosis
• Language model
• Artificial Intelligence
• Retrospective cohort
• Randomized trial
• Synthetic data

Claims Made by the Document

• RaDaR is an effective tool for rare disease diagnosis.
• RaDaR improves physicians' ability to diagnose rare diseases.
• Phenotype-anchored narratives provide useful training signal for long-tail rare diseases.

Evidence Used

• Performance on various benchmarks and validation centers
• Results from retrospective cohort and randomized physician-assistance trial
• Synthetic data ablations

Methods / Approach

UNKNOWN

Limitations Stated by the Authors

UNKNOWN

Limitations Noted by the Agent

Agent interpretation — not from the source.

UNKNOWN

Open Questions

UNKNOWN

Notes for Future Q&A

May include interpretation. Labeled where it does.

UNKNOWN

Raw Abstract / Excerpt

Rare diseases affect millions of individuals worldwide, yet timely diagnosis remains a major public health challenge due to scarcity of specialized clinical expertise. While large language models (LLMs) show promise to support rare disease diagnosis, current models are constrained by insufficient clinical deployability, limited clinically grounded evidence, and scarcity of training data. Here we present RaDaR (Rare Disease navigatoR), an open-source, compact reasoning LLM (32B parameters) for rare disease diagnosis. RaDaR was trained with 49,170 publicly available free-text cases and 104,666 synthetic cases with reasoning-enhanced training. RaDaR showed the strongest performance among evaluated open-source models, including the 671B DeepSeek-R1, across public benchmarks and four external validation centers. In a retrospective cohort, RaDaR prioritized the final diagnosis before documented clinical suspicion in 61.06 percent of cases, corresponding to a potential lead time of 1.87 months and 50.18 percent of the within-center interval. In a randomized physician-assistance trial, RaDaR assistance improved physicians' rare-disease diagnostic accuracy by 21.44 percentage points compared with internet search alone. Synthetic-data ablations suggested that phenotype-anchored narratives provide useful training signal for long-tail rare diseases, with a monotonic scaling trend within the tested data range. Together, RaDaR and its development and validation framework provide a deployable rare-disease reasoning model and a reproducible development framework for diagnostic AI under data scarcity.