Saved in:
Bibliographic Details
Main Authors: AlDin, Zilal Eiz, Wu, John, Fung, Jeffrey Paul, King, Jennifer, Watts, Mya, ONeill, Lauren, Cross, Adam Richard, Sun, Jimeng
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2601.11559
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908772266409984
author AlDin, Zilal Eiz
Wu, John
Fung, Jeffrey Paul
King, Jennifer
Watts, Mya
ONeill, Lauren
Cross, Adam Richard
Sun, Jimeng
author_facet AlDin, Zilal Eiz
Wu, John
Fung, Jeffrey Paul
King, Jennifer
Watts, Mya
ONeill, Lauren
Cross, Adam Richard
Sun, Jimeng
contents Despite rare diseases affecting 1 in 10 Americans, their differential diagnosis remains challenging. Due to their impressive recall abilities, large language models (LLMs) have been recently explored for differential diagnosis. Existing approaches to evaluating LLM-based rare disease diagnosis suffer from two critical limitations: they rely on idealized clinical case studies that fail to capture real-world clinical complexity, or they use ICD codes as disease labels, which significantly undercounts rare diseases since many lack direct mappings to comprehensive rare disease databases like Orphanet. To address these limitations, we explore MIMIC-RD, a rare disease differential diagnosis benchmark constructed by directly mapping clinical text entities to Orphanet. Our methodology involved an initial LLM-based mining process followed by validation from four medical annotators to confirm identified entities were genuine rare diseases. We evaluated various models on our dataset of 145 patients and found that current state-of-the-art LLMs perform poorly on rare disease differential diagnosis, highlighting the substantial gap between existing capabilities and clinical needs. From our findings, we outline several future steps towards improving differential diagnosis of rare diseases.
format Preprint
id arxiv_https___arxiv_org_abs_2601_11559
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle MIMIC-RD: Can LLMs differentially diagnose rare diseases in real-world clinical settings?
AlDin, Zilal Eiz
Wu, John
Fung, Jeffrey Paul
King, Jennifer
Watts, Mya
ONeill, Lauren
Cross, Adam Richard
Sun, Jimeng
Artificial Intelligence
Computation and Language
Machine Learning
Despite rare diseases affecting 1 in 10 Americans, their differential diagnosis remains challenging. Due to their impressive recall abilities, large language models (LLMs) have been recently explored for differential diagnosis. Existing approaches to evaluating LLM-based rare disease diagnosis suffer from two critical limitations: they rely on idealized clinical case studies that fail to capture real-world clinical complexity, or they use ICD codes as disease labels, which significantly undercounts rare diseases since many lack direct mappings to comprehensive rare disease databases like Orphanet. To address these limitations, we explore MIMIC-RD, a rare disease differential diagnosis benchmark constructed by directly mapping clinical text entities to Orphanet. Our methodology involved an initial LLM-based mining process followed by validation from four medical annotators to confirm identified entities were genuine rare diseases. We evaluated various models on our dataset of 145 patients and found that current state-of-the-art LLMs perform poorly on rare disease differential diagnosis, highlighting the substantial gap between existing capabilities and clinical needs. From our findings, we outline several future steps towards improving differential diagnosis of rare diseases.
title MIMIC-RD: Can LLMs differentially diagnose rare diseases in real-world clinical settings?
topic Artificial Intelligence
Computation and Language
Machine Learning
url https://arxiv.org/abs/2601.11559