An agentic system for rare disease diagnosis with traceable reasoning.

WHY IT MATTERS

Patients with rare diseases spend an average of 5+ years seeking diagnosis with repeated misdiagnoses; DeepRare could dramatically shorten this timeline by providing doctors with AI-powered diagnostic support that integrates genetic and phenotype data.

Researchers created DeepRare, a computer system that helps doctors diagnose rare diseases faster and more accurately. The system uses artificial intelligence to analyze patient information like symptoms, genetic test results, and medical history to suggest possible diagnoses. This could help patients avoid the long 'diagnostic odyssey' where they see many doctors over years before getting a correct diagnosis.

An agentic system for rare disease diagnosis with traceable reasoning. Abstract: Rare diseases affect more than 300 million people worldwide 1-3 , yet timely and accurate diagnosis remains an urgent challenge 1,3-5 . Patients often endure a prolonged 'diagnostic odyssey' exceeding 5 years, marked by repeated referrals, misdiagnoses and unnecessary interventions, leading to delayed treatment and substantial emotional and economic burden 4,5 . Here we present DeepRare-a multi-agent system for rare disease differential diagnosis decision support 6-8 powered by large language models, integrating more than 40 specialized tools and up-to-date knowledge sources. DeepRare processes heterogeneous clinical inputs, including free-text descriptions, structured human phenotype ontology terms and genetic testing results to generate ranked diagnostic hypotheses with tra Authors: Zhao et al. Journal: Nature MeSH: Rare Diseases, Humans, Diagnosis, Differential, Phenotype