A Versatile AI Agent for Rare Disease Diagnosis and Risk Gene Prioritization

2026-05-07

AI Summary

This study addresses the challenges in rare disease diagnosis—namely, prolonged diagnostic workflows, low accuracy, and ambiguous prioritization of candidate risk genes—by introducing Hygieia, a multimodal AI agent system. Hygieia employs a routing-driven architecture that integrates phenotypic data, genomic information, and clinical records, augmented with knowledge-enhanced reasoning and gene–phenotype association modeling to enable precise diagnosis and risk gene prioritization. The system outputs confidence scores to support clinical decision-making, effectively mitigating hallucinations and tailoring diagnostic strategies to specific diseases. Notably, it incorporates interpretability into gene prioritization for the first time. Evaluated across multiple benchmarks, Hygieia significantly outperforms existing methods, achieving 12%–60% higher diagnostic accuracy than clinicians and receiving validation from medical experts at Yale and Duke–NUS, demonstrating strong potential for real-world clinical deployment.

Abstract

Accurate and timely diagnosis is essential for effective treatment, particularly in the context of rare diseases. However, current diagnostic workflows often lead to prolonged assessment times and low accuracy. To address these limitations, we introduce Hygieia, a multi-modal AI agent system designed to support precision disease diagnosis by integrating diverse data sources, including phenotypic features, genetic profiles, and clinical records. Hygieia features a router-based and knowledge-enhanced framework that mitigates hallucination and tailors diagnostic strategies to different disease categories. Notably, it prioritizes risk-related genomic factors for rare diseases and provides confidence scores to assist clinical decision-making. We conducted a comprehensive evaluation demonstrating that Hygieia achieves state-of-the-art performance across multiple diagnostic benchmarks. In collaboration with clinical experts from Yale School of Medicine and Duke-NUS Medical School, we further validated its practical utility by showing (1) Hygieia's superior diagnostic performance compared to physicians with an improvement from 12%-60% and (2) its effectiveness in assisting clinicians with medical records for handling real-world cases. Our findings indicate that Hygieia not only enhances diagnostic accuracy and interpretability but also significantly reduces clinician workload, highlighting its potential as a valuable tool in clinical decision support systems.

Problem

• rare disease diagnosis
• diagnostic accuracy
• clinical decision support
• risk gene prioritization
• phenotypic features

Innovation

• multi-modal AI agent
• rare disease diagnosis
• risk gene prioritization
• knowledge-enhanced framework
• clinical decision support