New AI framework HPOQuest aids rare-disease diagnosis

Researchers have developed HPOQuest, a novel framework designed to aid in the diagnosis of rare diseases by actively acquiring patient phenotypes. This training-free system starts with a limited set of observed symptoms and iteratively selects the most informative follow-up questions for clinicians. By updating disease rankings with confirmed phenotypes and refining question sets based on responses, HPOQuest has demonstrated significant improvements in diagnostic accuracy, with gains of up to 30% points at Recall@1 and 45% points at Recall@5 across benchmark cohorts. The framework highlights the potential of sequential phenotype acquisition to enhance rare-disease diagnosis from sparse initial clinical data. AI

IMPACT This framework could significantly improve diagnostic accuracy for rare diseases, potentially leading to earlier and more effective treatments.

RANK_REASON Publication of a research paper detailing a new AI framework for a specific application. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.AI →

• arXiv
• HPOQuest
• Hugging Face
• phenotype
• rare disease
• Recall@1
• Recall@5

• paper
• product

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →