AI agent achieves 93.55% accuracy in genetic disease severity classification

Researchers have developed an AI agent that uses a combination of reasoning and retrieval-augmented generation to classify the severity of genetic diseases. This agent was trained on 10,211 Human Phenotype Ontology terms and utilized guidelines from the American College of Medical Genetics and the American College of Obstetricians and Gynecologists. The system achieved 93.55% accuracy at the phenotype level and demonstrated 95.2% concordance with an external gene list, offering a standardized and automated approach to genetic disease classification. AI

影响 This research could lead to more standardized and efficient genetic screening processes, potentially accelerating diagnosis and treatment for genetic conditions.

排序理由 The cluster contains an academic paper detailing a new AI model and its performance on a specific task. [lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.AI 阅读 →

• American College of Medical Genetics
• American College of Obstetricians and Gynecologists
• arXiv
• Human Phenotype Ontology
• Large Language Model Agents
• Mackenzie's Mission: The Australian Reproductive Carrier Screening Project
• PubMed

• 论文
• 产品

AI 生成摘要 · Google Gemini · 来自 1 个来源。 我们如何撰写摘要 →