CLOZE: AI that grows medical knowledge from clinical notes — no training needed
Meet CLOZE
Clinical notes are full of real-world details, but they’re hard for computers to use. CLOZE is a new AI framework that reads these notes to expand medical ontologies—think of them as maps of diseases, symptoms, and their relationships.
- Zero-shot: works without extra training or labeled data.
- Finds new medical concepts and places them in the right hierarchy.
- Privacy-first: automatically removes protected health information (PHI).
- Accurate and scalable, powered by large language models.
Why it matters: richer ontologies help researchers and health IT systems organize knowledge, search better, and build smarter tools for clinical informatics.
By Guanchen Wu, Yuzhang Xie, Huanwei Wu, Zhe He, Hui Shao, Xiao Hu, and Carl Yang. Read more: https://arxiv.org/abs/2511.16548v1
Paper: https://arxiv.org/abs/2511.16548v1
Register: https://www.AiFeta.com
AI Healthcare LLM ClinicalNotes Ontology Privacy NLP BiomedicalInformatics
