CLOZE: Letting AI Turn Doctors’ Notes into Smarter Medical Maps

Kari Jaaskelainen

21 Nov 2025 — 1 min read

Medical ontologies are like maps of diseases, drugs, and symptoms. They power search, decision support, and research—but they miss many real-world terms used in doctors’ notes.

A new framework called CLOZE taps large language models to read clinical notes and suggest new concepts and where they fit in the hierarchy—without extra training data.

Zero-shot: Works out of the box; no labeled data needed.
Privacy-first: Automatically removes protected health information (PHI).
Richer coverage: Finds disease-related entities and their parent/child links.
Scalable & cost-efficient: Automates what used to be slow expert curation.

In tests, CLOZE extended ontologies accurately and at scale, pointing to better tools for biomedical research and clinical informatics.

Paper: https://arxiv.org/abs/2511.16548v1

Paper: https://arxiv.org/abs/2511.16548v1

Register: https://www.AiFeta.com

#AI #Healthcare #ClinicalAI #LLM #NLP #MedicalInformatics #Privacy #Ontology

Read more

Meet GRACE: a moral governor for safer, more transparent AI

Meet GRACE: a moral governor for safer, more transparent AI

AI agents are getting powerful—so how do we make sure they do the right thing, not just the effective thing? Meet GRACE, a reason-based moral governor that keeps AI behavior aligned with human norms by separating moral reasoning from goal-driven decision-making. * Moral Module: uses deontic logic and explicit reasons

Why some fine-tuned LLMs miss phishing—and how to fix it

Why some fine-tuned LLMs miss phishing—and how to fix it

Not all fine-tuned LLMs spot phishing equally. A new study tests Llama 3.1 8B, Gemma 2 9B, and Mistral on high-stakes phishing detection—and uses SHAP and mechanistic interpretability to reveal why models do (or don’t) generalize. * Architecture × data diversity matters: Gemma 2 9B hits state-of-the-art performance (F1

AI that explains itself—by following the science

AI that explains itself—by following the science

AI that explains itself—by following the science Black-box AI can be powerful, but it often can’t tell us why it made a decision. Concept Bottleneck Models (CBMs) try to fix that by predicting human-understandable concepts first, then the final answer. The catch: standard CBMs ignore domain-specific cause-and-effect and

Meet GenomAgent: A Team of AI Specialists for Smarter Genomics Q&A

Meet GenomAgent: A Team of AI Specialists for Smarter Genomics Q&A

TL;DR: Finding reliable answers in genomics is hard. GenomAgent turns one big AI into a coordinating team of specialists—and beats the current leader by 12% on a key benchmark. Genomic facts live across many databases. Standard chatbots struggle because they can’t flexibly query those sources. GeneGPT added