← Back to Model Beat
Open Source·2d ago·all news from September 29, 2026

ChestPheNoT: Deployable, Auditable Label-Status-Evidence Extraction from Radiology Reports

Researchers have introduced ChestPheNoT, a system designed to extract clinical data from radiology reports while maintaining local processing and auditability. This tool addresses the challenge of identifying patient phenotypes without relying on extensive manual expert annotation, potentially improving the efficiency of clinical analytics and quality audits in healthcare settings.

Covered by 1 source

  • AarXiv CS.AI↗Kai Yu, Chenyu Zhu, Zaifu Zhan, Meijia Song, Min Zeng, Xiaoyi Chen, Mingquan Lin, Rui Zhang2d ago

Related stories

Open SourceFrom ASR to ASP: Evaluating Prompt Attack Vulnerabilities Against Open-Source LLMsSep 28Open SourceAgentXploit: Autonomous Repository-to-Runtime Red-Teaming for AI AgentsSep 28Open SourceSemantic Navigation for Issue Localization in Code RepositorySep 28Open SourceWhen Retrieval Hurts: Measuring and Explaining Retrieval-Induced Hallucination in Chest X-ray Report GenerationSep 29