{"version":1,"type":"story","url":"https://digestai.news/story/researchers-release-chestphenot-for-auditable-radiology-report-analysi","json":"https://digestai.news/story/researchers-release-chestphenot-for-auditable-radiology-report-analysi.json","markdown":"https://digestai.news/story/researchers-release-chestphenot-for-auditable-radiology-report-analysi.md","slug":"researchers-release-chestphenot-for-auditable-radiology-report-analysi","headline":"Researchers release ChestPheNoT for auditable radiology report analysis","summary":"Researchers introduced **ChestPheNoT**, a compact 0.5–3B language model designed to extract structured medical findings, status labels (present/absent/uncertain), and verbatim evidence spans from radiology reports. The model avoids external APIs by running locally, addressing concerns about data leaving institutional networks. It uses hybrid silver supervision (CheXbert + 72B models) and GRPO refinement to improve accuracy under distribution shifts, outperforming CheXbert on cross-institution detection by **+2.0 F1** and matching larger models on detection tasks.\n\nChestPheNoT achieves **99% evidence span locatability** and an **auditable-F1 of 47.5**, surpassing Qwen2.5-7B by **7.6 points**. The team claims it enables deployable, explainable radiology analytics without relying on cloud-based inference. Code and prompts will be open-sourced on GitHub.","keyPoints":["ChestPheNoT extracts findings, status labels, and evidence spans from radiology reports locally, not via APIs","Outperforms CheXbert on cross-institution detection by +2.0 F1 and matches larger models on detection tasks","Achieves 99% evidence span locatability and 47.5 auditable-F1, surpassing Qwen2.5-7B by 7.6 points"],"whyItMatters":"Locally deployable models like ChestPheNoT reduce reliance on cloud APIs for sensitive medical data, improving auditability and compliance while offering competitive performance to much larger models.","category":{"slug":"research","name":"Research","url":"https://digestai.news/category/research"},"entities":{"companies":[],"models":["ChestPheNoT","CheXbert","Qwen2.5-7B","Qwen2.5-72B"],"people":[]},"firstPublishedAt":"2026-09-29T04:00:00Z","updatedAt":"2026-09-29T04:00:00Z","sourceCount":1,"hasPrimarySource":true,"sources":[{"outlet":"arXiv cs.CL","title":"ChestPheNoT: Deployable, Auditable Label-Status-Evidence Extraction from Radiology Reports","url":"https://arxiv.org/abs/2609.31629","publishedAt":"2026-09-29T04:00:00Z","type":"primary","primary":true,"lead":true}],"sourceNotes":null,"discussions":[],"thread":null,"cite":{"text":"Digest AI, \"Researchers release ChestPheNoT for auditable radiology report analysis\", 29 September 2026, https://digestai.news/story/researchers-release-chestphenot-for-auditable-radiology-report-analysi","publisher":"Digest AI","title":"Researchers release ChestPheNoT for auditable radiology report analysis","datePublished":"2026-09-29T04:00:00Z","url":"https://digestai.news/story/researchers-release-chestphenot-for-auditable-radiology-report-analysi"},"generatedBy":"Written by Digest AI's editorial model from the linked sources; the sources are the record.","license":"Headlines, digests and key points are written by Digest AI and may be quoted with a link to the story page. Linked articles belong to their publishers. Terms: https://digestai.news/terms#reuse"}