English(EN) Privacy-Preserving Generation of Clinical Narratives from Medical Terminologies

新方法生成保护隐私的合成临床记录

作者 PulseAugur 编辑部 · [1 个来源] · 2026-09-01 04:00

研究人员开发了Term2Note，一种符合差分隐私（DP）约束的合成临床记录生成新方法。该方法将内容和形式分开，允许分别将DP应用于医学术语和生成的记录。实验表明，Term2Note生成的合成记录在统计特性上与真实临床数据相似，使得下游模型在性能上可与使用真实患者记录训练的模型相媲美。该方法在保真度和效用方面均显著优于现有的DP文本生成技术。 AI

影响使得可以使用合成临床数据来训练AI模型，有可能在不损害患者隐私的情况下加速医疗保健领域的研究和开发。

排序理由该集群包含一篇学术论文，详细介绍了一种具有隐私保证的合成临床数据生成新方法。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.CL 阅读 →

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

本文如何被排名

Signal score: 24 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 该集群包含一篇学术论文，详细介绍了一种具有隐私保证的合成临床数据生成新方法。[lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration: Single-source cluster; Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics: paper, safety; Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance: High; Clearly on-topic for AI-industry coverage.
Story freshness: Breaking (< 6h); Fresh story with cross-source coverage still developing. Ranking may shift as more sources report.

完整方法见我们的编辑标准。

报道来源 [1]

arXiv cs.CL TIER_1 English(EN) · Yuping Wu, Viktor Schlegel, Warren Del-Pinto, Srinivasan Nandakumar, Iqra Zahid, Yidan Sun, Hai Li, Usama Farghaly Omar, Amirah Jasmine, Arun-Kumar Kaliya-Perumal, Chun Shen Tham, Gabriel Connors, Anil A Bharath, Goran Nenadic · 2026-09-01 04:00

从医学术语生成保护隐私的临床叙述

arXiv:2509.10882v2 Announce Type: replace Abstract: In high-stakes domains such as healthcare, privacy concerns severely limit the use of real-world training data. Differentially private (DP) synthetic data offers a promising alternative with formal privacy guarantees, but achiev…

本文如何被排名

报道来源 [1]

从医学术语生成保护隐私的临床叙述

相关实体

相关话题