arXiv：cs.LG· Daniel Varab, Victor Petr\'en Bach Hansen, Asbj{\o}rn W. Helge, Kevin Pelgrims, Mathias Baltzersen, Adrian Young-San Roessler, Vanessa Klungtvedt, Maximilian Brand, Lasse Krogsb{\o}ll, Henrik Cullen, Lars Maal{\o}e·· 4 小时前AI 评分38
Corti 与通用 AI 临床记录工具对比：MedConv 临床笔记生成基准发布
Symphony for Text Generation: Benchmarking Clinical Note Generation
AI 导读
研究团队发布 MedConv 多语言数据集，包含英语、丹麦语和德语共 300 例临床问诊，并结合 ACI-BENCH 基准，将临床 AI 平台 Corti 与两款基于通用 AI 的主流环境记录软件进行对比。结果显示，Corti 基于 API 的文本生成基础设施表现与领先商业记录工具相当或更优。团队同时发布评估方法论与数据集，以支持环境文档系统的可复现比较。
正文
Authors:Daniel Varab, Victor Petrén Bach Hansen, Asbjørn W. Helge, Kevin Pelgrims, Mathias Baltzersen, Adrian Young-San Roessler, Vanessa Klungtvedt, Maximilian Brand, Lasse Krogsbøll, Henrik Cullen, Lars Maaløe
Abstract:Ambient documentation systems are rapidly gaining adoption, yet their impact on clinical note quality remains poorly characterized. We introduce MedConv, a multilingual dataset of 300 clinical encounters in English, Danish, and German, and use it alongside the Ambient Clinical Intelligence benchmark (ACI-BENCH) to compare Corti, a clinical AI platform, with two leading, accessible ambient scribe software applications built on general-purpose AI. We present a controlled clinical evaluation framework that combines entailment metrics with LLM-judged pairwise comparisons across eight dimensions adopted from PDSQI-9. Results show that Corti's API-based text-generation infrastructure is on par with or outperforms leading commercial scribes. We further show that Corti's configurable API provides the flexibility necessary to fine-tune quality dimensions for specific documentation use cases. We present the evaluation methodology and release a dataset to support future reproducible comparison of ambient documentation systems.
| Subjects: | Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Computation and Language (cs.CL) |
| Cite as: | arXiv:2610.08161 [cs.LG] |
| (or arXiv:2610.08161v1 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2610.08161 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Victor Petrén Bach Hansen [view email]
[v1]
Tue, 6 Oct 2026 11:13:02 UTC (1,693 KB)
来源：arXiv：cs.LG · arxiv.org