大模型
arxiv.org ·
用于乳腺癌多学科团队会议的边缘 AI 医疗器械系统的开发与可行性评估
该 arXiv 论文开发了一套完全本地运行的 AI 流水线，在单块 NVIDIA Jetson AGX Orin 上使用开源 ASR（Whisper large-v3）和 LLM（MedGemma）结合基于 NICE 指南的 RAG，对乳腺癌 MDT 讨论进行转录、临床信息结构化并生成治疗建议，使患者音频、转录与输出均留在机构内部。评估使用 2 段模拟 MDT 录音、10 段临床验证合成讨论和 1270 段声学增强录音：Whisper 优化使录音词错率分别降低 20.7% 和 24.4%，增强音频上与商业临床 ASR 基准的 WER 差距为 0.58%、词信息丢失差距 1.58%；MedGemma-RAG 识别出的与 MDT 一致的干预数量为某专有云对照的 2.3 倍（p=0.020），总体准确率无显著差异。利益相关方认为自动文档、治疗建议支持和病例分诊是最可信的近期应用，同时指出工作流集成、治理与临床医生信任是主要落地挑战。作者称结果证明隐私保护的全本地 AI 用于 MDT 文档与指南决策支持可行，但需前瞻性临床评估。
AI推荐理由 arXiv 论文（cs.AI），提出完全本地部署的边缘 AI 医疗器械系统：在单块 NVIDIA Jetson AGX Orin 上运行开源 ASR（Whisper large-v3）与 LLM（MedGemma）+ RAG，基于 NICE 指南为乳腺癌 MDT 会议做转录、结构化与治疗建议，避免患者可识别信息上云。评估含 2 段模拟 MDT 录音、10 段临床验证合成讨论和 1270 段声学增强录音；Whisper 优化使词错率降低 20.7%/24.4%，增强音频上 WER 与商业临床 ASR 基准差距在 0.58% 以内；MedGemma-RAG 识别出的与 MDT 一致干预为某专有云对照的 2.3 倍（p=0.020），总体准确率无显著差异。局限：仅为可行性评估，样本为模拟/合成数据，作者自述需前瞻性临床验证，不能视为已证实临床效果。
72
正文
Computer Science > Artificial Intelligence
arXiv:2608.22108 (cs)
[Submitted on 22 Aug 2026]
Title:Development and Feasibility Evaluation of an Edge AI as Medical Device System for Breast Cancer Multidisciplinary Team Meetings
Authors:Aarzoo Dhiman, Farzana Haque, Kartikae Grover, Lydia Brian Smith, William Stephen Jones
View a PDF of the paper titled Development and Feasibility Evaluation of an Edge AI as Medical Device System for Breast Cancer Multidisciplinary Team Meetings, by Aarzoo Dhiman and 4 other authors
View PDF
Abstract:Breast Cancer Multidisciplinary Team (MDT) meetings manage increasingly complex cases under considerable time pressure, and documentation requirements can reduce clinical efficiency and decision quality. Existing AI based MDT workflows rely on cloud-based processing, limiting their use because patient discussions contain identifiable information. We developed a fully on-device AI pipeline using open-source Automatic Speech Recognition (ASR) and Large Language Models (LLMs) that transcribes breast cancer MDT discussions, structures clinical information, and generates treatment recommendations using retrieval-augmented generation (RAG) grounded in National Institute for Health and Care Excellence (NICE) guidance. The pipeline runs on a single NVIDIA Jetson AGX Orin, ensuring that patient audio, transcripts, and outputs remain within institutional infrastructure. Evaluation included two recorded simulated MDT discussions, ten clinically validated synthetic discussions, and 1,270 acoustically augmented recordings. Optimisation of Whisper large-v3 reduced word error rate by 20.7% and 24.4% on the recorded discussions and achieved performance within 0.58% WER and 1.58% word information lost of a commercial clinical ASR benchmark on augmented audio. MedGemma-RAG identified 2.3 times more MDT-concordant interventions than a proprietary cloud comparator (p = 0.020), with no significant difference in overall accuracy. Stakeholders identified automated documentation, treatment recommendation support, and case triage as the most credible near-term applications while highlighting workflow integration, governance, and clinician trust as key implementation challenges. These findings demonstrate the feasibility of privacy-preserving, fully on-device AI for MDT documentation and guideline-informed decision support, providing a foundation for prospective clinical evaluation.
Subjects:
Artificial Intelligence (cs.AI); Machine Learning (cs.LG)
Cite as:
arXiv:2608.22108 [cs.AI]
(or
arXiv:2608.22108v1 [cs.AI] for this version)
https://doi.org/10.48550/arXiv.2608.22108
Focus to learn more
arXiv-issued DOI via DataCite
Submission history
From: Aarzoo Dhiman [view email]
[v1]
Sat, 22 Aug 2026 21:20:51 UTC (1,173 KB)
Full-text links:
Access Paper:
View a PDF of the paper titled Development and Feasibility Evaluation of an Edge AI as Medical Device System for Breast Cancer Multidisciplinary Team Meetings, by Aarzoo Dhiman and 4 other authors
View PDF
view license
Current browse context:
cs.AI
new
|
recent
| 2026-08
Change to browse by:
cs
cs.LG
References & Citations
NASA ADS
Google Scholar
Semantic Scholar
export BibTeX citation
Loading...
BibTeX formatted citation
×
loading...
Data provided by:
Bookmark
Bibliographic Tools
Bibliographic and Citation Tools
Bibliographic Explorer Toggle
Bibliographic Explorer (What is the Explorer?)
Connected Papers Toggle
Connected Papers (What is Connected Papers?)
Litmaps Toggle
Litmaps (What is Litmaps?)
scite.ai Toggle
scite Smart Citations (What are Smart Citations?)
Code, Data, Media
Code, Data and Media Associated with this Article
alphaXiv Toggle
alphaXiv (What is alphaXiv?)
Links to Code Toggle
CatalyzeX Code Finder for Papers (What is CatalyzeX?)
DagsHub Toggle
DagsHub (What is DagsHub?)
GotitPub Toggle
Gotit.pub (What is GotitPub?)
Huggingface Toggle
Hugging Face (What is Huggingface?)
ScienceCast Toggle
ScienceCast (What is ScienceCast?)
Demos
Demos
Replicate Toggle
Replicate (What is Replicate?)
Spaces Toggle
Hugging Face Spaces (What is Spaces?)
Spaces Toggle
TXYZ.AI (What is TXYZ.AI?)
Related Papers
Recommenders and Search Tools
Link to Influence Flower
Influence Flower (What are Influence Flowers?)
Core recommender toggle
CORE Recommender (What is CORE?)
Author
Venue
Institution
Topic
About arXivLabs
arXivLabs: experimental projects with community collaborators
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Which authors of this paper are endorsers? |
Disable MathJax (What is MathJax?)