arXivDaily arXiv每日学术速递 周一至周五更新

科学与医疗

医学 AI

医学智能、临床 AI、医学影像、病理、诊断和医疗健康大模型。

共收录 951 信号源:cs.CV, cs.LG, q-bio, eess.IV, eess.SP

1. 临床大模型 951 篇

2506.14400 2025-08-15 cs.LG cs.CY 74%

One Size Fits None: Rethinking Fairness in Medical AI

Roland Roller, Michael Hahn, Ajay Madhavan Ravichandran, Bilgin Osmanodja, Florian Oetke, Zeineb Sassi, Aljoscha Burchardt, Klaus Netter, Klemens Budde, Anne Herrmann, Tobias Strapatsas, Peter Dabrock, Sebastian Möller

机构 * DFKI Friedrich-Alexander-Universität Erlangen-Nürnberg(弗里德里希-亚历山大-埃朗根-纽伦堡大学) Charité - Universitätsmedizin Berlin(Charité - 大学医学中心柏林) DNC Information Management GmbH(DNC信息管理有限公司) University of Regensburg(雷根萨大学) University Hospital Regensburg(雷根萨大学医院) Asklepios Klinikum Harburg(阿斯克勒庇奥斯克linikum哈弗堡) TU Berlin(柏林技术大学)

专题命中 临床大模型 :medical AI(title);分类 cs.LG

Comments Accepted at the 6th Workshop on Gender Bias in Natural Language Processing at ACL 2025

Journal ref Proceedings of the 6th Workshop on Gender Bias in Natural Language Processing (GeBNLP), 2025, pp. 282-289

详情

展开后加载摘要…

URL PDF HTML 收藏
2110.03660 2021-10-08 cs.HC cs.LG 74%

Developing Medical AI : a cloud-native audio-visual data collection study

Sagi Schein, Greg Arutiunian, Vitaly Burshtein, Gal Sadeh, Michelle Townshend, Bruce Friedman, Shada Sadr-azodi

专题命中 临床大模型 :medical AI(title);分类 cs.LG

详情

展开后加载摘要…

URL PDF HTML 收藏
2507.12964 2026-07-30 cs.CV cs.AI cs.LG 73%

Demographic-aware fine-grained visual recognition of pediatric wrist pathologies

具有人口统计学意识的细粒度视觉识别用于儿童手腕病理学

Ammar Ahmed, Ali Shariq Imran, Zenun Kastrati, Sher Muhammad Daudpota

机构 * Department of Computer Science (IDI), Norwegian University of Science \& Technology (NTNU), Gjøvik, 2815, Norway Department of Informatics, Linnaeus University, V\"axj\"o, 351 95, Sweden Department of Computer Science, Sukkur IBA University, Sukkur, 65200, Pakistan

专题命中 临床大模型 :pathology(abstract);diagnosis(abstract);分类 cs.CV、cs.LG

AI总结 本文提出一种结合患者年龄和性别的混合卷积-Transformer模型,用于细粒度视觉识别儿童手腕病理学,以提高诊断准确性。

详情

展开后加载摘要…

URL PDF HTML 收藏
2503.12515 2025-03-18 cs.CV cs.LG physics.med-ph 73%

AI-Powered Automated Model Construction for Patient-Specific CFD Simulations of Aortic Flows

Pan Du, Delin An, Chaoli Wang, Jian-Xun Wang

专题命中 临床大模型 :medical image(abstract);diagnosis(abstract);分类 cs.CV、cs.LG

Comments 42 pages, 8 figures

详情

展开后加载摘要…

URL PDF HTML 收藏
2203.10517 2023-11-09 eess.IV cs.CE cs.CV physics.med-ph 73%

Learning Whole Heart Mesh Generation From Patient Images For Computational Simulations

Fanwei Kong, Shawn Shadden

专题命中 临床大模型 :medical image(abstract);CT(abstract);分类 cs.CV、eess.IV

Journal ref IEEE Transactions on Medical Imaging, vol. 42, no. 2, pp. 533-545, Feb. 2023

详情

展开后加载摘要…

URL PDF HTML 收藏
2110.14787 2021-10-29 eess.IV cs.CV 73%

SCALP -- Supervised Contrastive Learning for Cardiopulmonary Disease Classification and Localization in Chest X-rays using Patient Metadata

Ajay Jaiswal, Tianhao Li, Cyprian Zander, Yan Han, Justin F. Rousseau, Yifan Peng, Ying Ding

专题命中 临床大模型 :medical image(abstract);diagnosis(abstract);分类 cs.CV、eess.IV

详情

展开后加载摘要…

URL PDF HTML 收藏
2003.09404 2020-03-23 eess.IV cs.CV 73%

RGB-Topography and X-rays Image Registration for Idiopathic Scoliosis Children Patient Follow-up

Insaf Setitra, Noureddine Aouaa, Abdelkrim Meziane, Afef Benrabia, Houria Kaced, Hanene Belabassi, Sara Ait Ziane, Nadia Henda Zenati, Oualid Djekkoune

专题命中 临床大模型 :pathology(abstract);diagnosis(abstract);分类 cs.CV、eess.IV

详情

展开后加载摘要…

URL PDF HTML 收藏
2607.24371 2026-07-28 cs.CL cs.AI 新提交 71%

Closed-Loop Validation-Repair for Healthcare Interoperability: A Multi-Model Study of Schema Compliance in Clinical LLMs

医疗保健互操作性的闭环验证修复:临床大语言模型中模式合规性的多模型研究

Jianru Shen

机构 * University of Montana(蒙大拿大学)

专题命中 临床大模型 :clinical LLM(title)

AI总结 研究医疗大语言模型集成到电子健康记录系统面临的模式不合规问题,通过在多场景下部署三个开源模型并评估,发现模式不合规具有一致性,验证 - 修复框架可有效提高合规率,为医疗互操作性提供保障。

Comments Accepted at the 2026 IEEE International Conference on Systems, Man, and Cybernetics (SMC 2026)

详情

展开后加载摘要…

URL PDF HTML 收藏
2606.01766 2026-06-23 cs.DC cs.ET 71%

Night-Window Batching versus Carbon-Aware Scheduling for Clinical AI GPU Workloads

夜间批处理与碳感知调度在临床AI GPU工作负载中的比较

Nishi Doshi, Shrey Shah

专题命中 临床大模型 :clinical AI(title)

AI总结 通过计算机模拟,比较了夜间批处理与碳感知调度规则在混合GPU硬件上处理合成患者型作业时的碳足迹和截止时间遵守情况,发现夜间批处理在减少碳足迹的同时能更好地遵守紧急截止时间。

Comments International Conference on Technological Intelligence and Business Strategies (TIBS 2026)

详情

展开后加载摘要…

URL PDF HTML 收藏
2606.09789 2026-06-09 cs.CY 新提交 71%

Principled Uncertainty in Clinical AI: End-to-End Bayesian Modelling and Algorithmic Equity Auditing Across Multimodal Patient Data

临床AI中的原则性不确定性:跨多模态患者数据的端到端贝叶斯建模与算法公平审计

Oladimeji Anthonio, Dimeji Abdulsobur Olawuyi, Oloruntoba Ajayi, Temiloluwa Aderemi, Joseph Odamo

专题命中 临床大模型 :clinical AI(title)

AI总结 提出端到端贝叶斯不确定性建模框架,结合校准不确定性作为公平性度量,在模拟患者数据中识别出初级/农村设施和低社会经济地位患者的认知不确定性公平差距。

详情

展开后加载摘要…

URL PDF HTML 收藏
2606.02630 2026-06-03 cs.CR cs.AI 71%

MultiTurnPSB: Evaluating Multi-Turn Jailbreak Attacks an dClassifier-Based Defenses for Medical AI Safety

MultiTurnPSB:评估多轮越狱攻击与基于分类器的防御在医疗AI安全中的应用

Anushka Sheoran, Yiduo Hao

机构 * University of Pennsylvania(宾夕法尼亚大学)

专题命中 临床大模型 :medical AI(title)

AI总结 提出多轮对抗基准MultiTurnPSB,通过四轮对话评估医疗聊天机器人的安全漏洞,发现多轮攻击下不安全响应率从35%升至近80%,并验证了轻量级输入分类器可降低52个百分点的不安全响应但存在高误报率。

详情

展开后加载摘要…

URL PDF HTML 收藏
2605.16215 2026-06-01 cs.AI cs.CL 71%

Fully Open Meditron: An Auditable Pipeline for Clinical LLMs

完全开放的Meditron:临床大语言模型的可审计流水线

Xavier Theimer-Lienhard, Mushtaha El-Amin, Fay Elhassan, Sahaj Vaidya, Victor Cartier-Negadi, David Sasu, Lars Klein, Mary-Anne Hartley

机构 * EPFL(苏黎世联邦理工学院)

专题命中 临床大模型 :clinical LLM(title)

AI总结 提出首个完全开放的临床大语言模型构建流水线Fully Open Meditron,通过可审计的数据集、可复现的训练框架和对齐评估协议,在不牺牲可审计性和可复现性的前提下实现了领域最新性能。

Comments Preprint. 31 pages, 10 figures. Code, models, and data: https://github.com/EPFLiGHT/FullyOpenMeditron

详情

展开后加载摘要…

URL PDF HTML 收藏
2605.00796 2026-05-04 cs.CR cs.AI cs.CL 71%

When RAG Chatbots Expose Their Backend: An Anonymized Case Study of Privacy and Security Risks in Patient-Facing Medical AI

当RAG聊天机器人暴露其后端:对患者面向医疗AI隐私和安全风险的匿名案例研究

Alfredo Madrid-García, Miguel Rujas

机构 * Independent researcher(独立研究者) Escuela Técnica Superior de Ingenieros de Telecomunicación Universidad Politécnica de Madrid(电信工程学院理工大学)

专题命中 临床大模型 :medical AI(title)

AI总结 研究通过匿名案例分析,揭示了患者面向RAG聊天机器人中隐私和安全风险,指出通过浏览器工具可发现关键漏洞,强调部署前需独立审查。

详情

展开后加载摘要…

URL PDF HTML 收藏
2604.20791 2026-04-23 cs.CL cs.AI 71%

Can "AI" Be a Doctor? A Study of Empathy, Readability, and Alignment in Clinical LLMs

AI能成为医生吗?对临床LLM中共情、可读性和对齐性的研究

Mariano Barone, Francesco Di Serio, Roberto Moio, Marco Postiglione, Giuseppe Riccio, Antonio Romano, Vincenzo Moscato

机构 * Department of Electrical Engineering and Information Technology(电子工程与信息科技系) University of Naples Federico II(那不勒斯费德里科二世大学) Department of Translational Medical Sciences(转化医学科学系) University of Campania ”Luigi Vanvitelli”(坎帕尼亚“路易吉·范维蒂利”大学) Department of Computer Science, McCormick School of Engineering and Applied Science(计算机科学系,麦科马克工程与应用科学学院) Northwestern University(西北大学)

专题命中 临床大模型 :clinical LLM(title)

AI总结 本文研究了临床LLM在共情、可读性和对齐性方面的表现,发现协作重写能显著提升对齐效果,但LLM仍无法超越医生的临床专业性。

详情

展开后加载摘要…

URL PDF HTML 收藏
2602.00009 2026-03-17 cs.CL cs.AI cs.IR 71%

Unlocking Electronic Health Records: A Hybrid Graph RAG Approach to Safe Clinical AI for Patient QA

解锁电子健康记录:一种混合图RAG方法用于安全临床AI的患者问答

Samuel Thio, Matthew Lewis, Spiros Denaxas, Richard JB Dobson

专题命中 临床大模型 :clinical AI(title)

AI总结 本文提出MediGRAF,一种结合图检索与向量嵌入的混合RAG系统,通过整合结构化数据与非结构化文本,提升临床AI在患者问答中的安全性和准确性。

Comments 26 pages, 5 figures, 2 tables

Journal ref Frontiers in Digital Health, vol. 8, 2026

详情

展开后加载摘要…

URL PDF HTML 收藏
2602.19948 2026-03-06 cs.CL cs.AI cs.CY cs.HC cs.MA 71%

Assessing Risks of Large Language Models in Mental Health Support: A Framework for Automated Clinical AI Red Teaming

评估大型语言模型在心理健康支持中的风险:一种用于自动化临床AI红队测试的框架

Ian Steenstra, Paola Pedrelli, Weiyan Shi, Stacy Marsella, Timothy W. Bickmore

机构 * Northeastern University(东北大学) Harvard Medical School(哈佛医学院)

专题命中 临床大模型 :clinical AI(title)

AI总结 本文提出了一种评估AI心理治疗师在心理健康支持中安全风险的框架,通过模拟测试发现AI在治疗中的潜在风险,并验证了交互式可视化工具的有效性。

Comments This paper is a condensed version of the first author's Ph.D. dissertation submitted to Northeastern University

详情

展开后加载摘要…

URL PDF HTML 收藏
2603.03367 2026-03-05 cs.CY cs.AI 71%

Bridging the Reproducibility Divide: Open Source Software's Role in Standardizing Healthcare AI

弥合可重复性鸿沟:开源软件在标准化医疗AI中的作用

John Wu, Zhenbang Wu, Jimeng Sun

专题命中 临床大模型 :healthcare AI(title)

AI总结 本文探讨了开源软件在提升医疗AI可重复性中的作用,指出通过公开数据集和代码共享可显著提高论文影响力,并提出标准化数据预处理和开放科学实践的必要性。

Comments Old Preprint. Will update in a later revision

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.11040 2025-10-14 cs.CL 71%

Enabling Doctor-Centric Medical AI with LLMs through Workflow-Aligned Tasks and Benchmarks

Wenya Xie, Qingying Xiao, Yu Zheng, Xidong Wang, Junying Chen, Ke Ji, Anningzhe Gao, Prayag Tiwari, Xiang Wan, Feng Jiang, Benyou Wang

机构 * Shenzhen Research Institute of Big Data(大数据研究 institute) National Health Data Institute(国家健康数据研究所) Halmstad University(哈马碧大学) Shenzhen University of Advanced Technology(深圳先进技术大学)

专题命中 临床大模型 :medical AI(title)

详情

展开后加载摘要…

URL PDF HTML 收藏
2411.12808 2025-04-11 cs.AI cs.CY cs.HC 71%

Conversational Medical AI: Ready for Practice

Antoine Lizée, Pierre-Auguste Beaucoté, James Whitbeck, Marion Doumeingts, Anaël Beaugnon, Isabelle Feldhaus

专题命中 临床大模型 :medical AI(title)

Comments Accepted to AAAI25 (Oral, workshop) 14 pages, 7 figures, 3 tables

详情

展开后加载摘要…

URL PDF HTML 收藏
2503.05768 2025-03-11 cs.CY cs.AI 71%

A Collection of Innovations in Medical AI for patient records in 2024

Yuanyun Zhang, Shi Li

专题命中 临床大模型 :medical AI(title)

详情

展开后加载摘要…

URL PDF HTML 收藏
2412.10709 2024-12-17 cs.HC 71%

A Post a Day Keeps the Doctor Away: Sharing Personal Information on Self-Diagnosis Platforms

Roopa Bhat, Lord Crawford, Nicole Hong

专题命中 临床大模型 :diagnosis(title)

Comments 5 pages, 2 figures, Spring 2021 HCI Seminar, Columbia University, NY

Journal ref HCI Seminar, Spring 2021, Columbia University, NY

详情

展开后加载摘要…

URL PDF HTML 收藏
2408.06142 2024-08-13 cs.CL cs.AI 71%

Med42-v2: A Suite of Clinical LLMs

Clément Christophe, Praveen K Kanithi, Tathagata Raha, Shadab Khan, Marco AF Pimentel

专题命中 临床大模型 :clinical LLM(title)

详情

展开后加载摘要…

URL PDF HTML 收藏
2211.16553 2023-05-19 cs.LG q-bio.QM stat.ML 71%

Simple and Scalable Algorithms for Cluster-Aware Precision Medicine

Amanda M. Buch, Conor Liston, Logan Grosenick

专题命中 临床大模型 :diagnosis(abstract);biomedical(abstract);分类 cs.LG、q-bio

Comments 15 pages, 3 figures, 3 tables

详情

展开后加载摘要…

URL PDF HTML 收藏
2204.09952 2022-04-22 cs.CL cs.IR 71%

Recovering Patient Journeys: A Corpus of Biomedical Entities and Relations on Twitter (BEAR)

Amelie Wührl, Roman Klinger

专题命中 临床大模型 :biomedical(title)

Comments Accepted at LREC 2022

详情

展开后加载摘要…

URL PDF HTML 收藏
2105.01009 2021-05-04 cs.CL 71%

Leveraging Deep Representations of Radiology Reports in Survival Analysis for Predicting Heart Failure Patient Mortality

Hyun Gi Lee, Evan Sholle, Ashley Beecy, Subhi Al'Aref, Yifan Peng

专题命中 临床大模型 :radiology(title)

Comments NAACL-HLT 2021, Short Paper

详情

展开后加载摘要…

URL PDF HTML 收藏
2006.11988 2023-06-29 q-bio.QM cs.CV cs.LG eess.IV 71%

COVID-19 Image Data Collection: Prospective Predictions Are the Future

Joseph Paul Cohen, Paul Morrison, Lan Dao, Karsten Roth, Tim Q Duong, Marzyeh Ghassemi

专题命中 临床大模型 :diagnosis(abstract);分类 cs.CV、cs.LG、q-bio;biomedical(comments)

Comments Accepted for publication at the Journal of Machine Learning for Biomedical Imaging (MELBA) https://melba-journal.org. Code for baseline experiments can be found here: https://github.com/mlmed/covid-baselines

详情

展开后加载摘要…

URL PDF HTML 收藏
2607.28671 2026-08-03 stat.AP cs.LG 新提交 70%

Fracture Risk Prediction in Adults Over 50 Years Old Using DXA and EHR: Comparison of Traditional and Machine Learning Models in Two Large Cohorts

利用DXA和EHR预测50岁以上成人骨折风险:两个大型队列中传统模型与机器学习模型的比较

Jiahe Qian, Hao Dai, Kunyu Yu, Hexin Dong, Xing He, Erik A. Imel, Jiang Bian, Yifan Peng, Yi Liu

专题命中 临床大模型 :diagnosis(abstract);radiology(abstract);分类 cs.LG

AI总结 该研究针对50岁以上成人,基于EHR和DXA数据构建多种生存预测模型,发现其区分度优于FRAX,为骨折风险预测提供了更优工具,但需进一步评估后才可临床应用。

Comments 5 figures, 4 tables, 25 pages

详情

展开后加载摘要…

URL PDF HTML 收藏
2604.18753 2026-05-08 cs.LG cs.AI 70%

Handling and Interpreting Missing Modalities in Patient Clinical Trajectories via Autoregressive Sequence Modeling

通过自回归序列建模处理和解释患者临床轨迹中的缺失模态

Andrew Wang, Ellie Pavlick, Ritambhara Singh

机构 * Brown University(布朗大学)

专题命中 临床大模型 :clinical AI(abstract);diagnosis(abstract);分类 cs.LG

AI总结 本文通过自回归序列建模方法处理医疗数据中缺失模态的问题,提出对比预训练目标并验证了其在MIMIC-IV和eICU数据集上的有效性,提升了模型可解释性。

详情

展开后加载摘要…

URL PDF HTML 收藏
2605.01084 2026-05-05 cs.CV 70%

Patient-Specific Optimization for Mandibular Reconstruction Planning with Enhanced Bone Union

针对增强骨愈合的颌骨重建计划的患者特异性优化

Hamidreza Aftabi, John E. Lloyd, Amanda Ding, Benedikt Sagl, Eitan Prisman, Antony Hodgson, Sidney Fels

机构 * Department of Electrical and Computer Engineering, University of British Columbia(电气与计算机工程系,不列颠哥伦比亚大学) Department of Surgery, University of British Columbia, Gordon and Leslie Diamond Health Care Centre(不列颠哥伦比亚大学外科系,戈登和莱斯利钻石医疗中心) Center for Clinical Research, University Clinic of Dentistry, Medical University of Vienna(维也纳医科大学牙科学院临床研究中心) Department of Mechanical Engineering, University of British Columbia(机械工程系,不列颠哥伦比亚大学) Sunnybrook Research Institute, University of Toronto(多伦多大学 Sunnybrook 研究院)

专题命中 临床大模型 :CT(abstract,abstract_cn);分类 cs.CV

AI总结 本文提出OsteoOpt++,通过图像到决策的规划循环,优化颌骨重建中的切面和供体位置变量,以促进骨愈合。

详情

展开后加载摘要…

URL PDF HTML 收藏
2602.19483 2026-05-01 cs.LG cs.AI stat.ML 70%

Making Conformal Predictors Robust in Healthcare Settings: a Case Study on EEG Classification

在医疗环境中使符合预测器更加稳健:EEG分类的案例研究

Arjun Chatterjee, Sayeed Sajjad Razin, John Wu, Siddhartha Laghuvarapu, Jathurshan Pradeepkumar, Jimeng Sun

机构 * University of Illinois Urbana-Champaign(伊利诺伊大学厄巴纳-香槟分校) PyHealth Bangladesh University of Engineering and Technology(孟加拉工程与技术大学)

专题命中 临床大模型 :healthcare AI(abstract);diagnosis(abstract);分类 cs.LG

AI总结 本文评估了多种符合预测方法在EEG癫痫分类中的表现,发现个性化校准策略可提升覆盖度20%以上,同时保持预测集大小相近。

Comments Accepted to the International Conference on Artificial Intelligence in Medicine 2026

详情

展开后加载摘要…

URL PDF HTML 收藏