医学 AI - arXivDaily 专题

2604.22618 2026-04-27 cs.LG 70%

Beyond Patient Invariance: Learning Cardiac Dynamics via Action-Conditioned JEPAs

超越患者不变性：通过动作条件化JEPAs学习心脏动力学

Jose Geraldo Fernandes, Luiz Facury, Pedro Robles Dutenhefner, Wagner Meira

机构 * Department of Computer Science（计算机科学系）； Universidade Federal de Minas Gerais（巴西联邦大学矿务格里斯矿大学）； Belo Horizonte, Brazil（巴西伯洛霍内）

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

AI总结本文提出动作条件化世界模型，通过学习疾病进展动力学，区分稳定解剖特征与动态病理力量，提升心电图关键分诊任务的性能。

2603.20752 2026-03-24 cs.CV 70%

Smart Operation Theatre: An AI-based System for Surgical Gauze Counting

智能手术室：一种基于AI的手术纱布计数系统

Saraf Krish, Cai Yiyu, Huang Li Hui

机构 * School of Social Science（社会科学学院）； School of Mechanical and Aerospace Engineering（机械与航空航天工程学院）

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

AI总结本文提出一种基于AI的手术纱布计数系统，利用YOLOv5模型实现实时视频监控和物体识别，通过追踪'入'和'出'两个托盘上的纱布实现精准计数，减少纱布遗留风险。

Journal ref Proceedings of the URECA@NTU 2022-23, Nanyang Technological University

2512.14708 2025-12-18 cs.NE cs.LG cs.MA 70%

SGEMAS: A Self-Growing Ephemeral Multi-Agent System for Unsupervised Online Anomaly Detection via Entropic Homeostasis

SGEMAS：一种自生长瞬时多智能体系统，用于通过熵稳态的无监督在线异常检测

Mustapha Hamdi

机构 * InnoDeep, PhD, Co-founder（InnoDeep）

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

AI总结 SGEMAS通过熵稳态机制实现自生长多智能体系统，用于无监督在线异常检测，实验表明其在跨患者零样本设置中性能优于传统方法。

2512.12076 2025-12-16 cs.LG stat.ML 70%

SigTime: Learning and Visually Explaining Time Series Signatures

SigTime: 学习和可视化解释时间序列签名

Yu-Chia Huang, Juntong Chen, Dongyu Liu, Kwan-Liu Ma

机构 * Department of Computer Science, University of California, Davis（计算机科学系，加州大学戴维斯分校）

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

AI总结 SigTime通过联合训练Transformer模型，利用形状let和传统特征工程，实现时间序列的可解释学习与可视化分析，提升时间模式识别的准确性和可解释性。

2510.18841 2025-10-22 cs.LG 70%

A Hybrid Enumeration Framework for Optimal Counterfactual Generation in Post-Acute COVID-19 Heart Failure

Jingya Cheng, Alaleh Azhir, Jiazi Tian, Hossein Estiri

机构 * Clinical Augmented Intelligence Group, Massachusetts General Hospital, Boston, MA, USA（马萨诸塞州总医院临床增强智能组）； Department of Medicine, Brigham and Women’s Hospital, Boston, MA, USA（布里奇沃特医院内科部）

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

2509.08247 2025-09-24 cs.LG 70%

The CRITICAL Records Integrated Standardization Pipeline (CRISP): End-to-End Processing of Large-scale Multi-institutional OMOP CDM Data

Xiaolong Luo, Michael Lingzhi Li

机构 * Harvard University（哈佛大学）

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

Comments 15 pages, 9 figures

2505.23834 2025-06-02 cs.SD cs.LG eess.AS 70%

Patient-Aware Feature Alignment for Robust Lung Sound Classification:Cohesion-Separation and Global Alignment Losses

Seung Gyu Jeong, Seong Eun Kim

机构 * Seoul National University of Science and Technology（首尔科学技术大学）

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

Comments Accepted INTERSPEECH 2025

2503.06204 2025-03-11 cs.CL cs.AI cs.LG 70%

CUPCase: Clinically Uncommon Patient Cases and Diagnoses Dataset

Oriel Perets, Ofir Ben Shoham, Nir Grinberg, Nadav Rappoport

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

Comments Accepted to AAAI 2025

2412.10848 2024-12-17 cs.CL cs.AI cs.LG 70%

Large Language Models for Medical Forecasting -- Foresight 2

Zeljko Kraljevic, Joshua Au Yeung, Daniel Bean, James Teo, Richard J. Dobson

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

2402.16886 2024-12-04 cs.IR cs.AI cs.LG 70%

Using text embedding models as text classifiers with medical data

Rishabh Goel

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

Comments 15 pages, 6 figures

2305.15964 2024-05-22 cs.CV 70%

ChatCAD+: Towards a Universal and Reliable Interactive CAD using LLMs

Zihao Zhao, Sheng Wang, Jinchen Gu, Yitao Zhu, Lanzhuju Mei, Zixu Zhuang, Zhiming Cui, Qian Wang, Dinggang Shen

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

Comments Authors Zihao Zhao, Sheng Wang, Jinchen Gu, Yitao Zhu contributed equally to this work and should be considered co-first authors

2403.03217 2024-03-06 cs.CV 70%

Self-supervised 3D Patient Modeling with Multi-modal Attentive Fusion

Meng Zheng, Benjamin Planche, Xuan Gong, Fan Yang, Terrence Chen, Ziyan Wu

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

Comments MICCAI 2022

2307.10188 2023-07-21 cs.CL cs.LG 70%

Several categories of Large Language Models (LLMs): A Short Survey

Saurabh Pahune, Manoj Chandrasekharan

专题命中临床大模型：clinical LLM(abstract)；biomedical(abstract)；分类 cs.LG

2307.04772 2023-07-12 cs.LG 70%

Digital Twins for Patient Care via Knowledge Graphs and Closed-Form Continuous-Time Liquid Neural Networks

Logan Nye

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

Comments 6 pages

2306.10765 2023-06-21 cs.AI cs.CL cs.CV 70%

Path to Medical AGI: Unify Domain-specific Medical LLMs with the Lowest Cost

Juexiao Zhou, Xiuying Chen, Xin Gao

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

2207.14638 2022-08-03 cs.DB cs.LG stat.AP 70%

Building Trust: Lessons from the Technion-Rambam Machine Learning in Healthcare Datathon Event

Jonathan A. Sobel, Ronit Almog, Leo Anthony Celi, Michal Gaziel-Yablowitz, Danny Eytan, Joachim A. Behar

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

Comments 13 pages, 4 figures, 29 references

2109.00343 2021-11-12 cs.CL cs.LG cs.NE 70%

Exploring deep learning methods for recognizing rare diseases and their clinical manifestations from texts

Isabel Segura-Bedmar, David Camino-Perdonas, Sara Guerrero-Aspizua

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

1509.06035 2015-09-22 cs.CV 70%

Image Retrieval Based on LBP Pyramidal Multiresolution using Reversible Watermarking

H. Ouahi, K. Afdel, M. Machkour

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

1810.04289 2026-06-04 physics.comp-ph cs.CE cs.DC cs.NA math.NA 69%

Simulation of unsteady blood flows in a patient-specific compliant pulmonary artery with a highly parallel monolithically coupled fluid-structure interaction algorithm

在患者特异性顺应性肺动脉中模拟瞬态血流的高并行单体耦合流-结构相互作用算法

Fande Kong, Vitaly Kheyfets, Ender Finol, Xiao-Chuan Cai

专题命中临床大模型：CT(abstract,abstract_cn)；biomedical(comments)

AI总结本文提出了一种高并行算法，用于模拟患者特异性肺动脉中瞬态血流与动脉壁的相互作用，该算法在超算上可扩展至超过10000个处理器核心，首次实现了无假设刚性壁的全肺动脉瞬态血流模拟。

Comments 24 pages, 15 figures. Submitted to International Journal of Numerical Methods in Biomedical Engineering

2603.03916 2026-03-05 physics.med-ph 69%

A review of ventral hernia biomechanics

腹股沟疝生物力学综述

Victoria Joppin, Catherine Masson, David Bendahan, Thierry Bege

专题命中临床大模型：pathology(abstract)；diagnosis(abstract)；biomedical(comments)

AI总结本文综述探讨了腹疝的生物力学机制，强调生物力学在手术决策中的重要性，提出通过优化手术技术和材料选择以降低复发率。

Comments Journal of the mechanical behavior of biomedical materials, In press, pp.107159

2202.14001 2022-10-10 physics.med-ph 69%

Measurement and Analysis of Lobar Lung Deformation After a Change of Patient Position During Video-Assisted Thoracoscopic Surgery

Pablo Alvarez, Matthieu Chabanas, Stéphane Sikora, Simon Rouzé, Yohan Payan, Jean-Louis Dillenseger

专题命中临床大模型：CT(abstract)；diagnosis(abstract)；biomedical(comments)

Comments Accepted for publication in IEEE Transactions of Biomedical Engineering

2107.05990 2021-09-24 eess.IV cs.CV cs.LG 69%

Combining 3D Image and Tabular Data via the Dynamic Affine Feature Map Transform

Sebastian Pölsterl, Tom Nuno Wolf, Christian Wachinger

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

Comments Accepted at 2021 International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI)

2004.05640 2020-07-09 eess.IV cs.CV cs.LG 69%

Relational Learning between Multiple Pulmonary Nodules via Deep Set Attention Transformers

Jiancheng Yang, Haoran Deng, Xiaoyang Huang, Bingbing Ni, Yi Xu

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

Comments 2020 IEEE 17th International Symposium on Biomedical Imaging (ISBI 2020)

1907.07783 2019-09-10 eess.IV cs.CG cs.CV cs.LG 69%

Patient-specific Conditional Joint Models of Shape, Image Features and Clinical Indicators

Bernhard Egger, Markus D. Schirmer, Florian Dubost, Marco J. Nardin, Natalia S. Rost, Polina Golland

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

Comments Supplementary material: https://www.youtube.com/watch?v=gPoHP_iFQIA

Journal ref MICCAI 2019, the 22nd International Conference on Medical Image Computing and Computer Assisted Intervention, in Shenzhen, China

2310.06515 2023-10-11 q-bio.NC 68%

Identifying epileptogenic abnormality by decomposing intracranial EEG and MEG power spectra

Csaba Kozma, Gabrielle Schroeder, Tom Owen, Jane de Tisi, Andrew W. McEvoy, Anna Miserocchi, John Duncan, Yujiang Wang, Peter N. Taylor

专题命中临床大模型：pathology(abstract)；diagnosis(abstract)；分类 q-bio

1910.08157 2019-10-21 q-bio.QM cs.CV cs.LG eess.IV 68%

An Update on Machine Learning in Neuro-oncology Diagnostics

Thomas Booth

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

Comments arXiv admin note: substantial text overlap with arXiv:1910.07440

2607.11175 2026-08-13 cs.AI 版本更新 67%

The Path to Self-Evolving Clinical Systems: Scaling Medical Agents from Assistance to Autonomy

自我进化临床系统之路：将医疗智能体从辅助扩展到自主

Chunzheng Zhu, Lei Tian, Bohan Tan, Ziqi Zhou, Yuxuan Sun, Yijun Wang, Chengchao Lv, Yilin Wen, Yijun He, Jinghao Lin, Yihang Chen, Chee Wei Tan, Qianshan Wei, Lei Zhao, Bin Pu, Kenli Li, Yuan Xue, Jianxin Lin

机构 * Hunan University（湖南大学）； ByteDance（字节跳动）； Duke University（杜克大学）； Westlake University（西湖大学）； The University of Hong Kong（香港大学）； Nanyang Technological University（南洋理工大学）； Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）； University of Macau（澳门大学）； The Ohio State University（俄亥俄州立大学）

专题命中临床大模型：pathology(abstract)；radiology(abstract)

AI总结研究探讨大语言模型等对医疗智能体的重塑，从临床部署出发，将其形式化为决策系统并给出自主性分类。沿统一框架扩展，强调临床环境扩展为关键方向，定位临床自我进化为前沿，还研究了多领域应用及挑战，提供医学成像系统路线图。

Comments Project page: https://github.com/zhcz328/Awesome-Medical-Agents

2607.15314 2026-08-05 cs.AI 版本更新 67%

Cura 1T: Specialized Model for Agentic Healthcare

Cura 1T：用于智能医疗保健的专用模型

actAVA AI, :, Haolin Chen, Leon Qi, Steve Brown, Deon Metelski, Tao Xia, Joonyul Lee, Qixuan Wang, Kevin Riley, Frank Wang, Weiran Yao

机构 * actAVA AI（actAVA人工智能公司）

专题命中临床大模型：healthcare AI(abstract)；diagnosis(abstract)

AI总结研究针对医疗保健中多任务需求及能力失效问题，提出通过人工门控自我进化循环训练的Cura 1T模型，以数据为中心改进模型，该模型在医疗评估套件中表现优异，在相关基准测试中保持竞争力。

Comments Model: https://actava.ai/cura; Docs: https://actava.ai/cura/docs; Github: https://github.com/actava-ai/Cura

2607.19631 2026-07-23 physics.flu-dyn 新提交 67%

svMultiPhysics: a finite element-based solver for cardiovascular simulations

svMultiPhysics：一种用于心血管模拟的基于有限元的求解器

David Codoni, Sujal Dave, David W. Parker, Aaron L. Brown, Javiera Jilberto, Han Zhao, Divya Adil, Zachary A. Sexton, Martin R. Pfaller, Michele Bucelli, Shawn C. Shadden, Charles A. Taylor, Alison L. Marsden

专题命中临床大模型：pathology(abstract)；diagnosis(abstract)

AI总结研究旨在借助计算建模改善心脏病相关研究。核心方法是用C++编写的开源并行有限元求解器svMultiPhysics，它能统一模拟多物理场心血管问题的方程，可独立或耦合求解。主要贡献是为心血管研究提供强大平台，实现多物理场耦合模拟，加速模拟且促进开源协作。

2607.00472 2026-07-02 eess.IV cs.AI cs.CV cs.LG 新提交 67%

Predicting Lethal Outcome (Cause) And Understanding Key Biomarkers Linked With Acute Myocardial Infarction Using Deep Artificial Neural Network And Ensemble Of Machine Learning Methodologies

使用深度人工神经网络和集成机器学习方法预测急性心肌梗死的致命结果（原因）并理解关键生物标志物

Sagnik Ghosh

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

AI总结提出一种结合深度人工神经网络与集成机器学习（逻辑回归、随机森林、Light-GBM、Bagging SVM）的自动化模型，用于预测急性心肌梗死致命结果并识别关键生物标志物，旨在提高诊断速度和准确性。

Comments Master of Science (MSc), Thesis Report

1. 临床大模型 951 篇

Beyond Patient Invariance: Learning Cardiac Dynamics via Action-Conditioned JEPAs

Smart Operation Theatre: An AI-based System for Surgical Gauze Counting

SGEMAS: A Self-Growing Ephemeral Multi-Agent System for Unsupervised Online Anomaly Detection via Entropic Homeostasis

SigTime: Learning and Visually Explaining Time Series Signatures

A Hybrid Enumeration Framework for Optimal Counterfactual Generation in Post-Acute COVID-19 Heart Failure

The CRITICAL Records Integrated Standardization Pipeline (CRISP): End-to-End Processing of Large-scale Multi-institutional OMOP CDM Data

Patient-Aware Feature Alignment for Robust Lung Sound Classification:Cohesion-Separation and Global Alignment Losses

CUPCase: Clinically Uncommon Patient Cases and Diagnoses Dataset

Large Language Models for Medical Forecasting -- Foresight 2

Using text embedding models as text classifiers with medical data

ChatCAD+: Towards a Universal and Reliable Interactive CAD using LLMs

Self-supervised 3D Patient Modeling with Multi-modal Attentive Fusion

Several categories of Large Language Models (LLMs): A Short Survey

Digital Twins for Patient Care via Knowledge Graphs and Closed-Form Continuous-Time Liquid Neural Networks

Path to Medical AGI: Unify Domain-specific Medical LLMs with the Lowest Cost

Building Trust: Lessons from the Technion-Rambam Machine Learning in Healthcare Datathon Event

Exploring deep learning methods for recognizing rare diseases and their clinical manifestations from texts

Image Retrieval Based on LBP Pyramidal Multiresolution using Reversible Watermarking

Simulation of unsteady blood flows in a patient-specific compliant pulmonary artery with a highly parallel monolithically coupled fluid-structure interaction algorithm

A review of ventral hernia biomechanics

Measurement and Analysis of Lobar Lung Deformation After a Change of Patient Position During Video-Assisted Thoracoscopic Surgery

Combining 3D Image and Tabular Data via the Dynamic Affine Feature Map Transform

Relational Learning between Multiple Pulmonary Nodules via Deep Set Attention Transformers

Patient-specific Conditional Joint Models of Shape, Image Features and Clinical Indicators

Identifying epileptogenic abnormality by decomposing intracranial EEG and MEG power spectra

An Update on Machine Learning in Neuro-oncology Diagnostics

The Path to Self-Evolving Clinical Systems: Scaling Medical Agents from Assistance to Autonomy

Cura 1T: Specialized Model for Agentic Healthcare

svMultiPhysics: a finite element-based solver for cardiovascular simulations

Predicting Lethal Outcome (Cause) And Understanding Key Biomarkers Linked With Acute Myocardial Infarction Using Deep Artificial Neural Network And Ensemble Of Machine Learning Methodologies