Artificial intelligence has significantly impacted medical applications, particularly with the advent of Medical Large Vision Language Models (Med-LVLMs), sparking optimism for the future of automated and personalized healthcare. However, the trustworthiness of Med-LVLMs remains unverified, posing significant risks for future model deployment. In this paper, we introduce CARES and aim to comprehensively evaluate the Trustworthiness of Med-LVLMs across the medical domain. We assess the trustworthiness of Med-LVLMs across five dimensions, including trustfulness, fairness, safety, privacy, and robustness. CARES comprises about 41K question-answer pairs in both closed and open-ended formats, covering 16 medical image modalities and 27 anatomical regions. Our analysis reveals that the models consistently exhibit concerns regarding trustworthiness, often displaying factual inaccuracies and failing to maintain fairness across different demographic groups. Furthermore, they are vulnerable to attacks and demonstrate a lack of privacy awareness. We publicly release our benchmark and code in https://cares-ai.github.io/.
A Corpus for Detecting High-Context Medical Conditions in Intensive Care Patient Notes Focusing on Frequently Readmitted Patients
Massachusetts Institute of Technology（麻省理工学院）；University of Massachusetts（马萨诸塞大学）；Harvard T.H. Chan School of Public Health（哈佛大学陈曾熙公共卫生学院）；Massachusetts General Hospital（麻省总医院）；Tufts University School of Medicine（塔夫茨大学医学院）；Beth Israel Deaconess Medical Center（贝斯以色列女执事医疗中心）；Washington University School of Medicine（华盛顿大学医学院）；Philips Research North America（飞利浦北美研究院）；Harvard University（哈佛大学）；Adobe Research（Adobe研究院）
MedVLM-R1: Incentivizing Medical Reasoning Capability of Vision-Language Models (VLMs) via Reinforcement Learning
Technical University of Munich (TUM)（慕尼黑工业大学（TUM））；TUM University Hospital（慕尼黑工业大学医院）；University of Oxford（牛津大学）；Imperial College London（伦敦帝国学院）；Massachusetts General Hospital（麻省总医院）；Harvard Medical School（哈佛医学院）；University of Sheffield（谢菲尔德大学）
Diabetica: Adapting Large Language Model to Enhance Multiple Medical Tasks in Diabetes Care and Management
Qing Yuan Research Institute, SEIEE, Shanghai Jiao Tong University（上海交通大学电子信息与电气工程学院清源研究院）；Zhongshan Hospital, Fudan University（复旦大学附属中山医院）；Qingpu Branch of Zhongshan Hospital, Affiliated to Fudan University（复旦大学附属中山医院青浦分院）
HSCR: Hierarchical Self-Contrastive Rewarding for Aligning Medical Vision Language Models
Zhejiang University（浙江大学）；Byte Dance（字节跳动）；National University of Singapore（新加坡国立大学）；Angelalign Inc China（Angelalign中国公司）；Zhejiang Key Laboratory of Medical Imaging Artificial Intelligence（浙江省医学影像人工智能重点实验室）
One Patient, Many Contexts: Scaling Medical AI with Contextual Intelligence
Harvard Medical School（哈佛医学院）；Clalit Research Institute（Clalit研究所）；Boston Children’s Hospital（波士顿儿童医院）；Harvard Data Science Initiative（哈佛数据科学计划）；Beth Israel Deaconess Medical Center（贝斯以色列女执事医疗中心）；Harvard T.H. Chan School of Public Health（哈佛大学陈曾熙公共卫生学院）；Clalit Health Services（Clalit医疗服务集团）；Ben Gurion University（本-古里安大学）；Ben Gurion University of the Negev（内盖夫本-古里安大学）；Brigham and Women’s Hospital（布莱根妇女医院）；Harvard University（哈佛大学）；Broad Institute of MIT and Harvard（麻省理工学院与哈佛大学布罗德研究所）
Dissecting Medical Referral Mechanisms in Health Services: Role of Physician Professional Networks
Instituto Superior Técnico, University of Lisbon（里斯本大学高等技术学院）；Nova School of Business and Economics, Universidade Nova de Lisboa（新里斯本大学诺瓦商业与经济学院）；Nova School of Science and Technology, Universidade Nova de Lisboa（新里斯本大学诺瓦科学与技术学院）
CARE: Towards Clinical Accountability in Multi-Modal Medical Reasoning with an Evidence-Grounded Agentic Framework
Microsoft Research Asia（微软亚洲研究院）；Department of Biomedical Engineering, Yale University（耶鲁大学生物医学工程系）；Department of Radiology & Biomedical Imaging, Yale University（耶鲁大学放射学与生物医学成像系）
Medical Foundation Models are Susceptible to Targeted Misinformation Attacks
University Hospital Aachen（亚琛大学医院）；University Medical Center of the Johannes Gutenberg-University（约翰内斯·古腾堡大学医学中心）；University Medicine Essen（埃森大学医学部）；Ocumeda GmbH（Ocumeda有限公司）；Charité - Universitätsmedizin Berlin（柏林夏里特医学院）；Freie Universität Berlin（柏林自由大学）；Humboldt Universität zu Berlin（柏林洪堡大学）；Berlin Institute of Health at Charité - Universitätsmedizin Berlin（柏林夏里特医学院柏林健康研究所）；Technical University Dresden（德累斯顿工业大学）；University Hospital Dresden（德累斯顿大学医院）；University Hospital Heidelberg（海德堡大学医院）
Synthesizing time-series wound prognosis factors from electronic medical records using generative adversarial networks
University of Wisconsin-Milwaukee（威斯康星大学密尔沃基分校）；AZH Wound and Vascular Center（AZH伤口与血管中心）
伤口预后模型不仅提供伤口愈合时间的估计，以激励患者随访治疗，而且还可以帮助临床医生决定是否使用标准护理或辅助治疗，并帮助他们设计临床试验。然而，由于隐私、敏感性和保密性，从患者的电子病历（EMR）中收集预后因素具有挑战性。在这项研究中，我们开发了时间序列医学生成对抗网络（GANs），使用在专业伤口护理机构的常规护理期间收集的非常有限的信息来生成合成伤口预后因素。生成的预后变量用于开发慢性伤口愈合轨迹的预测模型。我们的新型医学GAN可以从EMR中产生连续和分类特征。此外，我们通过考虑从患者每周随访中收集的数据，将时间信息应用于我们的模型。有条件的训练策略被用来加强训练，并产生愈合或非愈合方面的分类数据。通过TSTR（test on the synthetic，训练on the real）、判别精度和可视化等方法对该模型生成真实EMR数据的能力进行了评价。我们利用我们提出的GAN生成的样本来训练预后模型，以展示其实际应用。与以前的EMR-GAN相比，使用生成的样本训练预测模型将分类准确率提高了6.66-10.01%。此外，建议的预后分类器在使用前三次访视、前两次访视和首次访视的数据训练网络时，分别实现了0.975、0.968和0.849的曲线下面积（AUC）。这些结果表明，与以前的预后模型相比，伤口愈合预测有显著改善。
