1
2
From Pixels to Prescriptions: Building an AI Pharmacist with YOLOv10 and RAG
用YOLOv10精准识别药品，结合RAG实现用药问答，零基础也能构建你的AI药师。
We’ve all been there: staring at a cluttered medicine cabinet, holding two different blister packs, and wondering, "Can I take these together?" In the…
3
ClinicalGPT-R1: Pushing reasoning capability of generalist disease diagnosis with large language model
面向全科疾病诊断的ClinicalGPT-R1，专注提升大模型临床推理能力，医学AI新突破。
arXiv:2504.09421v3 Announce Type: replace-cross Abstract: Recent advances in reasoning with large language models (LLMs)has shown remarkable reasoning…
4
Teaching LLMs How ICU Physicians Approach Clinical Reasoning Through OMOP-Aligned Retrieval Improves Reasoning Across Clinical Domains
用ICU医生的临床推理范式训练LLM检索，OMOP对齐让AI在跨医疗领域的推理能力显著提升。
arXiv:2608.22622v1 Announce Type: cross Abstract: Clinical decision-making relies on identifying relevant patient information to guide diagnosis and t…
5
Performance of a domain-specific large language model in answering patient questions in psychiatry
精神病学专用模型对战通用聊天机器人，评测医疗问答的临床准确性，AI落地医疗的新探索。
arXiv:2608.22797v1 Announce Type: new Abstract: Background This study was designed to evaluate whether a domain-specific large language model (LLM) tr…
6
MACD: Multi-Agent Clinical Diagnosis with Self-Learned Knowledge for LLM
多智能体协作+自学习知识，让大模型在临床诊断中更可靠。
arXiv:2509.20067v5 Announce Type: replace Abstract: Large language models (LLMs) have shown promise in supporting medical diagnosis, with prompting-ba…
7
Role-Specialized Mixture-of-Agents with Open-Weight LLMs for Clinical Prediction
多智能体角色分工协同开源大模型，精准提升临床预测表现，医疗AI新思路。
arXiv:2608.22176v1 Announce Type: new Abstract: Large Language Models (LLMs) are increasingly applied to clinical prediction tasks such as in-hospital…
8
阿里达摩院推出肝癌AI模型，精准识别1厘米微小肿瘤
肝癌CT筛查迎来AI“读片神器”，微小病灶难逃法眼，医疗AI进入精准诊断新阶段
8月24日消息，阿里巴巴达摩院联合中国医科大学附属盛京医院等机构研发出肝癌诊断AI模型DAMO LiON
9
联影医疗、天津大学发布全球首个磁共振脑机接口全栈式解决方案 uMR 神观
IT之家 8 月 23 日消息，由天津大学、脑机交互与人机共融海河实验室、联影医疗共同主办的全国首届磁共振脑机接口大会今日在天津市举办。 上海联影医疗科技股份有限公司与天津大学共同发布了 全球首个磁共振脑机接口全栈式解决方案“uMR 神观” ，该方案是以联影 uMR 系列设备为硬件基座，面向脑机接口…
10
亿万投资人马克 · 库班：医生应该教患者如何用 AI 来辅助治疗
库班给医疗AI指路：别谈取代，先教患者用AI辅助治疗。
IT之家 8 月 23 日消息，据《商业内幕》20 日报道，亿万富翁企业家马克 · 库班近期反驳了 AI 会取代医生的说法，并提出医生应该 主动帮助患者在治疗过程中使用 AI 。 库班认为，患者病情突然变化时，医生需要实时观察、沟通、共情并作出判断，这些能力并非 AI 可以复制。 不仅如此，他同时指…
11
AI isn’t close to curing cancer. This startup says it knows what it will take.
AI治癌盲目乐观？这家创业公司直言现有模型缺数据，戳破药物研发九成失败率的残酷现实。
It's the data, stupid.
12
OpenAI 前高管：相信 AI 能治愈所有疾病，但光靠大模型远远不够
AI 治病不能只靠大模型，还需要生物学基础设施同步进化，一文看懂关键分歧。
IT之家 8 月 18 日消息，曾任 OpenAI 高管、同时也是生物医药初创公司 ChronicleBio 联合创始人的 Fidji Simo 表示，她相信人工智能最终能够治愈所有疾病，但仅仅让 AI 模型变得更加智能，并不足以实现这一目标。 Simo 当地时间周一在 X 上回应了 Anthrop…
13
Fmr OpenAI exec Fidji Simo discusses POTS battle and plan to cure it with AI
POTS困扰多年，前OpenAI高管Fidji Simo亲述逆袭计划，AI如何成为她的终极解药？
Article URL: https://finance.yahoo.com/healthcare/articles/exclusive-former-openai-exec-fidji-192343263.html Comments URL: https://news.ycombinator.co…
14
Toddler's tragic death from brain-destroying amoeba offers lessons for doctors
罕见阿米巴感染摧毁幼儿大脑，医生为何错失救治时机？症状特征与诊断盲点解析，为医学诊疗提供重要警示。
Boy's unusual symptoms could help identify the next case sooner.
15
CARE: Confidence-Aware Reasoning for Reliable Medical VQA
医疗视觉问答也能“知道何时不懂”，置信度感知推理让AI诊断更可靠
arXiv:2608.10964v1 Announce Type: new Abstract: Reinforcement Fine-Tuning (RFT) has enabled medical Multimodal Large Language Models (MLLMs) to produc…
16
Validated Synthetic Patient Generation for Small Longitudinal Cohorts: Coagulation Dynamics Across Pregnancy
用AI合成患者数据破解小样本难题，精准还原妊娠凝血动态变化，医学研究新利器。
arXiv:2604.07557v2 Announce Type: replace Abstract: Small longitudinal cohorts, common in maternal health, rare diseases, and early-phase trials, limi…
17
MammoMix: Leveraging Mixture of Experts for Robust Mammogram Breast Detection
把混合专家模型用于乳腺钼靶检测，提升模型鲁棒性，医学影像AI值得一看的新思路。
arXiv:2608.10437v1 Announce Type: new Abstract: Breast lesion detection in mammography remains a challenging task due to variations in image quality, …
18
ConfTriage: A Calibration-Aware LLM Triage Framework for Pulmonary Nodule Malignancy with Selective Specialist Deferral
医学影像遇上大模型：校准感知的LLM分诊框架，对肺结节恶性风险智能判断，必要时转交专科医生，兼顾效率与安全。
arXiv:2608.10885v1 Announce Type: new Abstract: Pulmonary nodule malignancy prediction typically depends on image-trained specialist deep learning (DL…
19
When Confidence Fails: Overconfidence in LLMs under Uncertainty and Missing Clinical Information
当临床信息不完整时，大模型可能“迷之自信”，这项研究揭示风险并敲响医疗AI安全警钟。
arXiv:2608.09080v1 Announce Type: cross Abstract: Large Language Models (LLMs) have achieved strong performance in medical question answering and clin…
20
Your FHIR Sandbox Looks the Part. Nobody in It Has Aged.
为FHIR沙箱生成随真实时间老化的患者数据，让测试环境告别静止假数据，回归生产级真实感。
Epic's sandbox, an integration platform's dev environment, and the JSON fixtures in your repo. Pick any patient out of Open Epic's sandbox. Camila Lop…