1
2
小米冠名中国三大汽车赛事，YU7 GT 医疗车首次亮相赛道
小米首次冠名中国三大汽车赛事，YU7 GT医疗车赛道亮相，展现品牌跨界新动作。
IT之家 5 月 23 日消息，小米汽车今日宣布，今年，小米冠名的中国汽车场地职业联赛、中国超级跑车锦标赛、中国汽车耐力锦标赛三大汽车场地赛事， 后续都会使用 YU7 GT 作为医疗车 。今天的 CHINA GT 宁波站，小米 YU7 GT 医疗车首次亮相赛道。 IT之家注意到，今年 3 月，雷军宣…
3
对话王小川：离开通用人工智能的主干道之后
王小川放弃通用大模型主赛道，专注医疗AI：深度对话解读M4模型与百小医的转型逻辑与焦虑。
“如果没有转型，继续走主流道路，你也会有同等程度的焦虑。”王小川说，这次转型，让他真正回归到从创业第一天就最想做的事情：造AI医生。 访谈｜邓咏仪 杨轩 文｜邓咏仪 编辑｜张雨忻 一年前，王小川带着百川智能来了一次激烈的“大刹车”：大幅缩减通用模型团队，关闭金融等多条行业线，All in医疗大模型。…
4
AdventHealth advances whole-person care with OpenAI
医疗巨头如何用ChatGPT省下行政时间，把更多精力还给患者。
AdventHealth is using ChatGPT for Healthcare to streamline workflows, reduce administrative burden, and return more time to patient care.
5
圆桌对话：看见实效：从技术到处方，AI +医疗的场景落地与价值闭环| 2026AI Partner·北京亦庄AI+产业大会
从五年前的技术炫技到今天的临床刚需，AI+医疗终于走过了“证明我能”的喧嚣，进入“解决痛点”的深水区。不做替代医生的空想，只做减轻负担的助手——这场对话告诉我们，AI医疗落地的第一步不是说服院长，而是赢得科室主任的信任；关键不是单点突破，而是多元数据联动形成闭环 圆桌对话直面AI进医院的真实卡点：系…
6
Evaluating the Utility of Personal Health Records in Personalized Health AI
最新arXiv研究系统评估个人健康记录对个性化健康AI的效用，揭示数据价值与挑战
arXiv:2605.18937v1 Announce Type: new Abstract: Patient-managed Personal Health Records (PHRs) promises to empower patients to better understand their…
7
国家药监局批准染色体核型图像辅助诊断软件上市，可自动完成染色体的切割、计数及异常辅助提示等
国家药监局正式批准AI辅助染色体核型诊断软件，自动完成切割、计数与异常提示，医疗AI落地再提速。
IT之家 5 月 21 日消息，据国家药监局新闻宣传中心公众号“中国药闻”分享，近日，国家药品监督管理局批准了杭州德适生物科技股份有限公司的染色体核型图像辅助诊断软件注册申请。 据介绍，该产品由软件安装光盘和 U 盾组成，软件功能模块包括用户登录界面模块、主界面模块和分析界面模块。 该产品用于外周血…
8
Do LLMs Triage Like Clinicians? A Dynamic Study of Outpatient Referral
最新研究对比LLM与临床医生的门诊分诊表现，动态揭示AI在医疗决策中的潜力与局限。
arXiv:2503.08292v5 Announce Type: replace Abstract: Outpatient referral (OR) is a core clinical workflow that assigns patients to hospital departments…
9
PhysioSeq2Seq: A Hybrid Physiological Digital Twin and Sequence-to-Sequence LSTM for Long-Horizon Glucose Forecasting in Type 1 Diabetes
用混合数字孪生+LSTM实现1型糖尿病长期血糖预测，精准度突破现有方法。
arXiv:2605.16860v1 Announce Type: new Abstract: Accurate long-horizon glucose forecasting is critical for automated insulin delivery systems, which he…
10
Artificial Intolerance: Stigmatizing Language in Clinical Documentation Skews Large Language Model Decision-Making
临床文档里的污名化语言，会如何悄悄带偏大模型的医疗决策？这篇论文揭秘偏见机制
arXiv:2605.17228v1 Announce Type: new Abstract: Large Language Models (LLMs) are increasingly deployed in high-stakes domains such as clinical decisio…
11
Entry-level guide to the use of large language models for medical research
为医学研究者打造的LLM入门指南，系统讲解如何在科研中应用大语言模型
arXiv:2410.18856v4 Announce Type: replace-cross Abstract: Frontier large language models (LLMs), such as GPT-5, Claude 4.5, Gemini 3, Llama 4, and Dee…
12
Synthesis and Evaluation of Long-term History-aware Medical Dialogue
医学对话系统如何理解数轮前的病史？这篇被AAMAS 2026录用的论文提出合成与评估长程历史感知对话的新方法。
arXiv:2605.19766v1 Announce Type: new Abstract: An effective healthcare agent must be able to recall and reason over a patient's longitudinal medical …
13
Quantized Machine Learning Models for Medical Imaging in Low-Resource Healthcare Settings
量化技术让机器学习模型在低资源医疗影像场景下也能高效运行，大幅降低算力门槛，加速基层医疗智能化。
arXiv:2605.19207v1 Announce Type: cross Abstract: Deep learning models have shown strong performance in medical image analysis, but deploying them in …
14
ExECG: An Explainable AI Framework for ECG models
可解释AI赋能心电图分析，ExECG框架让模型不再黑箱，医疗AI可信任度再升级。
arXiv:2605.19258v1 Announce Type: new Abstract: Deep learning has enabled ECG diagnostic models with strong performance in tasks such as arrhythmia cl…
15
Patients Speak, AI Listens: LLM-based Analysis of Online Reviews Uncovers Key Drivers for Urgent Care Satisfaction
用LLM挖掘在线患者评论，揭示紧急护理满意度的关键驱动因素，医疗AI新视角
arXiv:2503.20981v2 Announce Type: replace Abstract: Investigating the public experience of urgent care facilities is essential for promoting community…
16
Adversarial Fragility and Language Vulnerability in Clinical AI: A Systematic Audit of Diagnostic Collapse Under Imperceptible Perturbations and Cross-Lingual Drift in Low-Resource Healthcare Settings
临床AI系统在细微扰动和多语言场景下存在诊断崩溃风险，这篇系统性审计揭开了安全漏洞。
arXiv:2605.16993v1 Announce Type: cross Abstract: Current clinical artificial intelligence (AI) systems are evaluated almost exclusively on clean, sta…
17
A Benchmark for Early-stage Parkinson's Disease Detection from Speech
首个从语音中检测早期帕金森病的标准化基准，填补跨研究比较空白。
arXiv:2605.14066v1 Announce Type: cross Abstract: Early-stage Parkinson's disease (EarlyPD) detection from speech is clinically meaningful yet underex…
18
GLT-PEFT: Gated Lie-Tucker Parameter-Efficient Fine-Tuning for Alzheimer's Disease Diagnosis with Hippocampal Segmentation Pretraining
提出GLT-PEFT新范式，用门控李-塔克分解实现参数高效微调，专攻阿尔茨海默病诊断中的海马分割预训练。
arXiv:2605.16769v1 Announce Type: new Abstract: Parameter-efficient fine-tuning (PEFT) has emerged as a promising paradigm for adapting pretrained mod…
19
NYC Health and Hospitals says hackers stole medical data and fingerprints during breach affecting at least 1.8 million people
纽约最大公立医疗系统遭数据泄露，180万人医疗记录和指纹被盗，敲响医疗安全警钟
The New York public healthcare system said hackers stole personal and medical data, and scans of biometrics — including fingerprints — in one of the l…
20
How OpenEvidence built a healthcare AI that physicians actually trust
医生信赖的医疗AI如何通过Vercel实现零妥协扩展，从TikTok爆红到系统稳如磐石。
Andy Yoon was scrolling through Slack when he saw the message: OpenEvidence had gone viral on TikTok. Not "gaining traction.” Actually viral, reaching…