UC Berkeley 衍生公司 Knit Health 获 NEA 领投 3500 万美元 A 轮融资,发布医疗世界模型 Med-BEAM
UC Berkeley Spinout Knit Health Raises $35M Series A Led by NEA to Launch Med-BEAM World Model for Healthcare
UC Berkeley 出来的 Knit Health 拿了 NEA 领投的 3500 万美元,还发了 Med-BEAM。它学的不是病历文字,而是数亿次真实诊疗决策的时序,做患者轨迹预测,方向和文本类医疗模型很不一样。做医疗 AI 的人可以看看这条路能不能落地。
Knit Health 宣布完成 3500 万美元 A 轮融资,由 NEA(New Enterprise Associates)领投,公司为 UC Berkeley 衍生企业,同时发布医疗基础世界模型 Med-BEAM。
Med-BEAM 的技术路线与临床文本预测模型不同:它不从临床笔记中预测下一个词,而是在数亿条去标识化的纵向患者记录上训练,学习数十亿次真实医疗决策的经验序列,以建模患者病情随时间的演变轨迹。
这一定位将其归入医疗基础模型赛道,与以病历文本为核心的模型形成差异。对开发者和医疗机构而言,能否将决策序列的建模能力转化为可验证的临床应用,是判断这类世界模型价值的关键。
UC Berkeley Spinout Knit Health Raises $35M Series A Led by NEA to Launch Med-BEAM World Model for Healthcare
What You Should Know The Med-BEAM Architecture: Modeling Patient Trajectories from Billions of Clinical Decisions Rather than predicting the next word in a clinical note, Med-BEAM is engineered as a foundational world model trained on billions of real-world healthcare decisions across hundreds of millions of longitudinal, de-identified patient records. By learning directly from empirical sequences ... Read More
This report is categorized under AITOP's "Models" desk, focusing on US frontier AI labs and Silicon Valley technology leaders. Within our cross-regional analytical framework, it directly maps to AI developer toolchains, coding agents, and engineering workflows and US-China foundation model benchmarks and commercialization comparison. Key entities and technical topics under continuous tracking include Med-BEAM, Knit Health, NEA, medical AI.
Source attribution: curated from HIT Consultant (@Jasmine Pennic).