用语言模型预测病人诊疗路径，让机器学会医生的思考顺序。
PRISM: A Transformer-based Language Model of Structured Clinical Event Data
- 将诊疗过程拆成事件序列，用Transformer建模其先后关系。
- 在真实数据上预测下一步诊疗行为，准确率显著高于随机猜测。
- 适合做临床决策支持、医疗模拟和医学教育的智能系统。
我们提出PRISM（Predictive Reasoning in Sequential Medicine），一种基于Transformer的架构，用于建模临床决策过程的时序演化。与传统孤立诊断分类不同，PRISM将临床轨迹视为诊断检验、实验室结果和诊断等事件组成的分词序列，学习预测患者诊疗路径中最可能的下一步。利用大规模自定义临床词汇表和自回归训练目标，PRISM能够捕捉长期患者时间线中的复杂依赖关系。实验表明，在下一步事件预测任务中，其表现显著优于随机基线，生成序列反映出真实的诊断路径、实验室结果演变及医生开单行为。这些结果证明了生成式语言建模技术在结构化医疗事件数据中的可行性，可应用于临床决策支持、模拟与教育。PRISM为基于序列的医疗建模奠定了基础，弥合了机器学习架构与真实诊疗推理之间的差距。
原文摘要 · Abstract (English)
We introduce PRISM (Predictive Reasoning in Sequential Medicine), a transformer-based architecture designed to model the sequential progression of clinical decision-making processes. Unlike traditional approaches that rely on isolated diagnostic classification, PRISM frames clinical trajectories as tokenized sequences of events - including diagnostic tests, laboratory results, and diagnoses - and learns to predict the most probable next steps in the patient diagnostic journey. Leveraging a large custom clinical vocabulary and an autoregressive training objective, PRISM demonstrates the ability to capture complex dependencies across longitudinal patient timelines. Experimental results show substantial improvements over random baselines in next-token prediction tasks, with generated sequences reflecting realistic diagnostic pathways, laboratory result progressions, and clinician ordering behaviors. These findings highlight the feasibility of applying generative language modeling techniques to structured medical event data, enabling applications in clinical decision support, simulation, and education. PRISM establishes a foundation for future advancements in sequence-based healthcare modeling, bridging the gap between machine learning architectures and real-world diagnostic reasoning.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。