Problem
Research questions and friction points this paper is trying to address.
large language models
clinical prediction
unstructured text
medical world models
time-indexed queries
Future Querying: Can LLMs Serve as Implicit Medical World Models?
🤖 AI Summary
研究通过未来查询方法，利用大型语言模型处理非结构化临床文档，以预测患者未来情况，无需特定任务训练或特征工程。
📝 Abstract
Traditional clinical prediction models rely on task-specific pipelines and curated, structured data, which scale poorly and underutilize unstructured text. To address this, we introduce future querying, a paradigm that probes whether large language models (LLMs) can function as implicit medical world models by evaluating their ability to answer time-indexed clinical queries about a patient's future. Our framework operates on unstructured clinical documentation using endpoint-agnostic training, enabling a single model to answer diverse clinical queries over patient trajectories without manual feature engineering or task-specific retraining. We show that small, locally fine-tuned open-weight models can match or approach larger proprietary systems, making the framework suitable for privacy-preserving, on-premise deployment. Evaluated on a new synthetic medical reports dataset and real ICU notes from the MIMIC-IV dataset, our results provide encouraging evidence that LLMs can capture aspects of clinical dynamics.
Innovation
Methods, ideas, or system contributions that make the work stand out.
Future Querying
Implicit Medical World Models
Unstructured Clinical Documentation
Endpoint-Agnostic Training
On-Premise Deployment
🔎 Similar Papers
No similar papers found.
