PRISM: A Transformer-based Language Model of Structured Clinical Event Data
This work addresses the need for better clinical decision support and simulation tools in healthcare by applying generative language modeling to structured medical event data.
The paper tackled the problem of modeling clinical decision-making processes by framing them as tokenized sequences of events, and introduced PRISM, a transformer-based model that predicts next steps in patient diagnostic journeys, showing substantial improvements over random baselines in next-token prediction tasks.
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.