Clinically Interpretable Sepsis Early Warning via LLM-Guided Simulation of Temporal Physiological Dynamics
Addresses the need for interpretable sepsis early warning in intensive care, where opaque models limit clinical trust and adoption.
Proposed an LLM-guided temporal simulation framework for sepsis early warning that models physiological trajectories before disease onset, achieving AUC scores of 0.861-0.903 on MIMIC-IV and eICU databases, outperforming conventional methods while providing interpretable predictions.
Timely and interpretable early warning of sepsis remains a major clinical challenge due to the complex temporal dynamics of physiological deterioration. Traditional data-driven models often provide accurate yet opaque predictions, limiting physicians' confidence and clinical applicability. To address this limitation, we propose a Large Language Model (LLM)-guided temporal simulation framework that explicitly models physiological trajectories prior to disease onset for clinically interpretable prediction. The framework consists of a spatiotemporal feature extraction module that captures dynamic dependencies among multivariate vital signs, a Medical Prompt-as-Prefix module that embeds clinical reasoning cues into LLMs, and an agent-based post-processing component that constrains predictions within physiologically plausible ranges. By first simulating the evolution of key physiological indicators and then classifying sepsis onset, our model offers transparent prediction mechanisms that align with clinical judgment. Evaluated on the MIMIC-IV and eICU databases, the proposed method achieves superior AUC scores (0.861-0.903) across 24-4-hour pre-onset prediction tasks, outperforming conventional deep learning and rule-based approaches. More importantly, it provides interpretable trajectories and risk trends that can assist clinicians in early intervention and personalized decision-making in intensive care environments.