PathwayLLM: Explainable Clinical Trajectory Modeling with Structured Pathways for Sepsis Prediction

Patient-level sepsis prediction requires models that track clinical deterioration over time and integrate heterogeneous structured evidence from electronic health records. We present PathwayLLM, a trajectory-based framework that grounds prediction on temporal signals, graph-structured evidence, and pathway-level clinical information derived from statistical dependency discovery. PathwayLLM follows a three-stage design. First, each observation window is encoded from multiple structured views, including physiological measurements, temporal dynamics, a heterogeneous patient-diagnosis-medication graph, and dependency-derived pathway signals. Second, these representations are injected into a pretrained language model as auxiliary contextual embeddings so that risk prediction and evidence-conditioned explanations can be learned jointly. Third, a Clinical Trajectory LSTM with Deterioration Attention aggregates window-level representations to highlight critical deterioration points and produce patient-level risk scores. On MIMIC-IV (15,410 ICU patients; 8.45% sepsis prevalence), PathwayLLM achieves AUROC 0.891 and AUPRC 0.724, outperforming strong time-series and pretrained baselines. External validation on eICU achieves AUROC 0.842 zero-shot and 0.867 after light fine-tuning. Ablation studies indicate that trajectory aggregation and structured clinical signals are key contributors, and clinician review suggests coherent, interpretable, and clinically relevant explanations.

Sepsis is a life-threatening reaction to infection, and recognizing it early can help clinicians begin treatment before a patient's condition worsens. This paper presents PathwayLLM, an AI approach for estimating sepsis risk from routinely collected electronic health record data. The system is designed to consider how a patient's condition changes over time and to combine different sources of clinical information rather than relying on a single measurement. It also aims to make its predictions easier to interpret by linking risk estimates to supporting clinical evidence. The goal is not to replace clinicians, but to provide an additional tool that may help identify high-risk patients earlier and support more informed clinical decision-making.