4 papers
Traj-Evolve: A Self-Evolving Multi-Agent System for Patient Trajectory Modeling in Lung Cancer Early Detection
Sihang Zeng, Matthew Thompson, Ruth Etzioni +1
Modeling patient trajectories from longitudinal electronic health records (EHRs) requires reasoning over sparse, noisy, and long-context multimodal sequences. Existing LLM-based mu…
The Dual-State Architecture for Reliable LLM Agents
Matthew Thompson
Large Language Models deployed as code generation agents exhibit stochastic behavior incompatible with the deterministic guarantees required by software engineering. We formalize t…
Traj-CoA: Patient Trajectory Modeling via Chain-of-Agents for Lung Cancer Risk Prediction
Sihang Zeng, Yujuan Fu, Sitong Zhou +6
Large language models (LLMs) offer a generalizable approach for modeling patient trajectories, but suffer from the long and noisy nature of electronic health records (EHR) data in…
Extracting COVID-19 Diagnoses and Symptoms From Clinical Text: A New Annotated Corpus and Neural Event Extraction Framework
Kevin Lybarger, Mari Ostendorf, Matthew Thompson +1
Coronavirus disease 2019 (COVID-19) is a global pandemic. Although much has been learned about the novel coronavirus since its emergence, there are many open questions related to t…