Guardado en:
| Autores principales: | , , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | https://arxiv.org/abs/2510.10454 |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866909044218789888 |
|---|---|
| author | Zeng, Sihang Fu, Yujuan Zhou, Sitong Yu, Zixuan Liu, Lucas Jing Wen, Jun Thompson, Matthew Etzioni, Ruth Yetisgen, Meliha |
| author_facet | Zeng, Sihang Fu, Yujuan Zhou, Sitong Yu, Zixuan Liu, Lucas Jing Wen, Jun Thompson, Matthew Etzioni, Ruth Yetisgen, Meliha |
| contents | 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 temporal reasoning. To address these challenges, we introduce Traj-CoA, a multi-agent system involving chain-of-agents for patient trajectory modeling. Traj-CoA employs a chain of worker agents to process EHR data in manageable chunks sequentially, distilling critical events into a shared long-term memory module, EHRMem, to reduce noise and preserve a comprehensive timeline. A final manager agent synthesizes the worker agents' summary and the extracted timeline in EHRMem to make predictions. In a zero-shot one-year lung cancer risk prediction task based on five-year EHR data, Traj-CoA outperforms baselines of four categories. Analysis reveals that Traj-CoA exhibits clinically aligned temporal reasoning, establishing it as a promisingly robust and generalizable approach for modeling complex patient trajectories. Implementation of Traj-CoA is available on https://github.com/zengsihang/Traj-CoA. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_10454 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Traj-CoA: Patient Trajectory Modeling via Chain-of-Agents for Lung Cancer Risk Prediction Zeng, Sihang Fu, Yujuan Zhou, Sitong Yu, Zixuan Liu, Lucas Jing Wen, Jun Thompson, Matthew Etzioni, Ruth Yetisgen, Meliha Artificial Intelligence 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 temporal reasoning. To address these challenges, we introduce Traj-CoA, a multi-agent system involving chain-of-agents for patient trajectory modeling. Traj-CoA employs a chain of worker agents to process EHR data in manageable chunks sequentially, distilling critical events into a shared long-term memory module, EHRMem, to reduce noise and preserve a comprehensive timeline. A final manager agent synthesizes the worker agents' summary and the extracted timeline in EHRMem to make predictions. In a zero-shot one-year lung cancer risk prediction task based on five-year EHR data, Traj-CoA outperforms baselines of four categories. Analysis reveals that Traj-CoA exhibits clinically aligned temporal reasoning, establishing it as a promisingly robust and generalizable approach for modeling complex patient trajectories. Implementation of Traj-CoA is available on https://github.com/zengsihang/Traj-CoA. |
| title | Traj-CoA: Patient Trajectory Modeling via Chain-of-Agents for Lung Cancer Risk Prediction |
| topic | Artificial Intelligence |
| url | https://arxiv.org/abs/2510.10454 |