TrajOnco:利用纵向电子健康记录进行时间推理的多智能体多癌种早期检测框架
TrajOnco: a multi-agent framework for temporal reasoning over longitudinal EHR for multi-cancer early detection
TrajOnco 是一个基于纵向电子健康记录进行时间推理的多智能体大语言模型框架,用于多癌种早期检测。在去标识化的 Truveta EHR 数据上,该框架对15种癌症的匹配病例对照队列预测1年内癌症诊断风险,零样本AUROC为0.64–0.80,在肺癌基准中与监督式机器学习相当,时间推理优于单智能体LLM。
该框架无需训练即可在15种癌症的零样本风险预测中达到与监督模型相当的水平,其可解释输出或有助于临床洞察。
- Article
- Open access
- Published: 15 October 2026
- Sihang Zeng ORCID: orcid.org/0009-0003-2921-829X1,2,3,
- Young Won Kim1,
- Wilson Lau1,
- Ehsan Alipour1,
- Ruth Etzioni2,3,
- Meliha Yetisgen2 &
- …
- Anand Oka1
npj Digital Medicine (2026) Cite this article
We’re sharing this article early to provide faster access to peer-reviewed, accepted research. It is citable and carries a permanent DOI. This version is subject to further edits and will be replaced automatically by the final Version of Record. All legal disclaimers apply.
Abstract
Accurate estimation of cancer risk from longitudinal electronic health records (EHRs) could support earlier detection and improved care, but modeling such complex patient trajectories remains challenging. We present TrajOnco, a training-free, multi-agent large language model (LLM) framework designed for scalable multi-cancer early detection. Using a chain-of-agents architecture with long-term memory, TrajOnco performs temporal reasoning over sequential clinical events to generate patient-level summaries, evidence-linked rationales, and predicted risk scores. We evaluated TrajOnco on de-identified Truveta EHR data across 15 cancer types using matched case-control cohorts, predicting risk of cancer diagnosis at 1 year. In zero-shot evaluation, TrajOnco achieved AUROCs of 0.64–0.80, performing comparably to supervised machine learning in a lung cancer benchmark while demonstrating better temporal reasoning than single-agent LLMs. The multi-agent design also enabled effective temporal reasoning with smaller-capacity models such as GPT-4.1-mini. The groundedness of TrajOnco’s output was supported by human evaluation. Furthermore, TrajOnco’s interpretable reasoning outputs can be aggregated to reveal population-level risk patterns that align with established clinical knowledge. These findings highlight the potential of multi-agent LLMs to execute interpretable temporal reasoning over longitudinal EHRs, advancing both scalable multi-cancer early detection and clinical insight generation.
Funding
This work was supported by Truveta Inc., which provided data access and computing resources, and by the National Institutes of Health (NIH) under award number R35CA274442 to R.E.
Author information
Authors and Affiliations
Truveta Inc., Bellevue, WA, USA
Sihang Zeng, Young Won Kim, Wilson Lau, Ehsan Alipour & Anand Oka
University of Washington, Seattle, WA, USA
Sihang Zeng, Ruth Etzioni & Meliha Yetisgen
Fred Hutch Cancer Center, Seattle, WA, USA
Sihang Zeng & Ruth Etzioni
Authors
- Sihang Zeng
- Young Won Kim
- Wilson Lau
- Ehsan Alipour
- Ruth Etzioni
- Meliha Yetisgen
- Anand Oka
Corresponding author
Correspondence to Sihang Zeng.
Ethics declarations
Competing interests
Y.W.K., W.L., E.A., and A.O. are employees of Truveta Inc. S.Z. conducted this research during an internship at Truveta. R.E. and M.Y. declare no competing interests.
Additional information
Publisher’s note Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Open Access This article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if changes were made. The images or other third party material in this article are included in the article’s Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creativecommons.org/licenses/by/4.0/.
About this article
Cite this article
Zeng, S., Kim, Y.W., Lau, W. et al. TrajOnco: a multi-agent framework for temporal reasoning over longitudinal EHR for multi-cancer early detection. npj Digit. Med. (2026). https://doi.org/10.1038/s41746-026-03377-9
Received: 15 April 2026
Accepted: 27 September 2026
Published: 15 October 2026
DOI: https://doi.org/10.1038/s41746-026-03377-9
来源:Nature 健康护理主题 · nature.com