Journal article · 2026 · Open access

TrajOnco: a multi-agent framework for temporal reasoning over longitudinal EHR for multi-cancer early detection

Sihang Zeng, Young Won Kim, Wilson Lau, Ehsan Alipour, Ruth Etzioni, Meliha Yetisgen, Anand Oka

npj Digital Medicine · Published 15 October 2026 · DOI 10.1038/s41746-026-03377-9

Open PDFView at the publisherCite this paper

In brief

“TrajOnco: a multi-agent framework for temporal reasoning over longitudinal EHR for multi-cancer early detection” is a 2026 journal article by Sihang Zeng and 6 co-authors, published in npj Digital Medicine. OpenAlex counts 2 citations as of 17 November 2026, which puts it in the top 6% of works published in 2026 by citations. It is open access under a CC BY licence: the full text is free to read at npj Digital Medicine.

Citations
2
Most cited in
2026 (2)
Field-weighted impact
2.16
References
57
Authors
7

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.

Cite this paper

Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.

APA 7

Zeng, S., Kim, Y. W., Lau, W., Alipour, E., Etzioni, R., Yetisgen, M., & Oka, A. (2026). TrajOnco: a multi-agent framework for temporal reasoning over longitudinal EHR for multi-cancer early detection. npj Digital Medicine. https://doi.org/10.1038/s41746-026-03377-9

MLA 9

Zeng, Sihang, et al. “TrajOnco: a multi-agent framework for temporal reasoning over longitudinal EHR for multi-cancer early detection.” npj Digital Medicine, 2026. https://doi.org/10.1038/s41746-026-03377-9.

Chicago

Zeng, Sihang, Young Won Kim, Wilson Lau, Ehsan Alipour, Ruth Etzioni, Meliha Yetisgen, and Anand Oka. 2026. “TrajOnco: a multi-agent framework for temporal reasoning over longitudinal EHR for multi-cancer early detection.” npj Digital Medicine. https://doi.org/10.1038/s41746-026-03377-9.

Harvard

Zeng, S. et al. (2026) ‘TrajOnco: a multi-agent framework for temporal reasoning over longitudinal EHR for multi-cancer early detection’, npj Digital Medicine. doi:10.1038/s41746-026-03377-9.

IEEE

S. Zeng et al., “TrajOnco: a multi-agent framework for temporal reasoning over longitudinal EHR for multi-cancer early detection,” npj Digital Medicine, 2026, doi: 10.1038/s41746-026-03377-9.

BibTeX

@article{zeng2026trajonco,
  title     = {{TrajOnco: a multi-agent framework for temporal reasoning over longitudinal EHR for multi-cancer early detection}},
  author    = {Zeng, Sihang and Kim, Young Won and Lau, Wilson and Alipour, Ehsan and Etzioni, Ruth and Yetisgen, Meliha and Oka, Anand},
  journal   = {npj Digital Medicine},
  year      = {2026},
  doi       = {10.1038/s41746-026-03377-9},
  url       = {https://doi.org/10.1038/s41746-026-03377-9}
}

Download for a reference manager: BibTeX (.bib) · RIS for Zotero, Mendeley and EndNote (.ris)

Topic and keywords

Physical Sciences › Computer Science › Artificial Intelligence › Machine Learning in Healthcare

  • multi-agent large language models
  • multi-cancer early detection
  • cancer risk prediction
  • temporal reasoning
  • longitudinal electronic health records
  • long-term memory
  • zero-shot learning
  • explainable reasoning

Work with this paper

Most-cited papers in Computer Science

All highly cited Computer Science papers

Questions about this paper

How do I cite this paper in APA style?

Zeng, S., Kim, Y. W., Lau, W., Alipour, E., Etzioni, R., Yetisgen, M., & Oka, A. (2026). TrajOnco: a multi-agent framework for temporal reasoning over longitudinal EHR for multi-cancer early detection. npj Digital Medicine. https://doi.org/10.1038/s41746-026-03377-9

How many times has this paper been cited?

2 times, according to OpenAlex on 17 November 2026. Google Scholar and Scopus count different sets of sources, so their numbers differ.

Is this paper free to read?

Yes. It is open access at npj Digital Medicine: sign in and open the PDF from this page.

Who wrote this paper?

Sihang Zeng, Young Won Kim, Wilson Lau, Ehsan Alipour, Ruth Etzioni, Meliha Yetisgen, Anand Oka.

What is the DOI of this paper?

10.1038/s41746-026-03377-9, permanently at https://doi.org/10.1038/s41746-026-03377-9. Sign in and open it from this page.

Bibliographic data from OpenAlex (CC0), last checked 17 November 2026. ResearchGuru does not host this paper; once you are signed in, the links open it at the publisher or the repository that does.