HemOncAgent: an artificial intelligence system for retrieving structured and narrative oncology knowledge
- 1Center for Clinical Cancer Informatics and Data Science, Legorreta Cancer Center, Brown University
Abstract
Oncology knowledge spans structured and unstructured datasets of drugs, regimens, conditions, and identifiers, as well as clinician-authored narratives describing treatment sequencing across disease settings. Answering clinical questions may require accessing both databases and free-text narratives, but existing intelligent retrieval systems favor either relational facts or narrative context. We developed HemOncAgent, an artificial intelligence agent that selects among retrieval tools for the HemOnc knowledge ecosystem: HemOncKB, a curated knowledge graph for pharmacologic relationships, and HemOnc.org, a narrative resource for care pathways. Across structured and narrative benchmarks, HemOncAgent maintained high-fidelity retrieval across question types for which single-source systems showed domain-specific limitations, supporting hybrid tool-based retrieval for more reliable oncology knowledge access.
Related
- Bias Mitigation Across the Healthcare Artificial Intelligence Lifecycle: A Structured Narrative Review
- Terminologia Anatomica Compliance in Generative Artificial Intelligence Outputs: A Structured Narrative Review and Terminology-Specific Verification Checklist.
- Progress in pharmacovigilance research based on artificial intelligence and real-world data: a structured narrative review.
- Artificial Intelligence-Driven Dietary Assessment Software: A Structured Narrative Review of Technological Advances, Persistent Measurement Error and Barriers to Clinical Translation
- Artificial intelligence in biomedical visualization and education: a narrative review
BibTeX
@misc{yang2026hemoncagent,
title = {{HemOncAgent: an artificial intelligence system for retrieving structured and narrative oncology knowledge}},
author = {A. J. Yang and H. A. Zaki and A. Seto and T. Kim and I. B. Riaz and A. Srisuwananukorn and A. J. Cowan and P. C. Yang and J. L. Warner},
howpublished = {medRxiv},
year = {2026},
month = sep,
doi = {10.64898/2026.09.09.26362651},
url = {https://www.medrxiv.org/content/10.64898/2026.09.09.26362651v1},
note = {CC BY},
}
RIS
TY - UNPB
TI - HemOncAgent: an artificial intelligence system for retrieving structured and narrative oncology knowledge
AU - A. J. Yang
AU - H. A. Zaki
AU - A. Seto
AU - T. Kim
AU - I. B. Riaz
AU - A. Srisuwananukorn
AU - A. J. Cowan
AU - P. C. Yang
AU - J. L. Warner
PY - 2026
DA - 2026/09/09
PB - medRxiv
DO - 10.64898/2026.09.09.26362651
UR - https://www.medrxiv.org/content/10.64898/2026.09.09.26362651v1
AB - Oncology knowledge spans structured and unstructured datasets of drugs, regimens, conditions, and identifiers, as well as clinician-authored narratives describing treatment sequencing across disease settings. Answering clinical questions may require accessing both databases and free-text narratives, but existing intelligent retrieval systems favor either relational facts or narrative context. We developed HemOncAgent, an artificial intelligence agent that selects among retrieval tools for the HemOnc knowledge ecosystem: HemOncKB, a curated knowledge graph for pharmacologic relationships, and HemOnc.org, a narrative resource for care pathways. Across structured and narrative benchmarks, HemOncAgent maintained high-fidelity retrieval across question types for which single-source systems showed domain-specific limitations, supporting hybrid tool-based retrieval for more reliable oncology knowledge access.
ER -