Evidence map›Paper›PMID 41544626›Full record

ArticleCancer cell2026

A context-augmented large language model for accurate precision oncology medicine recommendations.

Hyeji Jun, Yutaro Tanaka, Shreya Johri, Sabrina Y Camp, Erik L Bao, Filipe L F Carvalho, Dan Y Gui, Alexander C Jordan, Chris Labaki, Samantha D Martin and 10 more

Abstract read
PubMed Full text at PMC Publisher
In one paragraph

Article in Cancer cell, 2026. The graph could read no effect estimate from its abstract, so it casts no vote on the map. Cited by 3 papers.

0numbers the graph read from it
0cells of the map it votes in
3citing papers in PubMed
–field-weighted citation impact
1 · What the graph read from it

What it found

Each row is one number read from the abstract, on the scale the paper reported it, with its interval. Left of the dashed line favours the treatment, right favours the comparator. Under each row is the sentence it came from. New to these charts? A ten-minute tutorial.

The abstract states no effect estimate the extractor could read, or names no intervention and outcome on the map, so this paper lights no cell and moves no belief. It is still indexed, cited and linked below.

2 · The registry

The trial behind it

Trials whose registry record cites this paper, or whose number appears in the abstract. A trial that started after this paper was published is citing it as background, not reporting it.

Neither the registry nor the abstract names a trial number. If this is a trial report, that itself is worth knowing.

3 · Its place in the literature

Who cites it

3 citing papers in PubMed.

  1. Review
  2. Article
  3. Review
4 · The record

Corrections and comments

5 · Who and what money

Authors and funding

20 authors.

Hyeji JunDepartment of Medical Oncology, Dana-Farber Cancer Institute, Boston, MA 02115, USA; Broad Institute of Harvard and MIT, Cambridge, MA 02142, USA.
Yutaro TanakaBroad Institute of Harvard and MIT, Cambridge, MA 02142, USA; Department of Pediatric Oncology, Dana-Farber Cancer Institute, Boston, MA 02115, USA.
Shreya JohriDepartment of Medical Oncology, Dana-Farber Cancer Institute, Boston, MA 02115, USA; Broad Institute of Harvard and MIT, Cambridge, MA 02142, USA; Harvard Medical School, Boston, MA 02115, USA.
Sabrina Y CampDepartment of Medical Oncology, Dana-Farber Cancer Institute, Boston, MA 02115, USA; Broad Institute of Harvard and MIT, Cambridge, MA 02142, USA.
Erik L BaoDepartment of Medical Oncology, Dana-Farber Cancer Institute, Boston, MA 02115, USA; Broad Institute of Harvard and MIT, Cambridge, MA 02142, USA.
Filipe L F CarvalhoDepartment of Urology, Brigham and Women's Hospital, Boston, MA 02115, USA.
Dan Y GuiDepartment of Medical Oncology, Dana-Farber Cancer Institute, Boston, MA 02115, USA; Broad Institute of Harvard and MIT, Cambridge, MA 02142, USA; Harvard Medical School, Boston, MA 02115, USA.
Alexander C JordanDepartment of Medical Oncology, Dana-Farber Cancer Institute, Boston, MA 02115, USA; Broad Institute of Harvard and MIT, Cambridge, MA 02142, USA.
Chris LabakiDepartment of Medical Oncology, Dana-Farber Cancer Institute, Boston, MA 02115, USA; Department of Medicine, Beth Israel Deaconess Medical Center, Boston, MA 02215, USA.
Samantha D MartinBroad Institute of Harvard and MIT, Cambridge, MA 02142, USA; Department of Pediatric Oncology, Dana-Farber Cancer Institute, Boston, MA 02115, USA; Harvard Medical School, Boston, MA 02115, USA; Boston Children's Hospital, Boston, MA 02115, USA.
Matthew NagyBroad Institute of Harvard and MIT, Cambridge, MA 02142, USA; Department of Pediatric Oncology, Dana-Farber Cancer Institute, Boston, MA 02115, USA; Boston Children's Hospital, Boston, MA 02115, USA.
Tess A O'MearaDepartment of Medical Oncology, Dana-Farber Cancer Institute, Boston, MA 02115, USA; Broad Institute of Harvard and MIT, Cambridge, MA 02142, USA.
Theodora PappaDepartment of Medical Oncology, Dana-Farber Cancer Institute, Boston, MA 02115, USA; Broad Institute of Harvard and MIT, Cambridge, MA 02142, USA; Brigham and Women's Hospital, Boston, MA 02115, USA.
Erica Maria PimentaDepartment of Medical Oncology, Dana-Farber Cancer Institute, Boston, MA 02115, USA; Broad Institute of Harvard and MIT, Cambridge, MA 02142, USA.
Eddy SaadDepartment of Medical Oncology, Dana-Farber Cancer Institute, Boston, MA 02115, USA; Broad Institute of Harvard and MIT, Cambridge, MA 02142, USA.
David D YangDepartment of Medical Oncology, Dana-Farber Cancer Institute, Boston, MA 02115, USA; Department of Radiation Oncology, Brigham and Women's Hospital, Boston, MA 02115, USA.
Riaz GillaniBroad Institute of Harvard and MIT, Cambridge, MA 02142, USA; Department of Pediatric Oncology, Dana-Farber Cancer Institute, Boston, MA 02115, USA; Harvard Medical School, Boston, MA 02115, USA; Boston Children's Hospital, Boston, MA 02115, USA.
Alok K TewariDepartment of Medical Oncology, Dana-Farber Cancer Institute, Boston, MA 02115, USA; Broad Institute of Harvard and MIT, Cambridge, MA 02142, USA; Harvard Medical School, Boston, MA 02115, USA; Brigham and Women's Hospital, Boston, MA 02115, USA.
Brendan ReardonDepartment of Medical Oncology, Dana-Farber Cancer Institute, Boston, MA 02115, USA; Broad Institute of Harvard and MIT, Cambridge, MA 02142, USA.
Eliezer Van AllenDepartment of Medical Oncology, Dana-Farber Cancer Institute, Boston, MA 02115, USA; Broad Institute of Harvard and MIT, Cambridge, MA 02142, USA; Harvard Medical School, Boston, MA 02115, USA. Electronic address: eliezerm_vanallen@dfci.harvard.edu.

Funding

Physician Scientist Training in Cancer ResearchT32CA009172 · NCI · DANA-FARBER CANCER INSTITUTE · PI Jennifer R Brown, James A. DeCaprio · 1985 to 2026
$17.1M
Molecular Determinants of Response and Resistance to EZH2 and PARP inhibition in Prostate CancerP50CA272390 · NCI · DANA-FARBER CANCER INST · PI Steven P. Balk, Himisha Beltran · 2023 to 2026
$12.0M
Dissecting Convergent Somatic and Germline Alterations that Mediate the Origins and Evolution of Kidney CancerR01CA278980 · NCI · DANA-FARBER CANCER INST · PI Eliezer M Van Allen · 2024 to 2026
$2.1M
NCI NIH HHS P50 CA272390NCI NIH HHS R01 CA278980NCI NIH HHS T32 CA009172
6 · The paper itself

Abstract

The rapid expansion of molecularly informed therapies in oncology, coupled with evolving regulatory food and drug administration (FDA) approvals, poses a challenge for oncologists seeking to integrate precision oncology medicine into patient care. Large language models (LLMs) have clinical potential, but their reliance on general knowledge limits their ability to provide up-to-date and niche treatment recommendations. Here, we developed a retrieval-augmented generation (RAG)-LLM workflow using the molecular oncology almanac (MOAlmanac) and benchmarked it against an LLM-only approach for biomarker-driven treatment recommendations. Our RAG-LLM achieved up to 95% accuracy on synthetic queries and 93% on real-world queries collected from practicing oncologists. Finally, our study explored several prompting and retrieval strategies to enhance performance. Taken together, this approach may serve as valuable guidance for deploying LLMs to support cancer patients' treatment decisions in precision oncology clinical settings.

Indexed as

Large Language ModelsMedical OncologyNeoplasmsPrecision MedicineHumansArtificial intelligencebiomarker-driven therapycancer genomicsclinical AIclinical oncologyclinical queriesclinicogenomic knowledgecontext augmentationdecision support toollarge language modelLLMmolecular oncologyoncology databaseprecision cancer medicineprecision oncology therapyprompt engineeringprompt strategyRAGRAG-LLM frameworkreal-world clinical dataretrieval augmented generationtherapy predictiontherapy recommendationtreatment recommendation

Identifiers

PMID41544626
PMCPMC12811686

What OpenQuestion holds

Textmetadata
LicenceTDM
Read underepoch 390

Registered trials

None linked

Read under generation 80e0d062 · epoch 390. Bibliography from PubMed, PubMed Central and OpenAlex; grants from NIH RePORTER; trial links from ClinicalTrials.gov; estimates, votes and beliefs from the OpenQuestion graph.