Applications of Large Language Models in Radiation Oncology: From Workflow Automation to Clinical Intelligence

Yuzhen Ding , Jason Holmes , Yuexing Hao , Zhengliang Liu , Peilong Wang , Junjie Cui , Meiyun Cao , Caiwen Jiang

show 7 more authors

Shuoyang Wei Lin Zhao Chenbin Liu Lian Zhang Yunze Yang Tianming Liu Wei Liu

Authors on Pith no claims yet

Pith reviewed 2026-05-13 17:46 UTC · model grok-4.3

classification ⚛️ physics.med-ph

keywords large language modelsradiation oncologyworkflow automationclinical decision supportpatient safetyretrieval-augmented generationartificial intelligencemultimodal AI

0 comments

The pith

Large language models are shifting radiation oncology toward clinically grounded, auditable AI systems that improve workflow efficiency and patient safety.

A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.

The paper reviews recent uses of large language models in radiation oncology, such as fine-tuning for decision support, using agents to curate registries, and retrieval-augmented generation for evaluating radiotherapy plans. It also covers applications in patient safety analysis, electronic health record integration, and patient education. A sympathetic reader would care because these tools address the field's heavy documentation and data needs while aiming to keep systems auditable and safe for clinical use.

Core claim

This review establishes that applications of LLMs in radiation oncology, ranging from automated nomenclature standardization and protocol-aware plan evaluation to incident classification and multimodal contouring assistance, demonstrate a shift toward clinically grounded, auditable, and workflow-integrated AI systems that enhance efficiency, safety, and patient engagement.

What carries the argument

Large language models enhanced with domain-specific fine-tuning, autonomous agents, and modular retrieval-augmented generation, which process structured medical guidelines and data to support radiation oncology tasks.

If this is right

Automated registry curation by LLM agents improves data quality for research and quality assurance.
Protocol-aware evaluations reduce errors in radiotherapy planning.
Patient education systems using LLMs increase understanding and engagement.
Incident classification and root cause analysis enhance patient safety.
Multimodal LLMs enable context-aware contouring and treatment planning assistance.

Where Pith is reading between the lines

These are editorial extensions of the paper, not claims the author makes directly.

Integration with daily clinical tools could reduce clinician workload in routine documentation.
These systems may require ongoing validation to handle rare cases not in training data.
Future developments could include real-time feedback during treatment sessions.
Adoption might depend on regulatory approval for clinical decision support roles.

Load-bearing premise

The early studies and applications will translate to reliable, low-error performance in live clinical environments without introducing new risks from model hallucinations or incomplete context.

What would settle it

Demonstration of frequent model hallucinations or critical errors when LLMs are deployed in actual radiation oncology workflows, such as incorrect plan evaluations leading to unsafe treatments.

read the original abstract

Large language models (LLMs) have emerged as transformative tools in medicine, with strong capabilities in language understanding, reasoning, and structured information extraction. Radiation oncology is particularly well suited for LLM integration due to its data-intensive workflows, reliance on structured guidelines, and documentation burden. This review summarizes recent applications, including domain-specific fine-tuning for decision support, automated nomenclature standardization, registry curation using autonomous LLM agents, and protocol-aware radiotherapy plan evaluation using modular retrieval-augmented generation (RAG). Additional applications include patient safety analysis through incident classification and root cause analysis, electronic health record (EHR)-integrated communication, CT simulation order summarization, daily readiness briefings, and patient education systems. Emerging multimodal approaches enable context-aware contouring, while early studies show LLMs can assist treatment planning by interpreting dosimetric feedback. Together, these advances highlight a shift toward clinically grounded, auditable, and workflow-integrated AI systems that enhance efficiency, safety, and patient engagement.

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit. Tearing a paper down is the easy half of reading it; the pith above is the substance, this is the friction.

Desk Editor's Note private letter to a colleague

This is a review that rounds up existing LLM uses in radiation oncology but supplies no new data, checks, or validation of its own.

read the letter

This review pulls together the main ways people have tried applying large language models to radiation oncology tasks. It covers domain fine-tuning for decisions, RAG setups for plan checks, autonomous agents for registry work, incident classification, EHR notes, CT order summaries, and some multimodal contouring ideas. That list gives a decent snapshot of what is floating around in the literature right now. The authors do a straightforward job of grouping these examples and noting the data-heavy nature of the field as a reason LLMs might fit. No equations or derivations appear, so there is nothing to check on that front. The citation pattern looks like a normal sweep of recent papers on the topic. The soft spot is the closing claim that these efforts mark a shift toward clinically grounded, auditable systems that improve safety. The paper offers no error rates, hallucination tests, or live-clinic outcome numbers to support that. It simply describes what the cited studies attempted, and those are labeled as early work. Without any cross-check or quantitative summary here, the reliability part stays untested. This kind of overview is mainly useful for clinicians or medical AI researchers who want a quick map of current experiments rather than a source of proven methods. It is not the kind of paper that changes practice on its own. I would send it to peer review so referees can ask for tighter language on the limits of the cited evidence and perhaps a clearer section on what would count as real validation.

Axiom & Free-Parameter Ledger

0 free parameters · 0 axioms · 0 invented entities

The paper is a review and introduces no free parameters, axioms, or invented entities; all content rests on the existence and accuracy of the external studies it cites.

pith-pipeline@v0.9.0 · 5513 in / 1040 out tokens · 62909 ms · 2026-05-13T17:46:44.864628+00:00 · methodology

discussion (0)

Reference graph

Works this paper leans on

91 extracted references · 91 canonical work pages · 4 internal anchors

[1]

None of the above

Clinical Data Integration and Decision Support To understand the role of LLMs in radiation oncology, it is important to first examine the foundational components that enable their effective deployment. These include domain - specific data curation, model adaptation through supervised fine -tuning, and sys tematic benchmarking of model performance in clini...

work page 2024
[2]

high signal

Automation of Routine Clinical Tasks Building on these foundational methods, LLMs are increasingly being integrated into routine clinical workflows and core tasks in radiation oncology. Many of these activities— ranging from patient communication and order interpretation to chart review, contouring, and treatment planning —require synthesis of heterogeneo...

work page
[3]

Patient education and engagement are essential components of cancer care, yet existing approaches are often limited by st atic content and variable accessibility

Patient-Facing LLM Systems for Education and Engagement In addition to clinician -facing applications, LLMs are increasingly being explored for patient-facing use cases in radiation oncology. Patient education and engagement are essential components of cancer care, yet existing approaches are often limited by st atic content and variable accessibility. LL...

work page
[4]

Safety, Validation, and Implementation Considerations As LLM applications in radiation oncology expand from experimental use to clinical workflows, considerations of safety, validation, and implementation become increasingly central. While prior sections highlight promising use cases across data integration, workflow automation, and clinical decision supp...

work page
[5]

Summary and Conclusions LLM applications in radiation oncology are rapidly evolving from experimental demonstrations to workflow-integrated systems. The reviewed studies collectively indicate that clinically useful performance often depends on domain grounding —through fine - tuning on curated institutional data, retrieval of source -of-truth EHR fields, ...

work page
[6]

mental simulation

When extended to agentic architectures, such systems could coordinate specialized sub- agents for distinct tasks (e.g., image analysis, guideline retrieval, dose optimization, and safety checking), enabling end-to-end automation of complex radiotherapy pipelines while maintaining modularity and auditability at each step80, 81. A complementary and equally ...

work page
[7]

Artificial general intelligence for radiation oncology

Liu C, Liu Z, Holmes J, Zhang L, Zhang L, Ding Y, Shu P, Wu Z, Dai H, Li Y, Shen D, Liu N, Li Q, Li X, Zhu D, Liu T, Liu W. Artificial general intelligence for radiation oncology. Meta-Radiology. 2023;1(3):100045. doi: https://doi.org/10.1016/j.metrad.2023.100045

work page doi:10.1016/j.metrad.2023.100045 2023
[8]

Artificial intelligence in radiation oncology

Huynh E, Hosny A, Guthier C, Bitterman DS, Petit SF, Haas-Kogan DA, Kann B, Aerts HJWL, Mak RH. Artificial intelligence in radiation oncology. Nature Reviews Clinical Oncology. 2020;17(12):771-81. doi: 10.1038/s41571-020-0417-8

work page doi:10.1038/s41571-020-0417-8 2020
[9]

Proton beam therapy for locally advanced lung cancer: A review

Schild SE, Rule WG, Ashman JB, Vora SA, Keole S, Anand A, Liu W, Bues M. Proton beam therapy for locally advanced lung cancer: A review. World J Clin Oncol. 2014;5(4):568-75. Epub 2014/10/11. doi: 10.5306/wjco.v5.i4.568. PubMed PMID: 25302161; PMCID: PMC4129522

work page doi:10.5306/wjco.v5.i4.568 2014
[10]

Parameterization of multiple Bragg curves for scanning proton beams using simultaneous fitting of multiple curves

Zhang X, Liu W, Li Y, Li X, Quan M, Mohan R, Anand A, Sahoo N, Gillin M, Zhu XR. Parameterization of multiple Bragg curves for scanning proton beams using simultaneous fitting of multiple curves. Phys Med Biol. 2011;56(24):7725-35. Epub 2011/11/17. doi: 10.1088/0031- 9155/56/24/003. PubMed PMID: 22085829

work page doi:10.1088/0031- 2011
[11]

Matney J, Park PC, Bluett J, Chen YP, Liu W, Court LE, Liao Z, Li H, Mohan R. Effects of respiratory motion on passively scattered proton therapy versus intensity modulated photon therapy for stage III lung cancer: are proton plans more sensitive to breathing motion? International journal of radiation oncology, biology, physics. 2013;87(3):576-82. Epub 20...

work page doi:10.1016/j.ijrobp.2013.07.007 2013
[12]

Enabling clinical use of linear energy transfer in proton therapy for head and neck cancer – A review of implications for treatment planning and adverse events study

Chen J, Yang Y, Feng H, Liu C, Zhang L, Holmes JM, Liu Z, Lin H, Liu T, Simone CB, Lee NY, Frank SJ, Ma DJ, Patel SH, Liu W. Enabling clinical use of linear energy transfer in proton therapy for head and neck cancer – A review of implications for treatment planning and adverse events study. Vis Cancer Med. 2025;6:3

work page 2025
[13]

Critical review of patient outcome study in head and neck cancer radiotherapy

Chen J, Yang Y, Liu C, Feng H, Holmes J, Zhang L, Lin H, Lee N, Frank S, Simone CB, Ma DJ, Patel SH, Liu W. Critical review of patient outcome study in head and neck cancer radiotherapy. Meta-Radiology. 2025:100151. doi: https://doi.org/10.1016/j.metrad.2025.100151

work page doi:10.1016/j.metrad.2025.100151 2025
[14]

A Critical Review of LET-Based Intensity-Modulated Proton Therapy Plan Evaluation and Optimization for Head and Neck Cancer Management

Deng W, Yang Y, Liu C, Bues M, Mohan R, Wong WW, Foote RH, Patel SH, Liu W. A Critical Review of LET-Based Intensity-Modulated Proton Therapy Plan Evaluation and Optimization for Head and Neck Cancer Management. Int J Part Ther. 2021;8(1):36-49. Epub 2021/07/22. doi: 10.14338/IJPT-20-00049.1. PubMed PMID: 34285934; PMCID: PMC8270082

work page doi:10.14338/ijpt-20-00049.1 2021
[15]

Dynamically accumulated dose and 4D accumulated dose for moving tumors

Li H, Li Y, Zhang X, Li X, Liu W, Gillin MT, Zhu XR. Dynamically accumulated dose and 4D accumulated dose for moving tumors. Med Phys. 2012;39(12):7359-67. Epub 2012/12/13. doi: 10.1118/1.4766434. PubMed PMID: 23231285; PMCID: PMC3523466

work page doi:10.1118/1.4766434 2012
[16]

Shan J, Yang Y, Schild SE, Daniels TB, Wong WW, Fatyga M, Bues M, Sio TT, Liu W. Intensity-modulated proton therapy (IMPT) interplay effect evaluation of asymmetric breathing with simultaneous uncertainty considerations in patients with non-small cell lung cancer. Med Phys. 2020;47(11):5428-40. Epub 2020/09/24. doi: 10.1002/mp.14491. PubMed PMID: 32964474...

work page doi:10.1002/mp.14491 2020
[17]

PSA-Net: Deep learning–based physician style–aware segmentation network for postoperative prostate cancer clinical target volumes

Balagopal A, Morgan H, Dohopolski M, Timmerman R, Shan J, Heitjan DF, Liu W, Nguyen D, Hannan R, Garant A, Desai N, Jiang S. PSA-Net: Deep learning–based physician style–aware segmentation network for postoperative prostate cancer clinical target volumes. Artificial Intelligence in Medicine. 2021;121:102195. doi: https://doi.org/10.1016/j.artmed.2021.102195

work page doi:10.1016/j.artmed.2021.102195 2021
[18]

Deep‐learning based fast and accurate 3D CT deformable image registration in lung cancer

Ding Y, Feng H, Yang Y, Holmes J, Liu Z, Liu D, Wong WW, Yu NY, Sio TT, Schild SE. Deep‐learning based fast and accurate 3D CT deformable image registration in lung cancer. Medical Physics. 2023

work page 2023
[19]

Accurate Patient Alignment without Unnecessary Imaging Dose via Synthesizing Patient-specific 3D CT Images from 2D kV Images

Ding Y, Holmes JM, Feng H, Li B, McGee LA, Rwigema J-CM, Vora SA, Ma DJ, Foote RL, Patel SH. Accurate Patient Alignment without Unnecessary Imaging Dose via Synthesizing Patient-specific 3D CT Images from 2D kV Images. arXiv preprint arXiv:240519338. 2024

work page 2024
[20]

Technical note: Generalizable and promptable artificial intelligence model to augment clinical delineation in radiation oncology

Zhang L, Liu Z, Zhang L, Wu Z, Yu X, Holmes J, Feng H, Dai H, Li X, Li Q, Wong WW, Vora SA, Zhu D, Liu T, Liu W. Technical note: Generalizable and promptable artificial intelligence model to augment clinical delineation in radiation oncology. Medical Physics. 2024;51(3):2187-99. doi: https://doi.org/10.1002/mp.16965

work page doi:10.1002/mp.16965 2024
[21]

Streamlining Thoracic Radiotherapy Quality assurance: One-Class Classification for Automated OAR Contour Assessment

Zhao Y, Yuan C, Liang Y, Li Y, Li C, Zhao M, Hu J, Zhong N, Liu W, Liu C. Streamlining Thoracic Radiotherapy Quality assurance: One-Class Classification for Automated OAR Contour Assessment. Technol Cancer Res Treat. 2025;24:15330338251345895. Epub 20250522. doi: 10.1177/15330338251345895. PubMed PMID: 40400421; PMCID: PMC12099094

work page doi:10.1177/15330338251345895 2025
[22]

Beam mask and sliding window-facilitated deep learning-based accurate and efficient dose prediction for pencil beam scanning proton therapy

Zhang L, Holmes JM, Liu Z, Vora SA, Sio TT, Vargas CE, Yu NY, Keole SR, Schild SE, Bues M, Li S, Liu T, Shen J, Wong WW, Liu W. Beam mask and sliding window-facilitated deep learning-based accurate and efficient dose prediction for pencil beam scanning proton therapy. Med Phys. 2023. Epub 20230925. doi: 10.1002/mp.16758. PubMed PMID: 37748037

work page doi:10.1002/mp.16758 2023
[24]

Attention is All you Need

Vaswani A, Shazeer N, Parmar N, Uszkoreit J, Jones L, Gomez AN, Kaiser L, Polosukhin I, editors. Attention is All you Need. Neural Information Processing Systems; 2017

work page 2017
[25]

AugGPT: Leveraging ChatGPT for Text Data Augmentation

Dai H, Liu Z, Liao W, Huang X, Cao Y, Wu Z, Zhao L, Xu S, Zeng F, Liu W, Liu N, Li S, Zhu D, Cai H, Sun L, Li Q, Shen D, Liu T, Li X. AugGPT: Leveraging ChatGPT for Text Data Augmentation. IEEE Transactions on Big Data. 2025;11(03):907-18. doi: 10.1109/TBDATA.2025.3536934

work page doi:10.1109/tbdata.2025.3536934 2025
[26]

Mask-guided BERT for few-shot text classification

Liao W, Liu Z, Dai H, Wu Z, Zhang Y, Huang X, Chen Y, Jiang X, Liu D, Zhu D, Li S, Liu W, Liu T, Li Q, Cai H, Li X. Mask-guided BERT for few-shot text classification. Neurocomputing. 2024;610:128576. doi: https://doi.org/10.1016/j.neucom.2024.128576

work page doi:10.1016/j.neucom.2024.128576 2024
[27]

Instruction-ViT: Multi-modal prompts for instruction learning in vision transformer

Xiao Z, Chen Y, Yao J, Zhang L, Liu Z, Wu Z, Yu X, Pan Y, Zhao L, Ma C, Liu X, Liu W, Li X, Yuan Y, Shen D, Zhu D, Yao D, Liu T, Jiang X. Instruction-ViT: Multi-modal prompts for instruction learning in vision transformer. Information Fusion. 2023:102204. doi: https://doi.org/10.1016/j.inffus.2023.102204

work page doi:10.1016/j.inffus.2023.102204 2023
[28]

Knowledge distillation and dataset distillation of large language models: emerging trends, challenges, and future directions

Fang L, Yu X, Cai J, Chen Y, Wu S, Liu Z, Yang Z, Lu H, Gong X, Liu Y, Ma T, Ruan W, Abbasi A, Zhang J, Wang T, Latif E, Liu W, Zhang W, Kolouri S, Zhai X, Zhu D, Zhong W, Liu T, Ma P. Knowledge distillation and dataset distillation of large language models: emerging trends, challenges, and future directions. Artificial Intelligence Review. 2025;59(1):17....

work page doi:10.1007/s10462-025-11423-3 2025
[29]

Large language models for bioinformatics

Ruan W, Lyu Y, Zhang J, Cai J, Shu P, Ge Y, Lu Y, Gao S, Wang Y, Wang P, Zhao L, Wang T, Liu Y, Fang L, Liu Z, Liu Z, Li Y, Wu Z, Chen J, Jiang H, Pan Y, Yang Z, Chen J, Liang S, Zhang W, Ma T, Dou Y, Zhang J, Gong X, Gan Q, Zou Y, Chen Z, Qian Y, Yu S, Lu J, Song K, Wang X, Sikora A, Li G, Li X, Li Q, Wang Y, Zhang L, Abate Y, He L, Zhong W, Liu R, Huang...

work page doi:10.1002/qub2.70014 2026
[30]

Quantum artificial intelligence: A comprehensive survey

Jiang H, Pan Y, Chen J, Liu Z, Sun L, Li Q, Zhang L, Zhu D, Wang X, Liu W, Li X, Li G, Zhang W, Zhao L, Yu X, Wang Y, Liu T. Quantum artificial intelligence: A comprehensive survey. Meta-Radiology. 2026;4(1):100205. doi: https://doi.org/10.1016/j.metrad.2026.100205

work page doi:10.1016/j.metrad.2026.100205 2026
[31]

Artificial General Intelligence for Medical Imaging Analysis

Li X, Zhao L, Zhang L, Wu Z, Liu Z, Jiang H, Cao C, Xu S, Li Y, Dai H, Yuan Y, Liu J, Li G, Zhu D, Yan P, Li Q, Liu W, Liu T, Shen D. Artificial General Intelligence for Medical Imaging Analysis. IEEE Reviews in Biomedical Engineering. 2024. doi: 10.1109/RBME.2024.3493775

work page doi:10.1109/rbme.2024.3493775 2024
[32]

Survey on natural language processing in medical image analysis

Liu Z, He M, Jiang Z, Wu Z, Dai H, Zhang L, Luo S, Han T, Li X, Jiang X, Zhu D, Cai X, Ge B, Liu W, Liu J, Shen D, Liu T. Survey on natural language processing in medical image analysis. Zhong Nan Da Xue Xue Bao Yi Xue Ban. 2022;47(8):981-93. Epub 2022/09/14. doi: 10.11817/j.issn.1672-7347.2022.220376. PubMed PMID: 36097765

work page doi:10.11817/j.issn.1672-7347.2022.220376 2022
[33]

Radiology-GPT: A large language model for radiology

Liu Z, Li Y, Shu P, Zhong A, Jiang H, Pan Y, Yang L, Ju C, Wu Z, Ma C, Chen C, Kim S, Dai H, Zhao L, Sun L, Zhu D, Liu J, Liu W, Shen D, Li Q, Liu T, Li X. Radiology-GPT: A large language model for radiology. Meta-Radiology. 2025;3(2):100153. doi: https://doi.org/10.1016/j.metrad.2025.100153

work page doi:10.1016/j.metrad.2025.100153 2025
[34]

PharmacyGPT: Exploration of Artificial Intelligence for Medication Management in the Intensive Care Unit,

Liu Z, Xu S, Wu Z, Murray B, Barreto E, Most A, Li S, Liu W, Li X, Liu T, Sikora A. PharmacyGPT: Exploration of Artificial Intelligence for Medication Management in the Intensive Care Unit,. BMC Medical Informatics and Decision Making. 2025

work page 2025
[35]

Surviving ChatGPT in healthcare

Liu Z, Zhang L, Wu Z, Yu X, Cao C, Dai H, Liu N, Liu J, Liu W, Li Q, Shen D, Li X, Zhu D, Liu T. Surviving ChatGPT in healthcare. Front Radiol. 2023;3:1224682. Epub 20240223. doi: 10.3389/fradi.2023.1224682. PubMed PMID: 38464946; PMCID: PMC10920216

work page doi:10.3389/fradi.2023.1224682 2023
[36]

Tailoring Large Language Models to Radiology: A Preliminary Approach to LLM Adaptation for a Highly Specialized Domain

Liu Z, Zhong A, Li Y, Yang L, Ju C, Wu Z, Ma C, Shu P, Chen C, Kim S, Dai H, Zhao L, Zhu D, Liu J, Liu W, Shen D, Li Q, Liu T, Li X, editors. Tailoring Large Language Models to Radiology: A Preliminary Approach to LLM Adaptation for a Highly Specialized Domain. Machine Learning in Medical Imaging; 2024 2024//; Cham: Springer Nature Switzerland

work page 2024
[37]

ClinicalRadioBERT: Knowledge-Infused Few Shot Learning for Clinical Notes Named Entity Recognition

Rezayi S, Dai H, Liu Z, Wu Z, Hebbar A, Burns AH, Zhao L, Zhu D, Li Q, Liu W, Li S, Liu T, Li X, editors. ClinicalRadioBERT: Knowledge-Infused Few Shot Learning for Clinical Notes Named Entity Recognition. Machine Learning in Medical Imaging; 2022 2022//; Cham: Springer Nature Switzerland

work page 2022
[38]

A generalist vision–language foundation model for diverse biomedical tasks

Zhang K, Zhou R, Adhikarla E, Yan Z, Liu Y, Yu J, Liu Z, Chen X, Davison BD, Ren H, Huang J, Chen C, Zhou Y, Fu S, Liu W, Liu T, Li X, Chen Y, He L, Zou J, Li Q, Liu H, Sun L. A generalist vision–language foundation model for diverse biomedical tasks. Nature Medicine

work page
[39]

doi: 10.1038/s41591-024-03185-2

work page doi:10.1038/s41591-024-03185-2
[40]

Exploring the Trade-Offs: Unified Large Language Models vs Local Fine-Tuned Models for Highly-Specific Radiology NLI Task

Wu Z, Zhang L, Cao C, Yu X, Liu Z, Zhao L, Li Y, Dai H, Ma C, Li G, Liu W, Li Q, Shen D, Li X, Zhu D, Liu T. Exploring the Trade-Offs: Unified Large Language Models vs Local Fine-Tuned Models for Highly-Specific Radiology NLI Task. IEEE Transactions on Big Data. 2025;11(3):1027-41. doi: 10.1109/TBDATA.2025.3536928

work page doi:10.1109/tbdata.2025.3536928 2025
[41]

ChatRadio-Valuer: A Chat Large Language Model for Generalizable Radiology Impression Generation on Multi-institution and Multi-system Data

Zhong T, Zhao W, Zhang Y, Pan Y, Dong P, Jiang Z, Jiang H, Zhou Y, Kui X, Shang Y, Zhao L, Yang L, Wei Y, Li Z, Zhang J, Yang L, Chen H, Zhao H, Liu Y, Zhu N, Li Y, Wang Y, Yao J, Wang J, Zeng Y, He L, Zheng C, Zhang Z, Li M, Liu Z, Dai H, Wu Z, Zhang L, Zhang S, Cai X, Hu X, Zhao S, Jiang X, Zhang X, Liu W, Li X, Zhu D, Guo L, Shen D, Han J, Liu T, Liu J...

work page doi:10.1109/tbme.2025.3597325 2025
[42]

Med-VLM: Enhancing Medical Image Segmentation Accuracy through Vision-Language Model

Zhao Y, Zhong E, Yuan C, Li Y, Zhao M, Li C, Hu J, Liu W, Liu C. Med-VLM: Enhancing Medical Image Segmentation Accuracy through Vision-Language Model. 2025 ICCV PHAROS-AFE-AIMI Workshop 2025

work page 2025
[43]

Evaluating Large Language Models for Radiology Natural Language Processing2023 July 01, 2023:[arXiv:2307.13693 p.]

Liu Z, Zhong T, Li Y, Zhang Y, Pan Y, Zhao Z, Dong P, Cao C, Liu Y, Shu P, Wei Y, Wu Z, Ma C, Wang J, Wang S, Zhou M, Jiang Z, Li C, Holmes J, Xu S, Zhang L, Dai H, Zhang K, Zhao L, Chen Y, Liu X, Wang P, Yan P, Liu J, Ge B, Sun L, Zhu D, Li X, Liu W, Cai X, Hu X, Jiang X, Zhang S, Zhang X, Zhang T, Zhao S, Li Q, Zhu H, Shen D, Liu T. Evaluating Large Lan...

work page arXiv 2023
[44]

Holistic Evaluation of GPT-4V for Biomedical Imaging2023 November 01, 2023:[arXiv:2312.05256 p.]

Liu Z, Jiang H, Zhong T, Wu Z, Ma C, Li Y, Yu X, Zhang Y, Pan Y, Shu P, Lyu Y, Zhang L, Yao J, Dong P, Cao C, Xiao Z, Wang J, Zhao H, Xu S, Wei Y, Chen J, Dai H, Wang P, He H, Wang Z, Wang X, Zhang X, Zhao L, Liu Y, Zhang K, Yan L, Sun L, Liu J, Qiang N, Ge B, Cai X, Zhao S, Hu X, Yuan Y, Li G, Zhang S, Zhang X, Jiang X, Zhang T, Shen D, Li Q, Liu W, Li X...

work page arXiv 2023
[45]

The TRIPOD-LLM reporting guideline for studies using large language models

Gallifant J, Afshar M, Ameen S, Aphinyanaphongs Y, Chen S, Cacciamani G, Demner- Fushman D, Dligach D, Daneshjou R, Fernandes C, Hansen LH, Landman A, Lehmann L, McCoy LG, Miller T, Moreno A, Munch N, Restrepo D, Savova G, Umeton R, Gichoya JW, Collins GS, Moons KGM, Celi LA, Bitterman DS. The TRIPOD-LLM reporting guideline for studies using large languag...

work page doi:10.1038/s41591- 2025
[46]

Large language models for preventing medication direction errors in online pharmacies

Pais C, Liu J, Voigt R, Gupta V, Wade E, Bayati M. Large language models for preventing medication direction errors in online pharmacies. Nature Medicine. 2024;30(6):1574-

work page 2024
[47]

doi: 10.1038/s41591-024-02933-8

work page doi:10.1038/s41591-024-02933-8
[48]

Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks

Lewis P, Perez E, Piktus A, Petroni F, Karpukhin V, Goyal N, Kuttler H, Lewis M, Yih W-t, Rocktäschel T, Riedel S, Kiela D. Retrieval-Augmented Generation for Knowledge- Intensive NLP Tasks. ArXiv. 2020;abs/2005.11401

work page internal anchor Pith review Pith/arXiv arXiv 2020
[49]

LoRA: Low-Rank Adaptation of Large Language Models

Hu JE, Shen Y, Wallis P, Allen-Zhu Z, Li Y, Wang S, Chen W. LoRA: Low-Rank Adaptation of Large Language Models. ArXiv. 2021;abs/2106.09685

work page internal anchor Pith review Pith/arXiv arXiv 2021
[50]

Parameter-efficient fine-tuning large language model approach for hospital discharge paper summarization

Goswami J, Prajapati KK, Saha A, Saha AK. Parameter-efficient fine-tuning large language model approach for hospital discharge paper summarization. Applied Soft Computing. 2024;157:111531. doi: https://doi.org/10.1016/j.asoc.2024.111531

work page doi:10.1016/j.asoc.2024.111531 2024
[51]

An Automated Retrieval-Augmented Generation LLaMA-4 109B-based System for Evaluating Radiotherapy Treatment Plans

Cui J, Wang P, Holmes JM, Sun L, Hinni ML, Pockaj BA, Vora SA, Sio TT, Wong WW, Yu NY, Schild SE, Niska JR, Keole SR, Rwigema J-CM, Patel SH, McGee LA, Vargas CA, Liu W. An Automated Retrieval-Augmented Generation LLaMA-4 109B-based System for Evaluating Radiotherapy Treatment Plans. ArXiv. 2025;abs/2509.20707

work page arXiv 2025
[52]

American Association of Physicists in Medicine Task Group 263: Standardizing Nomenclatures in Radiation Oncology

Mayo CS, Moran JM, Bosch W, Xiao Y, McNutt T, Popple R, Michalski J, Feng M, Marks LB, Fuller CD, Yorke E, Palta J, Gabriel PE, Molineu A, Matuszak MM, Covington E, Masi K, Richardson SL, Ritter T, Morgas T, Flampouri S, Santanam L, Moore JA, Purdie TG, Miller RC, Hurkmans C, Adams J, Jackie Wu QR, Fox CJ, Siochi RA, Brown NL, Verbakel W, Archambault Y, C...

work page doi:10.1016/j.ijrobp.2017.12.013 2018
[53]

Wang P, Liu Z, Li Y, Holmes J, Shu P, Zhang L, Li X, Li Q, Laughlin BS, Toesca DS, Vargas CE, Vora SA, Patel SH, Sio TT, Liu T, Liu W. Fine-tuning open-source large language models to improve their performance on radiation oncology tasks: A feasibility study to investigate their potential clinical applications in radiation oncology. Medical Physics. 2025;...

work page doi:10.1002/mp.17985 2025
[54]

LLaMA: Open and Efficient Foundation Language Models

Touvron H, Lavril T, Izacard G, Martinet X, Lachaux M-A, Lacroix T, Rozière B, Goyal N, Hambro E, Azhar F, Rodriguez Ae, Joulin A, Grave E, Lample G. LLaMA: Open and Efficient Foundation Language Models. ArXiv. 2023;abs/2302.13971

work page internal anchor Pith review Pith/arXiv arXiv 2023
[55]

Mistral 7B

Jiang AQ, Sablayrolles A, Mensch A, Bamford C, Chaplot DS, Casas DdL, Bressand F, Lengyel G, Lample G, Saulnier L, Lavaud LeR, Lachaux M-A, Stock P, Scao TL, Lavril T, Wang T, Lacroix T, Sayed WE. Mistral 7B. ArXiv. 2023;abs/2310.06825

work page internal anchor Pith review Pith/arXiv arXiv 2023
[56]

Evaluating large language models on a highly-specialized topic, radiation oncology physics

Holmes J, Liu Z, Zhang L, Ding Y, Sio TT, McGee LA, Ashman JB, Li X, Liu T, Shen J, Liu W. Evaluating large language models on a highly-specialized topic, radiation oncology physics. Front Oncol. 2023;13. doi: 10.3389/fonc.2023.1219326

work page doi:10.3389/fonc.2023.1219326 2023
[57]

A recent evaluation on the performance of LLMs on radiation oncology physics using questions of randomly shuffled options

Wang P, Holmes J, Liu Z, Chen D, Liu T, Shen J, Liu W. A recent evaluation on the performance of LLMs on radiation oncology physics using questions of randomly shuffled options. Front Oncol. 2025;Volume 15 - 2025. doi: 10.3389/fonc.2025.1557064

work page doi:10.3389/fonc.2025.1557064 2025
[58]

Benchmarking a Foundation Large Language Model on its Ability to Relabel Structure Names in Accordance With the American Association of Physicists in Medicine Task Group-263 Report

Holmes J, Zhang L, Ding Y, Feng H, Liu Z, Liu T, Wong WW, Vora SA, Ashman JB, Liu W. Benchmarking a Foundation Large Language Model on its Ability to Relabel Structure Names in Accordance With the American Association of Physicists in Medicine Task Group-263 Report. Pract Radiat Oncol. 2024. Epub 20240726. doi: 10.1016/j.prro.2024.04.017. PubMed PMID: 39243241

work page doi:10.1016/j.prro.2024.04.017 2024
[59]

RadOnc-GPT: An Autonomous LLM Agent for Real-Time Patient Outcomes Labeling at Scale

Holmes JM, Hao Y, Borras-Osorio M, Mastroleo F, Romero-Brufau S, Carducci V, Abel KMV, Routman DM, Foong AYK, Muller LM, Shiraishi S, Ebner DK, Ma DJ, Keole SR, Patel SH, Fatyga M, Bues M, Stish BJ, Garces YI, Wittich MAN, Foote RL, Vora SA, Laack NN, Waddle MR, Liu W. RadOnc-GPT: An Autonomous LLM Agent for Real-Time Patient Outcomes Labeling at Scale. A...

work page arXiv 2025
[60]

Automated Triaging and Transfer Learning of Incident Learning Safety Reports Using Large Language Representational Models

Beidler P, Nguyen M, Lybarger K, Holmberg O, Ford E, Kang J. Automated Triaging and Transfer Learning of Incident Learning Safety Reports Using Large Language Representational Models. arXiv preprint arXiv:250913706. 2025

work page 2025
[61]

Semi‐ automated topic identification for radiation oncology safety event reports using natural language processing and statistical modeling

Zhang QS, Kang J, Lybarger K, Glenn MC, Sponseller P, Blau KH, Ford E. Semi‐ automated topic identification for radiation oncology safety event reports using natural language processing and statistical modeling. Medical physics. 2025;52(8):e17936

work page 2025
[62]

Root Cause Analysis of Radiation Oncology Incidents Using Large Language Models

Wang Y, De Ornelas M, Studenski MT, Bossart E, Najad-Davarani SP, Yang Y. Root Cause Analysis of Radiation Oncology Incidents Using Large Language Models. arXiv preprint arXiv:250817201. 2025

work page 2025
[63]

Quantitative Risk Assessment in Radiation Oncology via LLM-Powered Root Cause Analysis of Incident Reports

Wang Y, Najad-Davarani SP, Bossart E, Studenski MT, De Ornelas M, Yang Y. Quantitative Risk Assessment in Radiation Oncology via LLM-Powered Root Cause Analysis of Incident Reports. arXiv preprint arXiv:251102223. 2025

work page 2025
[64]

Retrospective Comparative Analysis of Prostate Cancer In-Basket Messages: Responses From Closed-Domain Large Language Models Versus Clinical Teams

Hao Y, Holmes J, Hobson J, Bennett A, McKone EL, Ebner DK, Routman DM, Shiraishi S, Patel SH, Yu NY, Hallemeier CL, Ball BE, Waddle M, Liu W. Retrospective Comparative Analysis of Prostate Cancer In-Basket Messages: Responses From Closed-Domain Large Language Models Versus Clinical Teams. Mayo Clinic Proceedings: Digital Health. 2025;3(1):100198. doi: htt...

work page doi:10.1016/j.mcpdig.2025.100198 2025
[65]

Evaluating the Performance of Using Large Language Models to Automate Summarization of CT Simulation Orders in Radiation Oncology

Cao M, Hu S, Sharp J, Clouser EL, Holmes J, Lam LL, Ding X, Toesca DS, Lindholm WS, Patel SH, Vora SA, Wang P, Liu W. Evaluating the Performance of Using Large Language Models to Automate Summarization of CT Simulation Orders in Radiation Oncology. JACMP. 2025

work page 2025
[66]

Verifiable Summarization of Electronic Health Records Using Large Language Models to Support Chart Review

Verma R, Alsentzer E, Strasser Z, Chang L, Roman K, Gershanik E, Hernandez C, Linares M, Rodriguez J, Thakral D, Unlu O, You J, Zhou L, Bates D. Verifiable Summarization of Electronic Health Records Using Large Language Models to Support Chart Review. medRxiv

work page
[67]

doi: 10.1101/2025.06.02.25328807

Epub 20250603. doi: 10.1101/2025.06.02.25328807. PubMed PMID: 40502573; PMCID: PMC12155021

work page doi:10.1101/2025.06.02.25328807 2025
[68]

Evaluating Hospital Course Summarization by an Electronic Health Record–Based Large Language Model

Small WR, Austrian J, O’Donnell L, Burk-Rafel J, Hochman KA, Goodman A, Zaretsky J, Martin J, Johnson S, Major VJ, Jones S, Henke C, Verplanke B, Osso J, Larson I, Saxena A, Mednick A, Simonis C, Han J, Kesari R, Wu X, Heery L, Desel T, Baskharoun S, Figman N, Farooq U, Shah K, Jahan N, Kim JM, Testa P, Feldman J. Evaluating Hospital Course Summarization ...

work page doi:10.1001/jamanetworkopen.2025.26339 2025
[69]

Towards Inpatient Discharge Summary Automation via Large Language Models: A Multidimensional Evaluation with a HIPAA-Compliant Instance of GPT-4o and Clinical Expert Assessment

Osborne T, Abbasi S, Hong S, Sexton R, Ambut J, Patel NJ, Rosenthal RN, Ung L, Wang F, Wong R. Towards Inpatient Discharge Summary Automation via Large Language Models: A Multidimensional Evaluation with a HIPAA-Compliant Instance of GPT-4o and Clinical Expert Assessment. medRxiv. 2025:2025.04.03.25325204. doi: 10.1101/2025.04.03.25325204

work page doi:10.1101/2025.04.03.25325204 2025
[70]

The Daily Dose: Workflow-Integrated Large Language Model Automation for Clinical Summarization and Trial Identification in Radiation Oncology JAMA Network Open

Holmes J, Mastroleo F, Borras-Osorio M, Seetamsetty S, Shiraishi S, Fatyga M, Boughey JC, Thiels CA, Breen WG, Ma DJ, Ebner DK, Routman DM, Laughlin BS, Vargas CE, Patel SH, Vora SA, Laack NN, Foong AYK, Liu W, WAddle MR. The Daily Dose: Workflow-Integrated Large Language Model Automation for Clinical Summarization and Trial Identification in Radiation On...

work page 2026
[71]

Matching patients to clinical trials with large language models

Jin Q, Wang Z, Floudas CS, Chen F, Gong C, Bracken-Clarke D, Xue E, Yang Y, Sun J, Lu Z. Matching patients to clinical trials with large language models. Nature Communications. 2024;15(1):9074. doi: 10.1038/s41467-024-53081-z

work page doi:10.1038/s41467-024-53081-z 2024
[72]

Learning to match patients to clinical trials using large language models

Rybinski M, Kusa W, Karimi S, Hanbury A. Learning to match patients to clinical trials using large language models. Journal of Biomedical Informatics. 2024;159:104734. doi: https://doi.org/10.1016/j.jbi.2024.104734

work page doi:10.1016/j.jbi.2024.104734 2024
[73]

Feasibility of institution-agnostic, EHR-integrated regional clinical trial matching

Shriver SP, Arafat W, Potteiger C, Butler DL, Beg MS, Hullings M, Semy S, Lister Z, Khosama L, Armstrong S, Hadley D, Pappa J, Fleury ME. Feasibility of institution-agnostic, EHR-integrated regional clinical trial matching. Cancer. 2024;130(1):60-7. Epub 20231018. doi: 10.1002/cncr.35022. PubMed PMID: 37851512

work page doi:10.1002/cncr.35022 2024
[74]

Piloting an automated clinical trial eligibility surveillance and provider alert system based on artificial intelligence and standard data models

Meystre SM, Heider PM, Cates A, Bastian G, Pittman T, Gentilin S, Kelechi TJ. Piloting an automated clinical trial eligibility surveillance and provider alert system based on artificial intelligence and standard data models. BMC Med Res Methodol. 2023;23(1):88. Epub 20230411. doi: 10.1186/s12874-023-01916-6. PubMed PMID: 37041475; PMCID: PMC10088225

work page doi:10.1186/s12874-023-01916-6 2023
[75]

Real-world validation of a multimodal LLM-powered pipeline for high-accuracy clinical trial patient matching

Callies A, Bodinier Q, Ravaud P, Davarpanah K. Real-world validation of a multimodal LLM-powered pipeline for high-accuracy clinical trial patient matching. Communications Medicine. 2025;5(1):536. doi: 10.1038/s43856-025-01256-0

work page doi:10.1038/s43856-025-01256-0 2025
[76]

Large Language Model Augmented Clinical Trial Screening

Beattie J, Owens D, Navar AM, Schmitt LG, Taing K, Neufeld S, Yang D, Chukwuma C, Gul A, Lee DS, Desai N, Moon D, Wang J, Jiang S, Dohopolski M. Large Language Model Augmented Clinical Trial Screening. medRxiv. 2024:2024.08.27.24312646. doi: 10.1101/2024.08.27.24312646

work page doi:10.1101/2024.08.27.24312646 2024
[77]

Online Adaptive Proton Therapy Facilitated by Artificial Intelligence-Based Autosegmentation in Pencil Beam Scanning Proton Therapy

Feng HY, Shan J, Vargas CE, Keole SR, Rwigema JCM, Yu NY, Ding YZ, Zhang L, Hu YL, Schild SE, Wong WW, Vora SA, Shen JJ, Liu W. Online Adaptive Proton Therapy Facilitated by Artificial Intelligence-Based Autosegmentation in Pencil Beam Scanning Proton Therapy. Int J Radiat Oncol. 2025;121(3):822-31. doi: 10.1016/j.ijrobp.2024.09.032. PubMed PMID: WOS:0014...

work page doi:10.1016/j.ijrobp.2024.09.032 2025
[78]

Clinical evaluation of deep learning and atlas-based auto-segmentation for critical organs at risk in radiation therapy

Gibbons E, Hoffmann M, Westhuyzen J, Hodgson A, Chick B, Last A. Clinical evaluation of deep learning and atlas-based auto-segmentation for critical organs at risk in radiation therapy. J Med Radiat Sci. 2023;70:15-25. doi: 10.1002/jmrs.618. PubMed PMID: WOS:000857004500001

work page doi:10.1002/jmrs.618 2023
[79]

Evaluation of AI-based auto-contouring tools in radiotherapy: A single-institution study

Wang TY, Tam J, Chum T, Tai C, Marshall DC, Buckstein M, Liu JRY, Green S, Stewart RD, Liu T, Chao M. Evaluation of AI-based auto-contouring tools in radiotherapy: A single-institution study. J Appl Clin Med Phys. 2025;26(4). doi: 10.1002/acm2.14620. PubMed PMID: WOS:001400965300001

work page doi:10.1002/acm2.14620 2025
[80]

Choi MS, Chang JS, Kim K, Kim JH, Kim TH, Kim S, Cha H, Cho O, Choi JH, Kim M, Kim J, Kim TG, Yeo SG, Chang AR, Ahn SJ, Choi J, Kang KM, Kwon J, Koo T, Kim MY, Choi SH, Jeong BK, Jang BS, Jo IY, Lee H, Kim N, Park HJ, Im JH, Lee SW, Cho Y, Lee SY, Chang JH, Chun J, Lee EM, Kim JS, Shin KH, Kim YB. Assessment of deep learning-based auto- contouring on inte...

work page doi:10.1016/j.breast.2023.103599 2024
[81]

LLM-driven multimodal target volume contouring in radiation oncology

Oh Y, Park S, Byun HK, Cho Y, Lee IJ, Kim JS, Ye JC. LLM-driven multimodal target volume contouring in radiation oncology. Nat Commun. 2024;15(1):9186. Epub 20241024. doi: 10.1038/s41467-024-53387-y. PubMed PMID: 39448587; PMCID: PMC11502670

work page doi:10.1038/s41467-024-53387-y 2024

Showing first 80 references.