Scaling Clinical Trial Matching Using Large Language Models: A Case Study in Oncology

被引:0
作者
Wong, Cliff [1 ]
Zhang, Sheng [1 ]
Gu, Yu [1 ]
Moung, Christine [2 ]
Abel, Jacob [2 ]
Usuyama, Naoto [1 ]
Weerasinghe, Roshanthi [3 ]
Piening, Brian [4 ]
Naumann, Tristan [1 ]
Bifulco, Carlo [4 ]
Poon, Hoifung [1 ]
机构
[1] Microsoft Res, Redmond, WA 98052 USA
[2] Providence Hlth & Serv, Mol Genom Lab, Portland, OR USA
[3] Providence Hlth & Serv, Clin Res Anal, Portland, OR USA
[4] Providence Canc Inst, Earle Chiles Res Inst, Portland, OR USA
来源
MACHINE LEARNING FOR HEALTHCARE CONFERENCE, VOL 219 | 2023年 / 219卷
关键词
EXTRACTION; SYSTEM;
D O I
暂无
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Clinical trial matching is a key process in health delivery and discovery. In practice, it is plagued by overwhelming unstructured data and unscalable manual processing. In this paper, we conduct a systematic study on scaling clinical trial matching using large language models (LLMs), with oncology as the focus area. Our study is grounded in a clinical trial matching system currently in test deployment at a large U.S. health network. Initial findings are promising: out of box, cutting-edge LLMs, such as GPT-4, can already structure elaborate eligibility criteria of clinical trials and extract complex matching logic (e.g., nested AND/OR/NOT). While still far from perfect, LLMs substantially outperform prior strong baselines and may serve as a preliminary solution to help triage patient-trial candidates with humans in the loop. Our study also reveals a few significant growth areas for applying LLMs to end-to-end clinical trial matching, such as context limitation and accuracy, especially in structuring patient information from longitudinal medical records.
引用
收藏
页数:24
相关论文
共 24 条
[11]  
Nori H., 2023, CAPABILITIES GPT 4 M
[12]  
Nye BE, 2020, 58TH ANNUAL MEETING OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS (ACL 2020): SYSTEM DEMONSTRATIONS, P63, DOI 10.18653/v1/2020.acl-demos.9
[13]  
Ouyang L, 2022, ADV NEUR IN
[14]   Toward structuring real-world data: Deep learning for extracting oncology information from clinical text with patient-level supervision [J].
Preston, Sam ;
Wei, Mu ;
Rao, Rajesh ;
Tinn, Robert ;
Usuyama, Naoto ;
Lucas, Michael ;
Gu, Yu ;
Weerasinghe, Roshanthi ;
Lee, Soohee ;
Piening, Brian ;
Tittel, Paul ;
Valluri, Naveen ;
Naumann, Tristan ;
Bifulco, Carlo ;
Poon, Hoifung .
PATTERNS, 2023, 4 (04)
[15]   Cancer statistics, 2022 [J].
Siegel, Rebecca L. ;
Miller, Kimberly D. ;
Fuchs, Hannah E. ;
Jemal, Ahmedin .
CA-A CANCER JOURNAL FOR CLINICIANS, 2022, 72 (01) :7-33
[16]   Adult Cancer Clinical Trials That Fail to Complete: An Epidemic? [J].
Stensland, Kristian D. ;
McBride, Russell B. ;
Latif, Asma ;
Wisnivesky, Juan ;
Hendricks, Ryan ;
Roper, Nitin ;
Boffetta, Paolo ;
Hall, Simon J. ;
Oh, William K. ;
Galsky, Matthew D. .
JNCI-JOURNAL OF THE NATIONAL CANCER INSTITUTE, 2014, 106 (09)
[17]   Systematic Review and Meta-Analysis of the Magnitude of Structural, Clinical, and Physician and Patient Barriers to Cancer Clinical Trial Participation [J].
Unger, Joseph M. ;
Vaidya, Riha ;
Hershman, Dawn L. ;
Minasian, Lori M. ;
Fleury, Mark E. .
JNCI-JOURNAL OF THE NATIONAL CANCER INSTITUTE, 2019, 111 (03) :245-255
[18]  
US National Library of Medicine, ClinicalTrials.gov
[19]   GNormPlus: An Integrative Approach for Tagging Genes, Gene Families, and Protein Domains [J].
Wei, Chih-Hsuan ;
Kao, Hung-Yu ;
Lu, Zhiyong .
BIOMED RESEARCH INTERNATIONAL, 2015, 2015
[20]   tmVar: a text mining approach for extracting sequence variants in biomedical literature [J].
Wei, Chih-Hsuan ;
Harris, Bethany R. ;
Kao, Hung-Yu ;
Lu, Zhiyong .
BIOINFORMATICS, 2013, 29 (11) :1433-1439