Extracting Systemic Anticancer Therapy and Response Information From Clinical Notes Following the RECIST Definition
JCO Clinical Cancer Informatics · 2024
DOI: 10.1200/cci.23.00166 ↗Kurz gefasst
Fachartikel in der Zeitschrift JCO Clinical Cancer Informatics, 2024. Verfasst von Xu Zuo und 9 weiteren Autor:innen. Beteiligte Einrichtung: University of Texas Health Science Center, Houston, TX. Hauptthemen laut MEDLINE: Natural Language Processing, Electronic Health Records, Neoplasms, Response Evaluation Criteria in Solid Tumors. Die Arbeit nennt 15 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar. Gefördert von: NCI NIH HHS.
Abstract (Originalsprache)
PURPOSE The RECIST guidelines provide a standardized approach for evaluating the response of cancer to treatment, allowing for consistent comparison of treatment efficacy across different therapies and patients. However, collecting such information from electronic health records manually can be extremely labor-intensive and time-consuming because of the complexity and volume of clinical notes. The aim of this study is to apply natural language processing (NLP) techniques to automate this process, minimizing manual data collection efforts, and improving the consistency and reliability of the results. METHODS We proposed a complex, hybrid NLP system that automates the process of extracting, linking, and summarizing anticancer therapy and associated RECIST-like responses from narrative clinical text. The system consists of multiple machine learning–/deep learning–based and rule-based modules for diverse NLP tasks such as named entity recognition, assertion classification, relation extraction, and text normalization, to address different challenges associated with anticancer therapy and response information extraction. We then evaluated the system performances on two independent test sets from different institutions to demonstrate its effectiveness and generalizability. RESULTS The system used domain-specific language models, BioBERT and BioClinicalBERT, for high-performance therapy mentions identification and RECIST responses extraction and categorization. The best-performing model achieved a 0.66 score in linking therapy and RECIST response mentions, with end-to-end performance peaking at 0.74 after relation normalization, indicating substantial efficacy with room for improvement. CONCLUSION We developed, implemented, and tested an information extraction system from clinical notes for cancer treatment and efficacy assessment information. We expect this system will support future cancer research, particularly oncologic studies that focus on efficiently assessing the effectiveness and reliability of cancer therapeutics.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Autor:innen und Institutionen
- University of Texas Health Science Center, Houston, TX.
- Mayo Clinic, Scottsdale, AZ.
- University of Maryland, College Park, College Park, MD.
- University of Southern California, Los Angeles, CA.
- Vanderbilt University Medical Center, Nashville, TN.
- Legorreta Cancer Center at Brown University, Providence, RI.
ORCID-Profile: Xu Zuo, Jianfu Li, Edward Jin, Qingxia Chen, Jeremy L Warner, Ping Yang
Förderung
- NCI NIH HHS
Zitieren
APA
Zuo, X., Kumar, A., Shen, S., Li, J., Cong, G., Jin, E., Chen, Q., Warner, J. L., Yang, P., & Xu, H. (2024). Extracting Systemic Anticancer Therapy and Response Information From Clinical Notes Following the RECIST Definition. JCO Clinical Cancer Informatics. https://doi.org/10.1200/cci.23.00166
Vancouver
Zuo X, Kumar A, Shen S, Li J, Cong G, Jin E, et al. Extracting Systemic Anticancer Therapy and Response Information From Clinical Notes Following the RECIST Definition. JCO Clinical Cancer Informatics. 2024. doi:10.1200/cci.23.00166
BibTeX
@article{Zuo2024,
author = {Zuo, Xu and Kumar, Ashok and Shen, Shuhan and Li, Jianfu and Cong, Grace and Jin, Edward and Chen, Qingxia and Warner, Jeremy L and Yang, Ping and Xu, Hua},
title = {Extracting Systemic Anticancer Therapy and Response Information From Clinical Notes Following the RECIST Definition},
journal = {JCO Clinical Cancer Informatics},
year = {2024},
doi = {10.1200/cci.23.00166}
}
EUVIMED