Large Language Model Applications for Health Information Extraction in Oncology: Scoping Review
Anwendungen von Large Language Models für die Extraktion von Gesundheitsinformationen in der Onkologie: Scoping Review
JMIR Cancer · 2025-03-28 · 11 · e65984-e65984
DOI: 10.2196/65984 ↗Auf einen Blick
Die Übersicht fasst 24 Studien zu Large Language Models (LLM) für die Datenerfassung aus klinischem Text in der Onkologie zusammen. Berichtet werden vor allem positive Extraktionsleistung und weniger manueller Aufwand.
Fragestellung
Welche Definitionen, Rahmenwerke und zukünftigen направленияn gibt es für LLM zur Datenerfassung aus klinischem Text in der Onkologie?
Methode
Scoping Review von Primärstudien in Ovid MEDLINE; Suche am 2. Juni 2024 nach Studien seit 2000; eingeschlossen wurden peer-reviewte Arbeiten zu LLM-gestützter Datenerfassung.
Ergebnisse
24 Studien. Häufigster Ansatz waren BERT-Varianten (n=18, 75 %), gefolgt von Chat-GPT (n=6, 25 %). Häufige Einsatzfelder waren Pan-Krebs (n=11, 46 %), Brustkrebs (n=4, 17 %) und Lungenkrebs (n=4, 17 %).
Einschränkungen
Weitere Studien nötig zur Leistung außerhalb der Trainingsdaten sowie zur Umsetzung in realen klinischen Umgebungen.
Schlussfolgerung der Autor:innen
LLM zur Datenerfassung in der Onkologie können den administrativen Aufwand beim Prüfen von Patientenakten verringern und mehr Zeit für die Patientenversorgung schaffen.
Kernaussagen
- 24 eingeschlossene Studien zu LLM-gestützter Datenerfassung in der Onkologie
- BERT-Varianten wurden am häufigsten untersucht
- Prompt Engineering und Fine-Tuning zeigen aktuelle Forschungstrends
Deutsche Zusammenfassung: KI-gestützt aus dem Original-Abstract erstellt; alle Zahlen wurden automatisch mit dem Original abgeglichen. Maßgeblich ist der Original-Abstract.
At a glance
Scoping Review in JMIR Cancer, published online on 2025-03-28. Written by David Chen and 4 co-authors. Institution: Temerty Faculty of Medicine, University of Toronto, Toronto, ON, Canada. Major MEDLINE topics: Natural Language Processing, Medical Oncology, Neoplasms, Information Storage and Retrieval. Cited 78 times so far (Crossref); 51 references. The full text is freely available in PubMed Central.
Abstract (original language)
Background
Natural language processing systems for data extraction from unstructured clinical text require expert-driven input for labeled annotations and model training. The natural language processing competency of large language models (LLM) can enable automated data extraction of important patient characteristics from electronic health records, which is useful for accelerating cancer clinical research and informing oncology care.
Objective
This scoping review aims to map the current landscape, including definitions, frameworks, and future directions of LLMs applied to data extraction from clinical text in oncology.
Methods
We queried Ovid MEDLINE for primary, peer-reviewed research studies published since 2000 on June 2, 2024, using oncology- and LLM-related keywords. This scoping review included studies that evaluated the performance of an LLM applied to data extraction from clinical text in oncology contexts. Study attributes and main outcomes were extracted to outline key trends of research in LLM-based data extraction.
Results
The literature search yielded 24 studies for inclusion. The majority of studies assessed original and fine-tuned variants of the BERT LLM (n=18, 75%) followed by the Chat-GPT conversational LLM (n=6, 25%). LLMs for data extraction were commonly applied in pan-cancer clinical settings (n=11, 46%), followed by breast (n=4, 17%), and lung (n=4, 17%) cancer contexts, and were evaluated using multi-institution datasets (n=18, 75%). Comparing the studies published in 2022‐2024 versus 2019‐2021, both the total number of studies (18 vs 6) and the proportion of studies using prompt engineering increased (5/18, 28% vs 0/6, 0%), while the proportion using fine-tuning decreased (8/18, 44.4% vs 6/6, 100%). Advantages of LLMs included positive data extraction performance and reduced manual workload.
Conclusions
LLMs applied to data extraction in oncology can serve as useful automated tools to reduce the administrative burden of reviewing patient health records and increase time for patient-facing care. Recent advances in prompt-engineering and fine-tuning methods, and multimodal data extraction present promising directions for future research. Further studies are needed to evaluate the performance of LLM-enabled data extraction in clinical domains beyond the training dataset and to assess the scope and integration of LLMs into real-world clinical environments.
Subjects
MeSH terms (MEDLINE)
Author keywords
Authors and institutions
- Temerty Faculty of Medicine, University of Toronto, Toronto, ON, Canada.
- Department of Systems Design Engineering, University of Waterloo, Waterloo, ON, Canada.
- Department of Radiation Oncology, BC Cancer Vancouver, 600 W 10th Ave, Vancouver, BC, V5Z 4E6, Canada, 1 416-946-4501.
ORCID profiles: David Chen, Saif Addeen Alnassar, Kate Elizabeth Avison, Ryan S Huang, Srinivas Raman
Cite
APA
Chen, D., Alnassar, S. A., Avison, K. E., Huang, R. S., & Raman, S. (2025). Large Language Model Applications for Health Information Extraction in Oncology: Scoping Review. JMIR Cancer, 11, e65984-e65984. https://doi.org/10.2196/65984
Vancouver
Chen D, Alnassar SA, Avison KE, Huang RS, Raman S. Large Language Model Applications for Health Information Extraction in Oncology: Scoping Review. JMIR Cancer. 2025;11:e65984-e65984. doi:10.2196/65984
BibTeX
@article{Chen2025,
author = {Chen, David and Alnassar, Saif Addeen and Avison, Kate Elizabeth and Huang, Ryan S and Raman, Srinivas},
title = {Large Language Model Applications for Health Information Extraction in Oncology: Scoping Review},
journal = {JMIR Cancer},
year = {2025},
volume = {11},
pages = {e65984--e65984},
doi = {10.2196/65984}
}
EUVIMED