Enhancing Malignancy Detection and Tumor Classification in Pathology Reports: A Comparative Evaluation of Large Language Models
Studies in Health Technology and Informatics · 2025
DOI: 10.3233/shti250200 ↗Kurz gefasst
Vergleichsstudie in der Zeitschrift Studies in Health Technology and Informatics, 2025. Verfasst von Sabrina B Neururer und 10 weiteren Autor:innen. Beteiligte Einrichtung: Department of Clinical Epidemiology, Tirol Kliniken GmbH, Innsbruck, Tirol, Austria. Hauptthemen laut MEDLINE: Neoplasms, Natural Language Processing, Electronic Health Records. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0).
Abstract (Originalsprache)
Background
Cancer registries require accurate and efficient documentation of malignancies, yet current manual methods are time-consuming and error-prone.
Objectives
This study evaluates the effectiveness of large language models (LLMs) in classifying malignancies and detecting tumor types from pathology reports.
Methods
Using a synthetic dataset of 227 reports, the performance of four LLMs and a score-based algorithm was compared against expert-labeled gold standards.
Results
The LLMs, particularly GPT-4o and Llama3.3, demonstrated high sensitivity and specificity in both malignancy detection and tumor classification, significantly outperforming traditional algorithms.
Conclusion
LLMs enhance the accuracy and efficiency of cancer data classification and hold promise for improving public health monitoring and clinical decision-making.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Clinical Epidemiology, Tirol Kliniken GmbH, Innsbruck, Tirol, Austria.
- Division for Digital Health and Telemedicine, UMIT-TIROL, Hall in Tirol, Austria.
- Department of Information Technology, Tirol Kliniken GmbH, Innsbruck, Austria.
Zitieren
APA
Neururer, S. B., Taha, H., Muehlboeck, H., Hickmann, C., Gscheidlinger, P., Richter, S., Danler, M., Hackl, W. O., Ueberegger, M., Schweitzer, M., & Pfeifer, B. (2025). Enhancing Malignancy Detection and Tumor Classification in Pathology Reports: A Comparative Evaluation of Large Language Models. Studies in Health Technology and Informatics. https://doi.org/10.3233/shti250200
Vancouver
Neururer SB, Taha H, Muehlboeck H, Hickmann C, Gscheidlinger P, Richter S, et al. Enhancing Malignancy Detection and Tumor Classification in Pathology Reports: A Comparative Evaluation of Large Language Models. Studies in Health Technology and Informatics. 2025. doi:10.3233/shti250200
BibTeX
@article{Neururer2025,
author = {Neururer, Sabrina B and Taha, Hasan and Muehlboeck, Helmut and Hickmann, Christoph and Gscheidlinger, Patricia and Richter, Stefan and Danler, Martin and Hackl, Werner O and Ueberegger, Marko and Schweitzer, Marco and Pfeifer, Bernhard},
title = {Enhancing Malignancy Detection and Tumor Classification in Pathology Reports: A Comparative Evaluation of Large Language Models},
journal = {Studies in Health Technology and Informatics},
year = {2025},
doi = {10.3233/shti250200}
}
EUVIMED