EUVIMEDEUVIMED entdecken
VergleichsstudieOpen Access · CC BY-NC 4.0

Enhancing Malignancy Detection and Tumor Classification in Pathology Reports: A Comparative Evaluation of Large Language Models

Sabrina B Neururer, Hasan Taha, Helmut Muehlboeck, Christoph Hickmann, Patricia Gscheidlinger, Stefan Richter, Martin Danler, Werner O Hackl, Marko Ueberegger, Marco Schweitzer, Bernhard Pfeifer

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).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

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)

NeoplasmsNatural Language ProcessingElectronic Health RecordsHumansSensitivity and SpecificityAlgorithmsReproducibility of ResultsLarge Language Models

Stichwörter der Autor:innen

Large Language ModelNeoplasm RegistriesText Mining

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}
}
Kostenlos starten →