Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Search research articles

Related Experiment Videos

Zero-Shot TNM Staging from German Pathology Reports Using Pre-Trained Transformer Models (BB-TEN).

Hasan Taha^1,2, Werner O Hackl^1,2, Sabrina B Neururer^1,2

¹Health Data Competence Center, Tirol Kliniken GmbH, Innsbruck, Austria.

Studies in Health Technology and Informatics

|May 12, 2026

Summary

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by

Same author

Agent-Based Model for Temperature and Precipitation-Dependent Population Dynamics of Aedes vexans.

Studies in health technology and informatics·2026

Same author

Semantic Text Vectorization in Healthcare: Transformer-Based Foundations and Benefit Potentials.

Studies in health technology and informatics·2026

Same author

An Agent-Based Cellular Automaton Platform for Simulating Climate-Driven Mosquito Vector Spread in Alpine Regions.

Studies in health technology and informatics·2026

Same author

Predictors of cervicogenic headache in patients with chronic neck pain: a prospective study of 6-month follow-up.

The Journal of manual & manipulative therapy·2025

Same author

Climate Change, Vectors, and Public Health: Predicting Future Disease Risks in the Federal State Tyrol.

Studies in health technology and informatics·2025

Same author

Development of a Synthetic Oncology Pathology Dataset for Large Language Model Evaluation in Medical Text Classification.

Studies in health technology and informatics·2025

Same journal

The Essential Components and Critical Conditions for Success in a Learning Health System in Oncology.

Studies in health technology and informatics·2026

Same journal

Use of Artificial Intelligence in Screening for Adolescent Idiopathic Scoliosis: A Scoping Review.

Studies in health technology and informatics·2026

Same journal

Movement Related Biomechanics in Adolescent Idiopathic Scoliosis: A Review of Reviews.

Studies in health technology and informatics·2026

Same journal

The Impact of Surgical Correction of Adolescent Idiopathic Scoliosis Using Posterior Spinal Fusion on Selected Radiological Parameters and Respiratory Function.

Studies in health technology and informatics·2026

Same journal

Acute Effect of Physio-logic® Exercises on Muscle Tone and Stiffness in Adolescent Idiopathic Scoliosis Patients: A Preliminary Study.

Studies in health technology and informatics·2026

Same journal

Effects of Integrated Music and Occupational Therapy on Motor and Autonomic Function in Children with Neurogenic Scoliosis.

Studies in health technology and informatics·2026

See all related articles

This summary is machine-generated.

English-trained AI models can extract cancer staging (TNM) from German pathology reports with high accuracy but lower recall. These tools show promise as screening aids for cancer registries, especially with further adaptation.

Area of Science:

Natural Language Processing
Computational Pathology
Oncology Informatics

Background:

TNM staging is crucial for cancer registries but often buried in unstructured pathology reports.
Manual extraction of TNM staging data is time-consuming and prone to errors.
Automated TNM classification using transformer models has shown success in English texts.

Purpose of the Study:

To evaluate the performance of English-trained TNM classifiers on German pathology reports without fine-tuning.
To assess the cross-lingual transferability and robustness of these AI models.
To determine the utility of zero-shot TNM classification in a new linguistic context.

Main Methods:

Three transformer-based TNM classifiers (T, N, M) were utilized.

Keywords:

Artificial Intelligence Machine Learning Natural Language Processing Neoplasm Staging Pathology Registries

Related Experiment Videos

A synthetic dataset of 109 German pathology reports (breast, lung, prostate cancer) was created.

Expert-assigned TNM labels served as the gold standard for comparison.

Main Results:

Models demonstrated high precision and specificity for tumor (T) and nodal (N) staging.
Sensitivity for T and N staging was moderate, while metastasis (M) staging sensitivity was low.
Frequent prediction of "Unknown" indicated a conservative model behavior.

Conclusions:

English-trained TNM classifiers can reliably extract staging information from German reports in a zero-shot manner.
The models exhibit high precision but reduced recall, acting as effective screening tools.
Performance could be enhanced with limited domain adaptation for improved registry workflows.