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

Related Concept Videos

Rapid Identification of Pathogens

Rapid Identification of Pathogens

MALDI-TOF MS has transformed clinical microbiology by offering a rapid and reliable method for pathogen identification. The traditional approach to microbial identification typically involves time-consuming culture techniques and biochemical tests, which can delay the initiation of appropriate antimicrobial therapy. MALDI-TOF MS avoids these delays by using characteristic ribosomal protein mass patterns of microbial cells, enabling accurate species-level identification within minutes.Principle...

You might also read

Related Articles

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

Sort by

Same author

Driver vs. passenger: Primary resistance to larotrectinib in synovial sarcoma harboring concurrent SS18 rearrangement and PDE3A-NTRK2 fusion.

Tumori·2026

Same author

Prognostic Value of Liver Function-based Scores in Hepatocellular Carcinoma Patients Undergoing Liver Transplantation.

In vivo (Athens, Greece)·2026

Same author

Gender Disparities in Response to Neoadjuvant Therapy for Early-Stage Breast Cancer: A Propensity Score-Matched Analysis of the SEER Database.

Breast care (Basel, Switzerland)·2026

Same author

Assessment of Large Language Models in Colorectal Cancer Multidisciplinary Tumor Board Decision-Making: A Retrospective Single-Center Comparison of Guideline-Integrated General-Purpose vs. Domain-Specialized Models.

Current oncology (Toronto, Ont.)·2026

Same author

In Regard to Karp et al.

International journal of radiation oncology, biology, physics·2026

Same author

Methodological considerations in prognostic modeling for HER2-positive breast cancer with lung metastasis.

Breast cancer (Tokyo, Japan)·2026

Search research articles

Related Experiment Video

Updated: Jun 19, 2026

Extraction of the EPP Component from the Surface EMG

Extraction of the EPP Component from the Surface EMG

Published on: December 16, 2009

Automated Extraction of Key Entities from Non-English Mammography Reports Using Named Entity Recognition with Prompt

Zafer Akcali^1,2, Hazal Selvi Cubuk³, Arzu Oguz²

¹Department of Medical Informatics, Faculty of Medicine, Baskent University, Ankara 06790, Türkiye.

Bioengineering (Basel, Switzerland)

|February 26, 2025

Summary

This study demonstrates that prompt-based named entity recognition (NER) using large language models effectively extracts clinical information from Turkish mammography reports, outperforming other few-shot methods.

Keywords:

clinicomics machine learning mammography named entity recognition (NER)natural language processing (NLP)prompt engineering radiology reports

More Related Videos

Detection of Architectural Distortion in Prior Mammograms via Analysis of Oriented Patterns

Detection of Architectural Distortion in Prior Mammograms via Analysis of Oriented Patterns

Published on: August 30, 2013

A Metadata Extraction Approach for Clinical Case Reports to Enable Advanced Understanding of Biomedical Concepts

A Metadata Extraction Approach for Clinical Case Reports to Enable Advanced Understanding of Biomedical Concepts

Published on: September 20, 2018

Related Experiment Videos

Last Updated: Jun 19, 2026

Extraction of the EPP Component from the Surface EMG

Extraction of the EPP Component from the Surface EMG

Published on: December 16, 2009

Detection of Architectural Distortion in Prior Mammograms via Analysis of Oriented Patterns

Detection of Architectural Distortion in Prior Mammograms via Analysis of Oriented Patterns

Published on: August 30, 2013

A Metadata Extraction Approach for Clinical Case Reports to Enable Advanced Understanding of Biomedical Concepts

A Metadata Extraction Approach for Clinical Case Reports to Enable Advanced Understanding of Biomedical Concepts

Published on: September 20, 2018

Area of Science:

Natural Language Processing (NLP)
Medical Informatics
Artificial Intelligence in Healthcare

Background:

Named Entity Recognition (NER) is crucial for extracting clinical information from text.
Existing NER models often lack robust support for non-English languages, limiting their global applicability.
Turkish mammography reports present a specific challenge due to limited NLP resources.

Purpose of the Study:

To investigate a prompt-based NER approach using Google's Gemini 1.5 Pro for Turkish clinical text.
To evaluate the model's efficacy in extracting key clinical entities from mammography reports.
To assess the performance of many-shot learning in a low-resource language setting.

Main Methods:

Employed a prompt-based NER strategy with Google's Gemini 1.5 Pro (1.5-million-token context window).
Utilized many-shot learning, incorporating 165 examples within a 26,000-token prompt.
Focused on extracting five key entities: anatomy (ANAT), impression (IMP), observation presence (OBS-P), absence (OBS-A), and uncertainty (OBS-U) from 85 unannotated reports.

Main Results:

Achieved high accuracy with macro-averaged F1 scores of 0.99 (relaxed match) and 0.84 (exact match).
Relaxed matching yielded F1 scores of 0.99 for ANAT, 0.99 for IMP, 1.00 for OBS-P, 1.00 for OBS-A, and 0.99 for OBS-U.
Exact matching achieved F1 scores of 0.88 for ANAT, 0.79 for IMP, 0.78 for OBS-P, 0.94 for OBS-A, and 0.82 for OBS-U.

Conclusions:

Many-shot prompt engineering with LLMs is an effective method for clinical information extraction in under-resourced languages.
This approach demonstrates superior performance compared to zero-shot and other few-shot methods.
Potential to significantly enhance clinical workflows and research in multilingual healthcare settings.