Search research articles

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

Enhanced Near-Field Focusing via Interior Cavity and Nanogap Coupling in Disk-Cavity-Trench Nanostructures.

Small (Weinheim an der Bergstrasse, Germany)·2026

Same author

Multi-Ion Zeolite-Based Antimicrobial LDPE Films for Active Food Packaging: Ion Combinations and Performance in Real Food Systems.

Journal of food science·2026

Same author

Design and evaluation of an automated pediatric acute lymphoblastic leukemia registry from clinical data warehouses.

BMC medical informatics and decision making·2026

Same author

I<sup>2</sup>MoE: Interpretable Multimodal Interaction-aware Mixture-of-Experts.

Proceedings of machine learning research·2026

Same author

Glucose-mediated Maillard crosslinking of pea protein scaffolds to enhance mechanical properties and myoblast proliferation.

Food chemistry·2026

Same author

Neural Correlates of Personality Traits in Adolescents Exhibiting Excessive Smartphone Use: A Resting-State FMRI Study.

Life (Basel, Switzerland)·2025

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 Video

Updated: Sep 12, 2025

Industrialized, Artificial Intelligence-guided Laser Microdissection for Microscaled Proteomic Analysis of the Tumor Microenvironment

Industrialized, Artificial Intelligence-guided Laser Microdissection for Microscaled Proteomic Analysis of the Tumor Microenvironment

Published on: June 3, 2022

Zero-Shot Clinical Data Extraction from Pathology Reports Using Llama 3.1.

Sunghyeon Park^1,2, Wona Choi¹, InYoung Choi¹

¹Department of Medical Informatics, College of Medicine, The Catholic University of Korea.

Studies in Health Technology and Informatics

|August 8, 2025

Summary

The Llama 3.1 large language model achieved 98% accuracy in extracting clinical data from pathology reports using zero-shot learning. This demonstrates its potential for automating medical information extraction and improving healthcare data management.

Keywords:

Information Extraction LLMs

More Related Videos

Introduction of an Integrated Pathology Image Management, Artificial Intelligence, and Reporting System

Introduction of an Integrated Pathology Image Management, Artificial Intelligence, and Reporting System

Published on: July 11, 2025

DNA-barcode-based Multiplex Immunofluorescence Imaging to Analyze FFPE Specimens from Genetically Reprogrammed Murine Melanoma

DNA-barcode-based Multiplex Immunofluorescence Imaging to Analyze FFPE Specimens from Genetically Reprogrammed Murine Melanoma

Published on: June 6, 2025

Related Experiment Videos

Last Updated: Sep 12, 2025

Industrialized, Artificial Intelligence-guided Laser Microdissection for Microscaled Proteomic Analysis of the Tumor Microenvironment

Industrialized, Artificial Intelligence-guided Laser Microdissection for Microscaled Proteomic Analysis of the Tumor Microenvironment

Published on: June 3, 2022

Introduction of an Integrated Pathology Image Management, Artificial Intelligence, and Reporting System

Introduction of an Integrated Pathology Image Management, Artificial Intelligence, and Reporting System

Published on: July 11, 2025

DNA-barcode-based Multiplex Immunofluorescence Imaging to Analyze FFPE Specimens from Genetically Reprogrammed Murine Melanoma

DNA-barcode-based Multiplex Immunofluorescence Imaging to Analyze FFPE Specimens from Genetically Reprogrammed Murine Melanoma

Published on: June 6, 2025

Area of Science:

Artificial Intelligence in Medicine
Natural Language Processing for Healthcare
Clinical Data Extraction

Background:

Pathology reports contain crucial clinical information but are often unstructured free text.
Manual extraction of this data is time-consuming and prone to errors.
Automated methods are needed to improve efficiency and accuracy in healthcare data analysis.

Purpose of the Study:

To evaluate the performance of the Llama 3.1 large language model (LLM) with 70 billion parameters (70b) for clinical information extraction.
To assess the model's zero-shot learning capabilities on free-text pathology reports.
To determine the feasibility of generating structured data directly from unstructured medical text.

Main Methods:

Utilized the Llama 3.1 (70b) model for zero-shot information extraction.
Applied the model to a dataset of free-text pathology reports.
Evaluated the accuracy of extracted clinically significant information.
Generated structured outputs in JSON format.

Main Results:

The Llama 3.1 model achieved a 98% accuracy rate in extracting clinically significant information.
The model successfully generated structured data in JSON format without prior annotation.
Demonstrated robust performance in zero-shot learning scenarios.

Conclusions:

Llama 3.1 shows significant potential for automated data extraction from complex medical documents.
The model can streamline clinical workflows by providing accurate, structured information.
This technology can enhance precision in healthcare information retrieval and analysis.