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

You might also read

Related Articles

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

Sort by

Same author

Hodgkin Lymphoma, Version 1.2026, NCCN Clinical Practice Guidelines In Oncology.

Journal of the National Comprehensive Cancer Network : JNCCN·2026

Same author

Patterns, risk factors and management of CD19-directed chimeric antigen receptor T-cell therapy failure in CNS lymphoma.

Journal of hematology & oncology·2026

Same author

A prospective study of prophylactic dexamethasone with glofitamab in relapsed/refractory large B-cell lymphoma.

Blood neoplasia·2025

Same author

Central nervous system involvement in chronic lymphocytic leukemia: a real-world analysis.

Leukemia & lymphoma·2025

Same author

Toward responsible AI governance: Balancing multi-stakeholder perspectives on AI in healthcare.

International journal of medical informatics·2025

Same author

Prognostic gene expression and microRNA profiling signatures and genetic alterations in primary testicular diffuse large B-cell lymphoma.

Blood cancer journal·2025

Search research articles

Related Experiment Video

Updated: May 4, 2026

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

Automatic lymphoma classification with sentence subgraph mining from pathology reports.

Yuan Luo¹, Aliyah R Sohani², Ephraim P Hochberg³

¹Computer Science and Artificial Intelligence Lab, Massachusetts Institute of Technology, Cambridge, Massachusetts, USA.

Journal of the American Medical Informatics Association : JAMIA

|January 17, 2014

Summary

This summary is machine-generated.

This study introduces an unsupervised method to extract medical concept relations from pathology reports, improving lymphoma classification accuracy without prior knowledge. The novel graph-based approach significantly outperforms existing methods.

Keywords:

Automatic lymphoma classification Natural language processing Pathology reports Sentence subgraph mining

More Related Videos

A Knowledge Graph Approach to Elucidate the Role of Organellar Pathways in Disease via Biomedical Reports

A Knowledge Graph Approach to Elucidate the Role of Organellar Pathways in Disease via Biomedical Reports

Published on: October 13, 2023

Automated Dissection Protocol for Tumor Enrichment in Low Tumor Content Tissues

Automated Dissection Protocol for Tumor Enrichment in Low Tumor Content Tissues

Published on: March 29, 2021

Related Experiment Videos

Last Updated: May 4, 2026

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

A Knowledge Graph Approach to Elucidate the Role of Organellar Pathways in Disease via Biomedical Reports

A Knowledge Graph Approach to Elucidate the Role of Organellar Pathways in Disease via Biomedical Reports

Published on: October 13, 2023

Automated Dissection Protocol for Tumor Enrichment in Low Tumor Content Tissues

Automated Dissection Protocol for Tumor Enrichment in Low Tumor Content Tissues

Published on: March 29, 2021

Area of Science:

Medical Informatics
Computational Pathology
Natural Language Processing

Background:

Pathology reports contain complex medical concept relations crucial for diagnosis.
Current relation extraction methods often rely on manual rules or supervised learning.
Automating relation extraction can enhance computational disease modeling.

Purpose of the Study:

To develop an unsupervised framework for automatically capturing relations from narrative pathology text.
To enable computational analysis of medical texts without predefined forms or explicit labels.

Main Methods:

A novel framework translates sentences into graph representations.
Sentence subgraphs are automatically mined, redundancies reduced, and features generated.
The Unified Medical Language System Metathesaurus maps text to medical concepts and graph nodes.
The system was tested on lymphoma classification tasks, excluding explicit lymphoma mentions.

Main Results:

The system achieved high F-measures in classifying multiple lymphoma types (e.g., diffuse large B-cell lymphoma: 0.909, Hodgkin lymphoma: 0.912).
Unsupervised subgraph features significantly outperformed baseline classifiers (n-grams, MetaMap concepts).
Feature analysis revealed insights consistent with current lymphoma classification knowledge.

Conclusions:

The developed unsupervised framework effectively captures medical relations for improved classification.
This approach offers a powerful tool for analyzing complex narrative medical data.
The extracted unsupervised relation features provide meaningful insights into disease classification.