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

Receptor discordance between primary tumors and nodal metastases and correlation with the 21-gene recurrence score in early-stage, estrogen receptor-positive, node-positive breast cancer.

Breast cancer research and treatment·2026

Same author

Dynamic monitoring of antibody drug conjugates targeting TROP2 or HER2 in breast cancer using circulating tumor cells.

Proceedings of the National Academy of Sciences of the United States of America·2026

Same author

Activating a B cell immune response regresses immunologically cold tumours.

Nature nanotechnology·2026

Same author

A Patient-Led Survey of Antibody Drug Conjugate Usage and Dosing for People Living With Metastatic Breast Cancer.

Journal of patient experience·2026

Same author

Prospective deployment of AI-based risk stratification to enable expedited mammography workflow in a safety-net setting.

NPJ digital medicine·2026

Same author

Concurrent Versus Sequential Radiation Dose Escalation to the Surgical Cavity for Conservative Treatment of High-Risk Early Breast Cancer: NRG/RTOG 1005 Phase III Trial.

Journal of clinical oncology : official journal of the American Society of Clinical Oncology·2026

Same journal

Comments on: Cost-effectiveness of DPYD genotyping prior to capecitabine administration for metastatic breast cancer.

Breast cancer research and treatment·2026

Same journal

Comments on: Predictors of pathologic complete response in early-stage triple-negative breast cancer treated with neoadjuvant chemo-immunotherapy.

Breast cancer research and treatment·2026

Same journal

Discrimination, spectrum, and clinical utility: ICG lymphography drainage time in axillary staging.

Breast cancer research and treatment·2026

Same journal

Tumor infiltrating lymphocytes (TILs) as a predictive marker of pathological complete response (pCR) in a diverse patient population with early triple negative breast cancer (TNBC) treated with neoadjuvant real-world KEYNOTE-522 regimen.

Breast cancer research and treatment·2026

Same journal

Role of individualized intervention(s) on quality of life and adherence to adjuvant endocrine therapy in premenopausal women with early-stage breast cancer: MyCHOICE study.

Breast cancer research and treatment·2026

Same journal

Subjective socioeconomic status moderates the relationship between objective neighborhood disadvantage and quality of life in middle- and older-aged women with breast cancer.

Breast cancer research and treatment·2026

See all related articles

Search research articles

Related Experiment Video

Updated: Mar 12, 2026

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma

Published on: October 10, 2018

Using machine learning to parse breast pathology reports.

Adam Yala¹, Regina Barzilay¹, Laura Salama²

¹Department of Electrical Engineering and Computer Science, CSAIL, MIT, Cambridge, USA.

Breast Cancer Research and Treatment

|November 10, 2016

Summary

This summary is machine-generated.

A machine learning model was developed to automatically extract tumor characteristics from breast pathology reports. This enables the creation of a searchable database, significantly reducing manual data extraction time and cost for medical research.

Keywords:

Atypia Breast pathology Carcinoma in situ Hyperplasia Machine learning Natural language processing Pathology reports

More Related Videos

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model

Published on: August 16, 2020

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

Related Experiment Videos

Last Updated: Mar 12, 2026

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma

Published on: October 10, 2018

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model

Published on: August 16, 2020

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

Area of Science:

Computational pathology
Medical informatics
Machine learning in healthcare

Background:

Manual extraction of information from electronic medical records is labor-intensive and costly.
Automated methods, including rule-based and machine learning techniques, offer potential solutions.
Pathology reports contain crucial tumor characteristics vital for patient cohort identification and research.

Purpose of the Study:

To develop and evaluate a machine learning model for automated extraction of tumor characteristics from breast pathology reports.
To create a searchable database of parsed pathology reports for efficient patient cohort identification.
To assess the model's performance and annotation requirements.

Main Methods:

A machine learning model was trained on a dataset of 91,505 breast pathology reports (1978-2016) from three hospitals.
Training involved two annotated datasets (6,295 and 10,841 reports).
The system extracts 20 categories, including atypia types and tumor receptors; learning curve analysis was performed.

Main Results:

The model achieved 90% accuracy in parsing all carcinoma and atypia categories on a test set of 500 reports.
Average accuracy for individual categories reached 97%.
A database of 91,505 parsed pathology reports was successfully created.

Conclusions:

The machine learning model effectively extracts key information from pathology reports, enabling database creation.
Reasonable model performance can be achieved with limited annotations, as shown by the learning curve analysis.
The developed system and database interface can significantly reduce the time and cost of medical data analysis for research.