Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Concept Videos

Imaging Studies III: Gastrointestinal Motility Studies and Virtual Colonoscopy01:26

Imaging Studies III: Gastrointestinal Motility Studies and Virtual Colonoscopy

This lesson explores three gastrointestinal imaging techniques: radionuclide testing, colonic transit studies, and virtual colonoscopy.
Radionuclide Testing
Radionuclide testing is a sophisticated medical technique for assessing gastrointestinal motility. It focuses on gastric emptying and colonic transit time. Radioactive markers track the movement of food through the digestive system, providing insights into gastrointestinal disorders.
In gastric emptying studies, a meal's liquid and solid...
Endoscopic Procedures II: Colonoscopy01:25

Endoscopic Procedures II: Colonoscopy

The colon, or large intestine, is the final segment of the digestive system. Its primary functions include absorbing water and vitamins produced by gut bacteria and transforming waste from liquid to solid to form stool. In adults, the large intestine is approximately 5 feet long and consists of four main sections:
Endoscopic Procedures IV: Sigmoidoscopy and Laproscopy01:26

Endoscopic Procedures IV: Sigmoidoscopy and Laproscopy

Sigmoidoscopy and laparoscopy are distinct medical procedures that enable physicians to internally inspect different parts of the GI tract. Although they serve different purposes, each is essential for diagnosing and, in some cases, treating various medical conditions.
Sigmoidoscopy
Sigmoidoscopy is a diagnostic procedure that uses a flexible sigmoidoscope equipped with a light source and camera to examine the rectum and sigmoid colon. The procedure involves inserting the tube through the anus...

You might also read

Related Articles

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

Sort by
Same author

Colon-Pilot: A Generative AI Tool for Automated Colonoscopy Surveillance Recommendations and 2024 ACG/ASGE Quality Benchmarking.

The American journal of gastroenterology·2026
Same author

Accuracy of Patient Self-Reported Menopause Stage: A Cross-Sectional Study.

Mayo Clinic proceedings·2026
Same author

Accurate and Scalable Classification of Colonoscopy Neoplasia Using Machine Learning and Natural Language Processing.

Clinical and translational gastroenterology·2025
Same author

Patient Engagement with General Bulk Outreach: Impact of Primary Care Provider vs. Care Team Signature in General Bulk Patient Outreach.

Population health management·2025
Same author

Massive Rectal Bleeding After Rubber Band Ligation of Internal Hemorrhoids: A Case Report.

WMJ : official publication of the State Medical Society of Wisconsin·2025
Same author

Addressing Menopause Symptoms: Barriers and Opportunities for Improvement.

Mayo Clinic proceedings·2025

Related Experiment Video

Updated: Jun 23, 2026

Introduction of an Integrated Pathology Image Management, Artificial Intelligence, and Reporting System
05:33

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

Published on: July 11, 2025

Distilling Knowledge in Gastroenterology: An Artificial Intelligence System for Assisting Colonoscopy and Pathology

Brayden Mau1, Sushil Kumar Garg2, Sarah B Harper3

  • 1Department of Computer Science, University of Wisconsin-Eau Claire, Eau Claire, WI.

Mayo Clinic Proceedings. Digital Health
|June 22, 2026
PubMed
Summary

This study developed an efficient natural language processing (NLP) model for processing colonoscopy and pathology reports using knowledge distillation. The smaller, domain-specific NLP model achieved high accuracy and improved inference speed, aiding in clinical documentation interpretation.

Related Experiment Videos

Last Updated: Jun 23, 2026

Introduction of an Integrated Pathology Image Management, Artificial Intelligence, and Reporting System
05:33

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

Published on: July 11, 2025

Area of Science:

  • Medical Informatics
  • Natural Language Processing
  • Gastroenterology

Background:

  • Clinical reports from colonoscopies and pathology contain crucial information for patient care.
  • Processing these complex documents manually is time-consuming and prone to errors.
  • Developing automated systems can improve efficiency and accuracy in clinical data analysis.

Purpose of the Study:

  • To create an efficient and domain-adapted natural language processing (NLP) system for processing colonoscopy and pathology reports.
  • To leverage knowledge distillation to develop a smaller, specialized NLP model.
  • To enhance the summarization and information extraction capabilities from clinical reports.

Main Methods:

  • Implemented a knowledge distillation framework to train a domain-specific NLP model.
  • Utilized a dataset of 5500 colonoscopy and 7000 pathology reports.
  • Evaluated model performance against ground truth polyp categories from pathology diagnoses.

Main Results:

  • The distilled model achieved 95.2% accuracy and 0.95 precision in domain-specific tasks.
  • Demonstrated a 31.5% improvement in inference speed compared to the larger teacher model.
  • Showcased strong capability in identifying polyp characteristics (number, size, histology, location) and received high agreement from clinicians.

Conclusions:

  • Knowledge distillation enables the creation of efficient and scalable domain-specific NLP models for gastroenterology.
  • The developed model assists in interpreting complex clinical documentation, supporting follow-up recommendations.
  • Future work includes real-world validation and expansion to other procedural report types.