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

Mouse Models of Cancer Study02:43

Mouse Models of Cancer Study

6.4K
Mice have long served as models for studying human biology and pathology because of their phylogenetic and physiological similarity with humans. They are also easy to maintain and breed in the laboratory, and hence, many inbred strains are now available for research. Studies on mice have contributed immeasurably to our understanding of cancer biology.
The development of transgenic, knockout, and knock-in mice has led to an exponential increase in their use as model organisms in research,...
6.4K

You might also read

Related Articles

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

Sort by
Same author

Toxicity from asparaginase during acute lymphoblastic leukemia induction: A report from the Children's Oncology Group.

Blood advances·2026
Same author

Federal housing assistance, cancer care, and overall survival among older adults with prostate cancer.

Journal of the National Cancer Institute·2026
Same author

Reply.

Gastro hep advances·2026
Same author

Mild Dilatation of the Main Pancreatic Duct Is a Risk Factor for Progression to Pancreatic Cancer in High-Risk Individuals.

Gastro hep advances·2025
Same author

Federal Housing Assistance and Stage at Cancer Diagnosis Among Older Adults in the US.

JAMA network open·2025
Same author

Personalizing CA125 Levels Using Tumor Marker Variants: A Case-Control Analysis of Diagnostic Performance for Pancreatic Cancer.

Cancer epidemiology, biomarkers & prevention : a publication of the American Association for Cancer Research, cosponsored by the American Society of Preventive Oncology·2025

Related Experiment Video

Updated: Jan 10, 2026

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness
03:14

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness

Published on: December 6, 2024

1000

Large Language Models Can Generate High-Quality Pathology Multiple-Choice Questions Comparable With Questions Written

Michael J Borowitz1, Amanda L Blackford2, Suman Nagelia3

  • 1Department of Pathology, Sol Goldman Pancreatic Cancer Research Center, Johns Hopkins University School of Medicine, Baltimore, Maryland; Sidney Kimmel Comprehensive Cancer Center, Johns Hopkins University School of Medicine, Baltimore, Maryland.

Modern Pathology : an Official Journal of the United States and Canadian Academy of Pathology, Inc
|November 23, 2025
PubMed
Summary
This summary is machine-generated.

Large language models (LLMs) can generate pathology test questions, but human experts are still needed for optimal quality. While LLM-generated questions showed slightly more poor-quality examples, their overall good or excellent ratings were comparable to human-authored questions.

Keywords:
artificial intelligencelarge language modelsmultiple-choice questionspancreaspathology

More Related Videos

Evidence-based Knowledge Synthesis and Hypothesis Validation: Navigating Biomedical Knowledge Bases via Explainable AI and Agentic Systems
05:47

Evidence-based Knowledge Synthesis and Hypothesis Validation: Navigating Biomedical Knowledge Bases via Explainable AI and Agentic Systems

Published on: June 13, 2025

1.3K
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

763

Related Experiment Videos

Last Updated: Jan 10, 2026

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness
03:14

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness

Published on: December 6, 2024

1000
Evidence-based Knowledge Synthesis and Hypothesis Validation: Navigating Biomedical Knowledge Bases via Explainable AI and Agentic Systems
05:47

Evidence-based Knowledge Synthesis and Hypothesis Validation: Navigating Biomedical Knowledge Bases via Explainable AI and Agentic Systems

Published on: June 13, 2025

1.3K
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

763

Area of Science:

  • Medical Education
  • Artificial Intelligence in Pathology
  • Question Generation

Background:

  • Creating high-quality multiple-choice questions for pathology assessment is time-consuming and requires expertise.
  • Large language models (LLMs) offer a potential solution for efficient question generation.

Purpose of the Study:

  • To evaluate the quality of pathology test questions generated by large language models (LLMs) compared to human experts.
  • To assess the performance and perception of LLM-generated pancreas pathology questions.

Main Methods:

  • 100 pancreas pathology questions were authored by a human expert.
  • 50 questions each were generated by ChatGPT-4.0 and Gemini 2.5 Flash.
  • 190 volunteers evaluated the quality, difficulty, and clinical realism of human-authored and LLM-generated questions.

Main Results:

  • LLM-generated questions required revision, with ChatGPT-generated questions rated as easier than human-authored ones.
  • LLM-generated questions had a slightly higher proportion of poor/unacceptable items (11.7%) versus human-authored (10.1%), but no difference in good/excellent ratings.
  • No significant difference was found in the mean point biserial correlation between human-authored and LLM-generated questions.

Conclusions:

  • LLMs show promise for efficiently generating pathology test questions, though human oversight remains crucial.
  • As LLMs advance, they are expected to become increasingly valuable tools for creating high-quality educational assessments in pathology.