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

Combination Therapies and Personalized Medicine02:50

Combination Therapies and Personalized Medicine

4.8K
Combining two or more treatment methods increases the life span of cancer patients while reducing damage to vital organs or tissue from the overuse of a single treatment. Combination therapy also targets different cancer-inducing pathways, thus reducing the chances of developing resistance to treatment.
The combination of the drug acetazolamide and sulforaphane is a good example of combination therapy to treat cancer. The cells in the interior of a large tumor often die due to the hypoxic and...
4.8K
Targeted Cancer Therapies02:57

Targeted Cancer Therapies

7.4K
The targeted cancer therapies, also known as “molecular targeted therapies,” take advantage of the molecular and genetic differences between the cancer cells and the normal cells. It needs a thorough understanding of the cancer cells to develop drugs that can target specific molecular aspects that drive the growth, progression, and spread of cancer cells without affecting the growth and survival of other normal cells in the body.
There are several types of targeted therapies against...
7.4K
Cancer Survival Analysis01:21

Cancer Survival Analysis

298
Cancer survival analysis focuses on quantifying and interpreting the time from a key starting point, such as diagnosis or the initiation of treatment, to a specific endpoint, such as remission or death. This analysis provides critical insights into treatment effectiveness and factors that influence patient outcomes, helping to shape clinical decisions and guide prognostic evaluations. A cornerstone of oncology research, survival analysis tackles the challenges of skewed, non-normally...
298
Mouse Models of Cancer Study02:43

Mouse Models of Cancer Study

5.4K
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,...
5.4K
Cancer Therapies02:49

Cancer Therapies

7.4K
Cancer therapies are various modes of treatment, such as surgery, radiation therapy, and chemotherapy that are administered to cancer patients.
However, cancer treatments can pose several challenges, as therapies used to kill cancer cells are generally also toxic to normal cells. Moreover, cancer cells mutate rapidly and can develop resistance to chemical agents or radiation therapy. Besides, all types of cancer cells may not respond to the same therapy. Some cancer cells respond to one...
7.4K

You might also read

Related Articles

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

Sort by
Same author

Dynamic genetic and nongenetic RAS pathway activation drives resistance to FLT3 and BCL2 inhibitor therapy.

Blood·2026
Same author

HIV-seq reveals gene expression differences between HIV-transcribing cells from viremic and suppressed people with HIV.

Nature communications·2026
Same author

Investigating CAR-T Treatment Access for Multiple Myeloma Patients Using Real-World Evidence.

Cancers·2026
Same author

Inclusion as innovation: broadening trial criteria in AML.

Blood·2026
Same author

Exploring the Past and Current Landscape of Biomarker-Driven Clinical Trials Through Large Language Models.

JCO clinical cancer informatics·2026
Same author

Assessment of Large Language Models for Enhancing Diabetologist-Developed Personalized Treatment Plans in Complex Type 2 Diabetes.

Clinical diabetes : a publication of the American Diabetes Association·2025
Same journal

The Inverse Care Law in the Age of AI - Geographic Disparities in Health Care Technology Access.

NEJM AI·2026
Same journal

AI-Guided Surgical Blood Readiness: Overcoming Real-World Challenges in Prospective Validation for Safer, More Efficient Blood Preparation.

NEJM AI·2026
Same journal

Brain Health from Sleep EEG: A Multicohort, Deep Learning Biomarker for Cognition, Disease, and Mortality.

NEJM AI·2026
Same journal

Developing ICU Clinical Behavioral Atlas Using Ambient Intelligence and Computer Vision.

NEJM AI·2026
Same journal

A Case Study of AI-Enabled Software as a Medical Device Cleared by the FDA for Assessing Hemorrhage Risk Index (APPRAISE-HRI) after Trauma.

NEJM AI·2026
Same journal

Catalyzing Health AI by Fixing Payment Systems.

NEJM AI·2026
See all related articles

Related Experiment Video

Updated: May 10, 2025

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

462

CORAL: Expert-Curated Oncology Reports to Advance Language Model Inference.

Madhumita Sushil1, Vanessa E Kennedy2, Divneet Mandair2

  • 1Bakar Computational Health Sciences Institute, University of California, San Francisco, San Francisco.

NEJM AI
|April 21, 2025
PubMed
Summary
This summary is machine-generated.

Large language models (LLMs) show promise for extracting oncology information from clinical notes, with GPT-4 demonstrating the best performance in a new benchmark dataset. Further improvements are needed for complex medical reasoning before widespread clinical application.

More Related Videos

Predictive Immune Modeling of Solid Tumors
08:50

Predictive Immune Modeling of Solid Tumors

Published on: February 25, 2020

6.8K
A Knowledge Graph Approach to Elucidate the Role of Organellar Pathways in Disease via Biomedical Reports
07:35

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

Published on: October 13, 2023

1.5K

Related Experiment Videos

Last Updated: May 10, 2025

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

462
Predictive Immune Modeling of Solid Tumors
08:50

Predictive Immune Modeling of Solid Tumors

Published on: February 25, 2020

6.8K
A Knowledge Graph Approach to Elucidate the Role of Organellar Pathways in Disease via Biomedical Reports
07:35

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

Published on: October 13, 2023

1.5K

Area of Science:

  • Computational oncology
  • Natural Language Processing (NLP) in medicine
  • Artificial Intelligence (AI) in healthcare

Background:

  • Accurate understanding of patient disease progression and treatment history is crucial in oncology care and research.
  • Clinical notes contain extensive but unstructured oncology information.
  • Evaluating the utility of large language models (LLMs) in oncology workflows is important, but current limitations exist due to a lack of comprehensive oncology information schemas and annotated datasets.

Purpose of the Study:

  • To assess the zero-shot information extraction capabilities of recent large language models (LLMs) in oncology clinical notes.
  • To develop a fine-grained, expert-labeled dataset and benchmark for evaluating LLMs in oncology.
  • To identify the strengths and limitations of LLMs for extracting detailed oncological information.

Main Methods:

  • A new dataset of 40 deidentified breast and pancreatic cancer progress notes was curated and expert-labeled.
  • Three LLMs (GPT-4, GPT-3.5-turbo, FLAN-UL2) were evaluated for zero-shot extraction of oncological information.
  • Performance was quantified using BLEU-4, ROUGE-1, and exact-match (EM) F1 score metrics.

Main Results:

  • A total of 9028 entities, 9986 modifiers, and 5312 relationships were annotated.
  • GPT-4 achieved the highest performance across metrics (average BLEU: 0.73, ROUGE: 0.72, EM F1: 0.51).
  • GPT-4 excelled in extracting tumor characteristics and medications, and in inferring symptoms and future medication considerations, despite some errors like partial responses and hallucinations.

Conclusions:

  • The developed schema and benchmark reveal both capabilities and limitations of current LLMs in oncology information extraction.
  • LLM performance varied, with GPT-4 showing the most promise but still requiring improvement in complex medical reasoning.
  • Further advancements are necessary for reliable clinical research, population management, and patient care documentation using LLMs.