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 Experiment Video

Updated: Jun 3, 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

Evaluating the Performance of Large Language Models for Breast Cancer Patient Education: A Comparative Study.

Qingyue Zhang1, Qian Yu2, Guili Wang2

  • 1National Clinical Research Center for Cancer, Tianjin's Clinical Research Center for Cancer, Key Laboratory of Cancer Prevention and Therapy, Tianjin Medical University Cancer Institute & Hospital, Department of Breast Oncoplatic Surgery, Tianjin, 300060, China.

Journal of Cancer Education : the Official Journal of the American Association for Cancer Education
|June 2, 2026
PubMed
Summary

Related Concept Videos

Cancer Survival Analysis01:21

Cancer Survival Analysis

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...

You might also read

Related Articles

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

Sort by
Same author

Abundance of <i>Yersinia pestis</i> Nucleic Acids in Soil from <i>Rattus tanezumi</i> Plague Foci in Yunnan Using ddPCR.

Pathogens (Basel, Switzerland)·2026
Same author

Obesity, White Matter Hyperintensities, and Cognitive Decline: Sex-Specific DTI-ALPS Index Mediation.

Stroke·2026
Same author

Single-atom photocatalyst for click reaction.

Nature communications·2026
Same author

Comparative Analysis of Two Strategies for Iliac Vein Stenting: Thrombus Clearance-Assisted Versus Direct Stenting.

Clinical and applied thrombosis/hemostasis : official journal of the International Academy of Clinical and Applied Thrombosis/Hemostasis·2026
Same author

A preclinical investigation into the potential associations of geraniin with ulcerative colitis alleviation through integrated multi-omics and <i>in vivo</i> analysis.

Frontiers in medicine·2026
Same author

Galangin alleviates cold stress-induced splenic injury in Danzhou chickens by inhibiting NLRP3 inflammasome-mediated pyroptosis.

Poultry science·2026

Six large language models (LLMs) were evaluated for breast cancer information accuracy and safety. ERNIE 4.5 Turbo ranked highest, but readability and safety concerns persist, highlighting the need for AI in cancer education.

Area of Science:

  • Artificial Intelligence in Medicine
  • Oncology Digital Health
  • Patient Education Technology

Background:

  • Effective breast cancer patient education is crucial.
  • Large language models (LLMs) offer potential for health consultations but may provide inaccurate or unsafe medical information.
  • Systematic evaluations of LLMs for breast cancer guidance are lacking.

Purpose of the Study:

  • To systematically evaluate the performance of six mainstream LLMs in providing breast cancer health information.
  • To assess LLM responses for quality, accuracy, comprehensiveness, and safety from both expert and patient perspectives.

Main Methods:

  • Developed 61 standardized breast cancer questions based on clinical guidelines and expert input.
  • Evaluated responses from ChatGPT-5.4-thinking, Claude-4.6-sonnet, Gemini-3.1-Pro, DeepSeek-V3.2, Doubao-2.2-thinking, and ERNIE 4.5 Turbo.
Keywords:
Breast cancerClinical questionLarge language modelsPatient education

Related Experiment Videos

Last Updated: Jun 3, 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

  • Assessed responses using expert reviews (quality, accuracy, comprehensiveness, safety) and patient evaluations (satisfaction, understandability).

    • Main Results:

    • ERNIE 4.5 Turbo demonstrated the highest descriptive quality and safety among experts, and highest patient satisfaction and understandability.
    • No significant differences in accuracy were found among the models.
    • ChatGPT-5.4-thinking scored lower in safety, while Doubao-2.2-thinking offered better readability metrics.

    Conclusions:

    • While several LLMs show promise for breast cancer question-answering, ERNIE 4.5 Turbo performed best overall.
    • Persistent issues with response readability and safety necessitate further research.
    • Improving AI-generated content readability is key for effective AI application in precision cancer patient education.