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

4.7K
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,...
4.7K
Cancer Survival Analysis01:21

Cancer Survival Analysis

870
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...
870

You might also read

Related Articles

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

Sort by
Same author

Clinical utility and implementation of a virtual molecular tumor board in real-world oncology practice.

Cancer genetics·2026
Same author

Real-World Outcomes of Nivolumab Plus Ipilimumab in Metastatic Melanoma: A Stratified Analysis of First- and Second-Line Treatment.

Cancers·2026
Same author

Exploratory analysis of PTEN deficiency by immunohistochemistry from the Phase III CAPItello-291 trial.

Clinical cancer research : an official journal of the American Association for Cancer Research·2026
Same author

Re: predictive modeling of treatment-related thyroid dysfunction and prognostic implication in advanced nasopharyngeal carcinoma with PD-1 inhibitors.

The oncologist·2026
Same author

Multicenter Prospective Phase II Study of Induction Therapy With Pembrolizumab, Cisplatin, and Fluorouracil in Patients With Locally Advanced Head and Neck Cancer.

Cancer control : journal of the Moffitt Cancer Center·2026
Same author

Artificial Intelligence for Tumor Tissue Detection in Stomach Cancer: A Retrospective Algorithm Development and Validation Study.

Journal of clinical medicine·2026

Related Experiment Video

Updated: May 6, 2026

Systems Biology of Metabolic Regulation by Estrogen Receptor Signaling in Breast Cancer
10:36

Systems Biology of Metabolic Regulation by Estrogen Receptor Signaling in Breast Cancer

Published on: March 17, 2016

10.9K

Deriving Real-World Evidence from Non-English Electronic Medical Records in Hormone Receptor-Positive Breast Cancer

Daur Meretukov1, Katerina Grechukhina2, Vladimir Evdokimov3

  • 1Department of Science, N.N. Blokhin Cancer Research Center, Moscow 115478, Russia.

Cancers
|December 11, 2025
PubMed
Summary

Large language models can accurately structure non-English electronic medical records to identify a novel "Luminal B poor-prognosis" breast cancer subgroup. This subgroup, defined by specific progesterone receptor and Ki-67 levels, indicates significantly poorer outcomes.

Keywords:
AIBCLLMLPPRWDartificial intelligencebreast cancerlarge language modelreal-world data“luminal B poor-prognosis” breast cancer

More Related Videos

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

986
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

1.2K

Related Experiment Videos

Last Updated: May 6, 2026

Systems Biology of Metabolic Regulation by Estrogen Receptor Signaling in Breast Cancer
10:36

Systems Biology of Metabolic Regulation by Estrogen Receptor Signaling in Breast Cancer

Published on: March 17, 2016

10.9K
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

986
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

1.2K

Area of Science:

  • Oncology
  • Medical Informatics
  • Artificial Intelligence in Medicine

Background:

  • Large language models (LLMs) show potential for structuring electronic medical records (EMRs).
  • Reliability of LLMs in non-English clinical text and their ability to generate new insights require validation.
  • This study addresses the need to assess LLM accuracy and utility in identifying novel breast cancer subgroups.

Purpose of the Study:

  • To utilize a domain-engineered LLM to identify a "Luminal B poor-prognosis" (LPP) breast cancer subgroup.
  • To define the LPP subgroup based on progesterone receptor (PR), Ki-67 index, and grade.
  • To concurrently validate the LLM's accuracy in extracting clinicopathological variables from non-English EMRs.

Main Methods:

  • Retrospective analysis of 7756 female breast cancer patients' EMRs from Moscow oncology centers.
  • LLM employed to extract eight clinicopathological variables; accuracy validated against oncologist annotations (ICC, weighted κ).
  • Survival analysis (Kaplan-Meier, Cox regression) performed on HR+/HER2- stage I-III sub-cohort (n=1419) to define and analyze LPP subgroup.

Main Results:

  • High LLM-human agreement observed for extracted variables (e.g., Ki-67 ICC=0.882, PR κ=0.975).
  • In HR+/HER2- patients, PR < 4 and Ki-67 ≥ 40% identified inferior survival.
  • The defined LPP subgroup (PR < 4 and Ki-67 ≥ 40%) constituted ~5.3% of patients and showed significantly poorer outcomes (aHR=2.60).

Conclusions:

  • The developed LLM reliably structures non-English EMRs and facilitates the discovery of clinically meaningful subgroups.
  • The identified LPP phenotype represents a small, high-risk breast cancer subset requiring external validation.
  • Findings are hypothesis-generating due to the retrospective, single-system design; further validation is essential.