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 17, 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

Assessing Eligibility for Anticancer Drug Health Insurance Reimbursement Using Large Language Models: Benchmark

Junhyuk Seo1, Taerim Kim1,2,3, Ju-Hyun Kim4

  • 1Healthcare Research Institute, ETOILE Inc, Seoul, Republic of Korea.

Journal of Medical Internet Research
|June 15, 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

Clinical practice guideline for high-risk human papillomavirus testing in cervical cancer screening: a consensus statement from the Korean Society of Gynecologic Oncology.

Journal of gynecologic oncology·2026
Same author

Clinical practice guidelines for uterine corpus cancer: an update to the Korean Society of Gynecologic Oncology guidelines.

Journal of gynecologic oncology·2025
Same author

Evaluation Framework of Large Language Models in Medical Documentation: Development and Usability Study.

Journal of medical Internet research·2024
Same author

Temporary Telemedicine Policy and Chronic Disease Management in South Korea: Retrospective Analysis Using National Claims Data.

JMIR public health and surveillance·2024
Same author

Real-Time Tracheal Ultrasound vs. Capnography for Intubation Confirmation during CPR Wearing a Powered Air-Purifying Respirator in COVID-19 Era.

Diagnostics (Basel, Switzerland)·2024
Same author

A Simple Bacteremia Score for Predicting Bacteremia in Patients with Suspected Infection in the Emergency Department: A Cohort Study.

Journal of personalized medicine·2024
Same journal

Comparative Effectiveness of AI-Assisted Telerehabilitation, Telerehabilitation, In-Person Care, and Usual Care for Chronic Nonspecific Low Back Pain: Bayesian Network Meta-Analysis.

Journal of medical Internet research·2026
Same journal

Effectiveness of WeChat Public Account Intervention Based on the Information-Motivation-Behavioral Skills Model Among College Students With Internet Addiction: Randomized Controlled Trial.

Journal of medical Internet research·2026
Same journal

Are Traditional Registries Becoming Obsolete in the Modern Digital Health Ecosystem?

Journal of medical Internet research·2026
Same journal

Detecting and Preventing Fraudulent Participation in Qualitative Research: Content Analysis of Two Multisite Studies.

Journal of medical Internet research·2026
Same journal

Patient Perceptions of Artificial Intelligence-Supported Shared Decision-Making in UK Primary Care for Multiple Long-Term Conditions: Qualitative Study.

Journal of medical Internet research·2026
Same journal

Impact of Telemedicine-Enhanced Integrated Management of Gestational Diabetes on Pregnancy Outcomes and Glycemic Control: Real-World Study Using TangMama App.

Journal of medical Internet research·2026
See all related articles
This summary is machine-generated.

Large language models (LLMs) show high accuracy for clear anticancer drug eligibility but struggle with complex cases. LLMs are best used as supervised tools, not independent reviewers, due to information gap-filling errors.

Area of Science:

  • Health Informatics
  • Artificial Intelligence in Healthcare
  • Health Services Research

Background:

  • Administrative costs in healthcare are increased by complex insurance eligibility determinations.
  • Large language models (LLMs) are increasingly used for health insurance queries.
  • The reliability of LLMs for structured logical reasoning over health coverage criteria is not well-evaluated.

Purpose of the Study:

  • Develop a benchmark for anticancer drug reimbursement eligibility determination.
  • Evaluate the reliability of LLMs in performing eligibility verification for anticancer drugs.

Main Methods:

  • Constructed a benchmark using South Korea's National Health Insurance reimbursement guidelines for 3 gynecologic cancers.
  • Utilized a tristate adjudication framework (eligible, ineligible, undeterminable) validated by experts.
Keywords:
National Health Insuranceanticancer drugsbenchmarkclinical decision supporteligibility verificationgynecologic cancerhealth insurancelarge language modelsnatural language processingreimbursement

Related Experiment Videos

Last Updated: Jun 17, 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

  • Evaluated 6 LLMs from 3 providers on 222 cases, with performance compared across outcome classes.

    • Main Results:

    • Overall verification accuracy ranged from 77.9% to 88.7% across 6 LLMs.
    • High recall was achieved for eligible and ineligible cases, but undeterminable cases showed significantly lower recall (44.6%-70.3%).
    • Information gap-filling was the dominant error pattern (83.4%), particularly in complex guidelines like uterine cancer.

    Conclusions:

    • LLMs demonstrate high recall for straightforward anticancer drug eligibility but limited reliability for undeterminable cases.
    • The primary failure mode involves LLMs inferring eligibility (information gap-filling) rather than indicating uncertainty.
    • Current LLMs are better suited as supervised decision-support tools than as independent adjudicators in reimbursement reviews.