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: May 13, 2026

Comparison of Predictive Performance of Three Lymph Node Staging Systems in Colorectal Signet Ring Cell Carcinoma Based on Machine Learning Model
07:13

Comparison of Predictive Performance of Three Lymph Node Staging Systems in Colorectal Signet Ring Cell Carcinoma Based on Machine Learning Model

Published on: April 18, 2025

Using Large Language Models to Determine Reasons for Missed Colon Cancer Screening Follow-Up.

Christopher Y K Williams, Urmimala Sarkar, Julia Adler-Milstein

    Joint Commission Journal on Quality and Patient Safety
    |May 11, 2026
    PubMed
    Summary
    This summary is machine-generated.

    Related Concept Videos

    You might also read

    Related Articles

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

    Sort by
    Same author

    Estimating the Cost of Poor Work Control Among Physicians in the United States.

    Mayo Clinic proceedings·2026
    Same author

    Characterizing emergency clinician engagement with social drivers of health data among patients with opioid use disorder.

    Journal of the American Medical Informatics Association : JAMIA·2026
    Same author

    From research to impact: two decades of advancing age-friendly policies worldwide.

    The Public policy and aging report·2026
    Same author

    Social Drivers of Health in the Electronic Health Record.

    Annual review of biomedical data science·2026
    Same author

    Physician Intent to Reduce Hours and Intent to Leave Organizations.

    JAMA network open·2026
    Same author

    Changes in Clinician Time Expenditure and Visit Quantity With Adoption of Artificial Intelligence-Powered Scribes: A Multisite Study.

    JAMA·2026
    Same journal

    Implementing the SSKIN Bundle in Home Healthcare: A Tool Tutorial for Reducing Pressure Injuries.

    Joint Commission journal on quality and patient safety·2026
    Same journal

    How Collaboration Between Surgeons and Medical Oncologists Affects Outcomes for Patients with Pancreatic Cancer.

    Joint Commission journal on quality and patient safety·2026
    Same journal

    Uneven Compassion and the Emotional Safety of the Healthcare Workforce.

    Joint Commission journal on quality and patient safety·2026
    Same journal

    Development and Implementation of a Machine Learning Model for Prediction of Surgical Case Duration.

    Joint Commission journal on quality and patient safety·2026
    Same journal

    Decreasing Herpes Simplex Virus (HSV) Testing Turnaround Time for Infants in a Hospital Setting: A Continuous Quality Improvement Project.

    Joint Commission journal on quality and patient safety·2026
    Same journal

    Symptom Tracking in Primary Care: Designing and Testing an EHR-Embedded Safety-Net System.

    Joint Commission journal on quality and patient safety·2026
    See all related articles

    Large language models (LLMs) can automate identifying why patients miss follow-up colonoscopies after abnormal stool tests. This technology shows promise for improving cancer screening quality by reducing manual chart review burdens.

    Area of Science:

    • Medical Informatics
    • Artificial Intelligence in Healthcare
    • Cancer Screening Quality Improvement

    Background:

    • Identifying reasons for missed preventive care, like follow-up colonoscopy after abnormal stool-based screening, is crucial for quality improvement.
    • Manual chart review for these care gaps is time-consuming and costly.
    • This study explores using large language models (LLMs) to automate this process.

    Purpose of the Study:

    • To demonstrate the potential of LLMs in automating the identification of documented reasons for colonoscopy follow-up gaps.
    • To assess if LLMs can accurately classify these reasons into clinically meaningful categories.

    Main Methods:

    • A cross-sectional study involving patients aged 45+ with abnormal fecal immunochemical/occult blood tests (FIT/FOBT) who did not receive a colonoscopy within 90 days.

    Related Experiment Videos

    Last Updated: May 13, 2026

    Comparison of Predictive Performance of Three Lymph Node Staging Systems in Colorectal Signet Ring Cell Carcinoma Based on Machine Learning Model
    07:13

    Comparison of Predictive Performance of Three Lymph Node Staging Systems in Colorectal Signet Ring Cell Carcinoma Based on Machine Learning Model

    Published on: April 18, 2025

  • Investigated LLM's ability to determine if reasons for lack of follow-up colonoscopy were documented in clinical notes.
  • Assessed LLM's accuracy in classifying documented reasons.

    • Main Results:

    • Out of 846 patients, 23.3% had explicit reasons documented for not having a colonoscopy.
    • LLM classification accuracy reached 89.0%.
    • Common reasons included patient refusal (35.2%), comorbidities (18.7%), and unavailability (16.8%).

    Conclusions:

    • LLMs can accurately categorize reasons for missed follow-up colonoscopies after abnormal FIT/FOBT.
    • LLMs show potential for automating chart review in quality improvement initiatives for colorectal cancer screening.