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: Jul 12, 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

Generating Question Prompt Lists From Electronic Health Record Data Using Large Language Models: Iterative Evaluation

Zhe He1, Balu Bhasuran1, Mia Liza A Lustria1

  • 1School of Information, Florida State University, 142 Collegiate Loop, Tallahassee, FL, 32306, United States, 1 8506445775.

Journal of Medical Internet Research
|July 9, 2026
PubMed
Summary

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

A Curated Dataset for Question Answering on Laboratory Test Reference Ranges and Interpretation.

Scientific data·2026
Same author

Patient Experiences With Online Laboratory Test Presentations From Access to Activation: Systematic Review.

Journal of medical Internet research·2026
Same author

Predicting Adherence to Computer-Based Cognitive Training Programs Among Older Adults Using Source-Free Domain Adaptation: Algorithm Development and Validation.

JMIR aging·2026
Same author

Mental Health, Nonadherence, and Healthcare Utilization in Pediatric Solid Organ Transplantation: Evidence From a Multistate Cohort.

Pediatric transplantation·2026
Same author

Growth Trajectories of Medication Adherence in Pediatric Organ Transplantation and Their Relationship to Posttransplant Health Outcomes.

Transplantation direct·2026
Same author

Prevalence of statin utilization in cancer survivors in a family medicine clinic.

Supportive care in cancer : official journal of the Multinational Association of Supportive Care in Cancer·2026
This summary is machine-generated.

Large language models (LLMs) can generate patient questions from lab results, but clinician review is essential. This study shows LLMs are feasible for creating question prompt lists (QPLs) from electronic health records (EHRs).

Area of Science:

  • Artificial Intelligence in Healthcare
  • Clinical Informatics
  • Patient Engagement Technologies

Background:

  • Patients often struggle to interpret laboratory results accessed via patient portals.
  • Existing question prompt lists (QPLs) lack personalization for individual clinical contexts.

Purpose of the Study:

  • To assess the feasibility of using large language models (LLMs) to create patient-friendly questions from electronic health record (EHR) laboratory data.
  • To generate clinically relevant questions tailored to individual patient profiles.

Main Methods:

  • Extracted deidentified EHR data (lab results, diagnoses, medications) for patients with chronic conditions.
  • Utilized GPT-4o and LLaMA 3.2 to generate questions, refining prompts based on clinician feedback (clarity, validity, significance, appropriateness, willingness to answer).
Keywords:
electronic health recordslaboratory results interpretationlarge language modelspatient-clinician communicationquestion prompt lists

More Related Videos

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

Related Experiment Videos

Last Updated: Jul 12, 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

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

  • Assessed question understandability, usefulness, and intention to use via patient evaluation and readability indices.

    • Main Results:

    • Iterative clinician feedback improved question clarity and relevance.
    • GPT-4o generated more coherent and patient-friendly questions; LLaMA 3.2 showed competitive performance and favored Likert-scale metrics.
    • Patient evaluations indicated moderate to high understandability and usefulness for GPT-4o generated questions.

    Conclusions:

    • LLMs show feasibility for generating contextualized QPLs from EHR laboratory data.
    • Model-generated questions require clinician review for clinical appropriateness and readability before patient use.
    • LLMs can enhance patient-provider communication regarding laboratory results.