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 11, 2026

A Machine Learning Approach to Design an Efficient Selective Screening of Mild Cognitive Impairment
12:18

A Machine Learning Approach to Design an Efficient Selective Screening of Mild Cognitive Impairment

Published on: January 11, 2020

Improving Readability of Stroke Clinical Trial Consent Forms Using Artificial Intelligence.

Rohan Arora1,2, Lesli E Skolarus3, Robert M Miller4

  • 1Department of Neurology, Northwell, New Hyde Park, NY (R.A., B.M.J.).

Stroke
|May 6, 2026
PubMed
Summary

Related Concept Videos

Clinical Trials: Overview01:11

Clinical Trials: Overview

Clinical development focuses on how the drug will interact with the human body and encompasses four key phases of clinical trials, each serving a specific purpose in assessing the safety and effectiveness of new drugs. These phases overlap and build upon one another. Phase I involves a small group of healthy volunteers (typically 20-80 individuals) or, in cases where significant toxicity is expected, patients with the targeted disease, such as cancer or AIDS. The volunteers are tested for...

You might also read

Related Articles

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

Sort by
Same author

Impact of Analytical Decisions on Physical Activity Outcomes in a Cardiovascular Mobile Health Study.

Journal of the American Heart Association·2026
Same author

Advancing Stroke Clinical Trials Using Community Engagement and Implementation Science Approaches.

Annals of clinical and translational neurology·2026
Same author

A Case of Lentigo Maligna Presenting as Repigmentation of Hair in a Scalp That Previously Underwent Radiotherapy for Tinea Capitis.

The Australasian journal of dermatology·2026
Same author

Factors Underlying Stroke Recovery Variation by Neighborhood Socioeconomic Status.

JAMA network open·2026
Same author

Is cycloplegic refraction necessary in adults? Insights from a comparative refraction study.

Indian journal of ophthalmology·2026
Same author

Impact of Push Notifications on Physical Activity and Sodium Intake Among Patients with Hypertension: Microrandomized Trial of a Just-in-Time Adaptive Intervention.

Journal of medical Internet research·2026

Artificial intelligence significantly improved clinical trial informed consent form readability. AI-edited forms achieved an eighth-grade reading level while maintaining content accuracy, aiding patient comprehension in stroke research.

Area of Science:

  • Clinical Informatics
  • Medical Writing
  • Artificial Intelligence in Healthcare

Background:

  • Informed consent forms (ICFs) for clinical trials often exceed recommended readability levels.
  • This study addresses the challenge of complex language in ICFs for National Institutes of Health-funded stroke trials.

Purpose of the Study:

  • To compare the readability of original ICFs with AI-edited versions.
  • To assess the effectiveness of a customized Generative Pre-Trained Transformer (GPT) in simplifying ICFs.

Main Methods:

  • Accessed ICFs from NIH-funded stroke trials via ClinicalTrials.gov.
  • Utilized a customized ChatGPT-4o (GPT) to lower reading levels to eighth grade or below.
  • Compared readability metrics (Flesch-Kincaid grade level) and semantic similarity (MPNet) between original and edited ICFs.
Keywords:
artificial intelligencecomprehensionhealth literacyinformed consentstroke

Related Experiment Videos

Last Updated: Jun 11, 2026

A Machine Learning Approach to Design an Efficient Selective Screening of Mild Cognitive Impairment
12:18

A Machine Learning Approach to Design an Efficient Selective Screening of Mild Cognitive Impairment

Published on: January 11, 2020

Main Results:

  • GPT-edited ICFs showed a significant reduction in Flesch-Kincaid grade level from 11.52 to 9.47 (P<0.001).
  • 39% of AI-edited ICFs met the eighth-grade reading level target, compared to only 2% of originals.
  • High semantic similarity (mean score 0.85) was maintained between original and edited ICFs.

Conclusions:

  • Customized GPTs effectively reduce ICF reading levels by approximately two grade levels.
  • AI-generated edits preserve essential content, suggesting GPTs are valuable for enhancing ICF readability.
  • Improved ICF readability can enhance patient understanding and participation in clinical trials.