LLM-Based Education for Glaucoma

Age: 18+
Sex: Any
Trial Phase: Academic
Sponsor: Stanford University
No Placebo GroupAll trial participants will receive the active study treatment (no placebo)

What You Need to Know Before You Apply

What is the purpose of this trial?

This trial explores whether an AI-powered educational tool can help glaucoma patients better understand the visual field test, which assesses their ability to see in all directions. The goal is to enhance the reliability of test results, improving care and saving time for both patients and clinic staff. Participants will receive either standard instructions or additional AI-based training (LLM-based Education) before their test. Ideal candidates are English-speaking adults diagnosed with or suspected to have glaucoma, who have previously struggled with visual field tests. As an unphased trial, this study provides a unique opportunity to contribute to innovative educational tools that could enhance patient care.

Do I need to stop my current medications to join the trial?

The trial information does not specify whether you need to stop taking your current medications. It seems focused on educational tools for glaucoma testing, so it's unlikely that medication changes are required.

What prior data suggests that this LLM-based educational tool is safe for glaucoma patients?

Research has shown that large language models (LLMs), like the one used in this study, are helpful in healthcare for education and support. They effectively answer clinical questions and often serve as educational tools.

For safety, the LLMs in this study are used solely for educational purposes. They assist patients in understanding the visual field test better, posing no direct risk to physical health. These tools do not diagnose or treat any conditions.

Studies have not identified any safety issues with using LLMs for education. This study is classified as "Not Applicable" for trial phase, indicating it is low-risk. The LLMs aim to enhance understanding of the test, potentially leading to more accurate results. Participants can feel confident that the goal is to simplify and improve the test process without introducing health risks.12345

Why are researchers excited about this trial?

Researchers are excited about this trial because it explores a new way to educate glaucoma patients using large language models (LLMs). Unlike the standard care, where patients rely solely on visual field technicians for information, this method provides additional audiovisual education powered by AI. This approach could enhance patient understanding and engagement, potentially leading to better outcomes. By leveraging advanced technology, researchers hope to find out if this dual method improves patient knowledge and experience during visual field testing.

What evidence suggests that this LLM-based education is effective for improving glaucoma test reliability?

Research has shown that using a large language model (LLM) for learning can help patients understand medical information better. One study found that an LLM like GPT-4 can simplify medical texts, aiding patients in learning important details about their glaucoma care. In this trial, participants in the LLM-based Education + Standard of Care arm will receive audiovisual education powered by an LLM before their visual field test, along with standard care information. This enhanced understanding can lead to improved performance on tests, such as the visual field test for glaucoma. By ensuring patients know what the test involves, LLM-based education aims to reduce mistakes and make test results more reliable. This approach may result in patients spending less time during testing and obtaining more accurate results, potentially leading to better treatment choices.12367

Who Is on the Research Team?

RT

Robert T Chang, MD

Principal Investigator

Stanford University

Are You a Good Fit for This Trial?

This trial is for adults over 18 with diagnosed or suspected glaucoma, who speak English and are scheduled for a specific visual field test. They must have had at least two prior tests and good vision with correction.

Inclusion Criteria

I've had at least 2 eye tests in the last 2 years.
Best corrected visual acuity in both eyes ≥ 20/40
I am 18 or older and have or might have glaucoma.
See 2 more

Exclusion Criteria

Unable to comply with study and questionnaires
Participant has, in the opinion of the investigator, any physical or mental condition that would affect the participation in the study or may interfere with the study procedures, evaluations and outcome assessments

Timeline for a Trial Participant

Screening

Participants are screened for eligibility to participate in the trial

1-2 weeks

Education

Participants receive audiovisual education powered by a large language model (LLM) before their visual field test, in addition to the standard of care information provided by the Humphrey visual field technicians.

Same day
1 visit (in-person)

Testing

Participants undergo the Humphrey visual field test to evaluate the effectiveness of the educational tool on test reliability and duration.

Same day
1 visit (in-person)

Follow-up

Participants are monitored for test reliability and satisfaction immediately after the test.

Same day
1 visit (in-person)

What Are the Treatments Tested in This Trial?

Interventions

  • LLM-based Education

Trial Overview

The study evaluates if an AI-powered educational tool can help patients understand the visual field test better, aiming to improve reliability of the results and reduce clinic burdens.

How Is the Trial Designed?

2

Treatment groups

Experimental Treatment

Active Control

Group I: LLM-based Education + Standard of CareExperimental Treatment1 Intervention
Group II: Standard of CareActive Control1 Intervention

Find a Clinic Near You

Who Is Running the Clinical Trial?

Stanford University

Lead Sponsor

Trials
2,527
Recruited
17,430,000+

Citations

Study Details | NCT07327242 | Effectiveness of a Large ...

The purpose of this study is to evaluate whether a large language model (LLM)-based audiovisual educational tool improves the test time and ...

Tailoring glaucoma education using large language models

This study evaluates the efficacy of GPT-4, a Large Language Model, in simplifying medical literature for enhancing patient comprehension in glaucoma care.

Performance of popular large language models in ...

Research has shown that allowing patients to browse their medical data may reduce the use and improve the effectiveness of glaucoma medication.

LLM-Based Education for Glaucoma · Info for Participants

Participants undergo the Humphrey visual field test to evaluate the effectiveness of the educational tool on test reliability and duration.

Performance of a Small Language Model Versus a Large ...

Objective: This study aimed to compare the performance of an LLM in answering frequently asked patient questions about glaucoma with that of a ...

Enhancing Ophthalmologic Diagnostic Performance Using ...

These results underscore the potential value of LLM-based chatbots as educational and clinical decision-support tools, especially for residents.

Leveraging Large Language Models to Generate Multiple ...

This survey study evaluates whether general-domain large language models can reliably generate high-quality, novel, and readable ...