AI to Create Accessible & Reliable Patient Education Materials

NCT06997107 | Active Not Recruiting

• 1 other identifier: 24-25-11-038
• Study Type: interventional
• Target: 50
• Locations: 1 country
• Sites: 1

Brief Summary

This study investigates the use of Generative AI (GAI) to support primary care practices in delivering accurate, accessible patient education. With the rise of health misinformation, increasingly complex patient needs, and a strained healthcare workforce, primary care must find new ways to communicate trusted health information effectively. Leveraging the Canadian Primary Care Information Network (CPIN), this study will generate patient education messages on key health topics using both GAI and human content experts. Diverse review panels of patients and providers will assess the messages on quality of information, adaptability, and relevance and usefulness, with special attention to socioeconomic factors that may impact message accessibility. CPIN will recruit a diverse sample of participants to evaluate both GAI- and human-generated messages. Review panels will provide structured feedback via surveys, aiming to identify differences in content quality and effectiveness. The study's goal is to determine whether GAI can produce high-quality health information that meets primary care standards. Results will reveal how GAI tools can support primary care in reducing misinformation and administrative burdens, fostering patient-provider relationships, and improving health equity. Findings will inform best practices for integrating GAI in primary care to ensure accessible, timely patient education across Canada.

Conditions

Primary Care Patients

Keywords

primary care; generative artificial intelligence; health promotion messages; patient education; primary care providers; primary care patients

Outcome Measures

Primary Outcomes (1)

• Clarity and Understandability score

  Message score on three statements related to Clarity and Understandability after the participant has read the message. Three Likert scale questions from 1 - 4 (1: Strongly disagree and 4: Strongly agree), total score between 3 - 12 (low score: poorly rated message, high score: well rated message).

  12 months

Secondary Outcomes (2)

• Overall message score

  12 months

• Message category and subcategory scores

  12 months

Study Arms (2)

Artificial Intelligence

EXPERIMENTAL

Other: Health promotional messages generated by Artificial Intelligence

Human expert

ACTIVE COMPARATOR

Other: Health promotional messages generated by humans

Interventions

Health promotional messages generated by Artificial Intelligence OTHER

Short (850 characters) and long (1 page) messages will be generated by a Generative Artificial Intelligence (ChatGPT 4.0) on different health-related topics

Artificial Intelligence

Health promotional messages generated by humans OTHER

Short (850 characters) and long (1 page) messages will be generated by a primary care and/or public health human expert on different health-related topics

Human expert

Eligibility Criteria

• Age: 18 Years+
• Sex: all
• Healthy Volunteers: Yes
• Age Groups: Adult (18-64), Older Adult (65+)

You may qualify if:

• Content team members: Content team members must have an expertise in primary care, public health, or health communication. The investigators aim to recruit at least two or three members whose mother tongue is French.
• Providers' review panel: The investigators will recruit a diverse group of primary care providers. All providers who provide comprehensive care in Canada and will be eligible to participate. They must be proficient in either written English or French. They must be able to consent to participate in this study.
• Patients' review panel: The investigators will recruit a diverse group of patients. All must be aged 18 years or older and be proficient in either written English or French. They must be able to consent to participate in this study.

You may not qualify if:

• Content team members, primary care providers, or patients who cannot write (content team members) or read (review panels) in either French or English will be excluded. Primary care providers or patients who do not have an email address, a computer or a cellphone to complete the evaluations on REDCap will also be excluded. The investigators will not include minors or patients who cannot provide informed consent themselves, such as those with advanced dementia.

Sponsors & Collaborators

• Hopital Montfort: lead
• Cheo Research Institute: collaborator
• Eastern Ontario Health Unit: collaborator

Study Sites (1)

Institut du Savoir Montfort

Ottawa, Ontario, K1N 0T2, Canada

Location

Related Publications (2)

• Tam TYC, Sivarajkumar S, Kapoor S, Stolyar AV, Polanska K, McCarthy KR, Osterhoudt H, Wu X, Visweswaran S, Fu S, Mathur P, Cacciamani GE, Sun C, Peng Y, Wang Y. A framework for human evaluation of large language models in healthcare derived from literature review. NPJ Digit Med. 2024 Sep 28;7(1):258. doi: 10.1038/s41746-024-01258-7.

  PMID: 39333376 BACKGROUND

• Bedi S, Liu Y, Orr-Ewing L, Dash D, Koyejo S, Callahan A, Fries JA, Wornow M, Swaminathan A, Lehmann LS, Hong HJ, Kashyap M, Chaurasia AR, Shah NR, Singh K, Tazbaz T, Milstein A, Pfeffer MA, Shah NH. Testing and Evaluation of Health Care Applications of Large Language Models: A Systematic Review. JAMA. 2025 Jan 28;333(4):319-328. doi: 10.1001/jama.2024.21700.

  PMID: 39405325 BACKGROUND

Related Links

• Canadian Primary Care Information Network

Study Officials

• Sharon Johnston, MD, LLM

  Institut du Savoir Montfort

  PRINCIPAL INVESTIGATOR

• William Hogg, MD, MSc

  Institut du Savoir Montfort

  PRINCIPAL INVESTIGATOR

Study Design

• Study Type: interventional
• Phase: not applicable
• Allocation: RANDOMIZED
• Masking: DOUBLE
• Who Masked: PARTICIPANT, OUTCOMES ASSESSOR
• Purpose: HEALTH SERVICES RESEARCH
• Intervention Model: CROSSOVER
• Sponsor Type: OTHER
• Responsible Party: SPONSOR

Model Details: Each month, patients and providers will receive a series of health promotion messages generated by AI and humans.

Study Record Dates

• First Submitted: May 21, 2025
• First Posted: May 30, 2025
• Study Start: January 16, 2025
• Primary Completion: April 1, 2026
• Study Completion (Estimated): September 1, 2026
• Last Updated: June 4, 2025

Record last verified: 2025-05

Data Sharing

• IPD Sharing: Will not share

Locations

CA (1)