The AI-CARE (for AI to Create Accessible & Reliable patient Education materials) 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.
Recruitment of primary care providers and patients for review panels
Recruitment of primary care providers and patients (francophones and anglophones) for our review panels is currently completed! Members of the review panel will be asked to review:
- 4 messages per topic: 2 short (less than 900 characters) and 2 long (up to one page)
- 4 topics per month
We anticipate that reviewing each topic will take approximately 1h or less. This commitment will last for about a year, during which members of the review panel will be compensated for their time:
- Providers: 100$ per hour (or per topic), for a maximum of $400 per month
- Patients: 25$ per hour (or per topic), for a maximum of $100 per month
Project Updates
October 2025 – January 2026
- Number of topics evaluated: 12
- Topics covered: Diabetes prevention, Postpartum depression, Upper respiratory tract infections (adult and pediatric), Breast cancer awareness, Dementia prevention, Falls prevention, COVID-19, Carbon monoxide poisoning, Urinary tract infections, Teen mental health, active outdoor play
- Review panel response rate: Consistently high, ranging from ~87% to nearly 98%
- Other highlights
- Distribution of December messages in early January 2026
- Preparation of conference abstract (AIME 2026)
- Plans for a “AI in Primary Care” newsletter preparation
- Transition toward analysis and dissemination
August – September 2025: Evaluation Consolidation and Process Optimization
- Number of topics evaluated: 8
- Topics covered: Heat and cognition, Polypharmacy and medication use, Heat exhaustion, Vaccines for children, Screen time for children (0–5 years), Pediatric upper respiratory tract infections, Social isolation and heatwaves, Vaccines for older adults
- Review panel response rate: 95.2% (june), 93.5% (july), and 57.8% (august; mid-cycle evaluation)
- Other highlights:
- Ethical amendment approved to expand patient recruitment pathways
- New participants were enrolled and additional providers were contacted
- Standardized content guidelines were shared with the content creation team and AI tools
- Continuous data quality control was implemented using scripted checks
May – July 2025: Study Launch and initial evaluations
- Number of topics evaluated: 9
- Topics covered: Alcohol consumption guidelines, Lice, Sleep, Stress and current events, High blood pressure, Sun safety, Cow’s milk protein allergy, Measles, Social isolation
- Review panel response rate: 90–95%
- Other highlights: first AI vs human message comparisons were completed