A double-blind, crossover, non-inferiority randomized controlled trial where primary care providers and patients compare human- and AI-generated digital health messages: the AI-CARE study protocol
Bibliographic record
Abstract
ABSTRACT Introduction Primary care is facing multiple crises, including an increase in health misinformation. Digital health messaging by primary care providers has been shown to reach a diverse patient population. With the uptake of Generative Artificial Intelligence (GenAI) usage in healthcare, there is an important opportunity to rapidly create messages that are tailored to different populations and conditions. However, thoroughly assessing AI-generated content is essential, as GenAI raises concerns regarding its accuracy, understandability, actionability, and bias perpetuation. We aim to investigate whether digital health messages created by GenAI are evaluated as noninferior compared to those created by human experts. Methods and analysis The AI-CARE (AI to Create Accessible and Reliable patient Education materials) study is a double-blind, crossover, non-inferiority randomized controlled trial. Data collection began on May 30, 2025, and is expected to be completed at the end of April 2026. Over 12 months, 192 messages on 48 topics will be written: half by primary care and public health experts and half by a GenAI tool (OpenAI’s ChatGPT). Review Panels composed of 24 primary care providers and 24 patients will evaluate these messages using an Evaluation Grid developed to assess the messages’ quality of information, adaptation to the target audience, relevance and usefulness, and readiness to be shared with patients. Evaluations will be completed via online REDCap surveys and the order in which the 192 messages appear will be randomized and will vary between individuals. Participants and analysts will be blinded to the generation source. The primary outcome will be the Clarity and Understandability score. Ethics and dissemination The Research Ethics Boards of the Hôpital Montfort (24-25-11-038) and the University of Ottawa (S-12-24-11153) formally approved this study in December 2024. Reported data will be grouped and anonymized for dissemination in peer-reviewed scientific journals and conferences. Trial registration number NCT06997107 ARTICLE SUMMARY Strengths and limitations of this study The AI-CARE study allows for within-participant comparison between human- and AI-generated digital health messages, minimizing variability due to individual differences. The Review Panels are diverse and composed of primary care providers and patients currently practicing in or using the healthcare system in five Canadian provinces. The developed Evaluation Grid allows for the assessment of multiple aspects related to digital health messages: quality of information, adaptability to the target audience, relevance and usefulness, and readiness to be shared with patients. One limitation is that messages generated by AI are created using only one LLM (Open AI’s ChatGPT). Due to the nature and location of recruitment, we may introduce selection bias (participants already engaged in research and interested in digital communication and AI) and the racial diversity of our study population may be limited.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.022 | 0.025 |
| Meta-epidemiology (narrow) | 0.006 | 0.002 |
| Meta-epidemiology (broad) | 0.009 | 0.003 |
| Bibliometrics | 0.002 | 0.002 |
| Science and technology studies | 0.002 | 0.004 |
| Scholarly communication | 0.003 | 0.003 |
| Open science | 0.003 | 0.001 |
| Research integrity | 0.008 | 0.006 |
| Insufficient payload (model declined to judge) | 0.039 | 0.007 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".