Automated Approaches of Text Simplification of Patient Education Materials: Scoping Review.
Cornelia Krenn, Christine Loder, Natalie Berger...
https://pubmed.ncbi.nlm.nih.gov/42097602/Actively Recruiting
Led by Harding Center for Risk Literacy · Updated on 2026-10-30
330
Participants Needed
1
Research Sites
N/A
Total Duration
Researchers are evaluating a novel Large Language Model LLM architecture designed to improve Shared Decision-Making SDM in healthcare. This study focuses on overcoming common issues in standard LLMs, such as difficulty maintaining context in multi-turn conversations and adapting to different reading levels, which can disadvantage vulnerable groups with low health literacy. The primary goal is to compare this new agentic LLM with standard LLMs and traditional informational brochures to see if it better supports informed decision-making. Participants will be randomly assigned to one of three groups interacting with the new agentic LLM chatbot that actively guides the SDM process and adapts to users reading levels using a standard, usual care LLM chatbot that lacks these specialized features or receiving and reading a standard patient brochure on mammography screening. These conversations and materials focus on mammography screening, and the study is conducted online. During the study, participants will engage in these interactions and complete questionnaires to assess the quality of shared decision-making, informed decision-making, decisional conflict, and the medical accuracy and safety of information provided. The research team monitors patient-reported outcomes immediately after the intervention. The total participation involves a single session, with data collected on the same day to evaluate the effectiveness of the different approaches.
CONDITIONS
Designing a Large Language Model Architecture for Shared Decision Making and Informed Intentions
F
Felix G Rebitschek, PhD
M
Martin Lipsdorf
Explore thousands of other clinical trials that might be a better match.
Sign up to get personalized trial recommendations delivered to your inbox.
Already have an account? Log in here
Harding Center for Risk Literacy
Lead Sponsor
You may qualify if you...
You will not qualify if you...
Duration - 2 to 4 weeks
Participants are screened for eligibility to participate in the trial.
1 online visit
Duration - Single session
Participants engage in an online AI-assisted consultation about mammography screening, using either the new agentic LLM chatbot, a standard LLM chatbot, or read a standard patient brochure.
1 online visit
Duration - Same day
Participants complete questionnaires to evaluate decision-making quality, understanding, and information accuracy immediately after the intervention.
1 online visit
Study Type
INTERVENTIONAL
Masking
NONE
Allocation
RANDOMIZED
Model
PARALLEL
Primary Purpose
HEALTH_SERVICES_RESEARCH
Number of Arms
3
Have more questions? Get in touch with our team for quick support
Cornelia Krenn, Christine Loder, Natalie Berger...
https://pubmed.ncbi.nlm.nih.gov/42097602/Felix G Rebitschek, Alessandra Carella, Silja Kohlrausch-Pazin...
https://pubmed.ncbi.nlm.nih.gov/40490558/Tamir Mendel, Nina Singh, Devin M Mann...
https://pubmed.ncbi.nlm.nih.gov/39946180/Sascha M Keij, Megan E Branda, Victor M Montori...
https://pubmed.ncbi.nlm.nih.gov/38563311/Harding Center for Risk Literacy
Lead Sponsor