Agentic LLM for Shared Decision Making in Health Care
Official title: DEONCAi 3-1: Can Large Language Models Support Shared Decision-Making and Informed Intentions in the Field: An Online Experiment Comparing Them to a Standard Model and to an Evidence-Based Decision Aid
Run by Harding Center for Risk Literacy · NCT07827924 · Data updated 2026-11-12
This project tests an agentic large language model to help patients participate in health decisions, especially for those with lower health literacy.
Quick facts
| Study type | Interventional |
|---|---|
| Ages | 40 Years to 70 Years |
| Sex | Women only |
| Enrollment | 330 (estimated) |
| Sponsor | Harding Center for Risk Literacy Academic / other |
| Locations | 1 site (Neuruppin) |
| Status | Recruiting |
| Started | October 23, 2026 |
| Main results expected | October 30, 2026 |
| Study ends | October 31, 2026 |
| Registry record updated | October 30, 2026 |
| Trial ID | NCT07827924 on ClinicalTrials.gov |
Is this trial a fit for you?
✓Likely a good fit
Adult women aged 40–70 who are native English speakers, reside in the US or UK, and are Prolific registered with the ability to read and consent digitally.
✕Probably not a fit
Participants with limited access to the internet or those who do not engage with the digital platform may not benefit.
A plain-English reading of the study's rules. Only the study team can confirm whether you qualify.
What this trial studies
Researchers will compare an agentic LLM chatbot designed to support SDM with a standard LLM chatbot and a traditional information brochure. The study focuses on adults aged 40–70 in the US or UK who are native English speakers and Prolific users, evaluating whether the agentic system improves understanding and participation in decision making. It uses a state-machine approach to maintain context, reduce over-enthusiastic responses, and better tailor information to reading level. Outcomes will assess accuracy, user comprehension, and engagement in multi-turn conversations. Overall, the trial explores whether this architecture can promote more informed decisions in a digital health setting.
Why it matters
Potential benefit: If successful, patients may experience clearer, more accurate guidance that supports informed choices and greater participation in medical decisions.
How similar studies have gone: Prior work shows potential for LLMs to support patient-facing information, but multi-turn SDM and health literacy customization remain areas of active investigation.
Who can join: the full rules
Show full inclusion / exclusion criteria
Inclusion Criteria: * Biological sex: Female. * Age: 40 to 70 years old. * Country of residence: United States (US) or United Kingdom (UK). * Language: Native English speaker (English as first language). * Registered and verified user on the academic research platform Prolific. * Able to read, understand, and provide informed consent digitally. Exclusion Criteria: * Individuals who do not meet the automated pre-screening criteria on the Prolific platform. * Inability to use or access a computer, smartphone, or internet browser required to complete the digital study. Note: Quotas will be enforced during recruitment to ensure a 50/50 stratified split between participants with and without university entrance qualifications to guarantee variance in educational backgrounds. Once a quota is filled, further participants matching that educational profile will be excluded. * Addendum: Women with BC symptoms
Where it's running
-
Brandenburg Medical School Theodor Fontane
Neuruppin, Germany Recruiting
Study contacts
- Principal investigator: Felix G Rebitschek, PhD — Harding Center for Risk Literacy
- Study coordinator: Felix G Rebitschek, PhD
- Email: felix.rebitschek@fgw-brandenburg.de
- Phone: +493319772162
Similar studies
Other studies for the same condition or treatment. Recruiting studies are listed first.
-
A digital tool to help decide about an ICD
We’re testing a patient-friendly online aid to help people with advanced heart failure decide whether an implantable cardioverter-defibrillator (ICD) is right for them.
-
My Symptoms Young: a web-based program for teens and young adults with persistent physical symptoms
A web-based self-help program is being tested to see if it helps 15- to 25-year-olds with persistent physical symptoms in primary care, and whether health literacy affects how well they use it.
-
AI-simplified discharge summaries to improve patient understanding
This randomized pilot tests whether ContextCare can help adults understand their discharge information better than standard discharge words and printouts.
-
Digital Health Education to Improve Heart Health Across Different Socioeconomic Groups (e-DUCASS Advance)
This study tests a 24-month digital health education program to see if it can improve cardiovascular health among people in Córdoba, Spain from varied socioeconomic backgrounds, by delivering weekly online content to families.
-
AI care summaries to help caregivers understand their child’s hospitalization
This trial tests whether an AI-generated plain-language summary of inpatient notes helps caregivers of hospitalized children understand their child’s care better.
-
Senior Center Medication Safety and Empowerment Curriculum
A program for adults 55+ and their care partners to learn how to safely manage medications and talk with doctors about safer options.
How to take part
- Review the eligibility criteria above with your treating physician.
- Check the official listing on ClinicalTrials.gov for the latest contact details and recruitment status.
- Contact the study coordinator or principal investigator to ask for pre-screening. Pre-screening is free and never obligates you to enroll.