trial summary · NCT07827924
Designing a Large Language Model Architecture for Shared Decision Making and Informed Intentions
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
Trial record from the TrialBase DB dataset, status RECRUITING, condition Shared Decision Making, sponsored by Harding Center for Risk Literacy. Facts below are exported values from the current release, not inferred or edited prose.
Summary
The brief summary is the registry's published description, capped for length. Field definitions, types, and provenance rules are in the data dictionary.
This study investigates a novel, agentic Large Language Model (LLM) architecture designed to facilitate Shared Decision-Making (SDM) in healthcare. While patients increasingly use standard LLMs for health information, these models often struggle with multi-turn conversations and fail to adapt to varying reading levels, disadvantaging vulnerable groups. By utilizing an agentic state-machine, this project aims to overcome common LLM deficits-such as context loss and uncritical agreement-to ensure clinically accurate, participatory patient conversations. The study evaluates whether this architecture improves informed decision-making compared to standard LLMs, particularly for patients with low health literacy.
Source record: https://clinicaltrials.gov/study/NCT07827924
Facts
| registry id | NCT07827924 |
|---|---|
| primary registry | clinicaltrials-gov |
| recruitment status | RECRUITING |
| phase | not reported |
| study type | INTERVENTIONAL |
| lead condition | Shared Decision Making |
| sponsor | Harding Center for Risk Literacy |
| sponsor class | OTHER |
| enrollment | 330 |
| start date | 2026-10-23 |
| primary completion | 2026-10-30 |
| completion | 2026-10-31 |
| results posted | not reported |
Conditions
- Shared Decision Making
- Health Literacy
- Patient Participation
- Artificial Intelligence
Interventions
- Agentic LLM Chatbot
- Usual Care LLM Chatbot
- IQWiG Standard Brochure
Countries
- Germany
Intervention types: BEHAVIORAL
Work with this record
- Field definitions
Types, scope, and provenance rules for every exported field.
- REST API
Query the same gate-backed records programmatically.
- Evaluation sample
Download a bounded slice before buying.
- $29 API Pass
Seven days of REST and MCP access; credited toward the licence.