Designing a Large Language Model Architecture for Shared Decision Making and Informed Intentions

NCT07827924 | Not Yet Recruiting

• 1 other identifier: DEONCAI3-1
• Study Type: interventional
• Target: 330
• Locations: 0 countries
• Sites: N/A

Brief Summary

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.

Conditions

Shared Decision Making; Health Literacy; Patient Participation; Artificial Intelligence

Keywords

Large Language Models (LLM); Generative AI; Shared Decision Making (SDM); Informed Decision Making; Patient Participation; Artificial Intelligence; Conversational Agents; Agentic AI

Outcome Measures

Primary Outcomes (1)

• Patient-Reported Quality of Shared Decision-Making

  Assessed using the 9-item Shared Decision Making Questionnaire (SDM-Q-9). This validated instrument measures the patient's perceived involvement in the medical decision-making process. The questionnaire consists of 9 items, each rated on a 6-point scale ranging from 0 ("completely disagree") to 5 ("completely agree"). The raw scores are summed and multiplied by 20/9 to yield a total score ranging from 0 to 100. Higher scores indicate a higher perceived quality and greater patient involvement in shared decision-making.

  Day 1

Secondary Outcomes (3)

• Multidimensional Informed Decision-Making

  Day 1

• Subjective Decisional Conflict

  Day 1

• Medical Accuracy and Safety of Generated Information

  Day 1

Study Arms (3)

Shared Decision Making Chatbot

EXPERIMENTAL

Participants will engage in a multi-turn, AI-assisted consultation about mammography screening. They will interact with a newly developed agentic Large Language Model architecture that uses an integrated state-machine designed to actively guide the Shared Decision-Making process, adapt to the user's reading level, and prevent context loss.

Behavioral: Agentic LLM Chatbot

Standard Chatbot

ACTIVE COMPARATOR

Participants will engage in a conversation about mammography screening using a standard, usual care Large Language Model (Mistral Large). This model represents the current consumer standard for AI health queries and lacks the specialized agentic state-machine and SDM workflow guidance.

Behavioral: Usual Care LLM Chatbot

Information brochure

ACTIVE COMPARATOR

Participants will receive and read the standard informational patient brochure on mammography screening published by the German Institute for Quality and Efficiency in Health Care (IQWiG). This represents the current standard of care for patient information.

Behavioral: IQWiG Standard Brochure

Interventions

Agentic LLM Chatbot BEHAVIORAL

An interactive AI chatbot built with an agentic state-machine architecture designed to systematically guide users through the Shared Decision-Making process regarding mammography screening, with built-in ethical guardrails to prevent hallucination and sycophancy.

Shared Decision Making Chatbot

Usual Care LLM Chatbot BEHAVIORAL

An unmodified, standard generative Large Language Model chatbot acting as a baseline control, used by participants to discuss mammography screening.

Standard Chatbot

IQWiG Standard Brochure BEHAVIORAL

The standard digital informational brochure on mammography screening provided by the german Institute for Quality and Efficiency in Health Care (IQWiG), used as a usual care baseline for patient education.

Information brochure

Eligibility Criteria

• Age: 40 Years - 70 Years
• Sex: female
• Healthy Volunteers: Yes
• Age Groups: Adult (18-64), Older Adult (65+)

You may qualify if:

• 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.

You may not qualify if:

• 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.

Sponsors & Collaborators

• Harding Center for Risk Literacy: lead

Related Publications (5)

• Rebitschek FG, Carella A, Kohlrausch-Pazin S, Zitzmann M, Steckelberg A, Wilhelm C. Evaluating evidence-based health information from generative AI using a cross-sectional study with laypeople seeking screening information. NPJ Digit Med. 2025 Jun 9;8(1):343. doi: 10.1038/s41746-025-01752-6.

  PMID: 40490558 BACKGROUND

• Mendel T, Singh N, Mann DM, Wiesenfeld B, Nov O. Laypeople's Use of and Attitudes Toward Large Language Models and Search Engines for Health Queries: Survey Study. J Med Internet Res. 2025 Feb 13;27:e64290. doi: 10.2196/64290.

  PMID: 39946180 BACKGROUND

• Laban, P., Hayashi, H., Zhou, Y., & Neville, J. (2025). Llms get lost in multi-turn conversation. arXiv preprint arXiv:2505.06120.

  BACKGROUND

• Krenn C, Loder C, Berger N, Jeitler K, Semlitsch T, Siebenhofer A, Wilfling D. Automated Approaches of Text Simplification of Patient Education Materials: Scoping Review. J Med Internet Res. 2026 May 7;28:e88365. doi: 10.2196/88365.

  PMID: 42097602 BACKGROUND

• Keij SM, Branda ME, Montori VM, Brito JP, Kunneman M, Pieterse AH. Patient Characteristics and the Extent to Which Clinicians Involve Patients in Decision Making: Secondary Analyses of Pooled Data. Med Decis Making. 2024 Apr;44(3):346-356. doi: 10.1177/0272989X241231721. Epub 2024 Mar 4.

  PMID: 38563311 BACKGROUND

MeSH Terms

Conditions

Patient Participation

Condition Hierarchy (Ancestors)

Patient Acceptance of Health Care; Treatment Adherence and Compliance; Health Behavior; Behavior

Study Officials

• Felix G Rebitschek, PhD

  Harding Center for Risk Literacy

  PRINCIPAL INVESTIGATOR

Central Study Contacts

Felix G Rebitschek, PhD

CONTACT

+493319772162; felix.rebitschek@fgw-brandenburg.de

Martin Lipsdorf

CONTACT

martin.lipsdorf@mhb-fontane.de

Study Design

• Study Type: interventional
• Phase: not applicable
• Allocation: RANDOMIZED
• Masking: NONE
• Purpose: HEALTH SERVICES RESEARCH
• Intervention Model: PARALLEL
• Sponsor Type: OTHER
• Responsible Party: PRINCIPAL INVESTIGATOR
• PI Title: Head of Research and CEO

Study Record Dates

• First Submitted: September 9, 2026
• First Posted: September 18, 2026
• Study Start: September 15, 2026
• Primary Completion: September 30, 2026
• Study Completion: September 30, 2026
• Last Updated: September 23, 2026

Record last verified: 2026-09

Data Sharing

• IPD Sharing: Will share
• Time Frame: Data will become available immediately following publication of the primary results and will be accessible indefinitely.
• Access Criteria: Data will be made publicly available as supplement material on the publishers website to any researcher or individual for non-commercial research purposes.