Shared Decision MakingDEONCAI3-1NCT07827924
Designing a Large Language Model Architecture for Shared Decision Making and Informed Intentions
A study testing Agentic LLM Chatbot and IQWiG Standard Brochure in people with Shared Decision Making and Health Literacy, run by Harding Center for Risk Literacy.
Trial 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… Read more about this study
- Who is it for?
- Ages 40 to 70 years, women onlyHealthy volunteers can take part
- Conditions the study is for
- Shared Decision Making, Health Literacy, Patient Participation
- What is being tested?
- Agentic LLM Chatbot and IQWiG Standard Brochure
- Type of treatment
- Lifestyle or therapy programme
- Could I receive a placebo?
- No, everyone receives an active treatment
- How many people
- 330 participants
- Where
- No sites listed yet
- Study dates
- 15 Sep 2026to 30 Sep 2026
- Phase
- Interventional
- Are there results?
- Not yet: the study is under way
Key requirements
Who can take part, as listed by the sponsor. Only the study team can confirm whether you are eligible, so take this list to your doctor.
- Ages 40 to 70 years
- Women only
- Healthy volunteers accepted
- Adult, Older adult
Who may be able to join
- 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.
Who cannot join
- 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.
- -
Trial locations and contacts
No sites are listed yet. Contact the study team or a site near you to ask about taking part.
Martin Lipsdorf contact
About this study
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
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.
Read the detailed description
Background \& Current State of Research Shared Decision-Making is widely recognized as the gold standard of patient-centered care. However, its successful implementation in clinical practice is frequently hindered by systemic time and budget constraints. Consequently, patients are increasingly turning to Large Language Models to independently access health information and navigate their medical options.
The Problem: Limitations of Standard LLMs Recent studies indicate that using standard LLMs can digitally reproduce existing health inequalities and participation gaps. These models struggle to adapt to different reading levels without a significant loss in quality. While highly developed prompting techniques can enhance clinical accuracy, the results remain highly variable depending on the specific model and technique used.
A central deficit becomes apparent in multi-turn interactions, which are essential for a natural SDM workflow. In these prolonged conversations, standard LLMs tend to exhibit "context rot," leading to a sharp decline in accuracy as the dialogue progresses. This issue is further exacerbated by model sycophancy (an uncritical tendency to agree with the user) and completion eagerness (a tendency to prematurely conclude the conversation). Because current LLMs often fail to meet evidence-based reporting standards and lack systematic validation of user comprehension, the burden of fact-checking remains entirely on the user. This dynamic significantly disadvantages vulnerable groups, particularly those with lower health literacy.
Project Objectives and Research Questions
This project proposes a technical and clinical solution to these challenges through the following core research questions:
Technical-Conceptual Framework: How can we develop a transparent and replicable workflow that formalizes the SDM process through an agentic state-machine, thereby eliminating structural deficits of LLMs (e.g., context rot and sycophancy) in prolonged interactions?
Clinical Evaluation (Primary Objective): Does this newly developed agentic LLM architecture achieve higher scores in participatory conversation management and demonstrate a significantly greater objective increase in informed decision-making among users during multi-turn interactions, compared to a standard baseline LLM?
Health Equity (Secondary Objective): To what extent can this agentic LLM architecture guarantee effective participatory conversation management for vulnerable patient groups with low health literacy?
- Being tested
- Agentic LLM Chatbot, Usual Care LLM Chatbot, IQWiG Standard Brochure
- Keywords
- Large Language Models (LLM), Generative AI, Shared Decision Making (SDM), Informed Decision Making, Patient Participation, Artificial Intelligence, Conversational Agents, Agentic AI
- Medical subject headings
- Patient Participation
What participants receive
What participants receive. In a randomised study each person is assigned to one group by chance.
Agentic LLM ChatbotBehavioural
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.
Usual Care LLM ChatbotBehavioural
An unmodified, standard generative Large Language Model chatbot acting as a baseline control, used by participants to discuss mammography screening.
IQWiG Standard BrochureBehavioural
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.
| Study group | Role | What they receive |
|---|---|---|
| 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. Receives: 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. Receives: 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. Receives: Behavioral: IQWiG Standard Brochure |
What is being measured
The primary outcome is the main question the study is designed to answer.
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.
Measured: Day 1
Secondary outcomes (3)
Multidimensional Informed Decision-Making
Based on Marteau's conceptualization of informed decision-making. An informed decision is achieved when a participant has sufficient objective knowledge about mammography screening and their behavioral intention (to screen or not to screen) is congruent with their personal attitudes toward the screening. This is calculated as a composite measure integrating an objective knowledge test, an attitude assessment, and a screening intention question. Higher objective knowledge scores and higher attitude-intention congruence indicate a better-informed decision.
Measured: Day 1
Subjective Decisional Conflict
Assessed using a standardized Decisional Conflict Scale. This measures the participant's perceived uncertainty in choosing a screening option, their clarity of personal values, and their feeling of being supported in decision-making. Scores are transformed to a 0 to 100 scale. Lower scores indicate less decisional conflict and greater decision certainty.
Measured: Day 1
Medical Accuracy and Safety of Generated Information
A quantitative and qualitative assessment of the medical accuracy of the AI-generated texts. This is operationalized by counting the frequency (number of occurrences) and categorizing the severity of deviations from established medical evidence (i.e., misinformation or "hallucinations"). These deviations are identified via an integrated ethics module and/or expert review. Lower frequencies and lower severity ratings indicate higher medical accuracy.
Measured: Day 1
Timeline
From the start of the study to its completion; the mark is today. Estimated dates are the sponsor’s plan.
- First posted18 Sep 2026
- Study start15 Sep 2026 (estimated)
- Primary completion30 Sep 2026 (estimated)
- Study completion30 Sep 2026 (estimated)
Resources
- Official record on ClinicalTrials.govThe registry entry this page is built from, with its full change history.
- Publications (5)Papers the sponsor has linked to this study.
- Other trials for Shared Decision MakingStudies of the same condition, open and under way.
- What the trial phases meanHow a treatment moves from first tests in people to approval.
More details
For doctors and researchers: how the study is designed, who runs it, and its registry IDs.
Study design
- Study type
- Interventional
- Phase
- Phase N/A
- Primary purpose
- Health services research
- Allocation
- Randomised
- Intervention model
- Parallel groups
- Masking
- None (open label)
- Enrolment
- 330 participants (estimated)
Sponsor and investigators
- Lead sponsor
- Harding Center for Risk Literacy
- Sponsor type
- University, hospital or other
- Responsible party
- Principal investigator, Felix G. Rebitschek, Harding Center for Risk Literacy
- Investigators
- Felix G Rebitschek, PhD, Principal investigator, Harding Center for Risk Literacy
IDs, dates and publications
- ClinicalTrials.gov ID
- NCT07827924
- Sponsor's protocol ID
- DEONCAI3-1
- Acronym
- DEONCAI3-1
- Status last verified
- Sep 2026
- First submitted
- 9 Sep 2026
- Last updated
- 23 Sep 2026
- Results posted
- No
- Data monitoring committee
- No
- FDA-regulated drug
- No
- FDA-regulated device
- No
- Individual data sharing
- Yes: De-identified individual participant data (IPD) underlying the results reported in the published article, including survey data (SDM-Q-9, decisional conflict, knowledge scores) and anonymized dialog transcripts, will be shared.
Publications
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.
PubMed 40490558Mendel 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.
PubMed 39946180Laban, P., Hayashi, H., Zhou, Y., & Neville, J. (2025). Llms get lost in multi-turn conversation. arXiv preprint arXiv:2505.06120.
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.
PubMed 42097602Keij 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.
PubMed 38563311
Study at a glance
From the registry record, last updated by the sponsor on 23 Sep 2026. Recruitment status is as the sponsor reported it: confirm with the study team.
- 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
- ClinicalTrials.gov ID
- NCT07827924
- Acronym / sponsor ID
- DEONCAI3-1 / DEONCAI3-1
- Keywords
- Large Language Models (LLM), Generative AI, Shared Decision Making (SDM), Informed Decision Making, Patient Participation, Artificial Intelligence, Conversational Agents, Agentic AI
- Study type
- Interventional
- Recruitment status
- Not yet recruiting
- Enrolment
- 330 participants (estimated)
- Lead sponsor
- Harding Center for Risk LiteracyUniversity, hospital or other
- Study start
- 15 Sep 2026 (estimated)
- Primary completion
- 30 Sep 2026 (estimated)
- Study completion
- 30 Sep 2026 (estimated)
- First posted
- 18 Sep 2026 (actual)
- Results
- Not posted in the source record
Clinical summary
The research question as the sponsor registered it. This describes what the study plans to test, not what it found.
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.
Detailed description
Background \& Current State of Research Shared Decision-Making is widely recognized as the gold standard of patient-centered care. However, its successful implementation in clinical practice is frequently hindered by systemic time and budget constraints. Consequently, patients are increasingly turning to Large Language Models to independently access health information and navigate their medical options.
The Problem: Limitations of Standard LLMs Recent studies indicate that using standard LLMs can digitally reproduce existing health inequalities and participation gaps. These models struggle to adapt to different reading levels without a significant loss in quality. While highly developed prompting techniques can enhance clinical accuracy, the results remain highly variable depending on the specific model and technique used.
A central deficit becomes apparent in multi-turn interactions, which are essential for a natural SDM workflow. In these prolonged conversations, standard LLMs tend to exhibit "context rot," leading to a sharp decline in accuracy as the dialogue progresses. This issue is further exacerbated by model sycophancy (an uncritical tendency to agree with the user) and completion eagerness (a tendency to prematurely conclude the conversation). Because current LLMs often fail to meet evidence-based reporting standards and lack systematic validation of user comprehension, the burden of fact-checking remains entirely on the user. This dynamic significantly disadvantages vulnerable groups, particularly those with lower health literacy.
Project Objectives and Research Questions
This project proposes a technical and clinical solution to these challenges through the following core research questions:
Technical-Conceptual Framework: How can we develop a transparent and replicable workflow that formalizes the SDM process through an agentic state-machine, thereby eliminating structural deficits of LLMs (e.g., context rot and sycophancy) in prolonged interactions?
Clinical Evaluation (Primary Objective): Does this newly developed agentic LLM architecture achieve higher scores in participatory conversation management and demonstrate a significantly greater objective increase in informed decision-making among users during multi-turn interactions, compared to a standard baseline LLM?
Health Equity (Secondary Objective): To what extent can this agentic LLM architecture guarantee effective participatory conversation management for vulnerable patient groups with low health literacy?
Study design
- Primary purpose
- Health services research
- Allocation
- Randomised
- Intervention model
- Parallel groups
- Masking
- None (open label)
- Number of arms
- 3
| Arm | Type | Receives |
|---|---|---|
| Shared Decision Making Chatbot | Experimental | Behavioral: Agentic LLM ChatbotParticipants 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. |
| Standard Chatbot | Active comparator | Behavioral: Usual Care LLM ChatbotParticipants 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. |
| Information brochure | Active comparator | Behavioral: IQWiG Standard BrochureParticipants 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. |
Who may qualify
- Ages
- 40 to 70 years
- Sex
- Female only
- Healthy volunteers
- Accepted
- Age groups
- Adult, Older adult
Key inclusion criteria (6 listed)
- 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.
Key exclusion criteria (4 listed)
- 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.
- -
Eligibility is decided by the study team after screening; this overview does not establish that a patient qualifies. Full inclusion and exclusion criteria.
Interventions
| Intervention | Type | Arms |
|---|---|---|
| Agentic LLM ChatbotAn 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. | Behavioural | Shared Decision Making Chatbot |
| Usual Care LLM ChatbotAn unmodified, standard generative Large Language Model chatbot acting as a baseline control, used by participants to discuss mammography screening. | Behavioural | Standard Chatbot |
| IQWiG Standard BrochureThe 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. | Behavioural | Information brochure |
Primary outcome
Patient-Reported Quality of Shared Decision-Making
Time frame: Day 1
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.
3 secondary outcomes
Multidimensional Informed Decision-Making
Time frame: Day 1
Subjective Decisional Conflict
Time frame: Day 1
Medical Accuracy and Safety of Generated Information
Time frame: Day 1
Results and safety
This study is still under way. Results are not available in the source record yet.
Research links
- Official record on ClinicalTrials.govLast updated by the sponsor 23 Sep 2026.
- Background: PubMed 40490558Rebitschek 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.
- Background: PubMed 39946180Mendel 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.
- BackgroundLaban, P., Hayashi, H., Zhou, Y., & Neville, J. (2025). Llms get lost in multi-turn conversation. arXiv preprint arXiv:2505.06120.
- Background: PubMed 42097602Krenn 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.
- Background: PubMed 38563311Keij 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.
- Individual participant dataSharing planned: Yes. De-identified individual participant data (IPD) underlying the results reported in the published article, including survey data (SDM-Q-9, decisional conflict, knowledge scores) and anonymized dialog transcripts, will be shared.
Related trials for Shared Decision Making
Active, not recruiting
Developing and Testing an Online Pathway From Screening to Treatment for Depression in Oncology: iPath*D (Aim 2)
Cancer, Depression
Not yet recruiting
Empowering Pain Psychology Access and Collaboration (EPPAC) to Improve Treatment Engagement Among Medicaid-insured Adults With Chronic Low Back Pain
Chronic Low Back Pain (CLBP)
Recruiting
BREATHE: An Efficacy-implementation Trial Among Black Adults With Uncontrolled Asthma
Asthma
Active, not recruiting
Engaging Adolescents in Decisions About Return of Genomic Research Results
Genetic Screening, Adolescent
RecruitingObservational study
A Prospective Registry of Patients With Endoscopically Resected Malignant Colorectal Polyps (pT1 Colorectal Cancer)
Malignant Colorectal Polyp, Colorectal Cancer
Referral and contact
AzTrials does not enrol participants or take referrals. Contact the study team or a site listed below; they decide who can take part.
Martin Lipsdorf contact
Felix G Rebitschek, PhD principal investigator
Harding Center for Risk Literacy
Questions about this trial
What is this clinical trial studying?
A study testing Agentic LLM Chatbot and IQWiG Standard Brochure in people with Shared Decision Making and Health Literacy, run by Harding Center for Risk Literacy.
The full registered description is in the About this study section and the official record.
Who may be eligible to take part?
The sponsor lists 6 inclusion and 4 exclusion criteria. Eligibility is decided by the study team after screening, so read the full criteria and contact a listed site.
Is this clinical trial currently recruiting?
The record says: opening soon, as of the sponsor's last update on 23 Sep 2026. Status can change between updates, so confirm with the study contact before making plans.
What are the possible benefits and risks?
They depend on the study and the treatment, and no study can promise a benefit. The study team explains the known risks during informed consent, before anyone joins; the record itself does not list them.
Are results available for this study?
This study is still under way. Results are not available in the source record yet.
How can a doctor refer a patient or contact the research team?
Contact Felix G Rebitschek, PhD (+493319772162, felix.rebitschek@fgw-brandenburg.de), or a site near the patient. AzTrials does not enrol participants or take referrals.
What does the primary outcome measure?
Patient-Reported Quality of Shared Decision-Making (time frame: Day 1). It is what the study was designed to measure, not a finding.
Where can I read the original study information?
On the ClinicalTrials.gov record for NCT07827924, which also lists 5 linked publications.
Does a listing mean the treatment is approved or proven to work?
No. A listing means the study is registered. It does not show that the treatment is safe, works, or is approved by a regulator.
How often is this information updated?
AzTrials copies changed records from ClinicalTrials.gov every night and reloads the whole registry every week. The sponsor last updated this record on 23 Sep 2026.