[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"health-studies-list:{\"overallStatus\":[\"RECRUITING\",\"AVAILABLE\",\"NOT_YET_RECRUITING\"],\"leadSponsorName\":\"Harding Center for Risk Literacy\",\"orderBy\":\"LastUpdateSubmitDate:desc\",\"size\":25,\"offset\":0}":3,"health-study-condition:":52},{"pageToken":4,"total":5,"offset":6,"count":5,"results":7},null,1,0,[8],{"id":9,"slug":10,"hasResults":11,"nctId":12,"briefTitle":13,"officialTitle":14,"acronym":15,"eligibilityCriteria":16,"healthyVolunteers":17,"sex":18,"minAge":19,"maxAge":20,"enrollmentInfo":21,"targetDuration":4,"studyType":24,"phases":25,"briefSummary":27,"conditions":28,"keywords":33,"overallStatus":40,"whyStopped":4,"lastUpdateSubmitDate":41,"lastUpdatePostDateStruct":42,"startDateStruct":45,"completionDateStruct":47,"leadSponsor":49,"locationsCount":4},"100656587","designing-a-large-language-model-architecture-for-shared-decision-making-and-informed-intentions-100656587",false,"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","DEONCAI3-1","Inclusion Criteria:\n\n* Biological sex: Female.\n* Age: 40 to 70 years old.\n* Country of residence: United States (US) or United Kingdom (UK).\n* Language: Native English speaker (English as first language).\n* Registered and verified user on the academic research platform Prolific.\n* Able to read, understand, and provide informed consent digitally.\n\nExclusion Criteria:\n\n* Individuals who do not meet the automated pre-screening criteria on the Prolific platform.\n* Inability to use or access a computer, smartphone, or internet browser required to complete the digital study.\n\nNote: Quotas will be enforced during recruitment to ensure a 50\u002F50 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.\n\n\\-",true,"FEMALE","40 Years","70 Years",{"count":22,"type":23},330,"ESTIMATED","INTERVENTIONAL",[26],"NA","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.",[29,30,31,32],"Shared Decision Making","Health Literacy","Patient Participation","Artificial Intelligence",[34,35,36,37,31,32,38,39],"Large Language Models (LLM)","Generative AI","Shared Decision Making (SDM)","Informed Decision Making","Conversational Agents","Agentic AI","NOT_YET_RECRUITING","2026-09-18",{"date":43,"type":44},"2026-09-23","ACTUAL",{"date":46,"type":23},"2026-09-15",{"date":48,"type":23},"2026-09-30",{"name":50,"class":51},"Harding Center for Risk Literacy","OTHER",""]