Domain-Specific Large Language Model Assistance for Emergency Neurological Diagnosis and Treatment（DEMAND）

Domain-Specific Large Language Model Assistance for Emergency Neurological Diagnosis and Treatment: A Randomized Controlled Clinical Trial

This study will evaluate whether Xuanwu-NeuroAid 2.0, a large language model for emergency neurology, can improve 30-day diagnostic quality in adults with acute neurological symptoms. Physicians will be randomly assigned to AI-assisted care or usual care. In the AI-assisted group, the model will provide diagnostic and management suggestions, while physicians will make all final clinical decisions. The usual-care group will receive standard emergency neurology care without large language model assistance.

Study Overview

• Status: Not yet recruiting
• Conditions: Acute Neurological Symptoms
• Intervention / Treatment: Device: Xuanwu-NeuroAid 2.0

Detailed Description

This multicenter, prospective, cluster randomized trial will evaluate whether Xuanwu-NeuroAid 2.0, a domain-specific large language model for emergency neurology, can improve diagnostic quality in adults presenting with acute neurological symptoms. Physicians will be randomized to AI-assisted care or usual care. In the AI-assisted group, the model will provide diagnostic and management suggestions based on available clinical information, while physicians will remain responsible for all final clinical decisions. the model's recommendations could be disregarded when they were considered inappropriate. The usual-care group will receive standard emergency neurology care without large language model assistance.

• Study Type: Interventional
• Enrollment (Estimated): 1360
• Phase: Not Applicable

Contacts and Locations

• Study Contact: Name: Xunming Ji; Phone Number: 01083198962; Email: jixm@ccmu.edu.cn
• Study Contact Backup: Name: Chuanjie Wu; Phone Number: 01083199439; Email: wuchuanjie@ccmu.edu.cn

Study Locations

• China
  • Beijing, China, 100053
    • Xuanwu Hospital，Capital Medical University
    • Contact: Chuanjie Wu; Phone Number: 010-83199439; Email: wuchuanjie@ccmu.edu.cn

Participation Criteria

Eligibility Criteria

• Ages Eligible for Study: Adult; Older Adult
• Accepts Healthy Volunteers: No

Description

Inclusion Criteria:

• Age ≥18 years;
• Presentation to the emergency neurology service with acute neurological symptoms;
• Written informed consent provided by the patient or a legally authorized representative.

Exclusion Criteria:

• Presention primarily for trauma;
• Pregnancy;
• Requiring immediate life-saving interventions;
• Estimated life expectancy of less than 30 days;
• Participation in another clinical trial within the previous 30 days or in a trial that could interfere with the study or outcome assessment;
• Any condition that, in the opinion of the investigators, would interfere with the conduct of the trial or the interpretation of the results.

Study Plan

How is the study designed?

Design Details

• Primary Purpose: Health Services Research
• Allocation: Randomized
• Interventional Model: Parallel Assignment
• Masking: Single

Number of Arms

2

Arms and Interventions

Participant Group / Arm	Intervention / Treatment
Experimental: AI-assisted group; Physicians in this group will use Xuanwu-NeuroAid 2.0 during emergency evaluation and management.	Device: Xuanwu-NeuroAid 2.0; Xuanwu-NeuroAid 2.0 is a large language model used to support emergency neurology evaluation and management. It generates diagnostic and management suggestions based on available clinical information, including history, physical examination, laboratory results, and imaging data. Physicians may interact with the model multiple times, but remain responsible for all final clinical decisions. Its recommendations may be overridden when considered inappropriate.
No Intervention: Usual-care group; Physicians in this group will provide standard emergency neurology care without large language model assistance.

What is the study measuring?

Primary Outcome Measures

Outcome Measure	Measure Description	Time Frame
Diagnostic-care quality risk	A composite outcome defined as the occurrence of any of the following: a diagnostic discrepancy within 30 days; unplanned medical care within 30 days; harms related to the index emergency care within 30 days; or all-cause death within 30 days.	Day 30

Secondary Outcome Measures

Outcome Measure	Measure Description	Time Frame
Diagnostic discrepancy	Diagnostic discrepancy is defined as disagreement between the emergency department final diagnosis and the 30-day expert-adjudicated reference diagnosis.	Day 30
Quality of diagnostic testing and management recommendations	The quality of diagnostic testing and management recommendations made during the index emergency department encounter will be assessed by blinded expert adjudicators after completion of 30-day follow-up, using a 5-point Likert scale. Higher scores indicate higher quality of diagnostic testing and management recommendations.	Day 30
Patient satisfaction with emergency care	Patient satisfaction with emergency care will be assessed after the index emergency department encounter using a 5-point Likert scale, ranging from 1 to 5, with higher scores indicating greater satisfaction.	Immediately after the index emergency department encounter, within 48 hours
Time spent per patient encounter	Time spent per patient encounter is defined as the duration from the start of physician evaluation to completion of the emergency department final diagnosis and disposition decision during the index emergency department encounter.	Time from start of physician evaluation to completion of final diagnosis and disposition decision, within 48 hours.
Clinician-reported workload	Clinician-reported workload will be assessed by the treating physician after each index emergency department encounter using a 5-point Likert scale. Higher scores indicate greater perceived workload.	Immediately after each index emergency department encounter, within 48 hours.
EQ-5D at 30 days	Health-related quality of life at Day 30, assessed using the EQ-5D questionnaire. Higher utility scores indicates better health status.	Day 30

Other Outcome Measures

Outcome Measure	Measure Description	Time Frame
Unplanned medical care within 30 days	Unplanned medical care is defined as any unscheduled emergency department visit, outpatient visit, or hospital admission within 30 days after the index emergency department encounter.	From completion of the index emergency department encounter to Day 30
Harms related to this emergency care within 30 days	Harms are defined as adverse clinical events within 30 days after the index emergency department encounter.	From completion of the index emergency department encounter to Day 30
All-cause death within 30 days	All-cause death is defined as death from any cause within 30 days after the index emergency department encounter.	From completion of the index emergency department encounter to Day 30

Collaborators and Investigators

• Sponsor: Capital Medical University

Study record dates

Study Major Dates

• Study Start (Estimated): June 2, 2026
• Primary Completion (Estimated): August 30, 2026
• Study Completion (Estimated): September 30, 2026

Study Registration Dates

• First Submitted: May 19, 2026
• First Submitted That Met QC Criteria: May 30, 2026
• First Posted (Actual): June 4, 2026

Study Record Updates

• Last Update Posted (Actual): June 4, 2026
• Last Update Submitted That Met QC Criteria: May 30, 2026
• Last Verified: May 1, 2026

More Information

Terms related to this study

• Keywords: Diagnostic; Large Language Model; Emergency Neurology
• Additional Relevant MeSH Terms: Pathologic Processes; Pathological Conditions, Signs and Symptoms; Disease
• Other Study ID Numbers: DEMAND

Plan for Individual participant data (IPD)

• Plan to Share Individual Participant Data (IPD)?: UNDECIDED

Drug and device information, study documents

• Studies a U.S. FDA-regulated drug product: No
• Studies a U.S. FDA-regulated device product: No