Physician Diagnosis of Neurologic Cases With Large Language Models

NCT07344792 | Completed

• 1 other identifier: LLM-001
• Study Type: interventional
• Target: 40
• Locations: 1 country
• Sites: 3

Brief Summary

This study is a prospective randomized controlled trial that aims to evaluate whether large language model (LLM) assistance improves physicians' diagnostic performance compared with conventional assistance.

Conditions

Neurology

Outcome Measures

Primary Outcomes (1)

• Top-1 diagnostic accuracy

  Top-1 diagnosis is considered correct if the physician's final top-ranked diagnosis matches the reference diagnosis or a clinically similar diagnosis judged as equivalent by neurologists.

  Baseline

Secondary Outcomes (3)

• Top-3 diagnostic accuracy

  Baseline

• Time spent on diagnosis

  Baseline

• Diagnostic confidence

  Baseline

Study Arms (2)

LLM assistance group

EXPERIMENTAL

Physicians are assisted by an in-house LLM and are allowed to use conventional resources. Access to any other LLMs is not permitted.

Other: LLM assistance

Conventional assistance group

NO INTERVENTION

Physicians use only conventional resources and do not have access to the in-house LLM or any other LLMs at any point during the study.

Interventions

LLM assistance OTHER

Physicians are assisted by an in-house large language model and are allowed to use conventional resources. Access to any other LLMs is not permitted.

LLM assistance group

Eligibility Criteria

• Sex: all
• Healthy Volunteers: Yes
• Age Groups: Child (0-17), Adult (18-64), Older Adult (65+)

You may qualify if:

• Licensed physicians who have completed at least two years of neurology training.
• Willing to participate in the study and able to provide written informed consent.

You may not qualify if:

• Physicians who have previously participated in the development of the in-house LLM or the construction of datasets used in this study.
• Physicians who were involved in the clinical care of patients whose cases were used to construct the case dataset for this study.
• Physicians who are known to have previously reviewed or been exposed to the specific cases used in this study.

Sponsors & Collaborators

• Capital Medical University: lead

Study Sites (3)

Beijing Luhe Hospital affiliated to Capital Medical University

Beijing, Beijing Municipality, 100000, China

Location

Xuanwu Hospital Capital Medical University

Beijing, Beijing Municipality, 100053, China

Location

Nanyang Central Hospital

Nanyang, Henan, 473000, China

Location

Study Design

• Study Type: interventional
• Phase: not applicable
• Allocation: RANDOMIZED
• Masking: SINGLE
• Who Masked: OUTCOMES ASSESSOR
• Purpose: DIAGNOSTIC
• Intervention Model: PARALLEL
• Sponsor Type: OTHER
• Responsible Party: PRINCIPAL INVESTIGATOR
• PI Title: Principal Investigator

Study Record Dates

• First Submitted: December 1, 2025
• First Posted: January 15, 2026
• Study Start: January 17, 2026
• Primary Completion: January 28, 2026
• Study Completion: January 28, 2026
• Last Updated: January 29, 2026

Record last verified: 2026-01

Locations

CN (3)