Evaluation of AI-Generated Clinical Advice by Physicians

Tsinghua University

Status: Not yet enrolling

Conditions: Artificial Intelligence (AI)

Treatments: Other: Large Language Model

Study type: Interventional

Funder types: Other

Identifiers

NCT06980467

2025-07

Details and patient eligibility

About

This study examines how artificial intelligence systems interact with medical professionals. Researchers will compare physician responses to different AI-generated outputs in simulative medical scenarios.

Enrollment: 8 estimated patients

Sex: All

Ages: 18 to 80 years old

Volunteers: Accepts Healthy Volunteers

Inclusion criteria

• Age ≥ 18 years old;
• Licensed physician or medical professional qualified to perform clinical evaluations;
• Willing to sign informed consent and commit time to participate in the study.

Exclusion criteria

• Unable to dedicate sufficient time to complete the study tasks;
• Unable or unwilling to understand and follow study instructions.

Trial design

Primary purpose: Other

Allocation: Randomized

Interventional model: Crossover Assignment

Masking: Single Blind

---

8 participants in 2 patient groups

control group

No Intervention group

Description:

Participants evaluate clinical recommendations generated by Language Model A (LLM-A), with subsequent assessments of communication style characteristics using rating scales.

intervention group

Experimental group

Description:

Participants evaluate clinical recommendations generated by Language Model B (LLM-B), followed by evaluations of communication style characteristics through metric instruments.

Treatment:

Other: Large Language Model