AI vs. Doctor's intuition: which leads to better diagnoses?

NCT ID NCT07760051

First seen Aug 12, 2026 · Last updated Aug 13, 2026 · Updated 1 time

Summary

This trial investigates whether AI-assisted workflows can improve how doctors make admission diagnoses. It compares three approaches: a traditional method using standard resources, a chatbot-style AI that doctors can ask questions, and a more advanced 'agent' that automatically reads patient records and provides structured summaries. Doctors from 15 hospitals in China will be randomly assigned to one of these methods and will work through six simulated patient cases, with their diagnostic accuracy and speed measured. The goal is to see if AI tools, especially the agent, can help doctors make more accurate and efficient diagnoses.

What this could mean

Our plain-language read of the trial. This is informational only — not medical advice or a prediction.

Active substance
AI-assisted diagnostic workflows (agent-based and LLM-based tools) compared to traditional methods
What this could lead to
If effective, AI-assisted workflows could help doctors make more accurate diagnoses, potentially reducing errors and improving patient care.
What could go wrong
The trial uses simulated cases, not real patients, and results may not translate to real-world settings. AI tools may also introduce new errors or over-reliance.

This is an AI summary of the original study and may miss details. Read our disclaimer.

Get updates

Get notified about this study

Sign up to get updates when this study changes or when new studies for ARTIFICIAL INTELLIGENCE (AI) are added.

Our safety recommendation!

By submitting, you agree to our Terms of use

As listed by the trial registrant

The condition terms exactly as the trial's registrant entered them.

Contacts and locations

Locations

  • 2nd Affiliated Hospital, School of Medicine, Zhejiang University

    Hangzhou, Zhejiang, 310009, China

More trials for these conditions

Other studies related to the condition(s) this trial covers.