AI helps doctors write faster, but is it good enough?

NCT ID NCT07187050

Completed Knowledge-focused Sponsor: Kyoto University, Graduate School of Medicine Source: ClinicalTrials.gov ↗

First seen Jun 26, 2026 · Last updated Jun 26, 2026

Summary

This pilot study tested whether an AI writing assistant (CocktailAI) could help doctors complete hospital discharge summaries and referrals faster while maintaining quality. Twenty-one ophthalmologists from Kyoto University Hospital wrote documents for six simulated patient cases, either using the AI to generate a first draft or writing from scratch. The study measured time and expert-rated quality to see if the AI approach is a practical tool for reducing paperwork burden.

What this could mean

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

Active substance: CocktailAI (template-based LLM assistant)
What this could lead to: If successful, this could show that AI can help doctors complete paperwork faster without sacrificing quality, potentially reducing burnout.
What could go wrong: This is a very small pilot (21 participants) using simulated patient records, not real patients. Results may not apply to real hospital settings or other medical fields.

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 CLINICAL DOCUMENTATION 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.

CLINICAL DOCUMENTATION CLINICIAN-IN-THE-LOOP LARGE LANGUAGE MODEL

Contacts and locations

Locations

Department of Ophthalmology and Visual Sciences Kyoto University Graduate School of Medicine 54 Shogoin, Kawahara, Sakyo

Kyoto, 606-8507, Japan

More trials for these conditions

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