LLM-Assisted vs Manual Writing for Clinical Documentation: Effects on Time and Quality

NCT07187050 | Completed

• 1 other identifier: clinician-in-the-loop_workflow
• Study Type: interventional
• Target: 21
• Locations: 1 country
• Sites: 1

Brief Summary

The goal of this clinical trial is to learn whether an LLM-assisted writing workflow can reduce the time to complete hospital discharge summaries and discharge referrals and maintain or improve document quality compared with writing from scratch by clinicians. The study used six simulated patient records (no real patient data). The main questions it aims to answer are:

• Does the LLM-assisted writing workflow reduce the time needed to complete each document compared with manual writing?
• Does the LLM-assisted writing workflow improve (or at least maintain) document quality compared with manual writing, as rated by blinded experts? Researchers will compare LLM-assisted versus manual writing to see if the LLM-assisted approach is faster and has equal or better quality. LLM-only drafts (unedited first drafts) will be evaluated as a separate third group to understand the baseline quality of LLM output without clinician edits. Participants will create two documents-a discharge summary and a discharge referral-for each of six simulated cases. Those assigned to CocktailAI \& Modification group will use an LLM assistant (called CocktailAI) to generate a first draft for each document and then review and edit it to finalize; those assigned to the control group will write each document from scratch without LLM assistance.

Conditions

Clinician-in-the-loop; Clinical Documentation; Large Language Model

Keywords

clinician-in-the-loop; Large Language Model; Clinical Documentation; Electronic Health Record

Outcome Measures

Primary Outcomes (1)

• Average time spent creating each document

  In the CocktailAI \& Modification group and the Control group, the time spent creating documents is measured in seconds. In the CocktailAI group, the time required for document generation is measured in seconds.

  On one study day within 2 weeks after enrollment

Secondary Outcomes (1)

• Document quality assessment

  On one study day within 2 weeks after enrollment

Study Arms (3)

CocktailAI & Modification arm

EXPERIMENTAL

Participants log into the study web application using a unique ID and their name. For each simulated patient case, they press "Start" to unlock the case record and initiate timing. After viewing the patient information, clinicians use CocktailAI to generate a first draft of the discharge summary. They then review and edit the draft and submit the final document by pressing "Submit." For the discharge referral of the same case, clinicians follow the same procedure. Copy-and-paste from the case record is permitted. This sequence is repeated for six simulated cases.

Other: Template-Based LLM Assistant

Control arm

ACTIVE COMPARATOR

Participants log into the study web application using a unique ID and their name. For each simulated patient case, they press "Start" to unlock the case record and initiate timing. After viewing the patient information, clinicians write the discharge summary from scratch and submit the document by pressing "Submit." They then write the discharge referral for the same case from scratch and submit it. Copy-and-paste from the case record is permitted. This sequence is repeated for six simulated cases.

Other: Manual Writing

CocktailAI arm

ACTIVE COMPARATOR

The LLM assistant generates drafts of discharge summaries and discharge referrals directly from the simulated patient records, with no clinician review or edits. These drafts are the unedited first drafts produced in the CocktailAI \& Modification arm (captured before any clinician edits) and are included as a separate group.

Other: Template-Based LLM Assistant

Interventions

Template-Based LLM Assistant OTHER

This study uses CocktailAI, a template-based LLM assistant co-developed by the Department of Ophthalmology and Visual Sciences, Kyoto University Graduate School of Medicine, and Fitting Cloud Inc. (Kyoto, Japan). It is designed to extract relevant information from EHRs using LLMs and embed the extracted content into predefined templates. In this trial, the inputs are six simulated patient records (no real patient data). Text generation uses Gemini-2.0-flash-lite. Templates for discharge summaries and discharge referrals are pre-defined by a team member.

CocktailAI & Modification arm; CocktailAI arm

Manual Writing OTHER

The same document templates are provided; however, all LLM instruction prompts are removed in advance. Clinicians manually write the documents, following the template structure, for each of the six simulated cases.

Control arm

Eligibility Criteria

• Sex: all
• Healthy Volunteers: No
• Age Groups: Child (0-17), Adult (18-64), Older Adult (65+)

You may qualify if:

• Ophthalmologists at Kyoto University Hospital
• Junior residents, senior residents, graduate students, board-certified ophthalmologists
• Physicians who confirm that they do not routinely use CocktailAI for clinical documentation and provide informed consent after receiving an explanation of the study.

Sponsors & Collaborators

• Kyoto University, Graduate School of Medicine: lead
• Fitting Cloud Inc.: collaborator

Study Sites (1)

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

Kyoto, 606-8507, Japan

Location

Study Design

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

Model Details: This is a prospective, randomized, open-label, blinded-endpoint (PROBE) trial.

Study Record Dates

• First Submitted: September 2, 2025
• First Posted: September 22, 2025
• Study Start: February 18, 2025
• Primary Completion: March 14, 2025
• Study Completion: July 16, 2025
• Last Updated: September 22, 2025

Record last verified: 2025-09

Locations

JP (1)