Generative AI-Assisted Clinical Decision Support for Medical Intensive Care Unit Physicians

NCT07708155 | Completed

• 1 other identifier: 2510-145-1689
• Study Type: interventional
• Target: 15
• Locations: 1 country
• Sites: 1

Brief Summary

This pilot study evaluated the feasibility and usefulness of generative artificial intelligence (AI) as a clinical decision-support tool for physicians working in a medical intensive care unit. Participating physicians were assigned by work period to either use a generative AI system in addition to usual clinical information resources or to use usual resources without generative AI. The assigned condition was then switched so that participants experienced both approaches. During the AI-assisted periods, physicians used de-identified clinical information and considered the AI-generated responses as reference information. All final clinical decisions remained the responsibility of the treating physicians. The study assessed acceptability, usability, satisfaction, perceived decision support, workload, confidence, and learning experience through repeated questionnaires.

Conditions

Clinical Decision Support; Clinical Decision-making

Keywords

ChatGPT; Generative Artificial Intelligence; Large Language Model; Clinical Decision Support; Physician Decision-Making; Medical Intensive Care Unit; Critical Care; Usability; Cluster-Randomized Crossover Study; Acceptability

Outcome Measures

Primary Outcomes (5)

• Daily Physician Satisfaction Score

  The score of 10 questionnaire items assessing physicians' satisfaction with their daily clinical work, modified from Shore and Franks (1986) and Suchman et al. (1993). Each item was rated on a 5-point Likert scale from -2 (strongly disagree) to +2 (strongly agree). Negatively worded items were reverse-scored. The mean score ranges from -2 to +2, with higher scores indicating greater satisfaction.

  At the end of each working day during the one-month medical intensive care unit rotation

• Daily Clinical Decision-Making Score

  The score of 6 questionnaire items assessing satisfaction with the clinical decision-making process, perceived decision difficulty, clarity of the preferred treatment, availability of relevant information, and identification of factors affecting the decision. Items were modified from Gedney (1994) and Dolan (1999) and rated on a 5-point Likert scale from -2 (strongly disagree) to +2 (strongly agree). Negatively worded items were reverse-scored. The mean score ranges from -2 to +2, with higher scores indicating a more favorable decision-making experience.

  At the end of each working day during the one-month medical intensive care unit rotation

• Perceived Quality Score for ChatGPT

  The score of 8 questionnaire items assessing the perceived information quality, system quality, and service quality of ChatGPT, modified from Pillong et al. (2025). Each item was rated on a 5-point Likert scale from -2 (strongly disagree) to +2 (strongly agree). The negatively worded response-time item was reverse-scored. The mean score ranges from -2 to +2, with higher scores indicating better perceived quality.

  At the end of the one-month medical intensive care unit rotation, after completion of both crossover periods

• Generative AI Usability Score

  The score of 3 questionnaire items assessing ease of use, ease of learning, and clarity of interaction with Generative AI (ChatGPT), modified from Pillong et al. (2025). Each item was rated on a 5-point Likert scale from -2 (strongly disagree) to +2 (strongly agree). The mean score ranges from -2 to +2, with higher scores indicating greater usability.

  At the end of the one-month medical intensive care unit rotation, after completion of both crossover periods

• Satisfaction Score for Generative AI Use

  The score of 6 questionnaire items assessing the perceived usefulness, productivity, effectiveness, overall satisfaction, appropriateness, and intention to reuse Generative AI (ChatGPT), modified from Pillong et al. (2025). Each item was rated on a 5-point Likert scale from -2 (strongly disagree) to +2 (strongly agree). The mean score ranges from -2 to +2, with higher scores indicating greater satisfaction.

  At the end of the one-month medical intensive care unit rotation, after completion of both crossover periods

Other Outcomes (8)

• Confidence

  At the end of the one-month medical intensive care unit rotation, after completion of both crossover periods

• Perceived Acquisition of New Knowledge or Clinical Insight

  At the end of the one-month medical intensive care unit rotation, after completion of both crossover periods

• Application of Generative AI-Derived Knowledge to Other Clinical Situations

  At the end of the one-month medical intensive care unit rotation, after completion of both crossover periods

Study Arms (2)

ChatGPT-Assisted Condition First, Then Control Condition

EXPERIMENTAL

Physician clusters used ChatGPT-assisted clinical decision support during the first approximately two weeks of their one-month medical intensive care unit rotation. They then crossed over to the control condition and used usual clinical information resources without generative AI for the remainder of the rotation.

Other: Generative AI-Assisted Clinical Decision Support; Other: Usual Clinical Information Resources

Control Condition First, Then ChatGPT-Assisted Condition

EXPERIMENTAL

Physician clusters used usual clinical information resources without generative AI during the first approximately two weeks of their one-month medical intensive care unit rotation. They then crossed over to the ChatGPT-assisted clinical decision-support condition for the remainder of the rotation.

Other: Generative AI-Assisted Clinical Decision Support; Other: Usual Clinical Information Resources

Interventions

Generative AI-Assisted Clinical Decision Support OTHER

During the assigned period, physicians were encouraged to use ChatGPT (OpenAI) as a generative AI-based reference tool to support clinical information review and decision-making.

ChatGPT-Assisted Condition First, Then Control Condition; Control Condition First, Then ChatGPT-Assisted Condition

Usual Clinical Information Resources OTHER

During the control period, physicians used usual clinical information resources, including discussions with other clinicians, multidisciplinary rounds, specialty consultations, textbooks, clinical practice guidelines, PubMed, and established clinical reference services. No generative AI tool was used for clinical decision support during this period.

ChatGPT-Assisted Condition First, Then Control Condition; Control Condition First, Then ChatGPT-Assisted Condition

Eligibility Criteria

• Age: 19 Years+
• Sex: all
• Healthy Volunteers: Yes
• Age Groups: Adult (18-64), Older Adult (65+)

You may qualify if:

• Age 19 years or older.
• Physicians, including residents, fellows, and attending physicians, working in the medical intensive care unit at Seoul National University Hospital.
• Scheduled to work as a primary treating physician for at least 5 days during a planned observation period.
• Able and willing to provide written informed consent.

You may not qualify if:

• Did not provide written informed consent.
• Withdrew consent from study participation.

Sponsors & Collaborators

• Seoul National University Hospital: lead

Study Sites (1)

Seoul National University Hospital

Seoul, Seoul, 03080, South Korea

Location

Study Officials

• Minju Han, M.D.

  Seoul National University Hospital

  PRINCIPAL INVESTIGATOR

Study Design

• Study Type: interventional
• Phase: not applicable
• Allocation: RANDOMIZED
• Masking: NONE
• Purpose: HEALTH SERVICES RESEARCH
• Intervention Model: CROSSOVER
• Sponsor Type: OTHER
• Responsible Party: SPONSOR

Model Details: The unit of randomization was the physician cluster within each one-month medical intensive care unit rotation. At the beginning of each one-month medical intensive care unit rotation, participating physicians were divided into two clusters. The physician clusters were randomized to one of two intervention sequences: the ChatGPT-assisted condition followed by the control condition, or the control condition followed by the ChatGPT-assisted condition. Each period lasted approximately two weeks, after which the clusters crossed over to the alternate condition. Thus, all participating physicians experienced both study conditions during the same monthly rotation.

Study Record Dates

• First Submitted: July 12, 2026
• First Posted: July 16, 2026
• Study Start: December 1, 2025
• Primary Completion: May 31, 2026
• Study Completion: May 31, 2026
• Last Updated: July 21, 2026

Record last verified: 2026-07

Data Sharing

• IPD Sharing: Will not share

Locations

KR (1)