Assessing Intensive Care Unit (ICU) Indications: Human vs. ChatGPT-4o Predictions

NCT06726733 | Completed

• 1 other identifier: BYIEAH-INKA
• Study Type: observational
• Target: 624
• Locations: 1 country
• Sites: 1

Brief Summary

This retrospective study evaluates the accuracy of ICU admission indications by comparing clinical decisions with predictions from ChatGPT-4. Patient data, including demographics, vital signs, laboratory results, imaging findings, and clinical decisions, will be retrospectively collected and documented systematically using Case Report Forms. The model will be trained using ICU admission guidelines and tasked to predict ICU needs based on collected patient data. This study aims to systematically assess the alignment between AI-based predictions and clinical decisions for ICU admissions.

Conditions

Intensive Care Unit (ICU) Admission; Emergency Department Patient; Artificial Intelligence (AI); Clinical Decision-making

Keywords

AI; Intensive Care Unit; Clinical decision-making; Artificial Intelligenc

Outcome Measures

Primary Outcomes (3)

• Accuracy rate of ChatGPT-4 in predicting ICU indications

  3 month

• False positive rate

  3 month

• False negative rate

  3 month

Secondary Outcomes (1)

• Kappa statistic

  3 month

Eligibility Criteria

• Age: 18 Years+
• Sex: all
• Age Groups: Adult (18-64), Older Adult (65+)
• Sampling Method: Non-Probability Sample

Study Population

500

You may qualify if:

• Patients aged 18 years and older who are consulted to the anesthesiology and reanimation clinic for ICU indications from the emergency department will be included in the study.

You may not qualify if:

• Patients consulted to the anesthesiology and reanimation clinic for ICU indications from inpatient services.
• Patients consulted to the anesthesiology and reanimation clinic from the emergency department for reasons other than ICU indications.
• Patients consulted to the anesthesiology and reanimation clinic for ICU indications from the emergency department but with insufficient recorded data (patients with data loss)

Sponsors & Collaborators

• Bursa Yuksek Ihtisas Training and Research Hospital: lead

Study Sites (1)

Bursa Yuksek Ihtisas Training and Research Hospital

Bursa, Turkey (Türkiye)

Location

Study Officials

• İlkay Ceylan

  ceylanilkay@yahoo.com

  PRINCIPAL INVESTIGATOR

Study Design

• Study Type: observational
• Observational Model: CASE CONTROL
• Time Perspective: RETROSPECTIVE
• Sponsor Type: OTHER GOV
• Responsible Party: PRINCIPAL INVESTIGATOR
• PI Title: Doctor of anesthesiology and reanimation

Study Record Dates

• First Submitted: December 6, 2024
• First Posted: December 10, 2024
• Study Start: September 1, 2024
• Primary Completion: November 30, 2024
• Study Completion: February 28, 2025
• Last Updated: April 14, 2026

Record last verified: 2026-04

Data Sharing

• IPD Sharing: Will not share

Locations

TU (1)