Evaluating the Efficacy of Artificial Intelligence Models in Predicting Intensive Care Unit Admission Needs

NCT06494748 | Completed

• 1 other identifier: ICU-retro
• Study Type: observational
• Target: 8,043
• Locations: 1 country
• Sites: 1

Brief Summary

This study aims to evaluate the efficacy of two artificial intelligence (AI) models in predicting the need for ICU admissions. By comparing the AI models' predictions with actual clinical decisions, we aim to determine their accuracy and potential utility in clinical decision support.

Conditions

Intensive Care Unit

Keywords

artificial intelligence

Outcome Measures

Primary Outcomes (1)

• Intensive Care Unit Need

  The primary outcome measure of this study is the accuracy of the predictions made by the artificial intelligence (AI) models, ChatGPT and Gemini, regarding the need for ICU admissions. This will be evaluated by comparing the AI model predictions to the actual clinical decisions made regarding ICU admissions.

  1 day

Study Arms (2)

Anesthesiologists Decision

Intensive Care Unit Follow up need is decided by anesthesiologists.

Other: Follow up Decision

Artificial Intelligence Decision

Intensive Care Unit Follow up need is decided by Artificial Intelligence

Other: Follow up Decision

Interventions

Follow up Decision OTHER

0: No need to follow up in Intensive Care Unit 1: Need to follow up in Intensive Care Unit

Anesthesiologists Decision; Artificial Intelligence Decision

Eligibility Criteria

• Age: 18 Years+
• Sex: all
• Healthy Volunteers: No
• Age Groups: Adult (18-64), Older Adult (65+)
• Sampling Method: Probability Sample

Study Population

Patients over the age of 18 of both genders who are consulted for anesthesia regarding intensive care needs will be included in the study.

You may qualify if:

• Patients over the age of 18
• Patients consulted for anesthesia regarding intensive care needs
• Patients with sufficient data in the hospital's electronic health record system

You may not qualify if:

• Patients with insufficient data in the hospital records

Sponsors & Collaborators

• Kanuni Sultan Suleyman Training and Research Hospital: lead

Study Sites (1)

Health Science University İstanbul Kanuni Sultan Süleyman Education and Training Hospital

Istanbul, 34303, Turkey (Türkiye)

Location

Study Officials

• Engin ihsan Turan, Specialist

  Health Science University İstanbul Kanuni Sultan Süleyman Education and Training Hospital

  PRINCIPAL INVESTIGATOR

Study Design

• Study Type: observational
• Observational Model: COHORT
• Time Perspective: RETROSPECTIVE
• Sponsor Type: OTHER
• Responsible Party: PRINCIPAL INVESTIGATOR
• PI Title: anesthesiology and reanimation specialist

Study Record Dates

• First Submitted: July 3, 2024
• First Posted: July 10, 2024
• Study Start: July 15, 2024
• Primary Completion: October 1, 2024
• Study Completion: October 2, 2024
• Last Updated: October 8, 2024

Record last verified: 2024-10

Locations

TU (1)