Agreement Between ChatGPT-5 and Anesthesiologists in Preoperative Risk Assessment: ASA Classification

NCT07459491 | Active Not Recruiting

• 1 other identifier: Antalya City Hospital
• Study Type: observational
• Target: 703
• Locations: 1 country
• Sites: 1

Brief Summary

Accurate preoperative risk stratification is essential for perioperative planning, resource allocation, and patient safety. The American Society of Anesthesiologists Physical Status (ASA-PS) classification remains the most widely used global system for assessing preoperative health status. However, ASA classification relies on clinician judgment and may demonstrate inter-observer variability. Recent advances in artificial intelligence (AI), particularly large language models (LLMs), have shown potential for assisting clinical decision-making by synthesizing structured and unstructured medical information. In perioperative medicine, AI systems may support more standardized risk assessment and laboratory testing strategies. The objective of this observational study is to evaluate the agreement between ASA classifications assigned by anesthesiologists and those generated by a large language model (ChatGPT-5) using anonymized preoperative clinical information. The study will also examine differences in laboratory test recommendations and explore the relationship between clinician- and AI-generated risk assessments and perioperative erythrocyte suspension utilization. Adult patients scheduled for elective surgery who undergo routine preoperative anesthesia assessment will be included. For each patient, the ASA classification assigned by the anesthesiologist will be recorded and compared with the classification generated by the AI system using the same anonymized clinical information. This study aims to assess whether AI-assisted preoperative evaluation may support more consistent risk stratification and potentially contribute to more standardized perioperative resource utilization.

Conditions

Artifical Intelligence; Preoperative Evaluation

Keywords

artifical intelligence; chatgpt; anesthesia; Risk stratification; Perioperative medicine; preoperative assessment; Perioperative outcomes; Agreement analysis

Outcome Measures

Primary Outcomes (1)

• Agreement Between Anesthesiologist-Assigned and ChatGPT-5-Generated ASA Physical Status Classification

  Agreement between ASA Physical Status classifications assigned by board-certified anesthesiologists and those generated by ChatGPT-5 using anonymized preoperative clinical data. Agreement will be quantified using Cohen's kappa and weighted kappa statistics for ordinal ASA categories (I-V). The comparison will be performed using identical anonymized preoperative clinical summaries.

  At the time of preoperative anesthesia assessment (baseline).

Interventions

No intervention (observational study) OTHER

This is a non-interventional observational study. No therapeutic or diagnostic intervention is performed as part of the study

Eligibility Criteria

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

Study Population

Adult patients (≥18 years) scheduled for elective surgery and evaluated at the preoperative anesthesia outpatient clinic of Antalya City Hospital during the study period will constitute the study population. All eligible patients with a completed standardized preoperative anesthesia assessment form and documented ASA Physical Status classification will be considered. Only patients whose clinical data can be fully anonymized and who provide written informed consent will be included. Patients undergoing emergency surgery, pediatric patients, pregnant patients, ASA VI classification, incomplete documentation, or cases with more than 30 days between preoperative assessment and surgery will be excluded.

You may qualify if:

• Age ≥ 18 years
• Scheduled for elective surgery
• Completed standardized preoperative anesthesia evaluation form
• ASA Physical Status classification assigned by a specialist anesthesiologist
• Written informed consent
• Clinical documentation suitable for anonymization

You may not qualify if:

• Emergency surgery
• ASA VI classification
• Pregnancy
• Pediatric patients (\<18 years)
• Incomplete or non-standardized clinical documentation
• Inability to anonymize clinical records
• More than 30 days between preoperative assessment and surgery

Sponsors & Collaborators

• Damla Kaytancı Özçelik: lead

Study Sites (1)

Antalya City Hospital

Antalya, Turkey (Türkiye)

Location

MeSH Terms

Interventions

Observation

Intervention Hierarchy (Ancestors)

Methods; Investigative Techniques

Study Officials

• Damla Kaytancı Özçelik

  Antalya City Hospital

  PRINCIPAL INVESTIGATOR

Study Design

• Study Type: observational
• Observational Model: COHORT
• Time Perspective: PROSPECTIVE
• Sponsor Type: OTHER
• Responsible Party: SPONSOR INVESTIGATOR
• PI Title: specialist in anaesthesiology and reanimation, Principal Investigator

Study Record Dates

• First Submitted: March 2, 2026
• First Posted: March 9, 2026
• Study Start: January 10, 2026
• Primary Completion: February 10, 2026
• Study Completion: May 1, 2026
• Last Updated: April 22, 2026

Record last verified: 2026-04

Locations

TU (1)