The Success of ChatGPT in Providing American Society of Anesthesiologist (ASA) Scores (ASA)

Patients applied to the anesthesia clinics of Health Science University Istanbul Kanuni Sultan Suleyman Training and Research Hospital and Basaksehir Cam and Sakura City Hospital were included in the study. Evaluation forms which will be filled in every preoperative examinations will be saved in the hospitals systems. Patients datas without indentification informations will be asked to ChatGpt to give anesthesiological risc scores. This scores will be compared with the scores already given by anesthesiologists.

Study Overview

• Status: Completed
• Conditions: Artificial Intelligence; Preoperative Evaluation
• Intervention / Treatment: Other: providing ASA score

Detailed Description

Patients of all ages and sexes with ASA scores ranging from I to IV who applied to the anesthesia clinics of Health Science University Istanbul Kanuni Sultan Suleyman Training and Research Hospital and Basaksehir Cam and Sakura City Hospital were included in the study. Patients with ASA scores of V and VI were not included in the study as their statistical distribution would be disrupted.

Data Collection Data were collected daily from preoperative examination evaluation forms in this study, which included Patient's Age Patient's Gender Patient's Weight Patient's Height Additional Illnesses Medications Used Abnormal Laboratory Findings Abnormal Imaging Findings Operation to be Performed Consultation Notes Given ASA Score ChatGPT's ASA Score. At Health Science University Istanbul Kanuni Sultan Suleyman Training and Research Hospita, the patient will be under the care of Specialist Doctor Engin İhsan Turan, and at Basaksehir Cam and Sakura City Hospital, under the care of Specialist Doctor Abdurrahman Engin Baydemir.

The natural language processing module ChatGPT 4, developed by OpenAI, was consulted for providing ASA scores based on the collected data. In addition to the collected data, ASA scores given by anesthesia experts were also entered into the system.

The investigators chose ChatGPT-4 among artificial intelligence models for our study due to its extensive use in the literature.

Primary Objective: To evaluate the success of ChatGPT-4 in predicting postoperative intensive care needs and mortality in adult patients with ASA scores of III and IV. Secondary Objectives: To examine the effectiveness of ChatGPT-4's recommendations on anesthesia methods and additional suggestions in the clinical decision-making process.

Benefits: Understanding the contributions of artificial intelligence-based systems to clinical decision-making processes.

Risks: The potential for ChatGPT-4's recommendations to be misleading, but the risk will be mitigated by doctors being the final decision-makers.

Use of ChatGPT 4 After the data mentioned above regarding the patients were transmitted to ChatGPT 4, ChatGPT 4 was asked to predict the ASA scores of the patients. To do so the investigators will create a special GPT which can provide ASA scores according to the newest guidelines. This GPT will assign patients an ASA score based on abnormal data while recognizing that the patients' other results and physical examination findings are normal.

• Study Type: Observational
• Enrollment (Actual): 2851

Contacts and Locations

Study Locations

• Turkey
  • Istanbul, Turkey, 34303
    • Health Science University İstanbul Kanuni Sultan Süleyman Education and Training Hospital

Participation Criteria

Eligibility Criteria

• Ages Eligible for Study: Child; Adult; Older Adult
• Accepts Healthy Volunteers: Yes

• Sampling Method: Probability Sample

Study Population

All patients who admitted to anesthesia clinics of Health Science University Istanbul Kanuni Sultan Suleyman Training and Research Hospital and Basaksehir Cam and Sakura City Hospital.

Description

Inclusion Criteria:

• Patient who admitted to anesthesia clinics for both hospital
• Patient with ASA scores between I-IV

Exclusion Criteria:

• ASA scores higher than IV
• Emergency cases patients have symptoms like upper and lower airway infections.
• patients haven't got enough informations to provide ASA scores.
• Patients with symptoms of an active upper or lower respiratory tract infection

Study Plan

How is the study designed?

Number of groups / cohorts

2

Cohorts and Interventions

Group / Cohort	Intervention / Treatment
Experts; ASA scores provided by anesthesiologists	Other: providing ASA score; ASA scoring, or the American Society of Anesthesiologists (ASA) Physical Status Classification System, is a framework used by anesthesiologists to assess the preoperative physical fitness of a patient before surgery. It categorizes patients into six classes based on their overall health status, ranging from ASA I (a healthy patient) to ASA VI (a declared brain-dead patient whose organs are being removed for donor purposes). The ASA score helps in predicting perioperative risks and assists healthcare professionals in making informed decisions about anesthesia management and the need for special precautions during and after surgery.
ChatGpt; ASA scores provided by ChatGpt	Other: providing ASA score; ASA scoring, or the American Society of Anesthesiologists (ASA) Physical Status Classification System, is a framework used by anesthesiologists to assess the preoperative physical fitness of a patient before surgery. It categorizes patients into six classes based on their overall health status, ranging from ASA I (a healthy patient) to ASA VI (a declared brain-dead patient whose organs are being removed for donor purposes). The ASA score helps in predicting perioperative risks and assists healthcare professionals in making informed decisions about anesthesia management and the need for special precautions during and after surgery.

What is the study measuring?

Primary Outcome Measures

Outcome Measure	Measure Description	Time Frame
The Success of ChatGPT in Providing American Society of Anesthesiologist (ASA) Scores	Comparison of ASA scores provided from ChatGpt and provided from anesthesiologists. ASA 1: A normal healthy patient. ASA 2: A patient with mild systemic disease. ASA 3: A patient with severe systemic disease that is not incapacitating. ASA 4: A patient with severe systemic disease that is a constant threat to life. ASA 5: A moribund patient who is not expected to survive without the operation. ASA 6: A declared brain-dead patient whose organs are being removed for donor purposes. Additional classifications include: E: This designation can be added to any of the above classifications (ASA 1E to ASA 6E) to indicate that the surgery is an emergency, which increases the risk of the procedure.	2 weeks

Secondary Outcome Measures

Outcome Measure	Measure Description	Time Frame
The Success of ChatGPT in clinical decisions	Comparison of ASA scores provided from ChatGpt and provided from anesthesiologists. ASA 1: A normal healthy patient. ASA 2: A patient with mild systemic disease. ASA 3: A patient with severe systemic disease that is not incapacitating. ASA 4: A patient with severe systemic disease that is a constant threat to life. ASA 5: A moribund patient who is not expected to survive without the operation. ASA 6: A declared brain-dead patient whose organs are being removed for donor purposes. Additional classifications include: E: This designation can be added to any of the above classifications (ASA 1E to ASA 6E) to indicate that the surgery is an emergency, which increases the risk of the procedure.	2 weeks

Collaborators and Investigators

• Sponsor: Kanuni Sultan Suleyman Training and Research Hospital
• Investigators: Principal Investigator: Engin ihsan Turan, Specialist, Health Science University İstanbul Kanuni Sultan Süleyman Education and Training Hospital

Publications and helpful links

General Publications

• Yeo YH, Samaan JS, Ng WH, Ting PS, Trivedi H, Vipani A, Ayoub W, Yang JD, Liran O, Spiegel B, Kuo A. Assessing the performance of ChatGPT in answering questions regarding cirrhosis and hepatocellular carcinoma. Clin Mol Hepatol. 2023 Jul;29(3):721-732. doi: 10.3350/cmh.2023.0089. Epub 2023 Mar 22.
• Wongtangman K, Aasman B, Garg S, Witt AS, Harandi AA, Azimaraghi O, Mirhaji P, Soby S, Anand P, Himes CP, Smith RV, Santer P, Freda J, Eikermann M, Ramaswamy P. Development and validation of a machine learning ASA-score to identify candidates for comprehensive preoperative screening and risk stratification. J Clin Anesth. 2023 Aug;87:111103. doi: 10.1016/j.jclinane.2023.111103. Epub 2023 Mar 8.

Study record dates

Study Major Dates

• Study Start (Actual): February 8, 2024
• Primary Completion (Actual): April 1, 2024
• Study Completion (Actual): May 1, 2024

Study Registration Dates

• First Submitted: March 11, 2024
• First Submitted That Met QC Criteria: March 14, 2024
• First Posted (Actual): March 20, 2024

Study Record Updates

• Last Update Posted (Actual): May 6, 2024
• Last Update Submitted That Met QC Criteria: May 3, 2024
• Last Verified: May 1, 2024

More Information

Terms related to this study

• Other Study ID Numbers: ChatGptASAscore

Plan for Individual participant data (IPD)

• Plan to Share Individual Participant Data (IPD)?: NO

Drug and device information, study documents

• Studies a U.S. FDA-regulated drug product: No
• Studies a U.S. FDA-regulated device product: No