Pediatric anesthesia & critical care
Evaluating the accuracy of ChatGPT-4 in predicting American Society of Anesthesiologists (ASA) scores: A prospective multicentric study ChatGPT-4 in ASA score prediction
Main finding · Concordance with anesthesiologists' ASA scoresResult — go to the resultCohen's kappa 0.858Authors' conclusion
The findings suggest that ChatGPT-4 can significantly contribute to the medical field by supporting anesthesiologists in preoperative assessments.
Study context
- Population
- Patients from anesthesiology outpatient clinics, neonates to all ages, ASA I–IV; excluding ASA V–VI, emergency operations, insufficient information
- Participants
- 2,851 patients
- Exposure
- ChatGPT-4 ASA score prediction vs anesthesiologists' ASA scores
- Outcome
- Concordance of ChatGPT-4 ASA score predictions with anesthesiologists' assessments (Cohen's kappa)
Methodological detailsagreement of AI prediction with expert assessment
- Agreement of AI prediction with expert assessment
Main finding
Concordance with anesthesiologists' ASA scores
Cohen's kappa
0.858
P = 0.000
As reported in the abstract
Observational data: associations, not effects.
Further findings
Accuracy by ASA class
- Accuracy in predicting ASA I to III
- over 90%
- Notable variance in ASA IV scores
Original publication
Evaluating the accuracy of ChatGPT-4 in predicting ASA scores: A prospective multicentric study ChatGPT-4 in ASA score prediction. J Clin Anesth. Published 23 April 2024. doi:10.
Composed by AI from the published abstract and checked against it. How Briefs are made →