Reliability of Large Language Model–Based Clinical Decision Support Systems for Procedural Sedation: A Standardized Scenario-Based Benchmarking Study

This repository contains the datasets supporting the manuscript entitled “Large Language Models in Sedation Decision-Making: An Expert Comparison Study”. The repository includes the clinical scenario list, anonymized raw scoring data from 270 evaluations, the inter-rater reliability (ICC) calculation dataset, and supplementary materials used in the analyses. No personally identifiable information is included.