Exploring the Feasibility of GPT-4 as a Data Extraction Tool for Renal Surgery Operative Notes.

Jessica Y HsuehDaniel NethalaShiva SinghJason A HymanDavid G GelikmanW Marston LinehanMark W Ball

Published in: Urology practice (2024)

Match and accuracy rates were higher for categorical variables. GPT-4 data extraction was particularly error prone for variables with heterogenous documentation styles. The role of a standard operative template to aid data extraction will be explored in the future. GPT-4 can be utilized as a helpful and efficient data extraction tool with manual feedback.

Keyphrases

electronic health record
big data
machine learning
data analysis
high resolution
coronary artery disease
mass spectrometry
coronary artery bypass
current status
liquid chromatography
tandem mass spectrometry