Leveraging Natural Language Processing and Structured Scoring to Evaluate Operative Note Quality in Surgical Training

Phillip Jenkins

doi:10.1016/j.jsurg.2026.104022

Leveraging Natural Language Processing and Structured Scoring to Evaluate Operative Note Quality in Surgical Training

2026-06-16

0

PRE

AI

P

Phillip Jenkins *

E

Eric Cramer

J

Julie Doberne

S

Steven Bedrick

K

Kenneth Azarow

R

Ruchi Thanawala

DOI：10.1016/j.jsurg.2026.104022

Original

Original request for help

Save

Abstract

En 中文

• Natural language processing diffing quantifies edits between resident and attending notes • SAFE-OR grading reveals lower resident scores in key domains • Grader-severity adjustment improves the reliability of comparisons • Differences seen in preop and postop, not intraop content • Scalable framework for objective operative note assessment

Leveraging Natural Language Processing and Structured Scoring to Evaluate Operative Note Quality in Surgical Training

Abstract

Journal

Organization