Files
Download Full Text (226 KB)
DOI
https://doi.org/10.63853/RAHD7980
Description
Purpose: The purpose of this study was to compare the performance of AI-generated summaries and physician-written summaries in the pediatric surgery population from nurses’ perspectives.
Methods: The study occurred at a large, academic-affiliated pediatric healthcare system designated as a Level 1 Children’s Surgery Center. Three clinical nurses independently reviewed and compared AI-generated summaries to physician written summaries for patients admitted to the surgery service line utilizing the validated Physician Documentation Quality Instrument (PDQI-9) tool. The nurse evaluation team met prior to scoring to ensure consistency of interpretation and scoring of PDQI-9 domains.
Results: AI-generated and physician written summaries for 117 patients were included, revealing a statistically significant higher ranking for AI-generated summaries (Z = 3.89, p < .001). AI-generated summaries outperformed physician written summaries in seven out of nine PDQI-9 domains (thorough, useful, organized, comprehensible, succinct, synthesized, and internally consistent). Fleiss’ Kappa analysis was conducted to assess the degree of agreement among the raters, showing fair agreement for five domains, and slight agreement for four domains, highlighting the need and complexity of multi-rater review of clinical summaries.
Publication Date
11-24-2025
Disciplines
Pediatric Nursing
Recommended Citation
Patton, Lindsey and Marshall, Nikki, "Pediatric Nurses’ Perceptions of the Quality and Usefulness of Clinical Summaries - Surgeons Versus Generative AI" (2025). 2025. 35.
https://scholarlycollection.childrens.com/nursing-anf2025/35
Creative Commons License
This work is licensed under a Creative Commons Attribution-NonCommercial-No Derivative Works 4.0 International License.
