Inter-Rater Reliability and Agreement Among Mass-Casualty Incident Algorithms Using a Pediatric Trauma Dataset: A Pilot Study.

Emilia H Fisher Ilene A ClaudiusAmy H KajiAlaa ShabanNicholas McGlynnMark X CiceroGenevieve SantillanesMarianne Gausche-HillTodd P ChangJ Joelle Donofrio-Odmann

Published in: Prehospital and disaster medicine (2022)

The IRR was excellent for a majority of the algorithms. The SALT algorithm, which contains subjective components, had the lowest IRR when applied to this dataset of pediatric trauma patients. Both J-START and CF demonstrated the best overall reliability and agreement.

Keyphrases

trauma patients
machine learning
deep learning
cystic fibrosis
cardiovascular disease
type diabetes
depressive symptoms
physical activity