@article{ref1,
title="Identification of factors associated with return of spontaneous circulation after pediatric out-of-hospital cardiac arrest using natural language processing",
journal="Prehospital emergency care",
year="2023",
author="Harris, M. and Crowe, R.P. and Anders, J. and D'Acunto, S. and Adelgais, K.M. and Fishe, J.N.",
volume="27",
number="5",
pages="687-694",
abstract="INTRODUCTION: Prior studies examining prehospital characteristics related to return of spontaneous circulation (ROSC) in pediatric out-of-hospital cardiac arrest (OHCA) are limited to structured data. Natural language processing (NLP) could identify new factors from unstructured data using free-text narratives. The purpose of this study was to use NLP to examine EMS clinician free-text narratives for characteristics associated with prehospital ROSC in pediatric OHCA. <br><br>METHODS: This was a retrospective analysis of patients ages 0-17 with OHCA in 2019 from the ESO Data Collaborative. We performed an exploratory analysis of EMS narratives using NLP with an a priori token library. We then constructed biostatistical and machine learning models and compared their performance in predicting ROSC. <br><br>RESULTS: There were 1,726 included EMS encounters for pediatric OHCA; 60% were male patients, and the median age was 1 year (IQR 0-9). Most cardiac arrest events (61.3%) were unwitnessed, 87.3% were identified as having medical causes, and 5.9% had initial shockable rhythms. Prehospital ROSC was achieved in 23.1%. Words most positively correlated with ROSC were &quot;ROSC&quot; (r = 0.42), &quot;pulse&quot; (r = 0.29), &quot;drowning&quot; (r = 0.13), and &quot;PEA&quot; (r = 0.12). Words negatively correlated with ROSC included &quot;asystole&quot; (r = −0.25), &quot;lividity&quot; (r = −0.14), and &quot;cold&quot; (r = −0.14). The terms &quot;asystole,&quot; &quot;pulse,&quot; &quot;no breathing,&quot; &quot;PEA,&quot; and &quot;dry&quot; had the greatest difference in frequency of appearance between encounters with and without ROSC (p < 0.05). The best-performing model for predicting prehospital ROSC was logistic regression with random oversampling using free-text data only (area under the receiver operating characteristic curve 0.92). <br><br>CONCLUSIONS: EMS clinician free-text narratives reveal additional characteristics associated with prehospital ROSC in pediatric OHCA. Incorporating those terms into machine learning models of prehospital ROSC improves predictive ability. Therefore, NLP holds promise as a tool for use in predictive models with the goal to increase evidence-based management of pediatric OHCA. <p /> <p>Language: en</p>",
language="en",
issn="1090-3127",
doi="10.1080/10903127.2022.2074180",
url="http://dx.doi.org/10.1080/10903127.2022.2074180"
}