A machine learning approach for modeling decisions in the out of hospital cardiac arrest care workflow

Samuel Harford; Marina Del Rios; Sara Heinert; Joseph Weber; Eddie Markul; Katie Tataris; Teri Campbell; Terry Vanden Hoek; Houshang Darabi

doi:10.1186/s12911-021-01730-4

Back

A machine learning approach for modeling decisions in the out of hospital cardiac arrest care workflow

Journal article

Open access

Peer reviewed

A machine learning approach for modeling decisions in the out of hospital cardiac arrest care workflow

Samuel Harford, Marina Del Rios, Sara Heinert, Joseph Weber, Eddie Markul, Katie Tataris, Teri Campbell, Terry Vanden Hoek and Houshang Darabi

BMC medical informatics and decision making, Vol.22(1), pp.21-21

01/25/2022

DOI: 10.1186/s12911-021-01730-4

PMCID: PMC8787933

PMID: 35078470

Files and links (1)

url

https://doi.org/10.1186/s12911-021-01730-4View

Published (Version of record) Open Access

Abstract

A growing body of research has shown that machine learning (ML) can be a useful tool to predict how different variable combinations affect out-of-hospital cardiac arrest (OHCA) survival outcomes. However, there remain significant research gaps on the utilization of ML models for decision-making and their impact on survival outcomes. The purpose of this study was to develop ML models that effectively predict hospital's practice to perform coronary angiography (CA) in adult patients after OHCA and subsequent neurologic outcomes. We utilized all (N = 2398) patients treated by the Chicago Fire Department Emergency Medical Services included in the Cardiac Arrest Registry to Enhance Survival (CARES) between 2013 and 2018 who survived to hospital admission to develop, test, and analyze ML models for decisions after return of spontaneous circulation (ROSC) and patient survival. ML classification models, including the Embedded Fully Convolutional Network (EFCN) model, were compared based on their ability to predict post-ROSC decisions and survival. The EFCN classification model achieved the best results across tested ML algorithms. The area under the receiver operating characteristic curve (AUROC) for CA and Survival were 0.908 and 0.896 respectively. Through cohort analyses, our model predicts that 18.3% (CI 16.4-20.2) of patients should receive a CA that did not originally, and 30.1% (CI 28.5-31.7) of these would experience improved survival outcomes. ML modeling effectively predicted hospital decisions and neurologic outcomes. ML modeling may serve as a quality improvement tool to inform system level OHCA policies and treatment protocols.

Adult

Cardiopulmonary Resuscitation

Decision Making

Emergency Medical Services

Humans

Machine Learning

Models, Theoretical

Out-of-Hospital Cardiac Arrest - etiology

Out-of-Hospital Cardiac Arrest - therapy

Workflow

Details

Title: Subtitle: A machine learning approach for modeling decisions in the out of hospital cardiac arrest care workflow
Creators: Samuel Harford - University of Illinois Chicago
Marina Del Rios - Roy J. and Lucille A. Carver College of Medicine
Sara Heinert - Rutgers, The State University of New Jersey
Joseph Weber - John H. Stroger, Jr. Hospital of Cook County
Eddie Markul - Advocate Illinois Masonic Medical Center
Katie Tataris - University of Chicago
Teri Campbell - University of Illinois Chicago
Terry Vanden Hoek - University of Illinois Chicago
Houshang Darabi - University of Illinois Chicago
Resource Type: Journal article
Publication Details: BMC medical informatics and decision making, Vol.22(1), pp.21-21
DOI: 10.1186/s12911-021-01730-4
PMID: 35078470
PMCID: PMC8787933
NLM abbreviation: BMC Med Inform Decis Mak
ISSN: 1472-6947
eISSN: 1472-6947
Language: English
Date published: 01/25/2022
Academic Unit: Emergency Medicine
Record Identifier: 9984297146002771

Metrics

22 Record Views

10 Times Cited - Web of Science

See more details