Skip to main content

Lund University Publications

LUND UNIVERSITY LIBRARIES

Predicting neurological outcome after out-of-hospital cardiac arrest with cumulative information; development and internal validation of an artificial neural network algorithm

Andersson, Peder LU orcid ; Johnsson, Jesper LU ; Björnsson, Ola LU ; Cronberg, Tobias LU ; Hassager, Christian ; Zetterberg, Henrik LU ; Stammet, Pascal ; Undén, Johan LU ; Kjaergaard, Jesper and Friberg, Hans LU , et al. (2021) In Critical Care 25(1).
Abstract

Background: Prognostication of neurological outcome in patients who remain comatose after cardiac arrest resuscitation is complex. Clinical variables, as well as biomarkers of brain injury, cardiac injury, and systemic inflammation, all yield some prognostic value. We hypothesised that cumulative information obtained during the first three days of intensive care could produce a reliable model for predicting neurological outcome following out-of-hospital cardiac arrest (OHCA) using artificial neural network (ANN) with and without biomarkers. Methods: We performed a post hoc analysis of 932 patients from the Target Temperature Management trial. We focused on comatose patients at 24, 48, and 72 h post-cardiac arrest and excluded patients... (More)

Background: Prognostication of neurological outcome in patients who remain comatose after cardiac arrest resuscitation is complex. Clinical variables, as well as biomarkers of brain injury, cardiac injury, and systemic inflammation, all yield some prognostic value. We hypothesised that cumulative information obtained during the first three days of intensive care could produce a reliable model for predicting neurological outcome following out-of-hospital cardiac arrest (OHCA) using artificial neural network (ANN) with and without biomarkers. Methods: We performed a post hoc analysis of 932 patients from the Target Temperature Management trial. We focused on comatose patients at 24, 48, and 72 h post-cardiac arrest and excluded patients who were awake or deceased at these time points. 80% of the patients were allocated for model development (training set) and 20% for internal validation (test set). To investigate the prognostic potential of different levels of biomarkers (clinically available and research-grade), patients’ background information, and intensive care observation and treatment, we created three models for each time point: (1) clinical variables, (2) adding clinically accessible biomarkers, e.g., neuron-specific enolase (NSE) and (3) adding research-grade biomarkers, e.g., neurofilament light (NFL). Patient outcome was the dichotomised Cerebral Performance Category (CPC) at six months; a good outcome was defined as CPC 1–2 whilst a poor outcome was defined as CPC 3–5. The area under the receiver operating characteristic curve (AUROC) was calculated for all test sets. Results: AUROC remained below 90% when using only clinical variables throughout the first three days in the ICU. Adding clinically accessible biomarkers such as NSE, AUROC increased from 82 to 94% (p < 0.01). The prognostic accuracy remained excellent from day 1 to day 3 with an AUROC at approximately 95% when adding research-grade biomarkers. The models which included NSE after 72 h and NFL on any of the three days had a low risk of false-positive predictions while retaining a low number of false-negative predictions. Conclusions: In this exploratory study, ANNs provided good to excellent prognostic accuracy in predicting neurological outcome in comatose patients post OHCA. The models which included NSE after 72 h and NFL on all days showed promising prognostic performance.

(Less)
Please use this url to cite or link to this publication:
author
; ; ; ; ; ; ; ; and , et al. (More)
; ; ; ; ; ; ; ; ; ; ; ; ; ; and (Less)
organization
publishing date
type
Contribution to journal
publication status
published
subject
keywords
Artificial intelligence, Artificial neural networks, Cardiac arrest, Cerebral performance category, Critical care, Intensive care, Machine learning, Neural networks, Out-of-hospital cardiac arrest, Prediction, Prognostication
in
Critical Care
volume
25
issue
1
article number
83
publisher
BioMed Central (BMC)
external identifiers
  • scopus:85101674034
  • pmid:33632280
ISSN
1364-8535
DOI
10.1186/s13054-021-03505-9
language
English
LU publication?
yes
id
ab6cec9b-a928-41d0-bf49-3db077d63cd6
date added to LUP
2021-03-11 15:00:40
date last changed
2024-03-05 23:12:34
@article{ab6cec9b-a928-41d0-bf49-3db077d63cd6,
  abstract     = {{<p>Background: Prognostication of neurological outcome in patients who remain comatose after cardiac arrest resuscitation is complex. Clinical variables, as well as biomarkers of brain injury, cardiac injury, and systemic inflammation, all yield some prognostic value. We hypothesised that cumulative information obtained during the first three days of intensive care could produce a reliable model for predicting neurological outcome following out-of-hospital cardiac arrest (OHCA) using artificial neural network (ANN) with and without biomarkers. Methods: We performed a post hoc analysis of 932 patients from the Target Temperature Management trial. We focused on comatose patients at 24, 48, and 72 h post-cardiac arrest and excluded patients who were awake or deceased at these time points. 80% of the patients were allocated for model development (training set) and 20% for internal validation (test set). To investigate the prognostic potential of different levels of biomarkers (clinically available and research-grade), patients’ background information, and intensive care observation and treatment, we created three models for each time point: (1) clinical variables, (2) adding clinically accessible biomarkers, e.g., neuron-specific enolase (NSE) and (3) adding research-grade biomarkers, e.g., neurofilament light (NFL). Patient outcome was the dichotomised Cerebral Performance Category (CPC) at six months; a good outcome was defined as CPC 1–2 whilst a poor outcome was defined as CPC 3–5. The area under the receiver operating characteristic curve (AUROC) was calculated for all test sets. Results: AUROC remained below 90% when using only clinical variables throughout the first three days in the ICU. Adding clinically accessible biomarkers such as NSE, AUROC increased from 82 to 94% (p &lt; 0.01). The prognostic accuracy remained excellent from day 1 to day 3 with an AUROC at approximately 95% when adding research-grade biomarkers. The models which included NSE after 72 h and NFL on any of the three days had a low risk of false-positive predictions while retaining a low number of false-negative predictions. Conclusions: In this exploratory study, ANNs provided good to excellent prognostic accuracy in predicting neurological outcome in comatose patients post OHCA. The models which included NSE after 72 h and NFL on all days showed promising prognostic performance.</p>}},
  author       = {{Andersson, Peder and Johnsson, Jesper and Björnsson, Ola and Cronberg, Tobias and Hassager, Christian and Zetterberg, Henrik and Stammet, Pascal and Undén, Johan and Kjaergaard, Jesper and Friberg, Hans and Blennow, Kaj and Lilja, Gisela and Wise, Matt P. and Dankiewicz, Josef and Nielsen, Niklas and Frigyesi, Attila}},
  issn         = {{1364-8535}},
  keywords     = {{Artificial intelligence; Artificial neural networks; Cardiac arrest; Cerebral performance category; Critical care; Intensive care; Machine learning; Neural networks; Out-of-hospital cardiac arrest; Prediction; Prognostication}},
  language     = {{eng}},
  number       = {{1}},
  publisher    = {{BioMed Central (BMC)}},
  series       = {{Critical Care}},
  title        = {{Predicting neurological outcome after out-of-hospital cardiac arrest with cumulative information; development and internal validation of an artificial neural network algorithm}},
  url          = {{http://dx.doi.org/10.1186/s13054-021-03505-9}},
  doi          = {{10.1186/s13054-021-03505-9}},
  volume       = {{25}},
  year         = {{2021}},
}