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

Research output: Contribution to journalArticle

Standard

Harvard

APA

CBE

MLA

Vancouver

Author

RIS

TY - JOUR

T1 - Predicting neurological outcome after out-of-hospital cardiac arrest with cumulative information; development and internal validation of an artificial neural network algorithm

AU - Andersson, Peder

AU - Johnsson, Jesper

AU - Björnsson, Ola

AU - Cronberg, Tobias

AU - Hassager, Christian

AU - Zetterberg, Henrik

AU - Stammet, Pascal

AU - Undén, Johan

AU - Kjaergaard, Jesper

AU - Friberg, Hans

AU - Blennow, Kaj

AU - Lilja, Gisela

AU - Wise, Matt P.

AU - Dankiewicz, Josef

AU - Nielsen, Niklas

AU - Frigyesi, Attila

PY - 2021

Y1 - 2021

N2 - 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.

AB - 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.

KW - Artificial intelligence

KW - Artificial neural networks

KW - Cardiac arrest

KW - Cerebral performance category

KW - Critical care

KW - Intensive care

KW - Machine learning

KW - Neural networks

KW - Out-of-hospital cardiac arrest

KW - Prediction

KW - Prognostication

U2 - 10.1186/s13054-021-03505-9

DO - 10.1186/s13054-021-03505-9

M3 - Article

C2 - 33632280

AN - SCOPUS:85101674034

VL - 25

JO - Critical Care

JF - Critical Care

SN - 1364-8535

IS - 1

M1 - 83

ER -