Artificial neural networks improve early outcome prediction and risk classification in out-of-hospital cardiac arrest patients admitted to intensive care
Johnsson, Jesper LU ; Björnsson, Ola LU ; Andersson, Peder LU
; Jakobsson, Andreas
LU
; Cronberg, Tobias
LU
; Lilja, Gisela
LU
; Friberg, Hans
LU
; Hassager, Christian
; Kjaergard, Jesper
and Wise, Matt
, et al.
(2020)
In Critical Care
24(1).
- Abstract
BACKGROUND: Pre-hospital circumstances, cardiac arrest characteristics, comorbidities and clinical status on admission are strongly associated with outcome after out-of-hospital cardiac arrest (OHCA). Early prediction of outcome may inform prognosis, tailor therapy and help in interpreting the intervention effect in heterogenous clinical trials. This study aimed to create a model for early prediction of outcome by artificial neural networks (ANN) and use this model to investigate intervention effects on classes of illness severity in cardiac arrest patients treated with targeted temperature management (TTM). METHODS: Using the cohort of the TTM trial, we performed a post hoc analysis of 932 unconscious patients from 36 centres with OHCA... (More)
BACKGROUND: Pre-hospital circumstances, cardiac arrest characteristics, comorbidities and clinical status on admission are strongly associated with outcome after out-of-hospital cardiac arrest (OHCA). Early prediction of outcome may inform prognosis, tailor therapy and help in interpreting the intervention effect in heterogenous clinical trials. This study aimed to create a model for early prediction of outcome by artificial neural networks (ANN) and use this model to investigate intervention effects on classes of illness severity in cardiac arrest patients treated with targeted temperature management (TTM). METHODS: Using the cohort of the TTM trial, we performed a post hoc analysis of 932 unconscious patients from 36 centres with OHCA of a presumed cardiac cause. The patient outcome was the functional outcome, including survival at 180 days follow-up using a dichotomised Cerebral Performance Category (CPC) scale with good functional outcome defined as CPC 1-2 and poor functional outcome defined as CPC 3-5. Outcome prediction and severity class assignment were performed using a supervised machine learning model based on ANN. RESULTS: The outcome was predicted with an area under the receiver operating characteristic curve (AUC) of 0.891 using 54 clinical variables available on admission to hospital, categorised as background, pre-hospital and admission data. Corresponding models using background, pre-hospital or admission variables separately had inferior prediction performance. When comparing the ANN model with a logistic regression-based model on the same cohort, the ANN model performed significantly better (p = 0.029). A simplified ANN model showed promising performance with an AUC above 0.852 when using three variables only: age, time to ROSC and first monitored rhythm. The ANN-stratified analyses showed similar intervention effect of TTM to 33 °C or 36 °C in predefined classes with different risk of a poor outcome. CONCLUSION: A supervised machine learning model using ANN predicted neurological recovery, including survival excellently, and outperformed a conventional model based on logistic regression. Among the data available at the time of hospitalisation, factors related to the pre-hospital setting carried most information. ANN may be used to stratify a heterogenous trial population in risk classes and help determine intervention effects across subgroups.
(Less)
- author
- Johnsson, Jesper
LU
; Björnsson, Ola
LU
; Andersson, Peder
LU
; Jakobsson, Andreas
LU
; Cronberg, Tobias
LU
; Lilja, Gisela
LU
; Friberg, Hans
LU
; Hassager, Christian
; Kjaergard, Jesper
and Wise, Matt
, et al. (More)
- Johnsson, Jesper
LU
; Björnsson, Ola
LU
; Andersson, Peder
LU
; Jakobsson, Andreas
LU
; Cronberg, Tobias
LU
; Lilja, Gisela
LU
; Friberg, Hans
LU
; Hassager, Christian
; Kjaergard, Jesper
; Wise, Matt
; Nielsen, Niklas
LU
and Frigyesi, Attila
LU
(Less)
- organization
- publishing date
- 2020
- type
- Contribution to journal
- publication status
- published
- subject
- keywords
- Artificial intelligence, Artificial neural networks, Cerebral performance category, Critical care, Intensive care, Machine learning, Out-of-hospital cardiac arrest, Prediction, Prognostication
- in
- Critical Care
- volume
- 24
- issue
- 1
- article number
- 474
- publisher
- BioMed Central (BMC)
- external identifiers
-
- scopus:85088908579
- pmid:32731878
- ISSN
- 1364-8535
- DOI
- 10.1186/s13054-020-03103-1
- language
- English
- LU publication?
- yes
- id
- 06f514e0-fb80-47f9-866c-d30be699549a
- date added to LUP
- 2020-08-13 09:00:35
- date last changed
- 2024-05-15 16:02:12
@article{06f514e0-fb80-47f9-866c-d30be699549a,
abstract = {{<p>BACKGROUND: Pre-hospital circumstances, cardiac arrest characteristics, comorbidities and clinical status on admission are strongly associated with outcome after out-of-hospital cardiac arrest (OHCA). Early prediction of outcome may inform prognosis, tailor therapy and help in interpreting the intervention effect in heterogenous clinical trials. This study aimed to create a model for early prediction of outcome by artificial neural networks (ANN) and use this model to investigate intervention effects on classes of illness severity in cardiac arrest patients treated with targeted temperature management (TTM). METHODS: Using the cohort of the TTM trial, we performed a post hoc analysis of 932 unconscious patients from 36 centres with OHCA of a presumed cardiac cause. The patient outcome was the functional outcome, including survival at 180 days follow-up using a dichotomised Cerebral Performance Category (CPC) scale with good functional outcome defined as CPC 1-2 and poor functional outcome defined as CPC 3-5. Outcome prediction and severity class assignment were performed using a supervised machine learning model based on ANN. RESULTS: The outcome was predicted with an area under the receiver operating characteristic curve (AUC) of 0.891 using 54 clinical variables available on admission to hospital, categorised as background, pre-hospital and admission data. Corresponding models using background, pre-hospital or admission variables separately had inferior prediction performance. When comparing the ANN model with a logistic regression-based model on the same cohort, the ANN model performed significantly better (p = 0.029). A simplified ANN model showed promising performance with an AUC above 0.852 when using three variables only: age, time to ROSC and first monitored rhythm. The ANN-stratified analyses showed similar intervention effect of TTM to 33 °C or 36 °C in predefined classes with different risk of a poor outcome. CONCLUSION: A supervised machine learning model using ANN predicted neurological recovery, including survival excellently, and outperformed a conventional model based on logistic regression. Among the data available at the time of hospitalisation, factors related to the pre-hospital setting carried most information. ANN may be used to stratify a heterogenous trial population in risk classes and help determine intervention effects across subgroups.</p>}},
author = {{Johnsson, Jesper and Björnsson, Ola and Andersson, Peder and Jakobsson, Andreas and Cronberg, Tobias and Lilja, Gisela and Friberg, Hans and Hassager, Christian and Kjaergard, Jesper and Wise, Matt and Nielsen, Niklas and Frigyesi, Attila}},
issn = {{1364-8535}},
keywords = {{Artificial intelligence; Artificial neural networks; Cerebral performance category; Critical care; Intensive care; Machine learning; Out-of-hospital cardiac arrest; Prediction; Prognostication}},
language = {{eng}},
number = {{1}},
publisher = {{BioMed Central (BMC)}},
series = {{Critical Care}},
title = {{Artificial neural networks improve early outcome prediction and risk classification in out-of-hospital cardiac arrest patients admitted to intensive care}},
url = {{http://dx.doi.org/10.1186/s13054-020-03103-1}},
doi = {{10.1186/s13054-020-03103-1}},
volume = {{24}},
year = {{2020}},
}