Highlights
- •The study established highly-accurate artificial neural network models to predict outcomes of in-hospital cardiac arrest.
- •The predicting model achieved area under the curve of 0.997, with sensitivity of 100% and specificity of 94.0%.
- •The key factors associated with outcomes after in-hospital cardiac arrest were identified using artificial neural networks.
- •Predictions with identified parameters achieved reliable performance for patients received targeted temperature management.
- •These models can be of clinical value in assisting with decision-making regarding optimal postresuscitation strategies.
Abstract
Background
Accurate estimation of neurological outcomes after in-hospital cardiac arrest (IHCA)
provides crucial information for clinical management. This study used artificial neural
networks (ANNs) to determine the prognostic factors and develop prediction models
for IHCA based on immediate preresuscitation parameters.
Methods
The derived cohort comprised 796 patients with IHCA between 2006 and 2014. We applied
ANNs to develop prediction models and evaluated the significance of each parameter
associated with favorable neurological outcomes. An independent dataset of 108 IHCA
patients receiving targeted temperature management was used to validate the identified
parameters. The generalizability of the models was assessed through fivefold cross-validation.
The performance of the models was assessed using the area under the curve (AUC).
Results
ANN model 1, based on 19 baseline parameters, and model 2, based on 11 prearrest parameters,
achieved validation AUCs of 0.978 and 0.947, respectively. ANN model 3 based on 30
baseline and prearrest parameters achieved an AUC of 0.997. The key factors associated
with favorable outcomes were the duration of cardiopulmonary resuscitation; initial
cardiac arrest rhythm; arrest location; and whether the patient had a malignant disease,
pneumonia, and respiratory insufficiency. On the basis of these parameters, the validation
performance of the ANN models achieved an AUC of 0.906 for IHCA patients who received
targeted temperature management.
Conclusion
The ANN models achieved highly accurate and reliable performance for predicting the
neurological outcomes of successfully resuscitated patients with IHCA. These models
can be of significant clinical value in assisting with decision-making, especially
regarding optimal postresuscitation strategies.
Keywords
To read this article in full you will need to make a payment
Purchase one-time access:
Academic & Personal: 24 hour online accessCorporate R&D Professionals: 24 hour online accessOne-time access price info
- For academic or personal research use, select 'Academic and Personal'
- For corporate R&D use, select 'Corporate R&D Professionals'
Subscribe:
Subscribe to Journal of the Neurological SciencesAlready a print subscriber? Claim online access
Already an online subscriber? Sign in
Register: Create an account
Institutional Access: Sign in to ScienceDirect
References
- Heart disease and stroke statistics-2019 update: a report from the American Heart Association.Circulation. 2019; 139: e56-e528
- One-year survival after in-hospital cardiac arrest: a systematic review and meta-analysis.Resuscitation. 2018; 132: 90-100
- A validated prediction tool for initial survivors of in-hospital cardiac arrest.Arch. Intern. Med. 2012; 172: 947-953
- Predictors of favourable outcome after in-hospital cardiac arrest treated with extracorporeal cardiopulmonary resuscitation: a systematic review and meta-analysis.Resuscitation. 2017; 121: 62-70
- Validation of the Cardiac Arrest Survival Postresuscitation In-hospital (CASPRI) score in an East Asian population.PLoS One. 2018; 13e0202938
- Artificial neural networks in medical diagnosis.J. Appl. Biomed. 2013; 11: 47-58
- Basic concepts of artificial neural network (ANN) modeling and its application in pharmaceutical research.J. Pharm. Biomed. Anal. 2000; 22: 717-727
- Primary outcomes for resuscitation science studies: a consensus statement from the American Heart Association.Circulation. 2011; 124: 2158-2177
- Post-cardiac arrest care and targeted temperature management: a consensus of scientific statement from the Taiwan Society of Emergency & Critical Care Medicine, Taiwan Society of Critical Care Medicine and Taiwan Society of Emergency Medicine.J. Formosan Med. Assoc. 2020; 120: 569-587
- Learning from imbalanced data.IEEE Trans. Knowl. Data Eng. 2009; 21: 1263-1284
- Ensemble based adaptive over-sampling method for imbalanced data learning in computer aided detection of microaneurysm.Comput. Med. Imag. Graph. 2017; 55: 54-67
- Global sensitivity indices for nonlinear mathematical models and their Monte Carlo estimates.Math. Comput. Simulat. 2001; 55: 271-280
- Making best use of model evaluations to compute sensitivity indices.Comput. Phys. Commun. 2002; 145: 280-297
- Development and validation of the Good Outcome Following Attempted Resuscitation (GO-FAR) score to predict neurologically intact survival after in-hospital cardiopulmonary resuscitation.JAMA Intern. Med. 2013; 173: 1872-1878
- Validation of the Good Outcome Following Attempted Resuscitation (GO-FAR) score in an East Asian population.Resuscitation. 2020; 150: 36-40
- Duration of resuscitation efforts and survival after in-hospital cardiac arrest: an observational study.Lancet (London, England). 2012; 380: 1473-1481
- In-hospital cardiac arrest: a review.Jama. 2019; 321: 1200-1210
- Predictors of survival and neurologic outcome for adults with extracorporeal cardiopulmonary resuscitation: a systemic review and meta-analysis.Medicine. 2018; 97e13257
- First documented rhythm and clinical outcome from in-hospital cardiac arrest among children and adults.Jama. 2006; 295: 50-57
- Artificial intelligence in healthcare: past, present and future.Stroke Vasc. Neurol. 2017; 2: 230-243
- Predicting major neurologic improvement and long-term outcome after thrombolysis using artificial neural networks.J. Neurol. Sci. 2020; 410: 116667
- Artificial neural network-based analysis of the safety and efficacy of thrombolysis for ischemic stroke in older adults in Taiwan.Neurol. Asia. 2020; 25: 109-117
- Rapid response systems.Resuscitation. 2018; 128: 191-197
- Post-resuscitation care following out-of-hospital and in-hospital cardiac arrest.Heart. 2015; 101: 1943-1949
- Racial disparities in outcomes following PEA and asystole in-hospital cardiac arrests.Resuscitation. 2015; 87: 69-74
Article info
Publication history
Published online: April 12, 2021
Accepted:
April 9,
2021
Received in revised form:
March 25,
2021
Received:
January 7,
2021
Identification
Copyright
© 2021 Elsevier B.V. All rights reserved.
