Artificial neural networks improve and simplify intensive care mortality prognostication: a national cohort study of 217,289 first-time intensive care unit admissions

Gustav Holmgren; Peder Andersson; Andreas Jakobsson; Attila Frigyesi

doi:10.1186/s40560-019-0393-1

Artificial neural networks improve and simplify intensive care mortality prognostication: a national cohort study of 217,289 first-time intensive care unit admissions

J Intensive Care. 2019 Aug 16:7:44. doi: 10.1186/s40560-019-0393-1. eCollection 2019.

Authors

Gustav Holmgren¹, Peder Andersson^{2

3}, Andreas Jakobsson¹, Attila Frigyesi^{1

2

3}

Affiliations

¹ 1Centre for Mathematical Sciences, Mathematical Statistics, Lund University, Sölvegatan 18, Lund, SE-22362 Sweden.
² 2Department of Clinical Medicine, Anaesthesiology and Intensive Care, Lund University, Lund, SE-22185 Sweden.
³ 3Skåne University Hospital, Intensive and Perioperative Care, Lund, SE-22185 Sweden.

Abstract

Purpose: We investigated if early intensive care unit (ICU) scoring with the Simplified Acute Physiology Score (SAPS 3) could be improved using artificial neural networks (ANNs).

Methods: All first-time adult intensive care admissions in Sweden during 2009-2017 were included. A test set was set aside for validation. We trained ANNs with two hidden layers with random hyper-parameters and retained the best ANN, determined using cross-validation. The ANNs were constructed using the same parameters as in the SAPS 3 model. The performance was assessed with the area under the receiver operating characteristic curve (AUC) and Brier score.

Results: A total of 217,289 admissions were included. The developed ANN (AUC 0.89 and Brier score 0.096) was found to be superior (p <10^-15 for AUC and p <10^-5 for Brier score) in early prediction of 30-day mortality for intensive care patients when compared with SAPS 3 (AUC 0.85 and Brier score 0.109). In addition, a simple, eight-parameter ANN model was found to perform just as well as SAPS 3, but with better calibration (AUC 0.85 and and Brier score 0.106, p <10^-5). Furthermore, the ANN model was superior in correcting mortality for age.

Conclusion: ANNs can outperform the SAPS 3 model for early prediction of 30-day mortality for intensive care patients.

Keywords: Artificial intelligence; Artificial neural networks; Critical care; Intensive care; Machine learning; Mortality; Prediction; Survival.