An Algorithm Based on Deep Learning for Predicting In‐Hospital Cardiac Arrest

Abstract

BackgroundIn‐hospital cardiac arrest is a major burden to public health, which affects patient safety. Although traditional track‐and‐trigger systems are used to predict cardiac arrest early, they have limitations, with low sensitivity and high false‐alarm rates. We propose a deep learning–based early warning system that shows higher performance than the existing track‐and‐trigger systems.Methods and ResultsThis retrospective cohort study reviewed patients who were admitted to 2 hospitals from June 2010 to July 2017. A total of 52 131 patients were included. Specifically, a recurrent neural network was trained using data from June 2010 to January 2017. The result was tested using the data from February to July 2017. The primary outcome was cardiac arrest, and the secondary outcome was death without attempted resuscitation. As comparative measures, we used the area under the receiver operating characteristic curve (AUROC), the area under the precision–recall curve (AUPRC), and the net reclassification index. Furthermore, we evaluated sensitivity while varying the number of alarms. The deep learning–based early warning system (AUROC: 0.850; AUPRC: 0.044) significantly outperformed a modified early warning score (AUROC: 0.603; AUPRC: 0.003), a random forest algorithm (AUROC: 0.780; AUPRC: 0.014), and logistic regression (AUROC: 0.613; AUPRC: 0.007). Furthermore, the deep learning–based early warning system reduced the number of alarms by 82.2%, 13.5%, and 42.1% compared with the modified early warning system, random forest, and logistic regression, respectively, at the same sensitivity.ConclusionsAn algorithm based on deep learning had high sensitivity and a low false‐alarm rate for detection of patients with cardiac arrest in the multicenter study.

An overview of deep learning in medical imaging focusing on MRI

“…ii) Activation layer: The feature maps from a convolutional layer are fed through nonlinear activation functions. This makes it possible for the entire neural network to approximate almost any nonlinear function [48,49] 19 The activation functions are generally the very simple rectified linear units, or ReLUs, defined as ReLU(z) = max(0, z), or variants like leaky ReLUs or parametric ReLUs. 20 See [60,61] for more information about these and other activation functions.…”

“…Healthcare applications of deep learning range from one-dimensional biosignal analysis [17] and the prediction of medical events, e.g. seizures [18] and cardiac arrests [19], to computer-aided detection [20] and diagnosis [21] supporting clinical decision making and survival analysis [22], to drug discovery [23] and as an aid in therapy selection and pharmacogenomics [24], to increased operational efficiency [25], stratified care delivery [26], and analysis of electronic health records [27,28].…”

Deep learning for predicting in‐hospital mortality among heart disease patients based on echocardiography

“…9 This is also why DL shows better results than traditional machine learning in several domains such as vision and prediction. 10,11 As DL and machine learning are not derived from medical knowledge-based rules but the relationship between the given data and results, the models memorize the characteristics of the derivation data. Due to this, the performances of prediction models are not guaranteed in other situations without external validation.…”

“…Because echocardiography is a non-invasive bedside examination whose results can be confirmed immediately, prediction models based on only echocardiography results will be helpful in the clinical setting. 10,11 To the best of our knowledge, this study is the first to predict mortality risk based on echocardiography results using DL. 9 Recently, DL has achieved state-of-the-art performance in several domains, including medical imaging and prognosis prediction.…”

“…9 Recently, DL has achieved state-of-the-art performance in several domains, including medical imaging and prognosis prediction. 10,11 To the best of our knowledge, this study is the first to predict mortality risk based on echocardiography results using DL.…”