Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
Multicenter Study
. 2018 Jun 26;7(13):e008678.
doi: 10.1161/JAHA.118.008678.

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

Joon-Myoung Kwon  1 , Youngnam Lee  2 , Yeha Lee  2 , Seungwoo Lee  2 , Jinsik Park  3
Affiliations
Multicenter Study

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

Joon-Myoung Kwon et al. J Am Heart Assoc. .

Abstract

Background: In-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 results: This 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.

Conclusions: An 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.

Keywords: artificial intelligence; cardiac arrest; deep learning; machine learning; rapid response system; resuscitation.

PubMed Disclaimer

Figures

Figure 1
Figure 1
The process of the DEWS. DEWS indicates deep learning–based early warning system; HR, heart rate; RNN, recurrent neural network; RR, respiratory rate; SBP, systolic blood pressure; BT, body temperature.
Figure 2
Figure 2
The architecture of the recurrent neural network. X t and h t indicate input and output at time t; W, weights.
Figure 3
Figure 3
Study flow chart. DEWS indicates deep learning–based early warning system.
Figure 4
Figure 4
Accuracy for predicting in‐hospital cardiac arrest and death without attempted resuscitation. AUPRC indicates area under the precision–recall curve; AUROC, area under the receiver operating characteristic curve; CI, confidence interval; DEWS, deep learning–based early warning system; MEWS, modified early warning score; SPTTS, single‐parameter track‐and‐trigger system.
Figure 5
Figure 5
Sensitivity according to MACHP for predicting in‐hospital cardiac arrest. DEWS indicates deep learning–based early warning system; MACHP, mean alarm count per hour per patient; MEWS, modified early warning score; SPTTS, single‐parameter track‐and‐trigger system; TTS, track‐and‐trigger system.
Figure 6
Figure 6
Trend of the DEWS score. A, The change in the mean of the DEWS scores over time as a group of patients. B, Cumulative percentage of cardiac arrest patients on detection time before event. We used the DEWS with sensitivity 70% for this plot. DEWS indicates deep learning–based early warning system.
See this image and copyright information in PMC

References

    1. Graham R, McCoy MA, Schultz AM; Committee on the Treatment of Cardiac Arrest: Current Status and Future Directions; Board on Health Sciences Policy; Institute of Medicine Strategies to Improve Cardiac Arrest Survival: A Time to Act. Washington, DC: National Academic Press; 2015. - PubMed
    1. Chan PS, Nallamothu BK, Krumholz HM, Curtis LH, Li Y, Hammill BG, Spertus JA. Readmission rates and long‐term hospital costs among survivors of an in‐hospital cardiac arrest. Circ Cardiovasc Qual Outcomes. 2014;7:889–895. - PMC - PubMed
    1. Stecker EC, Reinier K, Marijon E, Narayanan K, Teodorescu C, Uy‐Evanado A, Gunson K, Jui J, Chugh SS. Public health burden of sudden cardiac death in the United States. Circ Arrhythm Electrophysiol. 2014;7:212–217. - PMC - PubMed
    1. Benjamin EJ, Blaha MJ, Chiuve SE, Cushman M, Das SR, Deo R, De Ferranti SD, Floyd J, Fornage M, Gillespie C, Isasi CR, Jim'nez MC, Jordan LC, Judd SE, Lackland D, Lichtman JH, Lisabeth L, Liu S, Longenecker CT, MacKey RH, Matsushita K, Mozaffarian D, Mussolino ME, Nasir K, Neumar RW, Palaniappan L, Pandey DK, Thiagarajan RR, Reeves MJ, Ritchey M, Rodriguez CJ, Roth GA, Rosamond WD, Sasson C, Towfghi A, Tsao CW, Turner MB, Virani SS, Voeks JH, Willey JZ, Wilkins JT, Wu JHY, Alger HM, Wong SS, Muntner P. Heart disease and stroke statistics—2017 update: a report from the American Heart Association. Circulation. 2017; 135:e146–e603. - PMC - PubMed
    1. Nadkarni VM. First documented rhythm and clinical outcome from in‐hospital cardiac arrest among children and adults. JAMA. 2006;295:50. - PubMed

Publication types

MeSH terms