An algorithm based on deep learning for predicting in-hospital cardiac arrest
Open accessAbstract
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.
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
These methods improve interpretability but may not fully represent the internal decision process, leading to discrepancies between explanations and model behaviour.
“These methods improve interpretability but may not fully represent the internal decision process, leading to discrepancies between explanations and model behaviour [37,24].”
From Artificial Intelligence in Clinical Decision-Making: A Comprehensive Review of Diagnostic, Prognostic, and Therapeutic Applications, Validation Gaps, Bias, and Deployment Challenges (2026) · cites this paper as [37]
The Discussion (page unavailable) describes deep learning as a black box and says the authors' DEWS model is not interpretable; interpretable deep learning is identified as future work. It does not assess whether interpretability methods faithfully represent a model's decision process or whether explanations diverge from model behaviour. Searches for explanation fidelity and discrepancies found no passage addressing that claim. (LLM, conf=0.76)
Experimental — accuracy not yet measured
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Cites
Hochreiter, S., & Schmidhuber, J. (1997) · Neural Computation · doi:10.1162/neco.1997.9.8.1735 · Cited by 102,318 · see citing works
Adam: A Method for Stochastic Optimization
Kingma, D. P., & Ba, J. (2014) · arXiv · doi:10.48550/arxiv.1412.6980 · Cited by 98,946 · see citing works
LeCun, Y., Bengio, Y., & Hinton, G. (2015) · Nature · doi:10.1038/nature14539 · Cited by 84,126 · see citing works
Representation Learning: A Review and New Perspectives
Bengio, Y., Courville, A., & Vincent, P. (2013) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2013.50 · Cited by 13,001 · see citing works
Heart Disease and Stroke Statistics—2017 Update: A Report From the American Heart Association
Benjamin, E. J., Blaha, M. J., Chiuve, S. E., Cushman, M., Das, S. R., Deo, R., de Ferranti, S. D., Floyd, J., Fornage, M., Gillespie, C., et al. (2017) · Circulation · doi:10.1161/cir.0000000000000485 · Cited by 12,591 · see citing works
Gulshan, V., Peng, L., Coram, M., Stumpe, M. C., Wu, D., Narayanaswamy, A., Venugopalan, S., Widner, K., Madams, T., Cuadros, J., et al. (2016) · JAMA · doi:10.1001/jama.2016.17216 · Cited by 7,697 · see citing works
Heart Disease and Stroke Statistics—2015 Update: A Report From the American Heart Association
Mozaffarian, D., Benjamin, E. J., Go, A. S., Arnett, D. K., Blaha, M. J., Cushman, M., de Ferranti, S., Després, J.-P., Fullerton, H. J., Howard, V. J., et al. (2015) · Circulation · doi:10.1161/cir.0000000000000152 · Cited by 5,797 · see citing works
Deo, R. C. (2015) · Circulation · doi:10.1161/circulationaha.115.001593 · Cited by 3,466 · see citing works
InfoGAN: Interpretable Representation Learning by Information Maximizing Generative Adversarial NetsPreprint
Chen, X., Duan, Y., Houthooft, R., Schulman, J., Sutskever, I., & Abbeel, P. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1606.03657 · Cited by 3,379 · see citing works
Validation of a modified Early Warning Score in medical admissions
Subbe, C. P. (2001) · QJM · doi:10.1093/qjmed/94.10.521 · Cited by 1,767 · see citing works
Introduction of the medical emergency team (MET) system: a cluster-randomised controlled trial
‡ (2005) · The Lancet · doi:10.1016/s0140-6736(05)66733-5 · Cited by 1,291 · see citing works
Nadkarni, V. (2006) · JAMA · doi:10.1001/jama.295.1.50 · Cited by 1,140 · see citing works
Nolan, J. P., Soar, J., Cariou, A., Cronberg, T., Moulaert, V. R. M., Deakin, C. D., Böttiger, B. W., Friberg, H., Sunde, K., & Sandroni, C. (2015) · Resuscitation · doi:10.1016/j.resuscitation.2015.07.018 · Cited by 1,111 · see citing works
Smith, G. B., Prytherch, D. R., Meredith, P., Schmidt, P. E., & Featherstone, P. I. (2013) · Resuscitation · doi:10.1016/j.resuscitation.2012.12.016 · Cited by 1,077 · see citing works
Clinical Antecedents to In-Hospital Cardiopulmonary Arrest
Schein, R. M. H., Hazday, N., Pena, M., Ruben, B. H., & Sprung, C. L. (1990) · CHEST Journal · doi:10.1378/chest.98.6.1388 · Cited by 902 · see citing works
Jones, D. A., DeVita, M. A., & Bellomo, R. (2011) · New England Journal of Medicine · doi:10.1056/nejmra0910926 · Cited by 791 · see citing works
Littmann, L., Bustin, D. J., & Haley, M. W. (2013) · Medical Principles and Practice · doi:10.1159/000354195 · Cited by 739 · see citing works
Kause, J., Smith, G. B., Prytherch, D. R., Parr, M. J., Flabouris, A., & Hillman, K. (2004) · Resuscitation · doi:10.1016/j.resuscitation.2004.05.016 · Cited by 664 · see citing works
Churpek, M. M., Yuen, T. C., Winslow, C., Meltzer, D. O., Kattan, M. W., & Edelson, D. P. (2016) · Critical Care Medicine · doi:10.1097/ccm.0000000000001571 · Cited by 638 · see citing works
Adapting to Artificial Intelligence: Radiologists and Pathologists as Information Specialists
Jha, S., & Topol, E. J. (2016) · JAMA · doi:10.1001/jama.2016.17438 · Cited by 622 · see citing works
Developing strategies to prevent inhospital cardiac arrest
Franklin, C. M., & Mathew, J. (1994) · Critical Care Medicine · doi:10.1097/00003246-199402000-00014 · Cited by 618 · see citing works
Leening, M. J. G., Vedder, M. M., Witteman, J. C. M., Pencina, M. J., & Steyerberg, E. W. (2014) · Annals of Internal Medicine · doi:10.7326/m13-1522 · Cited by 594 · see citing works
ViEWS—Towards a national early warning score for detecting adult inpatient deterioration
Prytherch, D. R., Smith, G. B., Schmidt, P. E., & Featherstone, P. I. (2010) · Resuscitation · doi:10.1016/j.resuscitation.2010.04.014 · Cited by 535 · see citing works
Taylor, R. A., Pare, J. R., Venkatesh, A. K., Mowafi, H. O., Melnick, E. R., Fleischman, W. M., & Hall, M. K. (2015) · Academic Emergency Medicine · doi:10.1111/acem.12876 · Cited by 496 · see citing works
The Supervised Learning No-Free-Lunch Theorems
Wolpert, D. H. (2002) · Springer eBooks · doi:10.1007/978-1-4471-0123-9_3 · Cited by 476 · see citing works
Gao, H., McDonnell, A., Harrison, D. A., Moore, T., Adam, S. K., Daly, K., Esmonde, L., Goldhill, D. R., Parry, G. J., Rashidian, A., et al. (2007) · Intensive Care Medicine · doi:10.1007/s00134-007-0532-3 · Cited by 466 · see citing works
Scaling Learning Algorithms toward AI
Bengio, Y., & LeCun, Y. (2007) · The MIT Press eBooks · doi:10.7551/mitpress/7496.003.0016 · Cited by 457 · see citing works
Subbe, C. P., Davies, R. G., Williams, E., Rutherford, P., & Gemmell, L. (2003) · Anaesthesia · doi:10.1046/j.1365-2044.2003.03258.x · Cited by 444 · see citing works
Incidence of treated cardiac arrest in hospitalized patients in the United States*
Merchant, R. M., Yang, L., Becker, L. B., Berg, R. A., Nadkarni, V., Nichol, G., Carr, B. G., Mitra, N., Bradley, S. M., Abella, B. S., et al. (2011) · Critical Care Medicine · doi:10.1097/ccm.0b013e3182257459 · Cited by 429 · see citing works
Ozenne, B., Subtil, F., & Maucort-Boulch, D. (2015) · Journal of Clinical Epidemiology · doi:10.1016/j.jclinepi.2015.02.010 · Cited by 379 · see citing works
Pirracchio, R., Petersen, M. L., Carone, M., Rigon, M. R., Chevret, S., & van der Laan, M. J. (2015) · The Lancet Respiratory Medicine · doi:10.1016/s2213-2600(14)70239-5 · Cited by 374 · see citing works
DeVita, M. A., Smith, G. B., Adam, S. K., Adams-Pizarro, I., Buist, M., Bellomo, R., Bonello, R. S., Cerchiari, E., Farlow, B., Goldsmith, D., et al. (2010) · Resuscitation · doi:10.1016/j.resuscitation.2009.12.008 · Cited by 366 · see citing works
Review and performance evaluation of aggregate weighted ‘track and trigger’ systems
Smith, G. B., Prytherch, D. R., Schmidt, P. E., & Featherstone, P. I. (2008) · Resuscitation · doi:10.1016/j.resuscitation.2007.12.004 · Cited by 338 · see citing works
Public Health Burden of Sudden Cardiac Death in the United States
Stecker, E. C., Reinier, K., Marijon, É., Narayanan, K., Teodorescu, C., Uy‐Evanado, A., Gunson, K., Jui, J., & Chugh, S. S. (2014) · Circulation Arrhythmia and Electrophysiology · doi:10.1161/circep.113.001034 · Cited by 335 · see citing works
Physiological abnormalities in early warning scores are related to mortality in adult inpatients †
Goldhill, D. R., & McNarry, A. F. (2004) · British Journal of Anaesthesia · doi:10.1093/bja/aeh113 · Cited by 324 · see citing works
Part 4: Systems of Care and Continuous Quality Improvement
Kronick, S. L., Kurz, M. C., Lin, S., Edelson, D. P., Berg, R. A., Billi, J. E., Cabañas, J. G., Cone, D. C., Diercks, D. B., Foster, J. (., et al. (2015) · Circulation · doi:10.1161/cir.0000000000000258 · Cited by 274 · see citing works
Reliability and accuracy of the Glasgow Coma Scale with experienced and inexperienced users
ROWLEY, G. L., & Fielding, K. (1991) · The Lancet · doi:10.1016/0140-6736(91)91309-i · Cited by 266 · see citing works
Strategies to improve cardiac arrest survival: a time to act
Shinozaki, K., Nonogi, H., Nagao, K., & Becker, L. B. (2016) · Acute Medicine & Surgery · doi:10.1002/ams2.192 · Cited by 236 · see citing works
A review, and performance evaluation, of single-parameter “track and trigger” systems
Smith, G. B., Prytherch, D. R., Schmidt, P. E., et al. (2008) · Resuscitation · doi:10.1016/j.resuscitation.2008.05.004 · Cited by 184 · see citing works
Documenting Rapid Response System afferent limb failure and associated patient outcomes
Trinkle, R. M., & Flabouris, A. (2011) · Resuscitation · doi:10.1016/j.resuscitation.2011.03.019 · Cited by 181 · see citing works
Prevalence and sensitivity of MET-criteria in a Scandinavian University Hospital
Bell, M. B., Konrad, D., Granath, F., Ekbom, A., & Martling, C.-R. (2006) · Resuscitation · doi:10.1016/j.resuscitation.2005.11.011 · Cited by 130 · see citing works
A new evaluation measure for imbalanced datasets
Weng, C. G., & Poon, J. (2008) · Cited by 88 · see citing works
Widely used track and trigger scores: Are they ready for automation in practice?
Brufau, S. R., Huddleston, J. M., Naessens, J. M., et al. (2014) · Resuscitation · doi:10.1016/j.resuscitation.2013.12.017 · Cited by 62 · see citing works
Readmission Rates and Long-Term Hospital Costs Among Survivors of an In-Hospital Cardiac Arrest
Chan, P. S., Nallamothu, B. K., Krumholz, H. M., et al. (2014) · Circulation Cardiovascular Quality and Outcomes · doi:10.1161/circoutcomes.114.000925 · Cited by 26 · see citing works
Suwanpasu, S., & Sattayasomboon, Y. (2016) · Journal of Intensive and Critical Care · doi:10.21767/2471-8505.100029 · Cited by 11 · see citing works
Reliability and accuracy of the Glasgow coma scale
Starmark, J.-E., Holmgren, E., Stålhammar, D., et al. (1991) · The Lancet · doi:10.1016/0140-6736(91)92705-7 · Cited by 10 · see citing works
Flagged first, then by citations
Research works printed but not linked: 1
- [45]Fong RC, Vedaldi A. Interpretable explanations of black boxes by meaningful perturbation. Proc IEEE Int Conf Comput Vis. 2017; 1: 3449– 3457.
Cited by
Sorted by citations
An overview of deep learning in medical imaging focusing on MRI
Lundervold, A. S., & Lundervold, A. (2019) · Zeitschrift für Medizinische Physik · doi:10.1016/j.zemedi.2018.11.002 · Cited by 2,058 · see citing works
Deep-learning-based risk stratification for mortality of patients with acute myocardial infarction
Kwon, J.-M., Jeon, K.-H., Kim, H. M., Kim, M. J., Lim, S., Kim, K.-H., Song, P. S., Park, J., Choi, R. K., & Oh, B.-H. (2019) · PLOS ONE · doi:10.1371/journal.pone.0224502 · Cited by 86 · see citing works
Self-citationVarma, N., Cygankiewicz, I., Turakhia, M. P., Heidbuchel, H., Hu, Y.-F., Chen, L. Y., Couderc, J.-P., Cronin, E. M., Estep, J. D., Grieten, L., et al. (2021) · Circulation: Arrhythmia and Electrophysiology · doi:10.1161/circep.120.009204 · Cited by 74 · see citing works
Wang, Y., Gao, Z., Zhang, Y., Lu, Z., & Sun, F. (2025) · Internal and Emergency Medicine · doi:10.1007/s11739-024-03732-2 · Cited by 29 · see citing works
Patil, S. S., Jha, G. K., Mohsin, N., Patel, P., Ralte, L., & Shukla, A. K. (2026) · Cureus · doi:10.7759/cureus.109905
- Authors
- Kwon, J., Lee, Y., Lee, Y., Lee, S., & Park, J.
- Affiliations
- Department of Emergency Medicine Mediplex Sejong Hospital Incheon Korea
- VUNO Seoul Korea
- Department of Cardiology Mediplex Sejong Hospital Incheon Korea
- Corresponding author
- Kwon, Joon‐myoung
- Venue
- Journal of the American Heart Association
- Published
- 2018-07-03
- Volume
- 7
- Issue
- 13
- ISSN
- 2047-9980 (ISSN-L)
- PMC
- PMC6064911
- OpenAlex
- W2811095531
- Cited by
- 299
- References
- 46
- Citations by year
- 2026: 23 · 2025: 30 · 2024: 41 · 2023: 45 · 2022: 36 · 2021: 58 · 2020: 33 · 2019: 25 · 2018: 8
- FWCI
- 37.87
- Type
- journal article
- Language
- en
- Open access
- gold
- doi.org
- Licence
- cc-by-nc
- Locations
- Journal of the American Heart Association (publishedVersion, cc-by-nc)
- Europe PMC (PubMed Central) (publishedVersion, cc-by-nc)
- PubMed Central (publishedVersion, cc-by-nc)
- PubMed (publishedVersion)
- DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion)
- Topics
- Health Sciences › Medicine › Emergency Medicine › Cardiac Arrest and Resuscitation
- Physical Sciences › Computer Science › Artificial Intelligence › Machine Learning in Healthcare
- Health Sciences › Medicine › Surgery › Healthcare Technology and Patient Monitoring
- Keywords
- in-hospital cardiac arrest, early warning systems, deep learning, recurrent neural networks, track and trigger systems, Modified Early Warning Score, false alarm rate, hospital patient safety, risk prediction
- MeSH terms
- Deep Learning, Adult, Aged, Decision Support Techniques, Diagnosis, Computer-Assisted, Female, Heart Arrest, Humans, Inpatients, Male, Middle Aged, Predictive Value of Tests, Prognosis, Resuscitation, Retrospective Studies, Risk Factors, Time Factors, Reproducibility of Results, Risk Assessment, Early Diagnosis, Vital Signs, Seoul
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
