CoChat
Sign Up
Cited by 109ECG Monitoring and AnalysisMachine Learning in HealthcarePotassium and Related Disorders

A Deep-Learning Algorithm (ECG12Net) for Detecting Hypokalemia and Hyperkalemia by Electrocardiography: Algorithm Development

Open access
Lin, Chin-Sheng, Lin, Chin, Fang, Wen-Hui, Hsu, Chia-Jung, Chen, Sy-Jou, Huang, Kuo-Hua, Lin, Wei-Shiang, Tsai, Chien-Sung +4 more·2020·JMIR Medical Informatics
DOI 10.2196/15931PMC PMC7082733
Open this paper in CoChat — free account

Abstract

BACKGROUND: The detection of dyskalemias-hypokalemia and hyperkalemia-currently depends on laboratory tests. Since cardiac tissue is very sensitive to dyskalemia, electrocardiography (ECG) may be able to uncover clinically important dyskalemias before laboratory results. OBJECTIVE: Our study aimed to develop a deep-learning model, ECG12Net, to detect dyskalemias based on ECG presentations and to evaluate the logic and performance of this model. METHODS: concentration. Six clinicians-three emergency physicians and three cardiologists-participated in human-machine competition. Sensitivity, specificity, and balance accuracy were used to evaluate the performance of ECG12Net with that of these physicians. RESULTS: In a human-machine competition including 300 ECGs of different serum K+ concentrations, the area under the curve for detecting hypokalemia and hyperkalemia with ECG12Net was 0.926 and 0.958, respectively, which was significantly better than that of our best clinicians. Moreover, in detecting hypokalemia and hyperkalemia, the sensitivities were 96.7% and 83.3%, respectively, and the specificities were 93.3% and 97.8%, respectively. In a test set including 13,222 ECGs, ECG12Net had a similar performance in terms of sensitivity for severe hypokalemia (95.6%) and severe hyperkalemia (84.5%), with a mean absolute error of 0.531. The specificities for detecting hypokalemia and hyperkalemia were 81.6% and 96.0%, respectively. CONCLUSIONS: A deep-learning model based on a 12-lead ECG may help physicians promptly recognize severe dyskalemias and thereby potentially reduce cardiac events.

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.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.2196/15931

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.

A few free checks a day · papers already verified open instantly · results are public

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?

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

The citation lists haven’t been fetched yet

References 44 · Cited by 109

Research works printed but not linked: 37

  1. [1]No authors listed Editorial: Slow-K, quick quick, slow Lancet 1974 11 09 2 7889 1123 1124 4139417 4139417
  2. [2]Priori SG Blomström-Lundqvist C Mazzanti A Blom N Borggrefe M Camm J Elliott PM Fitzsimons D Hatala R Hindricks G Kirchhof P Kjeldsen K Kuck K Hernandez-Madrid A Nikolaou N Norekvål TM Spaulding C Van Veldhuisen DJ ESC Scientific Document Group 2015 ESC Guidelines for the management of patients with ventricular arrhythmias and the prevention of sudden cardiac death: The Task Force for the Management of Patients with Ventricular Arrhythmias and the Prevention of Sudden Cardiac Death of the European Society of Cardiology (ESC). Endorsed by: Association for European Paediatric and Congenital Cardiology (AEPC) Eur Heart J 2015 11 01 36 41 2793 2867 10.1093/eurheartj/ehv316 26320108 26320108 · DOI · Paper page
  3. [3]Gavala A Myrianthefs P Comparison of point-of-care versus central laboratory measurement of hematocrit, hemoglobin, and electrolyte concentrations Heart Lung 2017 46 4 246 250 10.1016/j.hrtlng.2017.04.003 28477952 28477952 · DOI · Paper page
  4. [4]Dylewski JF Linas S Variability of potassium blood testing: Imprecise nature of blood testing or normal physiologic changes? Mayo Clin Proc 2018 5 93 5 551 554 10.1016/j.mayocp.2018.03.019 29728197 29728197 · DOI
  5. [5]Diercks DB Shumaik GM Harrigan RA Brady WJ Chan TC Electrocardiographic manifestations: Electrolyte abnormalities J Emerg Med 2004 8 27 2 153 160 10.1016/j.jemermed.2004.04.006 15261358 15261358 · DOI
  6. [6]Slovis C Jenkins R ABC of clinical electrocardiography: Conditions not primarily affecting the heart BMJ 2002 6 01 324 7349 1320 1323 10.1136/bmj.324.7349.1320 12039829 12039829 PMC1123277 · DOI
  7. [7]Van Mieghem C Sabbe M Knockaert D The clinical value of the ECG in noncardiac conditions Chest 2004 4 125 4 1561 1576 10.1378/chest.125.4.1561 15078775 15078775 · DOI
  8. [8]Dillon JJ DeSimone CV Sapir Y Somers VK Dugan JL Bruce CJ Ackerman MJ Asirvatham SJ Striemer BL Bukartyk J Scott CG Bennet KE Mikell SB Ladewig DJ Gilles EJ Geva A Sadot D Friedman PA Noninvasive potassium determination using a mathematically processed ECG: Proof of concept for a novel "blood-less, blood test" J Electrocardiol 2015 48 1 12 18 10.1016/j.jelectrocard.2014.10.002 25453193 25453193 PMC4415373 · DOI
  9. [9]Attia ZI DeSimone CV Dillon JJ Sapir Y Somers VK Dugan JL Bruce CJ Ackerman MJ Asirvatham SJ Striemer BL Bukartyk J Scott CG Bennet KE Ladewig DJ Gilles EJ Sadot D Geva AB Friedman PA Novel bloodless potassium determination using a signal-processed single-lead ECG J Am Heart Assoc 2016 1 25 5 1 e002746 10.1161/JAHA.115.002746 26811164 26811164 PMC4859394 · DOI
  10. [11]Corsi C Cortesi M Callisesi G De Bie J Napolitano C Santoro A Mortara D Severi S Noninvasive quantification of blood potassium concentration from ECG in hemodialysis patients Sci Rep 2017 2 15 7 42492 10.1038/srep42492 10.1038/srep42492 28198403 28198403 PMC5309791 · DOI
  11. [13]Velagapudi V O'Horo JC Vellanki A Baker SP Pidikiti R Stoff JS Tighe DA Computer-assisted image processing 12 lead ECG model to diagnose hyperkalemia J Electrocardiol 2017 50 1 131 138 10.1016/j.jelectrocard.2016.09.001 27662777 27662777 · DOI
  12. [14]Montague BT Ouellette JR Buller GK Retrospective review of the frequency of ECG changes in hyperkalemia Clin J Am Soc Nephrol 2008 3 3 2 324 330 10.2215/CJN.04611007 18235147 18235147 PMC2390954 · DOI
  13. [15]Simonyan K Zisserman A Very deep convolutional networks for large-scale image recognition Proceedings of the 3rd International Conference on Learning Representations (ICLR 2015) 2015 3rd International Conference on Learning Representations (ICLR 2015) May 7-9, 2015 San Diego, CA 1 14
  14. [16]Szegedy C Liu W Jia Y Sermanet P Reed S Anguelov D Going deeper with convolutions Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2015) 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2015) June 7-12, 2015 Boston, MA 1 9 10.1109/cvpr.2015.7298594 · DOI · Paper page
  15. [18]Huang G Liu Z Weinberger KQ van der Maaten L Densely connected convolutional networks Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2017) 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2017) July 21-26, 2017 Hawaii, HI 2261 2269 10.1109/cvpr.2017.243 · DOI · Paper page
  16. [21]Amodei D Ananthanarayanan S Anubhai R Bai J Battenberg E Case C Casper J Catanzaro B Cheng Q Chen G Chen J Chen J Chen Z Chrzanowski M Coates A Diamos G Ding K Du N Elsen E Engel J Fang W Fan L Fougner C Gao L Gong C Hannun A Han T Johannes L Jiang B Ju C Jun B LeGresley P Lin L Liu J Liu Y Li W Li X Ma D Narang S Ng A Ozair S Peng Y Prenger R Qian S Quan Z Raiman J Rao V Satheesh S Seetapun D Sengupta S Srinet K Sriram A Tang H Tang L Wang C Wang J Wang K Wang Y Wang Z Wang Z Wu S Wei L Xiao B Xie W Xie Y Yogatama D Yuan B Zhan J Zhu Z Deep Speech 2: End-to-end speech recognition in English and Mandarin Proceedings of the International Conference on Machine Learning (ICML 2016) 2016 International Conference on Machine Learning (ICML 2016) June 19-24, 2016 New York, NY 1 10 10.1007/978-3-030-14596-5_12 · DOI
  17. [22]Esteva A Kuprel B Novoa RA Ko J Swetter SM Blau HM Thrun S Dermatologist-level classification of skin cancer with deep neural networks Nature 2017 2 02 542 7639 115 118 10.1038/nature21056 28117445 28117445 PMC8382232 · DOI · Paper page
  18. [23]Schenkel S Promoting patient safety and preventing medical error in emergency departments Acad Emerg Med 2000 11 7 11 1204 1222 10.1111/j.1553-2712.2000.tb00466.x 11073469 11073469 · DOI
  19. [24]Levey AS Stevens LA Schmid CH Zhang YL Castro AF Feldman HI Kusek JW Eggers P Van Lente F Greene T Coresh J CKD-EPI (Chronic Kidney Disease Epidemiology Collaboration) A new equation to estimate glomerular filtration rate Ann Intern Med 2009 5 05 150 9 604 612 10.7326/0003-4819-150-9-200905050-00006 19414839 19414839 PMC2763564 · DOI · Paper page
  20. [25]Yang Z Yang D Dyer C He X Smola A Hovy E Hierarchical attention networks for document classification Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (HLT-NAACL) 2016 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (HLT-NAACL) June 12-17, 2016 San Diego, CA 1480 1489 10.18653/v1/n16-1174 · DOI
  21. [26]Li C Zheng C Tai C Detection of ECG characteristic points using wavelet transforms IEEE Trans Biomed Eng 1995 1 42 1 21 28 10.1109/10.362922 7851927 7851927 · DOI
  22. [28]Zabihi M Rad A Katsaggelos A Kiranyaz S Narkilahti S Gabbouj M Detection of atrial fibrillation in ECG hand-held devices using a random forest classifier Comput Cardiol 2017 9 24 44 1 4 10.22489/cinc.2017.069-336 · DOI
  23. [29]Guglin ME Thatai D Common errors in computer electrocardiogram interpretation Int J Cardiol 2006 1 13 106 2 232 237 10.1016/j.ijcard.2005.02.007 16321696 16321696 · DOI
  24. [30]Rajpurkar P Hannun A Haghpanahi M Bourn C Ng A Stanford ML Group 2017 2020-02-21 Cardiologist-level arrhythmia detection with convolutional neural networks https://arxiv.org/pdf/1707.01836.pdf · arXiv
  25. [31]Zihlmann M Perekrestenko D Tschannen M Convolutional recurrent neural networks for electrocardiogram classification Comput Cardiol 2017 44 1 4 10.22489/cinc.2017.070-060 · DOI
  26. [32]Rubin J Parvaneh S Rahman A Conroy B Babaeizadeh S Densely connected convolutional networks and signal quality analysis to detect atrial fibrillation using short single-lead ECG recordings Proceedings of 2017 Computing in Cardiology Conference (CinC) 2017 2017 Computing in Cardiology Conference (CinC) September 24-27, 2017 Rennes, France 1 4 10.22489/cinc.2017.160-246 · DOI
  27. [33]Acharya UR Fujita H Lih OS Hagiwara Y Tan JH Adam M Automated detection of arrhythmias using different intervals of tachycardia ECG segments with convolutional neural network Inf Sci 2017 9 405 81 90 10.1016/j.ins.2017.04.012 · DOI
  28. [34]Tan JH Hagiwara Y Pang W Lim I Oh SL Adam M Tan RS Chen M Acharya UR Application of stacked convolutional and long short-term memory network for accurate identification of CAD ECG signals Comput Biol Med 2018 3 01 94 19 26 10.1016/j.compbiomed.2017.12.023 29358103 29358103 · DOI
  29. [35]Acharya UR Fujita H Oh SL Hagiwara Y Tan JH Adam M Application of deep convolutional neural network for automated detection of myocardial infarction using ECG signals Inf Sci 2017 11 415-416 190 198 10.1016/j.ins.2017.06.027 · DOI
  30. [37]Severi S Pogliani D Fantini G Fabbrini P Viganò MR Galbiati E Bonforte G Vincenti A Stella A Genovesi S Alterations of atrial electrophysiology induced by electrolyte variations: Combined computational and P-wave analysis Europace 2010 6 12 6 842 849 10.1093/europace/euq042 20185484 20185484 · DOI
  31. [38]Wrenn KD Slovis CM Slovis BS The ability of physicians to predict hyperkalemia from the ECG Ann Emerg Med 1991 11 20 11 1229 1232 10.1016/s0196-0644(05)81476-3 1952310 1952310 · DOI
  32. [39]Acker CG Johnson JP Palevsky PM Greenberg A Hyperkalemia in hospitalized patients: Causes, adequacy of treatment, and results of an attempt to improve physician compliance with published therapy guidelines Arch Intern Med 1998 4 27 158 8 917 924 10.1001/archinte.158.8.917 9570179 9570179 · DOI
  33. [40]Holzinger A Langs G Denk H Zatloukal K Müller H Causability and explainability of artificial intelligence in medicine WIREs Data Min Knowl Discov 2019 4 02 9 4 1 13 10.1002/widm.1312 PMC7017860 32089788 · DOI · Paper page
  34. [41]Holzinger A Kieseberg P Weippl E Tjoa A Current advances, trends and challenges of machine learning and knowledge extraction: From machine learning to explainable AI Proceedings of the International Cross-Domain Conference for Machine Learning and Knowledge Extraction 2018 International Cross-Domain Conference for Machine Learning and Knowledge Extraction August 27-30, 2018 Hamburg, Germany 1 8 10.1007/978-3-319-99740-7_1 · DOI
  35. [43]Zhou B Khosla A Lapedriza A Oliva A Torralba A Learning deep features for discriminative localization Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2016) 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2016) June 26-July 1, 2016 Las Vegas, NV 10.1109/cvpr.2016.319 · DOI · Paper page
  36. [44]Marti G Schwarz C Leichtle AB Fiedler G Arampatzis S Exadaktylos AK Lindner G Etiology and symptoms of severe hypokalemia in emergency department patients Eur J Emerg Med 2014 2 21 1 46 51 10.1097/MEJ.0b013e3283643801 23839104 23839104 · DOI
  37. [46]El-Sherif N Turitto G Electrolyte disorders and arrhythmogenesis Cardiol J 2011 18 3 233 245 21660912 21660912

Authors
Lin, C.-S., Lin, C., Fang, W.-H., Hsu, C.-J., Chen, S.-J., Huang, K.-H., Lin, W.-S., Tsai, C.-S., Kuo, C.-C., Chau, T., Yang, S. J., & Lin, S.-H.
Affiliations
  • Tri-Service General Hospital (TW)
  • National Taiwan University (TW)
  • Providence St. Vincent Medical Center (US)
  • National Central University (TW)
Corresponding author
Lin, Shih-Hua
ORCID
Venue
JMIR Medical Informatics
Publisher
JMIR Publications Inc.
Published
2020-03-05
Volume
8
Issue
3
Pages
e15931
ISSN
2291-9694 (ISSN-L)
DOI
10.2196/15931
PMC
PMC7082733
OpenAlex
W3009117699
Cited by
109
References
44
Citations by year
2026: 12 · 2025: 14 · 2024: 23 · 2023: 16 · 2022: 26 · 2021: 12 · 2020: 5
FWCI
9.13
Type
journal article
Language
en
Open access
Licence
cc-by
Locations
  • JMIR Medical Informatics (publishedVersion, cc-by)
  • PubMed Central (publishedVersion, cc-by)
  • PubMed (publishedVersion)
  • DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
Funders
  • Ministry of Science and Technology, Taiwan (MOST106-2314-B016-035-MY3, MOST 107?, MOST106-2314-B016-038-MY3, MOST 108-, MOST 106)
  • Tri-Service General Hospital (TSGH-C107-007-007-S02)
Topics
  • Health Sciences › Medicine › Cardiology and Cardiovascular Medicine › ECG Monitoring and Analysis
  • Physical Sciences › Computer Science › Artificial Intelligence › Machine Learning in Healthcare
  • Health Sciences › Medicine › Pulmonary and Respiratory Medicine › Potassium and Related Disorders
Keywords
hypokalemia, hyperkalemia, electrocardiogram, 12-lead ECG, deep learning, serum potassium, human-machine comparison, emergency medicine

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