Deep learning-based electrocardiographic screening for chronic kidney disease.


Journal

Communications medicine
ISSN: 2730-664X
Titre abrégé: Commun Med (Lond)
Pays: England
ID NLM: 9918250414506676

Informations de publication

Date de publication:
26 May 2023
Historique:
received: 22 08 2022
accepted: 10 03 2023
medline: 27 5 2023
pubmed: 27 5 2023
entrez: 26 5 2023
Statut: epublish

Résumé

Undiagnosed chronic kidney disease (CKD) is a common and usually asymptomatic disorder that causes a high burden of morbidity and early mortality worldwide. We developed a deep learning model for CKD screening from routinely acquired ECGs. We collected data from a primary cohort with 111,370 patients which had 247,655 ECGs between 2005 and 2019. Using this data, we developed, trained, validated, and tested a deep learning model to predict whether an ECG was taken within one year of the patient receiving a CKD diagnosis. The model was additionally validated using an external cohort from another healthcare system which had 312,145 patients with 896,620 ECGs between 2005 and 2018. Using 12-lead ECG waveforms, our deep learning algorithm achieves discrimination for CKD of any stage with an AUC of 0.767 (95% CI 0.760-0.773) in a held-out test set and an AUC of 0.709 (0.708-0.710) in the external cohort. Our 12-lead ECG-based model performance is consistent across the severity of CKD, with an AUC of 0.753 (0.735-0.770) for mild CKD, AUC of 0.759 (0.750-0.767) for moderate-severe CKD, and an AUC of 0.783 (0.773-0.793) for ESRD. In patients under 60 years old, our model achieves high performance in detecting any stage CKD with both 12-lead (AUC 0.843 [0.836-0.852]) and 1-lead ECG waveform (0.824 [0.815-0.832]). Our deep learning algorithm is able to detect CKD using ECG waveforms, with stronger performance in younger patients and more severe CKD stages. This ECG algorithm has the potential to augment screening for CKD. Chronic kidney disease (CKD) is a common condition involving loss of kidney function over time and results in a substantial number of deaths. However, CKD often has no symptoms during its early stages. To detect CKD earlier, we developed a computational approach for CKD screening using routinely acquired electrocardiograms (ECGs), a cheap, rapid, non-invasive, and commonly obtained test of the heart’s electrical activity. Our model achieved good accuracy in identifying any stage of CKD, with especially high accuracy in younger patients and more severe stages of CKD. Given the high global burden of undiagnosed CKD, novel and accessible CKD screening strategies have the potential to help prevent disease progression and reduce premature deaths related to CKD.

Sections du résumé

BACKGROUND BACKGROUND
Undiagnosed chronic kidney disease (CKD) is a common and usually asymptomatic disorder that causes a high burden of morbidity and early mortality worldwide. We developed a deep learning model for CKD screening from routinely acquired ECGs.
METHODS METHODS
We collected data from a primary cohort with 111,370 patients which had 247,655 ECGs between 2005 and 2019. Using this data, we developed, trained, validated, and tested a deep learning model to predict whether an ECG was taken within one year of the patient receiving a CKD diagnosis. The model was additionally validated using an external cohort from another healthcare system which had 312,145 patients with 896,620 ECGs between 2005 and 2018.
RESULTS RESULTS
Using 12-lead ECG waveforms, our deep learning algorithm achieves discrimination for CKD of any stage with an AUC of 0.767 (95% CI 0.760-0.773) in a held-out test set and an AUC of 0.709 (0.708-0.710) in the external cohort. Our 12-lead ECG-based model performance is consistent across the severity of CKD, with an AUC of 0.753 (0.735-0.770) for mild CKD, AUC of 0.759 (0.750-0.767) for moderate-severe CKD, and an AUC of 0.783 (0.773-0.793) for ESRD. In patients under 60 years old, our model achieves high performance in detecting any stage CKD with both 12-lead (AUC 0.843 [0.836-0.852]) and 1-lead ECG waveform (0.824 [0.815-0.832]).
CONCLUSIONS CONCLUSIONS
Our deep learning algorithm is able to detect CKD using ECG waveforms, with stronger performance in younger patients and more severe CKD stages. This ECG algorithm has the potential to augment screening for CKD.
Chronic kidney disease (CKD) is a common condition involving loss of kidney function over time and results in a substantial number of deaths. However, CKD often has no symptoms during its early stages. To detect CKD earlier, we developed a computational approach for CKD screening using routinely acquired electrocardiograms (ECGs), a cheap, rapid, non-invasive, and commonly obtained test of the heart’s electrical activity. Our model achieved good accuracy in identifying any stage of CKD, with especially high accuracy in younger patients and more severe stages of CKD. Given the high global burden of undiagnosed CKD, novel and accessible CKD screening strategies have the potential to help prevent disease progression and reduce premature deaths related to CKD.

Autres résumés

Type: plain-language-summary (eng)
Chronic kidney disease (CKD) is a common condition involving loss of kidney function over time and results in a substantial number of deaths. However, CKD often has no symptoms during its early stages. To detect CKD earlier, we developed a computational approach for CKD screening using routinely acquired electrocardiograms (ECGs), a cheap, rapid, non-invasive, and commonly obtained test of the heart’s electrical activity. Our model achieved good accuracy in identifying any stage of CKD, with especially high accuracy in younger patients and more severe stages of CKD. Given the high global burden of undiagnosed CKD, novel and accessible CKD screening strategies have the potential to help prevent disease progression and reduce premature deaths related to CKD.

Identifiants

pubmed: 37237055
doi: 10.1038/s43856-023-00278-w
pii: 10.1038/s43856-023-00278-w
pmc: PMC10220039
doi:

Types de publication

Journal Article

Langues

eng

Pagination

73

Informations de copyright

© 2023. The Author(s).

Références

Collaboration GBDCKD. Global, regional, and national burden of chronic kidney disease, 1990−2017: a systematic analysis for the Global Burden of Disease Study 2017. Lancet. 395, 709–733 (2020).
doi: 10.1016/S0140-6736(20)30045-3
Chu, C. D. et al. Centers for disease C and prevention chronic kidney disease surveillance T. CKD awareness among US adults by future risk of kidney failure. Am. J. Kidney Dis. 76, 174–183 (2020).
doi: 10.1053/j.ajkd.2020.01.007 pubmed: 32305206 pmcid: 7387135
Dharmarajan, S. H. et al. Centers for disease C and prevention CKDSS. state-level awareness of chronic kidney disease in the U.S. Am. J. Prev. Med. 53, 300–307 (2017).
doi: 10.1016/j.amepre.2017.02.015 pubmed: 28410862 pmcid: 5706661
Chronic Kidney Disease Prognosis, C. et al. Association of estimated glomerular filtration rate and albuminuria with all-cause and cardiovascular mortality in general population cohorts: a collaborative meta-analysis. Lancet. 375, 2073–2081 (2010).
doi: 10.1016/S0140-6736(10)60674-5
Gerstein, H. C. et al. and Investigators HS. Albuminuria and risk of cardiovascular events, death, and heart failure in diabetic and nondiabetic individuals. JAMA. 286, 421–426 (2001).
doi: 10.1001/jama.286.4.421 pubmed: 11466120
Bang, H. et al. SCreening for Occult REnal Disease (SCORED): a simple prediction model for chronic kidney disease. Arch Intern Med 167, 374–381 (2007).
doi: 10.1001/archinte.167.4.374 pubmed: 17325299
McKinney, S. M. et al. International evaluation of an AI system for breast cancer screening. Nature. 577, 89–94 (2020).
doi: 10.1038/s41586-019-1799-6 pubmed: 31894144
Ouyang, D. et al. Video-based AI for beat-to-beat assessment of cardiac function. Nature. 580, 252–256 (2020).
doi: 10.1038/s41586-020-2145-8 pubmed: 32269341 pmcid: 8979576
Raghunath, S. et al. Prediction of mortality from 12-lead electrocardiogram voltage data using a deep neural network. Nat. Med. 26, 886–891 (2020).
doi: 10.1038/s41591-020-0870-z pubmed: 32393799
Attia, Z. I. et al. Screening for cardiac contractile dysfunction using an artificial intelligence-enabled electrocardiogram. Nat. Med. 25, 70–74 (2019).
doi: 10.1038/s41591-018-0240-2 pubmed: 30617318
Kwon, J. M. et al. Comparing the performance of artificial intelligence and conventional diagnosis criteria for detecting left ventricular hypertrophy using electrocardiography. Europace 22, 412–419 (2020).
doi: 10.1093/europace/euz324 pubmed: 31800031
Attia, Z. I. et al. Age and sex estimation using artificial intelligence from standard 12-Lead ECGs. Circ. Arrhythm Electrophysiol. 12, e007284 (2019).
doi: 10.1161/CIRCEP.119.007284 pubmed: 31450977 pmcid: 7661045
Kwon, J. M. et al. A deep learning algorithm to detect anaemia with ECGs: a retrospective, multicentre study. Lancet Digit Health 2, e358–e367 (2020).
doi: 10.1016/S2589-7500(20)30108-4 pubmed: 33328095
Attia, Z. I. et al. An artificial intelligence-enabled ECG algorithm for the identification of patients with atrial fibrillation during sinus rhythm: a retrospective analysis of outcome prediction. Lancet. 394, 861–867 (2019).
doi: 10.1016/S0140-6736(19)31721-0 pubmed: 31378392
Hughes, J. W. et al. Performance of a convolutional neural network and explainability technique for 12-lead electrocardiogram interpretation. JAMA Cardiol. 6, 1285–1295 (2021).
doi: 10.1001/jamacardio.2021.2746 pubmed: 34347007 pmcid: 8340011
Jankowski, J., Floege, J., Fliser, D., Bohm, M. & Marx, N. Cardiovascular disease in chronic kidney disease: pathophysiological insights and therapeutic options. Circulation. 143, 1157–1172 (2021).
doi: 10.1161/CIRCULATIONAHA.120.050686 pubmed: 33720773 pmcid: 7969169
Hayer, M. K. et al. Defining myocardial abnormalities across the stages of chronic kidney disease: a cardiac magnetic resonance imaging study. JACC Cardiovasc. Imaging 13, 2357–2367 (2020).
doi: 10.1016/j.jcmg.2020.04.021 pubmed: 32682713 pmcid: 7607516
Diercks, D. B., Shumaik, G. M., Harrigan, R. A., Brady, W. J. & Chan, T. C. Electrocardiographic manifestations: electrolyte abnormalities. J. Emerg. Med. 27, 153–160 (2004).
doi: 10.1016/j.jemermed.2004.04.006 pubmed: 15261358
Galloway, C. D. et al. Development and validation of a deep-learning model to screen for hyperkalemia from the electrocardiogram. JAMA Cardiol. 4, 428–436 (2019).
doi: 10.1001/jamacardio.2019.0640 pubmed: 30942845 pmcid: 6537816
Urtnasan, E. et al. Noninvasive screening tool for hyperkalemia using a single-lead electrocardiogram and deep learning: development and usability study. JMIR Med. Inform. 10, e34724 (2022).
doi: 10.2196/34724 pubmed: 35657658 pmcid: 9206199
Ribeiro MT, Singh S & Guestrin C. “Why Should I Trust You?”: Explaining the Predictions of Any Classifier. Paper presented at: Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining; 2016; San Francisco, California, USA.
Berns, J. S. Routine screening for CKD should be done in asymptomatic adults… selectively. Clin. J. Am. Soc. Nephrol. 9, 1988–1992 (2014).
doi: 10.2215/CJN.02250314 pubmed: 25237073 pmcid: 4220752
Komenda, P. et al. Cost-effectiveness of primary screening for CKD: a systematic review. Am. J. Kidney Dis. 63, 789–797 (2014).
doi: 10.1053/j.ajkd.2013.12.012 pubmed: 24529536
Moyer, V. A., Force USPST. Screening for chronic kidney disease: U.S. Preventive Services Task Force recommendation statement. Ann. Intern. Med 157, 567–570 (2012).
doi: 10.7326/0003-4819-157-8-201210160-00533 pubmed: 22928170
Qaseem, A., Hopkins, R. H. Jr, Sweet, D. E., Starkey, M. & Shekelle, P. and Clinical Guidelines Committee of the American College of P. Screening, monitoring, and treatment of stage 1 to 3 chronic kidney disease: a clinical practice guideline from the American College of Physicians. Ann. Intern. Med. 159, 835–47 (2013).
doi: 10.7326/0003-4819-159-11-201312030-00009 pubmed: 24145991
Alfego, D. et al. Chronic kidney disease testing among at-risk adults in the U.S. remains low: real-world evidence from a national laboratory database. Diabetes Care 44, 2025–2032 (2021).
doi: 10.2337/dc21-0723 pubmed: 34353883 pmcid: 8740927
Kwon, J. M. et al. Artificial intelligence assessment for early detection and prediction of renal impairment using electrocardiography. Int. Urol. Nephrol. 54, 2733–2744 (2022).
doi: 10.1007/s11255-022-03165-w pubmed: 35403974 pmcid: 9463260
Huang, J. C. et al. P wave dispersion and maximum P wave duration are associated with renal outcomes in chronic kidney disease. PLoS ONE 9, e101962 (2014).
doi: 10.1371/journal.pone.0101962 pubmed: 25006682 pmcid: 4090207
Kestenbaum, B. et al. Kidney function, electrocardiographic findings, and cardiovascular events among older adults. Clin. J. Am. Soc. Nephrol. 2, 501–508 (2007).
doi: 10.2215/CJN.04231206 pubmed: 17699457
Sherif, K. A., Abo-Salem, E., Panikkath, R., Nusrat, M. & Tuncel, M. Cardiac repolarization abnormalities among patients with various stages of chronic kidney disease. Clin. Cardiol. 37, 417–421 (2014).
doi: 10.1002/clc.22277 pubmed: 25043948 pmcid: 6649453
Stewart, G. A. et al. Electrocardiographic abnormalities and uremic cardiomyopathy. Kidney Int. 67, 217–226 (2005).
doi: 10.1111/j.1523-1755.2005.00072.x pubmed: 15610245
Himmelfarb, J. & Ikizler, T. A. Hemodialysis. New Engl. J. Med. 363, 1833–1845 (2010).
doi: 10.1056/NEJMra0902710 pubmed: 21047227
Liyanage, T. et al. Worldwide access to treatment for end-stage kidney disease: a systematic review. Lancet. 385, 1975–1982 (2015).
doi: 10.1016/S0140-6736(14)61601-9 pubmed: 25777665
theurerjohn & Christensen, K. ecg-net/CKDscreening: COMMSMED Publication Release. https://doi.org/10.5281/zenodo.7713558 .

Auteurs

Lauri Holmstrom (L)

Department of Cardiology, Smidt Heart Institute, Cedars-Sinai Medical Center, Los Angeles, CA, USA.
Center for Cardiac Arrest Prevention, Department of Cardiology, Smidt Heart Institute, Cedars-Sinai Medical Center, Los Angeles, CA, USA.
Research Unit of Internal Medicine, Medical Research Center Oulu, University of Oulu and Oulu University Hospital, Oulu, Finland.
Division of Artificial Intelligence in Medicine, Department of Medicine, Cedars-Sinai Medical Center, Los Angeles, CA, USA.

Matthew Christensen (M)

Department of Cardiology, Smidt Heart Institute, Cedars-Sinai Medical Center, Los Angeles, CA, USA.
Division of Artificial Intelligence in Medicine, Department of Medicine, Cedars-Sinai Medical Center, Los Angeles, CA, USA.

Neal Yuan (N)

Department of Medicine, Division of Cardiology, San Francisco VA, UCSF, San Francisco, CA, USA.

J Weston Hughes (J)

Department of Computer Science, Stanford University, Palo Alto, CA, USA.

John Theurer (J)

Department of Cardiology, Smidt Heart Institute, Cedars-Sinai Medical Center, Los Angeles, CA, USA.
Division of Artificial Intelligence in Medicine, Department of Medicine, Cedars-Sinai Medical Center, Los Angeles, CA, USA.

Melvin Jujjavarapu (M)

Enterprise Information Service, Cedars-Sinai Medical Center, Los Angeles, CA, USA.

Pedram Fatehi (P)

Division of Nephrology, Department of Medicine, Stanford University, Palo Alto, CA, USA.

Alan Kwan (A)

Department of Cardiology, Smidt Heart Institute, Cedars-Sinai Medical Center, Los Angeles, CA, USA.

Roopinder K Sandhu (RK)

Department of Cardiology, Smidt Heart Institute, Cedars-Sinai Medical Center, Los Angeles, CA, USA.

Joseph Ebinger (J)

Department of Cardiology, Smidt Heart Institute, Cedars-Sinai Medical Center, Los Angeles, CA, USA.

Susan Cheng (S)

Department of Cardiology, Smidt Heart Institute, Cedars-Sinai Medical Center, Los Angeles, CA, USA.

James Zou (J)

Department of Computer Science, Stanford University, Palo Alto, CA, USA.
Department of Biomedical Data Science, Stanford University, Palo Alto, CA, USA.

Sumeet S Chugh (SS)

Department of Cardiology, Smidt Heart Institute, Cedars-Sinai Medical Center, Los Angeles, CA, USA.
Center for Cardiac Arrest Prevention, Department of Cardiology, Smidt Heart Institute, Cedars-Sinai Medical Center, Los Angeles, CA, USA.
Division of Artificial Intelligence in Medicine, Department of Medicine, Cedars-Sinai Medical Center, Los Angeles, CA, USA.

David Ouyang (D)

Department of Cardiology, Smidt Heart Institute, Cedars-Sinai Medical Center, Los Angeles, CA, USA. David.Ouyang@cshs.org.
Division of Artificial Intelligence in Medicine, Department of Medicine, Cedars-Sinai Medical Center, Los Angeles, CA, USA. David.Ouyang@cshs.org.

Classifications MeSH