-
Something wrong with this record ?
Prognostic Significance and Associations of Neural Network-Derived Electrocardiographic Features
A. Sau, AH. Ribeiro, KA. McGurk, L. Pastika, N. Bajaj, M. Gurnani, E. Sieliwonczyk, K. Patlatzoglou, M. Ardissino, JY. Chen, H. Wu, X. Shi, K. Hnatkova, SL. Zheng, A. Britton, M. Shipley, I. Andršová, T. Novotný, EC. Sabino, L. Giatti, SM....
Language English Country United States
Document type Journal Article, Multicenter Study
Grant support
FS/CRTF/21/24183
British Heart Foundation - United Kingdom
MR/Y000803/1
Medical Research Council - United Kingdom
RG/F/22/110078
British Heart Foundation - United Kingdom
NLK
Free Medical Journals
from 2008 to 1 year ago
Open Access Digital Library
from 2008-09-01
- MeSH
- Time Factors MeSH
- Electrocardiography * MeSH
- Phenotype * MeSH
- Risk Assessment MeSH
- Cardiovascular Diseases diagnosis mortality genetics physiopathology MeSH
- Middle Aged MeSH
- Humans MeSH
- Neural Networks, Computer * MeSH
- Predictive Value of Tests * MeSH
- Prognosis MeSH
- Reproducibility of Results MeSH
- Risk Factors MeSH
- Aged MeSH
- Heart Rate MeSH
- Unsupervised Machine Learning MeSH
- Check Tag
- Middle Aged MeSH
- Humans MeSH
- Male MeSH
- Aged MeSH
- Female MeSH
- Publication type
- Journal Article MeSH
- Multicenter Study MeSH
- Geographicals
- United States MeSH
BACKGROUND: Subtle, prognostically important ECG features may not be apparent to physicians. In the course of supervised machine learning, thousands of ECG features are identified. These are not limited to conventional ECG parameters and morphology. We aimed to investigate whether neural network-derived ECG features could be used to predict future cardiovascular disease and mortality and have phenotypic and genotypic associations. METHODS: We extracted 5120 neural network-derived ECG features from an artificial intelligence-enabled ECG model trained for 6 simple diagnoses and applied unsupervised machine learning to identify 3 phenogroups. Using the identified phenogroups, we externally validated our findings in 5 diverse cohorts from the United States, Brazil, and the United Kingdom. Data were collected between 2000 and 2023. RESULTS: In total, 1 808 584 patients were included in this study. In the derivation cohort, the 3 phenogroups had significantly different mortality profiles. After adjusting for known covariates, phenogroup B had a 20% increase in long-term mortality compared with phenogroup A (hazard ratio, 1.20 [95% CI, 1.17-1.23]; P<0.0001; phenogroup A mortality, 2.2%; phenogroup B mortality, 6.1%). In univariate analyses, we found phenogroup B had a significantly greater risk of mortality in all cohorts (log-rank P<0.01 in all 5 cohorts). Phenome-wide association study showed phenogroup B had a higher rate of future atrial fibrillation (odds ratio, 2.89; P<0.00001), ventricular tachycardia (odds ratio, 2.00; P<0.00001), ischemic heart disease (odds ratio, 1.44; P<0.00001), and cardiomyopathy (odds ratio, 2.04; P<0.00001). A single-trait genome-wide association study yielded 4 loci. SCN10A, SCN5A, and CAV1 have roles in cardiac conduction and arrhythmia. ARHGAP24 does not have a clear cardiac role and may be a novel target. CONCLUSIONS: Neural network-derived ECG features can be used to predict all-cause mortality and future cardiovascular diseases. We have identified biologically plausible and novel phenotypic and genotypic associations that describe mechanisms for the increased risk identified.
Department of Cardiology Chelsea and Westminster Hospital NHS Foundation Trust London United Kingdom
Department of Electrical and Electronic Engineering Imperial College London United Kingdom
Department of Information Technology Uppsala University Sweden
Medical Research Council Laboratory of Medical Sciences Imperial College London United Kingdom
National Heart and Lung Institute Imperial College London United Kingdom
Research Department of Epidemiology and Public Health University College London United Kingdom
References provided by Crossref.org
- 000
- 00000naa a2200000 a 4500
- 001
- bmc25003160
- 003
- CZ-PrNML
- 005
- 20250206104057.0
- 007
- ta
- 008
- 250121s2024 xxu f 000 0|eng||
- 009
- AR
- 024 7_
- $a 10.1161/CIRCOUTCOMES.123.010602 $2 doi
- 035 __
- $a (PubMed)39540287
- 040 __
- $a ABA008 $b cze $d ABA008 $e AACR2
- 041 0_
- $a eng
- 044 __
- $a xxu
- 100 1_
- $a Sau, Arunashis $u National Heart and Lung Institute (A.S., K.A.M., L.P., N.B., M.G., E. Sieliwonczyk, K.P., M.A., J.Y.C., H.W., X.S., K.H., S.Z., D.B.K., N.S.P., M.M., J.S.W., F.S.N.), Imperial College London, United Kingdom $u Department of Cardiology, Imperial College Healthcare National Health Service Trust, London, United Kingdom (A.S., N.S.P., F.S.N.) $1 https://orcid.org/0000000202047078
- 245 10
- $a Prognostic Significance and Associations of Neural Network-Derived Electrocardiographic Features / $c A. Sau, AH. Ribeiro, KA. McGurk, L. Pastika, N. Bajaj, M. Gurnani, E. Sieliwonczyk, K. Patlatzoglou, M. Ardissino, JY. Chen, H. Wu, X. Shi, K. Hnatkova, SL. Zheng, A. Britton, M. Shipley, I. Andršová, T. Novotný, EC. Sabino, L. Giatti, SM. Barreto, JW. Waks, DB. Kramer, D. Mandic, NS. Peters, DP. O'Regan, M. Malik, JS. Ware, ALP. Ribeiro, FS. Ng
- 520 9_
- $a BACKGROUND: Subtle, prognostically important ECG features may not be apparent to physicians. In the course of supervised machine learning, thousands of ECG features are identified. These are not limited to conventional ECG parameters and morphology. We aimed to investigate whether neural network-derived ECG features could be used to predict future cardiovascular disease and mortality and have phenotypic and genotypic associations. METHODS: We extracted 5120 neural network-derived ECG features from an artificial intelligence-enabled ECG model trained for 6 simple diagnoses and applied unsupervised machine learning to identify 3 phenogroups. Using the identified phenogroups, we externally validated our findings in 5 diverse cohorts from the United States, Brazil, and the United Kingdom. Data were collected between 2000 and 2023. RESULTS: In total, 1 808 584 patients were included in this study. In the derivation cohort, the 3 phenogroups had significantly different mortality profiles. After adjusting for known covariates, phenogroup B had a 20% increase in long-term mortality compared with phenogroup A (hazard ratio, 1.20 [95% CI, 1.17-1.23]; P<0.0001; phenogroup A mortality, 2.2%; phenogroup B mortality, 6.1%). In univariate analyses, we found phenogroup B had a significantly greater risk of mortality in all cohorts (log-rank P<0.01 in all 5 cohorts). Phenome-wide association study showed phenogroup B had a higher rate of future atrial fibrillation (odds ratio, 2.89; P<0.00001), ventricular tachycardia (odds ratio, 2.00; P<0.00001), ischemic heart disease (odds ratio, 1.44; P<0.00001), and cardiomyopathy (odds ratio, 2.04; P<0.00001). A single-trait genome-wide association study yielded 4 loci. SCN10A, SCN5A, and CAV1 have roles in cardiac conduction and arrhythmia. ARHGAP24 does not have a clear cardiac role and may be a novel target. CONCLUSIONS: Neural network-derived ECG features can be used to predict all-cause mortality and future cardiovascular diseases. We have identified biologically plausible and novel phenotypic and genotypic associations that describe mechanisms for the increased risk identified.
- 650 _2
- $a senioři $7 D000368
- 650 _2
- $a ženské pohlaví $7 D005260
- 650 _2
- $a lidé $7 D006801
- 650 _2
- $a mužské pohlaví $7 D008297
- 650 _2
- $a lidé středního věku $7 D008875
- 650 _2
- $a kardiovaskulární nemoci $x diagnóza $x mortalita $x genetika $x patofyziologie $7 D002318
- 650 12
- $a elektrokardiografie $7 D004562
- 650 _2
- $a srdeční frekvence $7 D006339
- 650 12
- $a neuronové sítě $7 D016571
- 650 12
- $a fenotyp $7 D010641
- 650 12
- $a prediktivní hodnota testů $7 D011237
- 650 _2
- $a prognóza $7 D011379
- 650 _2
- $a reprodukovatelnost výsledků $7 D015203
- 650 _2
- $a hodnocení rizik $7 D018570
- 650 _2
- $a rizikové faktory $7 D012307
- 650 _2
- $a časové faktory $7 D013997
- 650 _2
- $a strojové učení bez učitele $7 D000069558
- 651 _2
- $a Spojené státy americké $x epidemiologie $7 D014481
- 655 _2
- $a časopisecké články $7 D016428
- 655 _2
- $a multicentrická studie $7 D016448
- 700 1_
- $a Ribeiro, Antônio H $u Department of Information Technology, Uppsala University, Sweden (A.H.R.) $1 https://orcid.org/0000000336328529
- 700 1_
- $a McGurk, Kathryn A $u National Heart and Lung Institute (A.S., K.A.M., L.P., N.B., M.G., E. Sieliwonczyk, K.P., M.A., J.Y.C., H.W., X.S., K.H., S.Z., D.B.K., N.S.P., M.M., J.S.W., F.S.N.), Imperial College London, United Kingdom $u Medical Research Council Laboratory of Medical Sciences (K.A.M., E. Sieliwonczyk, D.P.O., J.S.W.), Imperial College London, United Kingdom $1 https://orcid.org/0000000254456906
- 700 1_
- $a Pastika, Libor $u National Heart and Lung Institute (A.S., K.A.M., L.P., N.B., M.G., E. Sieliwonczyk, K.P., M.A., J.Y.C., H.W., X.S., K.H., S.Z., D.B.K., N.S.P., M.M., J.S.W., F.S.N.), Imperial College London, United Kingdom
- 700 1_
- $a Bajaj, Nikesh $u National Heart and Lung Institute (A.S., K.A.M., L.P., N.B., M.G., E. Sieliwonczyk, K.P., M.A., J.Y.C., H.W., X.S., K.H., S.Z., D.B.K., N.S.P., M.M., J.S.W., F.S.N.), Imperial College London, United Kingdom $1 https://orcid.org/0000000233610118
- 700 1_
- $a Gurnani, Mehak $u National Heart and Lung Institute (A.S., K.A.M., L.P., N.B., M.G., E. Sieliwonczyk, K.P., M.A., J.Y.C., H.W., X.S., K.H., S.Z., D.B.K., N.S.P., M.M., J.S.W., F.S.N.), Imperial College London, United Kingdom $1 https://orcid.org/0009000392282518
- 700 1_
- $a Sieliwonczyk, Ewa $u National Heart and Lung Institute (A.S., K.A.M., L.P., N.B., M.G., E. Sieliwonczyk, K.P., M.A., J.Y.C., H.W., X.S., K.H., S.Z., D.B.K., N.S.P., M.M., J.S.W., F.S.N.), Imperial College London, United Kingdom $u Medical Research Council Laboratory of Medical Sciences (K.A.M., E. Sieliwonczyk, D.P.O., J.S.W.), Imperial College London, United Kingdom $u Faculty of Medicine and Health Sciences, Center for Medical Genetics, University of Antwerp and Antwerp University Hospital, Antwerp, Belgium (E. Sieliwonczyk) $1 https://orcid.org/0000000286037044
- 700 1_
- $a Patlatzoglou, Konstantinos $u National Heart and Lung Institute (A.S., K.A.M., L.P., N.B., M.G., E. Sieliwonczyk, K.P., M.A., J.Y.C., H.W., X.S., K.H., S.Z., D.B.K., N.S.P., M.M., J.S.W., F.S.N.), Imperial College London, United Kingdom $1 https://orcid.org/0000000258888490
- 700 1_
- $a Ardissino, Maddalena $u National Heart and Lung Institute (A.S., K.A.M., L.P., N.B., M.G., E. Sieliwonczyk, K.P., M.A., J.Y.C., H.W., X.S., K.H., S.Z., D.B.K., N.S.P., M.M., J.S.W., F.S.N.), Imperial College London, United Kingdom $1 https://orcid.org/0000000226548117
- 700 1_
- $a Chen, Jun Yu $u National Heart and Lung Institute (A.S., K.A.M., L.P., N.B., M.G., E. Sieliwonczyk, K.P., M.A., J.Y.C., H.W., X.S., K.H., S.Z., D.B.K., N.S.P., M.M., J.S.W., F.S.N.), Imperial College London, United Kingdom $1 https://orcid.org/0000000218238282
- 700 1_
- $a Wu, Huiyi $u National Heart and Lung Institute (A.S., K.A.M., L.P., N.B., M.G., E. Sieliwonczyk, K.P., M.A., J.Y.C., H.W., X.S., K.H., S.Z., D.B.K., N.S.P., M.M., J.S.W., F.S.N.), Imperial College London, United Kingdom $1 https://orcid.org/0000000218099729
- 700 1_
- $a Shi, Xili $u National Heart and Lung Institute (A.S., K.A.M., L.P., N.B., M.G., E. Sieliwonczyk, K.P., M.A., J.Y.C., H.W., X.S., K.H., S.Z., D.B.K., N.S.P., M.M., J.S.W., F.S.N.), Imperial College London, United Kingdom
- 700 1_
- $a Hnatkova, Katerina $u National Heart and Lung Institute (A.S., K.A.M., L.P., N.B., M.G., E. Sieliwonczyk, K.P., M.A., J.Y.C., H.W., X.S., K.H., S.Z., D.B.K., N.S.P., M.M., J.S.W., F.S.N.), Imperial College London, United Kingdom $1 https://orcid.org/0000000201591610
- 700 1_
- $a Zheng, Sean L $u National Heart and Lung Institute (A.S., K.A.M., L.P., N.B., M.G., E. Sieliwonczyk, K.P., M.A., J.Y.C., H.W., X.S., K.H., S.Z., D.B.K., N.S.P., M.M., J.S.W., F.S.N.), Imperial College London, United Kingdom
- 700 1_
- $a Britton, Annie $u Research Department of Epidemiology and Public Health, University College London, United Kingdom (A.B., M.S.) $1 https://orcid.org/0000000264125430
- 700 1_
- $a Shipley, Martin $u Research Department of Epidemiology and Public Health, University College London, United Kingdom (A.B., M.S.)
- 700 1_
- $a Andršová, Irena $u Department of Internal Medicine and Cardiology, University Hospital Brno and Masaryk University, Czech Republic (I.A., T.N., M.M.) $1 https://orcid.org/0000000189735967
- 700 1_
- $a Novotný, Tomáš $u Department of Internal Medicine and Cardiology, University Hospital Brno and Masaryk University, Czech Republic (I.A., T.N., M.M.) $1 https://orcid.org/0000000202924034 $7 xx0055126
- 700 1_
- $a Sabino, Ester C $u Department of Infectious Diseases, School of Medicine and Institute of Tropical Medicine, University of São Paulo, Brazil (E. Sabino) $1 https://orcid.org/0000000326235126
- 700 1_
- $a Giatti, Luana $u Department of Preventive Medicine, School of Medicine, and Hospital das Clínicas/Empresa Brasileira de Serviços Hospitalares (L.G., S.M.B.), Universidade Federal de Minas Gerais, Belo Horizonte, Brazil $1 https://orcid.org/0000000154542460
- 700 1_
- $a Barreto, Sandhi M $u Department of Preventive Medicine, School of Medicine, and Hospital das Clínicas/Empresa Brasileira de Serviços Hospitalares (L.G., S.M.B.), Universidade Federal de Minas Gerais, Belo Horizonte, Brazil $1 https://orcid.org/0000000173837811
- 700 1_
- $a Waks, Jonathan W $u Harvard-Thorndike Electrophysiology Institute (J.W.W.), Beth Israel Deaconess Medical Center, Harvard Medical School, Boston, MA $1 https://orcid.org/0000000155605638
- 700 1_
- $a Kramer, Daniel B $u National Heart and Lung Institute (A.S., K.A.M., L.P., N.B., M.G., E. Sieliwonczyk, K.P., M.A., J.Y.C., H.W., X.S., K.H., S.Z., D.B.K., N.S.P., M.M., J.S.W., F.S.N.), Imperial College London, United Kingdom $u Richard A. and Susan F. Smith Center for Outcomes Research in Cardiology (D.B.K.), Beth Israel Deaconess Medical Center, Harvard Medical School, Boston, MA $1 https://orcid.org/0000000342413586
- 700 1_
- $a Mandic, Danilo $u Department of Electrical and Electronic Engineering (D.M.), Imperial College London, United Kingdom
- 700 1_
- $a Peters, Nicholas S $u National Heart and Lung Institute (A.S., K.A.M., L.P., N.B., M.G., E. Sieliwonczyk, K.P., M.A., J.Y.C., H.W., X.S., K.H., S.Z., D.B.K., N.S.P., M.M., J.S.W., F.S.N.), Imperial College London, United Kingdom $u Department of Cardiology, Imperial College Healthcare National Health Service Trust, London, United Kingdom (A.S., N.S.P., F.S.N.) $1 https://orcid.org/0000000235818078
- 700 1_
- $a O'Regan, Declan P $u Medical Research Council Laboratory of Medical Sciences (K.A.M., E. Sieliwonczyk, D.P.O., J.S.W.), Imperial College London, United Kingdom $1 https://orcid.org/0000000206910270
- 700 1_
- $a Malik, Marek $u National Heart and Lung Institute (A.S., K.A.M., L.P., N.B., M.G., E. Sieliwonczyk, K.P., M.A., J.Y.C., H.W., X.S., K.H., S.Z., D.B.K., N.S.P., M.M., J.S.W., F.S.N.), Imperial College London, United Kingdom $u Department of Internal Medicine and Cardiology, University Hospital Brno and Masaryk University, Czech Republic (I.A., T.N., M.M.) $1 https://orcid.org/0000000229041223
- 700 1_
- $a Ware, James S $u National Heart and Lung Institute (A.S., K.A.M., L.P., N.B., M.G., E. Sieliwonczyk, K.P., M.A., J.Y.C., H.W., X.S., K.H., S.Z., D.B.K., N.S.P., M.M., J.S.W., F.S.N.), Imperial College London, United Kingdom $u Medical Research Council Laboratory of Medical Sciences (K.A.M., E. Sieliwonczyk, D.P.O., J.S.W.), Imperial College London, United Kingdom $u Department of Cardiology, Royal Brompton and Harefield Hospitals, Guy's and St. Thomas' NHS Foundation Trust, London, United Kingdom (J.S.W.) $1 https://orcid.org/0000000261105880
- 700 1_
- $a Ribeiro, Antonio Luiz P $u Department of Internal Medicine, Faculdade de Medicina, and Telehealth Center and Cardiology Service, Hospital das Clínicas (A.L.P.R.), Universidade Federal de Minas Gerais, Belo Horizonte, Brazil $1 https://orcid.org/0000000227400042
- 700 1_
- $a Ng, Fu Siong $u National Heart and Lung Institute (A.S., K.A.M., L.P., N.B., M.G., E. Sieliwonczyk, K.P., M.A., J.Y.C., H.W., X.S., K.H., S.Z., D.B.K., N.S.P., M.M., J.S.W., F.S.N.), Imperial College London, United Kingdom $u Department of Cardiology, Imperial College Healthcare National Health Service Trust, London, United Kingdom (A.S., N.S.P., F.S.N.) $u Department of Cardiology, Chelsea and Westminster Hospital NHS Foundation Trust, London, United Kingdom (F.S.N.) $1 https://orcid.org/0000000286814368
- 773 0_
- $w MED00205665 $t Circulation. Cardiovascular quality and outcomes $x 1941-7705 $g Roč. 17, č. 12 (2024), s. e010602
- 856 41
- $u https://pubmed.ncbi.nlm.nih.gov/39540287 $y Pubmed
- 910 __
- $a ABA008 $b sig $c sign $y - $z 0
- 990 __
- $a 20250121 $b ABA008
- 991 __
- $a 20250206104053 $b ABA008
- 999 __
- $a ok $b bmc $g 2263110 $s 1239167
- BAS __
- $a 3
- BAS __
- $a PreBMC-MEDLINE
- BMC __
- $a 2024 $b 17 $c 12 $d e010602 $e 20241114 $i 1941-7705 $m Circulation. Cardiovascular quality and outcomes $n Circ Cardiovasc Qual Outcomes $x MED00205665
- GRA __
- $a FS/CRTF/21/24183 $p British Heart Foundation $2 United Kingdom
- GRA __
- $a MR/Y000803/1 $p Medical Research Council $2 United Kingdom
- GRA __
- $a RG/F/22/110078 $p British Heart Foundation $2 United Kingdom
- LZP __
- $a Pubmed-20250121
