这是indexloc提供的服务，不要输入任何密码
Skip to main content

Thank you for visiting nature.com. You are using a browser version with limited support for CSS. To obtain the best experience, we recommend you use a more up to date browser (or turn off compatibility mode in Internet Explorer). In the meantime, to ensure continued support, we are displaying the site without styles and JavaScript.

  • Article
  • Published:

Synthetic generation of cardiac tissue motion from surface electrocardiograms

Nature Cardiovascular Research volume 4, pages 445–457 (2025)Cite this article

Subjects

Abstract

Cardiac tissue motion is a sensitive biomarker for detecting early myocardial damage. Here, we show the similarity, interpretability and diagnostic accuracy of synthetic tissue Doppler imaging (TDI) waveforms generated from surface electrocardiograms (ECGs). Prospectively collected ECG and TDI data were cross-matched as 9,144 lateral and 8,722 septal TDI–ECG pairs (463 patients) for generating synthetic TDI across every 1% interval of the cardiac cycle. External validation using 816 lateral and 869 septal TDI–ECG pairs (314 patients) demonstrated strong correlation (repeated-measures r = 0.90, P < 0.0001), cosine similarity (0.89, P < 0.0001) and no differences during a randomized visual Turing test. Synthetic TDI correlated with clinical parameters (585 patients) and detected diastolic and systolic dysfunction with an area under the curve of 0.80 and 0.81, respectively. Furthermore, synthetic TDI systolic and early diastolic measurements generated from an external ECG dataset (233,647 patients) were associated with all-cause mortality during both sinus rhythm and atrial fibrillation, underscoring their potential for personalized cardiac care.

Access through your institution
Buy or subscribe

This is a preview of subscription content, access via your institution

Access options

Access through your institution

Buy this article

  • Purchase on SpringerLink
  • Instant access to full article PDF
Buy now

Prices may be subject to local taxes which are calculated during checkout

Fig. 1: Study design.
Fig. 2: Overview of the GAN system for runtime and training.
Fig. 3: Real versus synthetic tissue Doppler waveforms.
Fig. 4: Univariate associations with clinical and echocardiographic features.
Fig. 5: Diagnostic value of synthetic TDI waveforms for screening for LV dysfunction.
Fig. 6: Survival analysis using TDI-based average e′.

Similar content being viewed by others

Data availability

Data used for training and validation are not publicly available because they are prospectively acquired in a clinical study. Sharing these data externally without additional consent compromises patient privacy and violates the study’s institutional review board approval. However, data that support the plots and Extended Data figures within this paper are made available as source data. Any additional data of this study are available from the corresponding author upon request and would require adherence to policies and procedures for data transfer agreement followed by Rutgers Health. Source data are provided with this paper.

Code availability

The code itself cannot be shared because it contains proprietary intellectual property (patent applications are pending in the United States (US20240306974A1), Europe (EP4355209A1) and India (202417003493), all titled ‘Synthetic echo from ECG’ and assigned to Rutgers University with P.P.S. and N.Y. as inventors) and due to ongoing collaborations with the industry to implement the code for clinical diagnostic use.

References

  1. Vaduganathan, M., Mensah, G. A., Turco, J. V., Fuster, V. & Roth, G. A. The global burden of cardiovascular diseases and risk: a compass for future health. J. Am. Coll. Cardiol. 80, 2361–2371 (2022).

    Article  PubMed  Google Scholar 

  2. Elias, P. et al. Artificial intelligence for cardiovascular care—part 1: advances: JACC review topic of the week. J. Am. Coll. Cardiol. 83, 2472–2486 (2024).

    Article  PubMed  Google Scholar 

  3. Khera, R. et al. Transforming cardiovascular care with artificial intelligence: from discovery to practice: JACC state-of-the-art review. J. Am. Coll. Cardiol. 84, 97–114 (2024).

    Article  PubMed  Google Scholar 

  4. Jain, S. S. et al. Artificial intelligence in cardiovascular care—part 2: applications: JACC review topic of the week. J. Am. Coll. Cardiol. 83, 2487–2496 (2024).

    Article  PubMed  Google Scholar 

  5. Bjerkén, L. V., Rønborg, S. N., Jensen, M. T., Ørting, S. N. & Nielsen, O. W. Artificial intelligence enabled ECG screening for left ventricular systolic dysfunction: a systematic review. Heart Fail. Rev. 28, 419–430 (2023).

    Article  PubMed  Google Scholar 

  6. Wang, Y.-R. J. et al. Screening and diagnosis of cardiovascular disease using artificial intelligence-enabled cardiac magnetic resonance imaging. Nat. Med. 30, 1471–1480 (2024).

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  7. Seetharam, K., Shrestha, S. & Sengupta, P. P. Artificial intelligence in cardiovascular medicine. Curr. Treat. Options Cardiovasc. Med. 21, 25 (2019).

    Article  PubMed  Google Scholar 

  8. Yao, X. et al. Artificial intelligence-enabled electrocardiograms for identification of patients with low ejection fraction: a pragmatic, randomized clinical trial. Nat. Med. 27, 815–819 (2021).

    Article  CAS  PubMed  Google Scholar 

  9. Siontis, K. C., Noseworthy, P. A., Attia, Z. I. & Friedman, P. A. Artificial intelligence-enhanced electrocardiography in cardiovascular disease management. Nat. Rev. Cardiol. 18, 465–478 (2021).

    Article  PubMed  PubMed Central  Google Scholar 

  10. Lin, C.-S. et al. AI-enabled electrocardiography alert intervention and all-cause mortality: a pragmatic randomized clinical trial. Nat. Med. 30, 1461–1470 (2024).

    Article  CAS  PubMed  Google Scholar 

  11. Al-Zaiti, S. S. et al. Machine learning for ECG diagnosis and risk stratification of occlusion myocardial infarction. Nat. Med. 29, 1804–1813 (2023).

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  12. Lee, E. et al. Artificial intelligence-enabled ECG for left ventricular diastolic function and filling pressure. NPJ Digit. Med. 7, 4 (2024).

    Article  PubMed  PubMed Central  Google Scholar 

  13. Khunte, A. et al. Detection of left ventricular systolic dysfunction from single-lead electrocardiography adapted for portable and wearable devices. NPJ Digit. Med. 6, 124 (2023).

    Article  PubMed  PubMed Central  Google Scholar 

  14. Jones, C. J., Raposo, L. & Gibson, D. G. Functional importance of the long axis dynamics of the human left ventricle. Br. Heart J. 63, 215–220 (1990).

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  15. Henein, M. Y. & Gibson, D. G. Normal long axis function. Heart 81, 111–113 (1999).

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  16. Diller, G.-P. et al. Left ventricular longitudinal function predicts life-threatening ventricular arrhythmia and death in adults with repaired tetralogy of Fallot. Circulation 125, 2440–2446 (2012).

    Article  PubMed  Google Scholar 

  17. Potter, E. & Marwick, T. H. Assessment of left ventricular function by echocardiography: the case for routinely adding global longitudinal strain to ejection fraction. JACC Cardiovasc. Imaging 11, 260–274 (2018).

    Article  PubMed  Google Scholar 

  18. Rangarajan, V. et al. Left ventricular long axis function assessed during cine-cardiovascular magnetic resonance is an independent predictor of adverse cardiac events. J. Cardiovasc. Magn. Reson. 18, 35 (2016).

    Article  PubMed  PubMed Central  Google Scholar 

  19. Thavendiranathan, P. & Calvillo-Argüelles, O. Breast cancer treatment and diastolic dysfunction: should we worry about relaxing in cardio-oncology? JACC Cardiovasc. Imaging 13, 211–214 (2020).

    Article  PubMed  Google Scholar 

  20. Rahimi, M., Ahluwalia, M., Sulague, R. M. & Kpodonu, J. Cardiac myosin inhibitors in hypertrophic cardiomyopathy: gaps in knowledge and future opportunities. Shanghai Chest https://doi.org/10.21037/shc-24-12 (2024).

    Article  Google Scholar 

  21. Chen, X., Roberts, R., Liu, Z. & Tong, W. A generative adversarial network model alternative to animal studies for clinical pathology assessment. Nat. Commun. 14, 7141 (2023).

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  22. Ahmad, W., Ali, H., Shah, Z. & Azmat, S. A new generative adversarial network for medical images super resolution. Sci. Rep. 12, 9533 (2022).

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  23. Ktena, I. et al. Generative models improve fairness of medical classifiers under distribution shifts. Nat. Med. 30, 1166–1173 (2024).

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  24. Ehrhart, M., Resch, B., Havas, C. & Niederseer, D. A conditional GAN for generating time series data for stress detection in wearable physiological sensor data. Sensors (Basel) 22, 5969 (2022).

    Article  PubMed  Google Scholar 

  25. Chandra, S., Prakash, P. K. S., Samanta, S. & Chilukuri, S. ClinicalGAN: powering patient monitoring in clinical trials with patient digital twins. Sci. Rep. 14, 12236 (2024).

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  26. Golany, T. & Radinsky, K. PGANs: Personalized generative adversarial networks for ecg synthesis to improve patient-specific deep ecg classification. Proc. AAAI Conference on Artificial Intelligence 2019 557–564 (AAAI, 2019).

  27. Alessandrini, R. S., McPherson, D. D., Kadish, A. H., Kane, B. J. & Goldberger, J. J. Cardiac memory: a mechanical and electrical phenomenon. Am. J. Physiol. 272, H1952–H1959 (1997).

    CAS  PubMed  Google Scholar 

  28. Sauer, A. et al. Diastolic electromechanical coupling: association of the ECG T-peak to T-end interval with echocardiographic markers of diastolic dysfunction. Circ. Arrhythm. Electrophysiol. 5, 537–543 (2012).

    Article  PubMed  PubMed Central  Google Scholar 

  29. Quinn, T. A. & Kohl, P. Cardiac mechano-electric coupling: acute effects of mechanical stimulation on heart rate and rhythm. Physiol. Rev. 101, 37–92 (2021).

    Article  CAS  PubMed  Google Scholar 

  30. Salvador, M. et al. Whole-heart electromechanical simulations using Latent Neural Ordinary Differential Equations. NPJ Digit. Med. 7, 90 (2024).

    Article  PubMed  PubMed Central  Google Scholar 

  31. Pfeiffer, E. R., Tangney, J. R., Omens, J. H. & McCulloch, A. D. Biomechanics of cardiac electromechanical coupling and mechanoelectric feedback. J. Biomech. Eng. 136, 021007 (2014).

    Article  PubMed  Google Scholar 

  32. Wang, M. et al. Peak early diastolic mitral annulus velocity by tissue Doppler imaging adds independent and incremental prognostic value. J. Am. Coll. Cardiol. 41, 820–826 (2003).

    Article  PubMed  Google Scholar 

  33. Yu, C.-M., Sanderson, J. E., Marwick, T. H. & Oh, J. K. Tissue Doppler imaging: a new prognosticator for cardiovascular diseases. J. Am. Coll. Cardiol. 49, 1903–1914 (2007).

    Article  PubMed  Google Scholar 

  34. Kadappu, K. K. & Thomas, L. Tissue Doppler imaging in echocardiography: value and limitations. Heart Lung Circ. 24, 224–233 (2015).

    Article  PubMed  Google Scholar 

  35. Kagiyama, N. et al. Machine learning assessment of left ventricular diastolic function based on electrocardiographic features. J. Am. Coll. Cardiol. 76, 930–941 (2020).

    Article  PubMed  Google Scholar 

  36. Dhutia, N. M. et al. Open-source, vendor-independent, automated multi-beat tissue Doppler echocardiography analysis. Int. J. Cardiovasc. Imaging 33, 1135–1148 (2017).

    Article  PubMed  PubMed Central  Google Scholar 

  37. Nagueh, S. F. et al. Recommendations for the evaluation of left ventricular diastolic function by echocardiography: an update from the American Society of Echocardiography and the European Association of Cardiovascular Imaging. J. Am. Soc. Echocardiogr. 29, 277–314 (2016).

    Article  PubMed  Google Scholar 

  38. Geman, D., Geman, S., Hallonquist, N. & Younes, L. Visual Turing test for computer vision systems. Proc. Natl Acad. Sci. USA 112, 3618–3623 (2015).

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  39. Macfarlane, P. W., Devine, B. & Clark, E. The University of Glasgow (Uni-G) ECG analysis program. In Computers in Cardiology, 2005 451–454 (IEEE, 2005).

  40. Kligfield, P. et al. Comparison of automated measurements of electrocardiographic intervals and durations by computer-based algorithms of digital electrocardiographs. Am. Heart J. 167, 150–159 (2014).

    Article  PubMed  Google Scholar 

  41. Macfarlane, P. W. et al. Methodology of ECG interpretation in the Glasgow program. Methods Inf. Med. 29, 354–361 (1990).

    Article  CAS  PubMed  Google Scholar 

  42. Macfarlane, P. W. Evolution of the Glasgow program for computer-assisted reporting of electrocardiograms—1964/1998. Acta Cardiol. 53, 117–120 (1998).

    CAS  PubMed  Google Scholar 

  43. Ribeiro, A. H. et al. Automatic diagnosis of the 12-lead ECG using a deep neural network. Nat. Commun. 11, 1760 (2020).

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  44. Lam, C. S. P. & Solomon, S. D. Classification of heart failure according to ejection fraction: JACC review topic of the week. J. Am. Coll. Cardiol. 77, 3217–3225 (2021).

    Article  PubMed  Google Scholar 

  45. Wehner, G. J. et al. Routinely reported ejection fraction and mortality in clinical practice: where does the nadir of risk lie? Eur. Heart J. 41, 1249–1257 (2020).

    Article  PubMed  Google Scholar 

  46. Levene, J. et al. Patient outcomes by ventricular systolic and diastolic function. J. Am. Heart Assoc. 13, e033211 (2024).

    Article  PubMed  PubMed Central  Google Scholar 

  47. Fukuta, H. & Little, W. C. Contribution of systolic and diastolic abnormalities to heart failure with a normal and a reduced ejection fraction. Prog. Cardiovasc. Dis. 49, 229–240 (2007).

    Article  PubMed  Google Scholar 

  48. Khurshid, S. Clinical perspectives on the adoption of the artificial intelligence-enabled electrocardiogram. J. Electrocardiol. 81, 142–145 (2023).

    Article  PubMed  PubMed Central  Google Scholar 

  49. Goodfellow, I. et al. Generative adversarial networks. Commun. ACM 63, 139–144 (2020).

    Article  Google Scholar 

  50. Zhang, Z., Yang, L. & Zheng, Y. Translating and segmenting multimodal medical volumes with cycle- and shape-consistency generative adversarial network. In 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition 9242–9251 (IEEE, 2018).

  51. Chartsias, A., Joyce, T., Dharmakumar, R. & Tsaftaris, S. A. Adversarial image synthesis for unpaired multi-modal cardiac data. In Simulation and Synthesis in Medical Imaging (eds Tsaftaris, S. A. et al.) 3–13 (Springer International Publishing, 2017).

  52. Isola, P., Zhu, J.-Y., Zhou, T. & Efros, A. A. Image-to-image translation with conditional adversarial networks. In Proc. IEEE Conference on Computer Vision and Pattern Recognition 1125–1134 (IEEE, 2017).

  53. Wolterink, J. M., Leiner, T., Viergever, M. A. & Išgum, I. Generative adversarial networks for noise reduction in low-dose CT. IEEE Trans. Med. Imaging 36, 2536–2545 (2017).

    Article  PubMed  Google Scholar 

  54. Zhu, F., Ye, F., Fu, Y., Liu, Q. & Shen, B. Electrocardiogram generation with a bidirectional LSTM–CNN generative adversarial network. Sci. Rep. 9, 6734 (2019).

    Article  PubMed  PubMed Central  Google Scholar 

  55. Huang, Z., Chen, S., Zhang, J. & Shan, H. PFA-GAN: progressive face aging with generative adversarial network. IEEE Trans. Inf. Forensics Secur. 16, 2031–2045 (2020).

    Article  Google Scholar 

  56. Zhu, J.-Y., Park, T., Isola, P. & Efros, A. A. Unpaired image-to-image translation using cycle-consistent adversarial networks. In Proc. IEEE International Conference on Computer Vision 2223–2232 (IEEE, 2017).

  57. Oh, J. K., Miranda, W. R., Bird, J. G., Kane, G. C. & Nagueh, S. F. The 2016 diastolic function guideline: is it already time to revisit or revise them? JACC Cardiovasc. Imaging 13, 327–335 (2020).

    Article  PubMed  Google Scholar 

  58. Bae, S. et al. Usefulness of diastolic function score as a predictor of long-term prognosis in patients with acute myocardial infarction. Front. Cardiovasc. Med. 8, 730872 (2021).

    Article  PubMed  PubMed Central  Google Scholar 

  59. Lang, R. M. et al. Recommendations for cardiac chamber quantification by echocardiography in adults: an update from the American Society of Echocardiography and the European Association of Cardiovascular Imaging. J. Am. Soc. Echocardiogr. 28, 1–39 (2015).

    Article  PubMed  Google Scholar 

  60. Raghu, A., Shanmugam, D., Pomerantsev, E., Guttag, J. & Stultz, C. M. Data augmentation for electrocardiograms. In Conference on Health, Inference, and Learning 282–310 (PMLR, 2022).

  61. Odena, A., Olah, C. & Shlens, J. Conditional image synthesis with auxiliary classifier GANs. In International Conference on Machine Learning 2642–2651 (PMLR, 2017).

  62. Bakdash, J. Z. & Marusich, L. R. Repeated measures correlation. Front. Psychol. 8, 456 (2017).

    Article  PubMed  PubMed Central  Google Scholar 

  63. DeLong, E. R., DeLong, D. M. & Clarke-Pearson, D. L. Comparing the areas under two or more correlated receiver operating characteristic curves: a nonparametric approach. Biometrics 44, 837–845 (1988).

    Article  CAS  PubMed  Google Scholar 

  64. Youden, W. J. Index for rating diagnostic tests. Cancer 3, 32–35 (1950).

    Article  CAS  PubMed  Google Scholar 

Download references

Acknowledgements

P.P.S. and N.Y. received funding support from the National Science Foundation (award number 2125872). We thank HeartSciences for providing a clinical study database for this investigation.

Author information

Author notes

  1. These authors contributed equally: Aditya Radhakrishnan, Naveena Yanamala.

Authors and Affiliations

  1. Georgia Institute of Technology, Atlanta, GA, USA

    Aditya Radhakrishnan

  2. Carnegie Mellon University, Pittsburgh, PA, USA

    Aditya Radhakrishnan & Naveena Yanamala

  3. Rutgers Robert Wood Johnson Medical School, New Brunswick, NJ, USA

    Naveena Yanamala, Ankush Jamthikar, Yanting Wang, Sasha-Ann East, Yasmin Hamirani, Kameswari Maganti & Partho P. Sengupta

Authors
  1. Aditya Radhakrishnan
    View author publications

    Search author on:PubMed Google Scholar

  2. Naveena Yanamala
    View author publications

    Search author on:PubMed Google Scholar

  3. Ankush Jamthikar
    View author publications

    Search author on:PubMed Google Scholar

  4. Yanting Wang
    View author publications

    Search author on:PubMed Google Scholar

  5. Sasha-Ann East
    View author publications

    Search author on:PubMed Google Scholar

  6. Yasmin Hamirani
    View author publications

    Search author on:PubMed Google Scholar

  7. Kameswari Maganti
    View author publications

    Search author on:PubMed Google Scholar

  8. Partho P. Sengupta
    View author publications

    Search author on:PubMed Google Scholar

Contributions

Design and implementation: A.R., N.Y., A.J. Concept and design: N.Y., P.P.S. Manuscript design and editing: A.R., A.J., N.Y., P.P.S., S.-A.E., Y.W., Y.H., K.M.

Corresponding author

Correspondence to Partho P. Sengupta.

Ethics declarations

Competing interests

P.P.S. has served on the advisory board of RCE Technologies and HeartSciences and holds stock options; received grants or contracts from RCE Technologies, HeartSciences, Butterfly and MindMics; and holds patents with Mayo Clinic (US8328724B2), HeartSciences (US11445918B2) and Rutgers Health (62/864,771, US202163152686P, WO2022182603A1, US202163211829P, WO2022266288A1 and US202163212228P). N.Y. declares grants or contracts from MindMics, RCE Technologies, HeartSciences and Abiomed; receives consulting fees from Turnkey Learning and Turnkey Insights; receives payment or honoraria and support for attending meetings or travel from West Virginia University (WVU) and the National Science Foundation; is an advisor or board member for Research Spark Hub and Magnetic 3D; is an adjunct professor or faculty member at Carnegie Mellon University; is an editorial board member for the American Society of Echocardiography; is a special government employee of the Center for Devices and Radiological Health at the US Food and Drug Association; and holds patents with Rutgers (US202163152686P, WO2022182603A1, US202163211829P, WO2022266288A1, US202163212228P and WO2022266291A1) and WVU (invention numbers 2021-20 and 2021-047). Rutgers University has filed three patent applications related to the publication. These include a US patent application (US20240306974A1) titled ‘Synthetic echo from ECG’, which is currently pending. The same title is applied to an EP (European) patent application (EP4355209A1) and an India patent application (202417003493), both also in pending status. All three applications list P.P.S. and N.Y. as the inventors and Rutgers University as the assignee. These patents detail the development of synthetic echocardiography from surface ECGs using GAN methods, including clinical models and telemedicine applications. The other authors declare no competing interests.

Peer review

Peer review information

Nature Cardiovascular Research thanks Natalia Trayanova and the other, anonymous, reviewer(s) for their contribution to the peer review of this work.

Additional information

Publisher’s note Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Extended data

Extended Data Fig. 1 Similarity analysis between real and synthetic TDI waveforms separately assessed for lateral and septal walls using repeated measure correlation and Bland-Altman analysis.

Panels a and b repeated measures correlation (rrm) demonstrating the strong association between synthetic and real TDI velocity measurements (n = 311 each for septal lateral, repeated measures correlation, two-sided p-value < 0.0001). Panels c and d show Bland-Altman analysis with multiple measurements per subject with the bias and limits of agreement between synthetic and real TDI measurements indicated by the dotted lines. SD, standard deviation; TDI, tissue Doppler imaging.

Source data

Extended Data Fig. 2 Comparison of real and synthetic TDI waveforms for their systolic and diastolic time intervals for averaged waveforms at lateral, and septal walls (n = 1103, Pearson’s correlation coefficient).

a, Duration of mechanical systole: ECG R-to-peak contraction-relaxation cross-over measured by integrating the tissue velocity signals to develop time-displacement curves, b, Ratio of electrical systole (QT) to mechanical systole, and c, duration of diastolic relaxation measured as the difference of sinus cycle length and the duration of mechanical systole.

Source data

Extended Data Fig. 3 Association between real spectral TDI average e’ and synthetic TDI average e’ with the physiological parameters.

Pearson’s correlation coefficient with p values are displayed for e’ and respective physiological parameters. a, measured real spectral e’ and age (r = -0.64, p < 0.0001). b, measured real spectral e’ and systolic blood pressure (BP) (r = -0.28, p < 0.0001). c, measured real spectral e’ and diastolic BP (r = -0.08, p = 0.013). d, Depicts the correlation between GAN-based synthetic e’ and age (r = -0.49, p < 0.0001). e, the relationship between GAN-based synthetic e’ and systolic BP, (r = -0.26, p < 0.0001). f, correlation between GAN-based synthetic e’ and diastolic BP (r = -0.13, p < 0.0001). In all scatter plots, the red and green dots represent the training (n = 518) and external test (n = 585) datasets, respectively.

Source data

Extended Data Table 1 Baseline clinical and echocardiography characteristics for all patients within the training and external validation sets
Full size table
Extended Data Table 2 Evaluation of the GAN-based TDI waveforms, external validation
Full size table
Extended Data Table 3 Comparing real and GAN-based TDI waveforms using a visual Turing test taken by four cardiologists
Full size table
Extended Data Table 4 Comparing the performance of six machine learning models in predicting the LVDD using clinical, ECG-based, and GAN-generated features
Full size table
Extended Data Table 5 Comparing the machine learning model’s performance in predicting LV diastolic dysfunction for different feature categories
Full size table
Extended Data Table 6 Comparing the machine learning model’s performance in predicting LV systolic dysfunction (EF < 50%) for different feature categories
Full size table

Supplementary information

Source data

Source Data Fig. 3

Statistical source data.

Source Data Fig. 4

Statistical source data.

Source Data Fig. 5

Statistical source data.

Source Data Fig. 6

Statistical source data.

Source Data Extended Data Fig. 1

Statistical source data.

Source Data Extended Data Fig. 2

Statistical source data.

Source Data Extended Data Fig. 3

Statistical source data.

Rights and permissions

Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Radhakrishnan, A., Yanamala, N., Jamthikar, A. et al. Synthetic generation of cardiac tissue motion from surface electrocardiograms. Nat Cardiovasc Res 4, 445–457 (2025). https://doi.org/10.1038/s44161-025-00629-x

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1038/s44161-025-00629-x

Search

Advanced search

Quick links

Nature Briefing

Sign up for the Nature Briefing newsletter — what matters in science, free to your inbox daily.

Get the most important science stories of the day, free in your inbox. Sign up for Nature Briefing