Explaining deep neural networks for knowledge discovery in electrocardiogram analysis

Hicks, Steven A.; Isaksen, Jonas L.; Thambawita, Vajira; Ghouse, Jonas; Ahlberg, Gustav; Linneberg, Allan; Grarup, Niels; Strümke, Inga; Ellervik, Christina; Olesen, Morten S.; Hansen, Torben; Graff, Claus; Holstein‐Rathlou, Niels‐Henrik; Halvorsen, Pål; Maleckar, Mary M.; Riegler, Michael; Kanters, Jørgen K.

doi:10.1038/s41598-021-90285-5

Cited by 45 publications

(26 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To examine exactly what features the CNN models are examining to make these predictions, we would have to use certain explainable AI models, which would be more interpretable. This was beyond the scope of the current project, but future studies may be able to harness new computational techniques 38 to improve approaches in this regard. It is also difficult to speculate what steps may be taken to improve model performance.…”

Section: Discussionmentioning

confidence: 99%

Identifying risk of adverse outcomes in COVID-19 patients via artificial intelligence–powered analysis of 12-lead intake electrocardiogram

Sridhar

Chen

Mayfield

et al. 2022

Cardiovascular Digital Health Journal

Self Cite

View full text Add to dashboard Cite

Background Adverse events in COVID-19 are difficult to predict. Risk stratification is encumbered by the need to protect healthcare workers. We hypothesize that AI can help identify subtle signs of myocardial involvement in the 12-lead electrocardiogram (ECG), which could help predict complications. Objective Use intake ECGs from COVID-19 patients to train AI models to predict risk of mortality or major adverse cardiovascular events (MACE). Methods We studied intake ECGs from 1448 COVID-19 patients (60.5% male, 63.4±16.9 years). Records were labeled by mortality (death vs. discharge) or MACE (no events vs. arrhythmic, heart failure [HF], or thromboembolic [TE] events), then used to train AI models; these were compared to conventional regression models developed using demographic and comorbidity data. Results 245 (17.7%) patients died (67.3% male, 74.5±14.4 years); 352 (24.4%) experienced at least one MACE (119 arrhythmic; 107 HF; 130 TE). AI models predicted mortality and MACE with area under the curve (AUC) values of 0.60±0.05 and 0.55±0.07, respectively; these were comparable to AUC values for conventional models (0.73±0.07 and 0.65±0.10). There were no prominent temporal trends in mortality rate or MACE incidence in our cohort; holdout testing with data from after a cutoff date (June 9, 2020) did not degrade model performance. Conclusion Using intake ECGs alone, our AI models had limited ability to predict hospitalized COVID-19 patients’ risk of mortality or MACE. Our models’ accuracy was comparable to that of conventional models built using more in-depth information, but translation to clinical use would require higher sensitivity and positive predictive value. In the future, we hope that mixed-input AI models utilizing both ECG and clinical data may be developed to enhance predictive accuracy.

show abstract

Section: Discussionmentioning

confidence: 99%

Identifying risk of adverse outcomes in COVID-19 patients via artificial intelligence–powered analysis of 12-lead intake electrocardiogram

Sridhar

Chen

Mayfield

et al. 2022

Cardiovascular Digital Health Journal

Self Cite

View full text Add to dashboard Cite

show abstract

“…Although deep learning has previously been used for ECG analysis 16 , 17 , this study is the first study to generate realistic synthetic 10-s 12-lead DeepFake ECGs. We demonstrate that the characteristics of the real ECGs were preserved with the DeepFake ECGs.…”

Section: Discussionmentioning

confidence: 99%

DeepFake electrocardiograms using generative adversarial networks are the beginning of the end for privacy issues in medicine

Thambawita

Isaksen

Hicks

et al. 2021

Sci Rep

Self Cite

View full text Add to dashboard Cite

Recent global developments underscore the prominent role big data have in modern medical science. But privacy issues constitute a prevalent problem for collecting and sharing data between researchers. However, synthetic data generated to represent real data carrying similar information and distribution may alleviate the privacy issue. In this study, we present generative adversarial networks (GANs) capable of generating realistic synthetic DeepFake 10-s 12-lead electrocardiograms (ECGs). We have developed and compared two methods, named WaveGAN* and Pulse2Pulse. We trained the GANs with 7,233 real normal ECGs to produce 121,977 DeepFake normal ECGs. By verifying the ECGs using a commercial ECG interpretation program (MUSE 12SL, GE Healthcare), we demonstrate that the Pulse2Pulse GAN was superior to the WaveGAN* to produce realistic ECGs. ECG intervals and amplitudes were similar between the DeepFake and real ECGs. Although these synthetic ECGs mimic the dataset used for creation, the ECGs are not linked to any individuals and may thus be used freely. The synthetic dataset will be available as open access for researchers at OSF.io and the DeepFake generator available at the Python Package Index (PyPI) for generating synthetic ECGs. In conclusion, we were able to generate realistic synthetic ECGs using generative adversarial neural networks on normal ECGs from two population studies, thereby addressing the relevant privacy issues in medical datasets.

show abstract

“…Surrogate methods have been employed in the cardiology literature for applications such as explaining machine learning prediction models for hypertension 19 and to explain ECG classifications. 49,50 Surrogate methods can be both global and local. Global surrogate methods include decision trees 22 and logistic/linear regression.…”

Section: Surrogate Methodsmentioning

confidence: 99%

Opening the Black Box: The Promise and Limitations of Explainable Machine Learning in Cardiology

Petch

Nelson

2022

Canadian Journal of Cardiology

310

109

View full text Add to dashboard Cite

This is a PDF file of an article that has undergone enhancements after acceptance, such as the addition of a cover page and metadata, and formatting for readability, but it is not yet the definitive version of record. This version will undergo additional copyediting, typesetting and review before it is published in its final form, but we are providing this version to give early visibility of the article. Please note that, during the production process, errors may be discovered which could affect the content, and all legal disclaimers that apply to the journal pertain.

show abstract

Explaining deep neural networks for knowledge discovery in electrocardiogram analysis

Cited by 45 publications

References 37 publications

Identifying risk of adverse outcomes in COVID-19 patients via artificial intelligence–powered analysis of 12-lead intake electrocardiogram

Identifying risk of adverse outcomes in COVID-19 patients via artificial intelligence–powered analysis of 12-lead intake electrocardiogram

DeepFake electrocardiograms using generative adversarial networks are the beginning of the end for privacy issues in medicine

Opening the Black Box: The Promise and Limitations of Explainable Machine Learning in Cardiology

Contact Info

Product

Resources

About