Artificial Intelligence for Aortic Pressure Waveform Analysis During Coronary Angiography

Howard, James P.; Cook, Christopher; Hoef, Tim P. van de; Meuwissen, Martijn; Waard, Guus A. de; Lavieren, Martijn A. van; Echavarría‐Pinto, Mauro; Danad, Ibrahim; Piek, Jan J.; Götberg, Matthias; Al‐Lamee, Rasha; Sen, Sayan; Nijjer, Sukhjinder; Seligman, Henry; Royen, Niels van; Knaapen, Paul; Escaned, Javier; Francis, Dárrel P.; Petraco, Ricardo; Davies, Justin E.

doi:10.1016/j.jcin.2019.06.036

Cited by 29 publications

(14 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…CNNs have been used successfully in the past to classify biological waveform data such as ECGs, 32 encephalograms, 33 aortic pressure waveforms, 8 and even sleep sounds. 34 CNNs are not the only approaches that can be used for waveform classification, but they have rapidly become the state of the art for analyzing 1-, 2-, and 3-dimensional medical data.…”

Section: Why Cnns May Excel At Ecg Analysismentioning

confidence: 99%

“…Machine learning is a form of artificial intelligence (AI) that allows automation of tasks that otherwise would require human expertise, including ECG classification. [8][9][10][11][12] Automated analysis of HBP ECGs could prevent adverse consequences of ECG misdiagnosis, allow more rapid global uptake of HBP, assist operators in HBP implant procedures, and facilitate management of patients with HBP devices attending centers that do not perform HBP practice. In this study, we sought to use machine learning to automate ECG analysis for HBP.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Discriminating electrocardiographic responses to His-bundle pacing using machine learning

Arnold¹,

Howard²,

Gopi

et al. 2020

Cardiovascular Digital Health Journal

Self Cite

View full text Add to dashboard Cite

BACKGROUND His-bundle pacing (HBP) has emerged as an alternative to conventional ventricular pacing because of its ability to deliver physiological ventricular activation. Pacing at the His bundle produces different electrocardiographic (ECG) responses: selective His-bundle pacing (S-HBP), non-selective His bundle pacing (NS-HBP), and myocardium-only capture (MOC). These 3 capture types must be distinguished from each other, which can be challenging and time-consuming even for experts. OBJECTIVE The purpose of this study was to use artificial intelligence (AI) in the form of supervised machine learning using a convolutional neural network (CNN) to automate HBP ECG interpretation. METHODS We identified patients who had undergone HBP and extracted raw 12-lead ECG data during S-HBP, NS-HBP, and MOC. A CNN was trained, using 3-fold cross-validation, on 75% of the segmented QRS complexes labeled with their capture type. The remaining 25% was kept aside as a testing dataset. RESULTS The CNN was trained with 1297 QRS complexes from 59 patients. Cohen kappa for the neural network's performance on the 17-patient testing set was 0.59 (95% confidence interval 0.30 to 0.88; P ,.0001), with an overall accuracy of 75%. The CNN's accuracy in the 17-patient testing set was 67% for S-HBP, 71% for NS-HBP, and 84% for MOC. CONCLUSION We demonstrated proof of concept that a neural network can be trained to automate discrimination between HBP ECG responses. When a larger dataset is trained to higher accuracy, automated AI ECG analysis could facilitate HBP implantation and follow-up and prevent complications resulting from incorrect HBP ECG analysis.

show abstract

Section: Why Cnns May Excel At Ecg Analysismentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Discriminating electrocardiographic responses to His-bundle pacing using machine learning

Arnold¹,

Howard²,

Gopi

et al. 2020

Cardiovascular Digital Health Journal

Self Cite

View full text Add to dashboard Cite

show abstract

“…Specifically, in relation to patho-physiology, the advancement on measuring and imaging techniques has encouraged the employment of machine learning for estimating clinical pathophysiological indices and validating their results. This promising area of research could not exclude applications on cardiovascular health 25,47,55,56 . High correlation between peripheral pressure and central aortic pressure indicates the potential to estimate the latter from the former.…”

Section: Discussionmentioning

confidence: 99%

Noninvasive estimation of aortic hemodynamics and cardiac contractility using machine learning

Bikia

Papaioannou

Pagoulatou

et al. 2020

Sci Rep

View full text Add to dashboard Cite

Cardiac and aortic characteristics are crucial for cardiovascular disease detection. However, noninvasive estimation of aortic hemodynamics and cardiac contractility is still challenging. This paper investigated the potential of estimating aortic systolic pressure (aSBP), cardiac output (CO), and end-systolic elastance (Ees) from cuff-pressure and pulse wave velocity (PWV) using regression analysis. The importance of incorporating ejection fraction (EF) as additional input for estimating Ees was also assessed. The models, including Random Forest, Support Vector Regressor, Ridge, Gradient Boosting, were trained/validated using synthetic data (n = 4,018) from an in-silico model. When cuff-pressure and PWV were used as inputs, the normalized-RMSEs/correlations for aSBP, CO, and Ees (best-performing models) were 3.36 ± 0.74%/0.99, 7.60 ± 0.68%/0.96, and 16.96 ± 0.64%/0.37, respectively. Using EF as additional input for estimating Ees significantly improved the predictions (7.00 ± 0.78%/0.92). Results showed that the use of noninvasive pressure measurements allows estimating aSBP and CO with acceptable accuracy. In contrast, Ees cannot be predicted from pressure signals alone. Addition of the EF information greatly improves the estimated Ees. Accuracy of the model-derived aSBP compared to in-vivo aSBP (n = 783) was very satisfactory (5.26 ± 2.30%/0.97). Future in-vivo evaluation of CO and Ees estimations remains to be conducted. This novel methodology has potential to improve the noninvasive monitoring of aortic hemodynamics and cardiac contractility.

show abstract

“…Artificial intelligence in cardiology: examples of applications in interventional cardiology,7 electrophysiology5 and imaging 2. AF, atrial fibrillation; CMR, cardiovascular magnetic resonance; CNN, convolutional neural network; DL, deep learning.…”

mentioning

confidence: 99%

“…Interventional cardiology has also embraced the opportunities of ML, with pilot research applications in the identification and evaluation of coronary disease from angiograms, analysis of intravascular ultrasound, non-invasive functional assessment of coronary stenosis and interpretation of pressure-wire pull back data 6. A specific example of such an application is the use of a neural network to perform automated pressure waveform analysis and to allow real-time identification of the characteristic ‘damping’ waveform that occurs during deep intubation of the coronary arteries 7. This can assist physicians in performing safer angiography, in addition to improving the diagnostic accuracy of physiological assessment of coronary stenosis.…”

mentioning

confidence: 99%

Artificial intelligence and the cardiologist: what you need to know for 2020

Marvao

Dawes

Howard

et al. 2020

Heart

View full text Add to dashboard Cite

Artificial Intelligence for Aortic Pressure Waveform Analysis During Coronary Angiography

Cited by 29 publications

References 9 publications

Discriminating electrocardiographic responses to His-bundle pacing using machine learning

Discriminating electrocardiographic responses to His-bundle pacing using machine learning

Noninvasive estimation of aortic hemodynamics and cardiac contractility using machine learning

Artificial intelligence and the cardiologist: what you need to know for 2020

Contact Info

Product

Resources

About