Screening and early diagnosis of pulmonary hypertension (PH) are critical for managing progression and preventing associated mortality; however, there are no tools for this purpose. We developed and validated an artificial intelligence (AI) algorithm for predicting PH using electrocardiography (ECG).
This historical cohort study included data from consecutive patients from 2 hospitals. The patients in one hospital were divided into derivation (56,670 ECGs from 24,202 patients) and internal validation (3,174 ECGs from 3,174 patients) datasets, whereas the patients in the other hospital were included in only an external validation (10,865 ECGs from 10,865 patients) dataset. An AI algorithm based on an ensemble neural network was developed using 12-lead ECG signal and demographic information from the derivation dataset. The end-point was the diagnosis of PH. In addition, the interpretable AI algorithm identified which region had the most significant effect on decision making using a sensitivity map.
During the internal and external validation, the area under the receiver operating characteristic curve of the AI algorithm for detecting PH was 0.859 and 0.902, respectively. In the 2,939 individuals without PH at initial echocardiography, those patients that the AI defined as having a higher risk had a significantly higher chance of developing PH than those in the low-risk group (31.5% vs 5.9%, p < 0.001) during the follow-up period. The sensitivity map showed that the AI algorithm focused on the S-wave, P-wave, and T-wave for each patient by QRS complex characteristics.
The AI algorithm demonstrated high accuracy for PH prediction using 12-lead and single-lead ECGs.
To read this article in full you will need to make a payment
Purchase one-time access:Academic & Personal: 24 hour online accessCorporate R&D Professionals: 24 hour online access
One-time access price info
- For academic or personal research use, select 'Academic and Personal'
- For corporate R&D use, select 'Corporate R&D Professionals'
Subscribe:Subscribe to The Journal of Heart and Lung Transplantation
Already a print subscriber? Claim online access
Already an online subscriber? Sign in
Register: Create an account
Institutional Access: Sign in to ScienceDirect
- Predicting survival in pulmonary arterial hypertension: insights from the Registry to Evaluate Early and Long-Term Pulmonary Arterial Hypertension Disease Management (REVEAL).Circulation. 2010; 122: 164-172
- The new haemodynamic definition of pulmonary hypertension: evidence prevails, finally!.Eur Respir J. 2019; 531900038
- 2015 ESC/ERS Guidelines for the diagnosis and treatment of pulmonary hypertension: the Joint Task Force for the diagnosis and treatment of pulmonary hypertension of the European Society of Cardiology (ESC) and the European Respiratory Society (ERS): endorsed by: Association for European Paediatric and Congenital Cardiology (AEPC), International Society for Heart and Lung Transplantation (ISHLT).Eur Heart J. 2016; 37: 67-119
- Pulmonary hypertension.JAMA. 2012; 308: 1366-1374
- Clinical diagnosis of pulmonary hypertension.Circulation. 2014; 130: 1820-1830
- Pulmonary hypertension: the role of the electrocardiogram.Neth Heart J. 2008; 16: 250-254
- Artificial intelligence in cardiology.J Am Coll Cardiol. 2018; 71: 2668-2679
- Screening for cardiac contractile dysfunction using an artificial intelligence-enabled electrocardiogram.Nat Med. 2019; 25: 70-74
- Guidelines for the echocardiographic assessment of the right heart in adults: a report from the American Society of Echocardiography endorsed by the European Association of Echocardiography, a registered branch of the European Society of Cardiology, and the Canadian Society of Echocardiography.J Am Soc Echocardiogr. 2010; 23: 685-788
- Deep learning in neural networks: an overview.Neural Netw. 2015; 61: 85-117
- Deep learning.Nature. 2015; 521: 436-444
- Deep residual learning for image recognition.Proceedings of the IEEE computer society conference on computer vision and pattern recognition. Institute of Electrical and Electronics Engineers, Las Vegas, NV2016: 770-778
- Ensemble methods in machine learning.Multiple Classifier Systems. MCS 2000. Lecture Notes in Computer Science, vol 1857. Springer, Berlin, Heidelberg2000: 1-15
- TensorFlow: a system for large-scale machine learning.(Paper presented at:)in: 12th USENIX symposium Operating Systems Design and Implementation (OSDI ’16), Savannah, GA2016 (November 2-4)
- Prediction of abnormal myocardial relaxation From signal processed surface ECG.J Am Coll Cardiol. 2018; 71: 1650-1660
- Analysis of machine learning techniques for heart failure readmissions.Circ Cardiovasc Qual Outcomes. 2016; 9: 629-640
- Visual explanations from deep networks via gradient-based localization.(Paper presented at:)in: Proceedings of the IEEE international conference on computer vision 2017, Venice, Italy2017 (October 22-29)
- The precision-recall plot is more informative than the ROC plot when evaluating binary classifiers on imbalanced datasets.PLoS One. 2015; 10: 1-21
- Bootstrap confidence intervals: when, which, what? A practical guide for medical statisticians.Stat Med. 2000; 19: 1141-1164
- Optimal cut-point and its corresponding Youden index to discriminate individuals using pooled blood samples.Epidemiology. 2005; 16: 73-81
- Prolonged QRS Duration: a new predictor of adverse outcome in idiopathic pulmonary arterial hypertension.Chest. 2012; 141: 374-380
- Deeper S Wave in lead V5 and broader extent of T Wave inversions in the precordial leads are clinically useful electrocardiographic parameters for predicting pulmonary hypertension.Int Heart J. 2018; 59: 136-142
- Connection between right ventricular pressure and the ECG.J Electrocardiol. 1994; 27: 23-27
- The heart and pulmonary circulation at high altitudes: healthy highlanders and chronic mountain sickness.Circulation. 2007; 115: 1132-1146
- The prognostic role of the ECG in primary pulmonary hypertension.Chest. 2002; 121: 513-518
- The electrocardiogram at extreme altitude: experience on Mt.Everest. Am Heart J. 1985; 109: 505-513
- Assessment of cardiac stress from massive pulmonary embolism With 12-lead ECG.Chest. 2001; 120: 474-481
- Pulmonary hypertension in the elderly: a different disease?.Breathe (Sheff). 2016; 12: 43-49
- Boosting for transfer learning.in: ICML ’07 Proceedings of the 24th international conference on Machine learning. ACM Press, New York, NY2007: 193-200
- Interpretable explanations of black boxes by meaningful perturbation.(Paper presented at:)in: Proceedings of the IEEE international conference on computer vision 2017, Venice, Italy2017 (October 22-29)
Published online: April 23, 2020
© 2020 International Society for Heart and Lung Transplantation. All rights reserved.