ATS 2021 will feature presentations of original research from accepted abstracts. Mini Symposia and Thematic Poster Sessions are abstract based sessions.
Please use the form below to browse scientific abstracts and case reports accepted for ATS 2021. Abstracts presented at the ATS 2021 will be published in the Online Abstract Issue of the American Journal of Respiratory and Critical Care Medicine, Volume 203, May 3, 2021.
Search Tips:
- Use the keyword search to search by keyword or author's name.
- Filter your search results by selecting the checkboxes that apply.
- Click on "Clear" to clear the form and start a new search. .
Search results will display below the form.
An Automated Screening Algorithm Using Electrocardiograms for Pulmonary Hypertension
Session Title
D3 - D003 COME TOGETHER - CLINICAL ADVANCES IN PULMONARY HYPERTENSION: LESSONS FROM BEST ABSTRACTS
Abstract
A1179 - An Automated Screening Algorithm Using Electrocardiograms for Pulmonary Hypertension
Author Block: H. M. Dubrock1, T. Wagner2, Z. I. Attia3, S. J. Asirvatham3, S. Awasthi2, M. Babu4, R. Barve4, K. Carlson2, C. L. Carpenter2, R. P. Frantz3, P. A. Friedman3, A. Prasad4, C. Chehoud5, E. Kogan5, A. Nnewihe5, D. Quinn5, C. Bridges5, S. Kapa3, V. Soundararajan2; 1Division of Pulmonary & Critical Care Medicine, Mayo Clinic, Rochester, MN, United States, 2nference, Cambridge, MA, United States, 3Department of Cardiovascular Medicine, Mayo Clinic, Rochester, MN, United States, 4nference Labs, Bangalore, India, 5Janssen Pharmaceuticals, Inc, Raritan, NJ, United States.
Rationale: Pulmonary hypertension (PH) is a life-threatening disease that is typically detected after significant pulmonary vascular remodeling has occurred. Longer diagnostic delays are associated with higher mortality and there is a need for a simple, fast, non-invasive PH screening tool. Currently, electrocardiograms often only identify abnormalities in severe PH. However, deep learning-based algorithms may enable detection of early, subtle, disease-specific changes, and could allow this inexpensive and ubiquitous test to serve as a powerful screening tool for PH. Methods: We used convolutional neural networks (CNN) to develop an algorithm for PH using retrospective electrocardiogram voltage-time data from Mayo Clinic. Each standard 12-lead electrocardiogram was paired with right heart catheterization to define patients as PH or non-PH, and the non-PH group was supplemented with patients in whom PH was excluded by echocardiogram. PH was defined as mean pulmonary arterial pressure (mPAP) ≥25 mmHg (at rest or during drug or exercise challenge), and non-PH was defined as mPAP <21 mmHg or tricuspid regurgitation velocity ≤2.8 m/s, if mPAP was not available. All patients were then randomly partitioned into training (48%), validation (12%) and test sets (40%) for building, optimizing and testing the models, respectively. Models were trained using electrocardiograms performed within 1 month of PH diagnosis (diagnostic dataset) and performance was tested on the diagnostic dataset and on electrocardiograms from 6-18 months (pre-emptive dataset) and 36-60 months before diagnosis. Model performance was evaluated by calculating the area under the curve (AUC) of the receiver operating characteristic curve, sensitivity, specificity, and diagnostic odds ratios. Results: In total, 56,612 unique patients were identified: 11,138 PH and 45,474 non-PH patients. Several model structures were tested, and the best performing were CNNs with residual connections incorporating the 12-lead voltage-time electrocardiogram data. The final model yielded an AUC, sensitivity and specificity, respectively, of 0.91, 83.5%, and 83.6% in the diagnostic test set and 0.86, 77.8% and 78.3% in the pre-emptive dataset (Table). AUC remained above 0.81 for detection of PH using electrocardiograms from 6-monthly intervals up to 5 years before diagnosis. Among the PH patients, 2,134 patients had pre-capillary PH, which includes some progressive but potentially treatable forms of PH, and AUC was 0.95 for detection of PH in this diagnostic dataset. Conclusions: The electrocardiogram algorithm was able to detect PH up to 5 years prior to diagnosis. This type of algorithm has the potential to accelerate diagnosis and management of PH.
Author Block: H. M. Dubrock1, T. Wagner2, Z. I. Attia3, S. J. Asirvatham3, S. Awasthi2, M. Babu4, R. Barve4, K. Carlson2, C. L. Carpenter2, R. P. Frantz3, P. A. Friedman3, A. Prasad4, C. Chehoud5, E. Kogan5, A. Nnewihe5, D. Quinn5, C. Bridges5, S. Kapa3, V. Soundararajan2; 1Division of Pulmonary & Critical Care Medicine, Mayo Clinic, Rochester, MN, United States, 2nference, Cambridge, MA, United States, 3Department of Cardiovascular Medicine, Mayo Clinic, Rochester, MN, United States, 4nference Labs, Bangalore, India, 5Janssen Pharmaceuticals, Inc, Raritan, NJ, United States.
Rationale: Pulmonary hypertension (PH) is a life-threatening disease that is typically detected after significant pulmonary vascular remodeling has occurred. Longer diagnostic delays are associated with higher mortality and there is a need for a simple, fast, non-invasive PH screening tool. Currently, electrocardiograms often only identify abnormalities in severe PH. However, deep learning-based algorithms may enable detection of early, subtle, disease-specific changes, and could allow this inexpensive and ubiquitous test to serve as a powerful screening tool for PH. Methods: We used convolutional neural networks (CNN) to develop an algorithm for PH using retrospective electrocardiogram voltage-time data from Mayo Clinic. Each standard 12-lead electrocardiogram was paired with right heart catheterization to define patients as PH or non-PH, and the non-PH group was supplemented with patients in whom PH was excluded by echocardiogram. PH was defined as mean pulmonary arterial pressure (mPAP) ≥25 mmHg (at rest or during drug or exercise challenge), and non-PH was defined as mPAP <21 mmHg or tricuspid regurgitation velocity ≤2.8 m/s, if mPAP was not available. All patients were then randomly partitioned into training (48%), validation (12%) and test sets (40%) for building, optimizing and testing the models, respectively. Models were trained using electrocardiograms performed within 1 month of PH diagnosis (diagnostic dataset) and performance was tested on the diagnostic dataset and on electrocardiograms from 6-18 months (pre-emptive dataset) and 36-60 months before diagnosis. Model performance was evaluated by calculating the area under the curve (AUC) of the receiver operating characteristic curve, sensitivity, specificity, and diagnostic odds ratios. Results: In total, 56,612 unique patients were identified: 11,138 PH and 45,474 non-PH patients. Several model structures were tested, and the best performing were CNNs with residual connections incorporating the 12-lead voltage-time electrocardiogram data. The final model yielded an AUC, sensitivity and specificity, respectively, of 0.91, 83.5%, and 83.6% in the diagnostic test set and 0.86, 77.8% and 78.3% in the pre-emptive dataset (Table). AUC remained above 0.81 for detection of PH using electrocardiograms from 6-monthly intervals up to 5 years before diagnosis. Among the PH patients, 2,134 patients had pre-capillary PH, which includes some progressive but potentially treatable forms of PH, and AUC was 0.95 for detection of PH in this diagnostic dataset. Conclusions: The electrocardiogram algorithm was able to detect PH up to 5 years prior to diagnosis. This type of algorithm has the potential to accelerate diagnosis and management of PH.
