Automated echocardiographic detection of heart failure with preserved ejection fraction using artificial intelligence
Journal article
Akerman, A.P., Porumb, M., Scott, C.G., Beqiri, A., Chartsiad, A., Ryu, A.J., Hawkes, W., Huntley, G.D., Arystan, A.Z., Kane, G.C., Pislaru, S.V., Lopez-Jimenez, F., Sarwar, R., O'Driscoll, J., Leeson, P., Upton, R., Woodward, G. and Pellikka, P.A. 2023. Automated echocardiographic detection of heart failure with preserved ejection fraction using artificial intelligence. JACC Advances - Journal of the American College of Cardiology. 2 (6), p. 100452. https://doi.org/10.1016/j.jacadv.2023.100452
Authors | Akerman, A.P., Porumb, M., Scott, C.G., Beqiri, A., Chartsiad, A., Ryu, A.J., Hawkes, W., Huntley, G.D., Arystan, A.Z., Kane, G.C., Pislaru, S.V., Lopez-Jimenez, F., Sarwar, R., O'Driscoll, J., Leeson, P., Upton, R., Woodward, G. and Pellikka, P.A. |
---|---|
Abstract | Background: Detection of heart failure with preserved ejection fraction (HFpEF) involves integration of multiple imaging and clinical features which are often discordant or indeterminate. Objectives: We applied artificial intelligence (AI) to analyze a single apical four-chamber (A4C) transthoracic echocardiogram videoclip to detect HFpEF. Methods: A three-dimensional convolutional neural network was developed and trained on A4C videoclips to classify patients with HFpEF (diagnosis of HF, EF≥50%, and echocardiographic evidence of increased filling pressure; cases) versus without HFpEF (EF≥50%, no diagnosis of HF, normal filling pressure; controls). Model outputs were classified as HFpEF, no HFpEF, or non-diagnostic (high uncertainty). Performance was assessed in an independent multi-site dataset and compared to previously validated clinical scores. Results: Training and validation included 2971 cases and 3785 controls (validation holdout, 16.8% patients), and demonstrated excellent discrimination (AUROC:0.97 [95%CI:0.96-0.97] and 0.95 [0.93-0.96] in training and validation, respectively). In independent testing (646 cases, 638 controls), 94 (7.3%) were non-diagnostic; sensitivity (87.8%; 84.5-90.9%) and specificity (81.9%; 78.2-85.6%) were maintained in clinically relevant subgroups, with high repeatability and reproducibility. Of 701 and 776 indeterminate outputs from the HFA-PEFF and H2FPEF scores, the AI HFpEF model correctly reclassified 73.5 and 73.6%, respectively. During follow-up (median [IQR]:2.3 [0.5-5.6] years), 444 (34.6%) patients died; mortality was higher in patients classified as HFpEF by AI (hazard ratio [95%CI]:1.9 [1.5-2.4]). Conclusion: An AI HFpEF model based on a single, routinely acquired echocardiographic video demonstrated excellent discrimination of patients with versus without HFpEF, more often than clinical scores, and identified patients with higher mortality. |
Keywords | Heart failure; Echocardiography; Maching learning; Imaging; Diastolic function |
Year | 2023 |
Journal | JACC Advances - Journal of the American College of Cardiology |
Journal citation | 2 (6), p. 100452 |
Publisher | Elsevier |
ISSN | 2772-963X |
Digital Object Identifier (DOI) | https://doi.org/10.1016/j.jacadv.2023.100452 |
Official URL | https://www.jacc.org/doi/10.1016/j.jacadv.2023.100452 |
Publication process dates | |
Accepted | 29 May 2023 |
Deposited | 08 Nov 2023 |
Publisher's version | License File Access Level Open |
Output status | Published |
https://repository.canterbury.ac.uk/item/96465/automated-echocardiographic-detection-of-heart-failure-with-preserved-ejection-fraction-using-artificial-intelligence
Download files
Publisher's version
akerman-et-al-2023-automated-echocardiographic-detection-of-heart-failure-with-preserved-ejection-fraction-using.pdf | ||
License: CC BY 4.0 | ||
File access level: Open |
66
total views20
total downloads1
views this month2
downloads this month