Search

Aims: Echocardiographic strain imaging reflects myocardial deformation and is a sensitive measure of cardiac function and wall-motion abnormalities. Deep learning (DL) algorithms could automate the interpretation of echocardiographic strain imaging., Methods and Results: We developed and trained an automated DL-based algorithm for left ventricular (LV) strain measurements in an internal dataset. Global longitudinal strain (GLS) was validated externally in (i) a real-world Taiwanese cohort of participants with and without heart failure (HF), (ii) a core-lab measured dataset from the multinational prevalence of microvascular dysfunction-HF and preserved ejection fraction (PROMIS-HFpEF) study, and regional strain in (iii) the HMC-QU-MI study of patients with suspected myocardial infarction. Outcomes included measures of agreement [bias, mean absolute difference (MAD), root-mean-squared-error (RMSE), and Pearson's correlation (R)] and area under the curve (AUC) to identify HF and regional wall-motion abnormalities. The DL workflow successfully analysed 3741 (89%) studies in the Taiwanese cohort, 176 (96%) in PROMIS-HFpEF, and 158 (98%) in HMC-QU-MI. Automated GLS showed good agreement with manual measurements (mean ± SD): -18.9 ± 4.5% vs. -18.2 ± 4.4%, respectively, bias 0.68 ± 2.52%, MAD 2.0 ± 1.67, RMSE = 2.61, R = 0.84 in the Taiwanese cohort; and -15.4 ± 4.1% vs. -15.9 ± 3.6%, respectively, bias -0.65 ± 2.71%, MAD 2.19 ± 1.71, RMSE = 2.78, R = 0.76 in PROMIS-HFpEF. In the Taiwanese cohort, automated GLS accurately identified patients with HF (AUC = 0.89 for total HF and AUC = 0.98 for HF with reduced ejection fraction). In HMC-QU-MI, automated regional strain identified regional wall-motion abnormalities with an average AUC = 0.80., Conclusion: DL algorithms can interpret echocardiographic strain images with similar accuracy as conventional measurements. These results highlight the potential of DL algorithms to democratize the use of cardiac strain measurements and reduce time-spent and costs for echo labs globally., Competing Interests: Conflict of interest: P.L.M. has received research grants from AstraZenca and consulting fees from Amarin, AmGen, AstraZeneca, Bayer, Boehringer-Ingelheim, Bristol Myers Squibb, Novartis, Novo Nordisk, Orion Pharma, Pharmacosmos, Vifor, and Us2.ai. A.S. received research grants from Academy of Finland and Finnish Foundation for Cardiovascular Research during the conduct of the study; and consulting fees from GE healthcare, Novartis, Abbot, Astra Zeneca. C.H. has received consulting fees from Novartis and MSD. M.J.F., Z.J., Y.M.H. are all employees of Us2.ai. M.L.F. is employee of AstraZeneca R&D. L.H.L. reports no disclosures related to this work. Outside the present work: Grants from AstraZeneca, Vifor, Boston Scientific, Boehringer Ingelheim, Novartis, MSD. Consulting for Vifor, AstraZeneca, Bayer, Pharmacosmos, MSD, MedScape, Sanofi, Lexicon, Myokardia, Boehringer Ingelheim, Servier, Edwards Life Sciences, Alleviant. Speaker’s honoraria from Abbott, OrionPharma, MedScape, Radcliffe, AstraZeneca, Novartis, Boehringer Ingelheim, Bayer. Patent and stock ownership for AnaCardio. S.J.S. has received research grants from Actelion, AstraZeneca, Corvia, and Novartis; and consulting fees from Actelion, Amgen, AstraZeneca, Bayer, Boehringer-Ingelheim, Cardiora, Eisai, Ironwood, Merck, Novartis, Sanofi, Tenax, and United Therapeutics. C.S.L. has received research support from Novo Nordisk and Roche Diagnostics; and has consulted for Alleviant Medical, Allysta Pharma, Amgen, AnaCardio AB, Applied Therapeutics, AstraZeneca, Bayer, Biopeutics, Boehringer Ingelheim, Boston Scientific, Bristol Myers Squibb, CardioRenal, Cytokinetics, Darma Inc., EchoNous Inc, Eli Lilly, Impulse Dynamics, Intellia Therapeutics, Ionis Pharmaceutical, Janssen Research & Development LLC, Medscape/WebMD Global LLC, Merck, Novartis, Novo Nordisk, Prosciento Inc, Quidel Corporation, Radcliffe Group Ltd., Recardio Inc, ReCor Medical, Roche Diagnostics, Sanofi, Siemens Healthcare Diagnostics, and Us2.ai. J.T. is supported by the National University of Singapore Start-up grant, the tier 1 grant from the ministry of education and the CS-IRG New Investigator Grant from the National Medical Research Council; has received research support from AstraZeneca, consulting or speaker fees from Daiichi-Sankyo, Boehringer Ingelheim, Roche diagnostics and Us2.ai, and owns patent US-10702247-B2 related to the present work. All other authors have no disclosures., (© The Author(s) 2023. Published by Oxford University Press on behalf of the European Society of Cardiology.)