A machine learning derived echocardiographic algorithm identifies people at risk of heart failure with distinct cardiac structure, function, and response to spironolactone: findings from the HOMAGE trial

Kobayashi, M. et al. (2023) A machine learning derived echocardiographic algorithm identifies people at risk of heart failure with distinct cardiac structure, function, and response to spironolactone: findings from the HOMAGE trial. European Journal of Heart Failure, (doi: 10.1002/ejhf.2859) (Early Online Publication)

Abstract

Background: An echocardiographic algorithm derived by machine learning (e′VM) characterizes preclinical individuals with different cardiac structure and function, biomarkers, and long-term risk of heart failure (HF). Our aim was the external validation of the e′VM algorithm and to explore whether it may identify subgroups who benefit from spironolactone. Methods: The HOMAGE (Heart OMics in Aging) trial enrolled participants at high risk of developing HF randomly assigned to spironolactone or placebo over 9 months. The e′VM algorithm was applied to 416 participants (mean age 74±7years, 25% women) with available echocardiographic variables (i.e., e′ mean, left ventricular [LV] end-diastolic volume and mass indexed by body surface area [LVMi]). The effects of spironolactone on changes in echocardiographic and biomarker variables were assessed across e′VM phenotypes. Results: A majority (>80%) had either “diastolic changes (D)”, or “diastolic changes with structural remodeling (D/S)” phenotype. D/S phenotype had the highest LVMi, left atrial volume, E/e', natriuretic peptide and troponin levels (all p<0.05). Spironolactone significantly reduced E/e' and b-type natriuretic peptide (BNP) levels in D/S phenotype (p<0.01), but not in other phenotypes (p>0.10; Pinteraction<0.05 for both). These interactions were not observed when considering guideline-recommended echocardiographic structural and functional abnormalities. The magnitude of effects of spironolactone on LVMi, left atrial volume and a type I collagen marker was numerically higher in D/S phenotype than D phenotype but the interaction test did not reach significance. Conclusions: In the HOMAGE trial, the e'VM algorithm identified echocardiographic phenotypes with distinct responses to spironolactone as assessed by changes in E/e' and BNP.

• Item Type: Articles
• Additional Information: The research leading to these results has received funding from the European Union Commission’s Seventh Framework program under grant agreement N° 305507 (HOMAGE).
• Status: Early Online Publication
• Refereed: Yes
• Glasgow Author(s) Enlighten ID: Cleland, Professor John and Ferreira, Mr Joao Pedro and Pellicori, Dr Pierpaolo
• Authors: Kobayashi, M., Huttin, O., Ferreira, J. P., Duarte, K., González, A., Heymans, S., Verdonschot, J. A.J., Brunner-La Rocca, H.-P., Pellicori, P., Clark, A. L., Petutschnigg, J., Edelmann, F., Cleland, J. G., Rossignol, P., Zannad, F., and Girerd, N.
• College/School: College of Medical Veterinary and Life Sciences > School of Cardiovascular & Metabolic Health
• Journal Name: European Journal of Heart Failure
• Publisher: Wiley
• ISSN: 1388-9842
• ISSN (Online): 1879-0844
• Published Online: 16 April 2023
• Copyright Holders: Copyright © 2023 The Authors
• First Published: First published in European Journal of Heart Failure 2023
• Publisher Policy: Reproduced under a Creative Commons License

Project Code	Award No	Project Name	Principal Investigator	Funder's Name	Funder Ref	Lead Dept
190666		HOMAGE: Heart OMics in AGEing	Christian Delles	European Commission (EC)	305507	Institute of Cardiovascular & Medical Sciences