Population data-based federated machine learning improves automated echocardiographic quantification of cardiac structure and function: the Automatisierte Vermessung der Echokardiographie project.

Autor:	Morbach C; Department Clinical Research and Epidemiology, Comprehensive Heart Failure Center, University Hospital Würzburg, Am Schwarzenberg 15, D-97078 Würzburg, Germany.; Department of Medicine I, University Hospital Würzburg, Oberdürrbacherstr. 6, D-97080 Würzburg, Germany., Gelbrich G; Institute of Clinical Epidemiology and Biometry, University of Würzburg, Josef-Schneider-Str. 2, 97080 Würzburg, Germany.; Clinical Trial Center, University Hospital Würzburg, Josef-Schneider-Str. 2, 97080 Würzburg, Germany., Schreckenberg M; TOMTEC Imaging Systems GmbH, Freisinger Str. 9, 85716 Unterschleissheim, Germany., Hedemann M; Department Clinical Research and Epidemiology, Comprehensive Heart Failure Center, University Hospital Würzburg, Am Schwarzenberg 15, D-97078 Würzburg, Germany., Pelin D; Department Clinical Research and Epidemiology, Comprehensive Heart Failure Center, University Hospital Würzburg, Am Schwarzenberg 15, D-97078 Würzburg, Germany., Scholz N; Department Clinical Research and Epidemiology, Comprehensive Heart Failure Center, University Hospital Würzburg, Am Schwarzenberg 15, D-97078 Würzburg, Germany., Miljukov O; Institute of Clinical Epidemiology and Biometry, University of Würzburg, Josef-Schneider-Str. 2, 97080 Würzburg, Germany., Wagner A; Service Center Medical Informatics, University Hospital Würzburg, Josef-Schneider-Str. 2, 97080 Würzburg, Germany., Theisen F; Department Clinical Research and Epidemiology, Comprehensive Heart Failure Center, University Hospital Würzburg, Am Schwarzenberg 15, D-97078 Würzburg, Germany., Hitschrich N; TOMTEC Imaging Systems GmbH, Freisinger Str. 9, 85716 Unterschleissheim, Germany., Wiebel H; TOMTEC Imaging Systems GmbH, Freisinger Str. 9, 85716 Unterschleissheim, Germany., Stapf D; TOMTEC Imaging Systems GmbH, Freisinger Str. 9, 85716 Unterschleissheim, Germany., Karch O; Service Center Medical Informatics, University Hospital Würzburg, Josef-Schneider-Str. 2, 97080 Würzburg, Germany., Frantz S; Department Clinical Research and Epidemiology, Comprehensive Heart Failure Center, University Hospital Würzburg, Am Schwarzenberg 15, D-97078 Würzburg, Germany.; Department of Medicine I, University Hospital Würzburg, Oberdürrbacherstr. 6, D-97080 Würzburg, Germany., Heuschmann PU; Institute of Clinical Epidemiology and Biometry, University of Würzburg, Josef-Schneider-Str. 2, 97080 Würzburg, Germany.; Clinical Trial Center, University Hospital Würzburg, Josef-Schneider-Str. 2, 97080 Würzburg, Germany., Störk S; Department Clinical Research and Epidemiology, Comprehensive Heart Failure Center, University Hospital Würzburg, Am Schwarzenberg 15, D-97078 Würzburg, Germany.; Department of Medicine I, University Hospital Würzburg, Oberdürrbacherstr. 6, D-97080 Würzburg, Germany.
Jazyk:	angličtina
Zdroj:	European heart journal. Digital health [Eur Heart J Digit Health] 2023 Nov 15; Vol. 5 (1), pp. 77-88. Date of Electronic Publication: 2023 Nov 15 (Print Publication: 2024).
DOI:	10.1093/ehjdh/ztad069
Abstrakt:	Aims: Machine-learning (ML)-based automated measurement of echocardiography images emerges as an option to reduce observer variability. The objective of the study is to improve the accuracy of a pre-existing automated reading tool ('original detector') by federated ML-based re-training. Methods and Results: Automatisierte Vermessung der Echokardiographie was based on the echocardiography images of n = 4965 participants of the population-based Characteristics and Course of Heart Failure Stages A-B and Determinants of Progression Cohort Study. We implemented federated ML: echocardiography images were read by the Academic Core Lab Ultrasound-based Cardiovascular Imaging at the University Hospital Würzburg (UKW). A random algorithm selected 3226 participants for re-training of the original detector. According to data protection rules, the generation of ground truth and ML training cycles took place within the UKW network. Only non-personal training weights were exchanged with the external cooperation partner for the refinement of ML algorithms. Both the original detectors as the re-trained detector were then applied to the echocardiograms of n = 563 participants not used for training. With regard to the human referent, the re-trained detector revealed (i) superior accuracy when contrasted with the original detector's performance as it arrived at significantly smaller mean differences in all but one parameter, and a (ii) smaller absolute difference between measurements when compared with a group of different human observers. Conclusion: Population data-based ML in a federated ML set-up was feasible. The re-trained detector exhibited a much lower measurement variability than human readers. This gain in accuracy and precision strengthens the confidence in automated echocardiographic readings, which carries large potential for applications in various settings. Competing Interests: Conflict of interest: C.M. reports research cooperation with the University of Würzburg and TOMTEC Imaging Systems GmbH funded by a research grant from the Bavarian Ministry of Economic Affairs, Regional Development and Energy, Germany. G.G. reports research cooperation with the University Hospital of Würzburg and TOMTEC Imaging Systems GmbH funded by a research grant from the Bavarian Ministry of Economic Affairs, Regional Development and Energy, Germany. M.S. is a full-time employee of TOMTEC imaging systems. He further reports research cooperation with the University and University Hospital of Würzburg funded by a research grant from the Bavarian Ministry of Economic Affairs, Regional Development and Energy, Germany. N.H., H.W., and D.S. are full-time employees of TOMTEC imaging systems. H.W. and S.S. are supported by the CHFC Würzburg and by the German Federal Ministry of Education and Research (BMBF). All other authors report no conflict of interest. (© The Author(s) 2023. Published by Oxford University Press on behalf of the European Society of Cardiology.)
Databáze:	MEDLINE
Externí odkaz:	Zobrazit plný text záznamu