Improved patient classification from 2D cardiac ultrasound using multi-modal transfer learning

Debbie Zhao¹, Joshua R. Dillon¹, Gina M. Quill¹, Bram W. M. Geven^1,2, Stephen A. Creamer¹, Edward Ferdian¹, Vicky Y. Wang¹, Thiranja P. Babarenda Gamage¹, Timothy M. Sutton³, Boris S. Lowe⁴, Malcolm E. Legget⁵, Nicola C. Edwards^4,5, Robert N. Doughty^4,5, Alistair A. Young⁶, Martyn P. Nash⁷

¹Auckland Bioengineering Institute, University of Auckland, Auckland, New Zealand; ²Department of Biomedical Engineering, Eindhoven University of Technology, Eindhoven, The Netherlands; ³Counties Manukau Health Cardiology, Middlemore Hospital, Auckland, New Zealand; ⁴Green Lane Cardiovascular Service, Auckland City Hospital, Auckland, New Zealand; ⁵Department of Medicine, University of Auckland, Auckland, New Zealand; ⁶School of Biomedical Engineering and Imaging Sciences, King’s College London, London, United Kingdom; ⁷Department of Engineering Science and Biomedical Engineering, University of Auckland, Auckland, New Zealand

Bayesian inversion enables personalised septic shock treatment guided by noisy arterial pressure waveforms

Finneas JR Catling^1,2, Kim H Parker¹, Alun D Hughes², Steve Harris², Rebecca J Shipley², Anthony C Gordon¹

¹Imperial College London, London, United Kingdom; ²University College London, London, United Kingdom

Enhancing ECMO device development through machine-learned virtual patient data

Micha Landoll^1,2,3, Yifei Huang¹, Ulrich Steinseifer¹, Stephan Strassmann², Christian Karagiannidis², Michael Neidlin¹

¹Department of Cardiovascular Engineering, Institute of Applied Medical Engineering, Helmholtz Institute, RWTH Aachen University, Aachen, Germany; ²ARDS and ECMO Centre Cologne-Merheim, Dept. of Pneumology and Critical Care Medicine, Kliniken der Stadt Köln gGmbH, Witten/Herdecke University, Cologne, Germany; ³Institute for Computational Biomedicine II, University Hospital Aachen, RWTH Aachen University, Aachen, Germany

Towards an in silico clinical trial on the use of fractional flow reserve based on a data-driven modeling approach

Pjotr Hilhorst¹, Sabine Verstraeten¹, Frans van de Vosse¹, Marcel van 't Veer^1,2, Pim Tonino², Wouter Huberts¹

¹Eindhoven University of Technology, Netherlands, The; ²Catharina Hospital Eindhoven, Netherlands, The

Predicting ventricular tachycardia, taking time into the equations

Carlijn Buck¹, Marloes de Winter¹, Anouk de Lepper², Marcel van 't Veer², Wouter Huberts¹, Frans van de Vosse¹, Lukas Dekker²

¹Eindhoven University of Technology, the Netherlands; ²Catharina Hospital Eindhoven, the Netherlands

Patient-specific hemodynamic effects of acute exercise in hypertensive subjects and controls revealed by 4D flow MRI and cardiovascular modeling

Kajsa Tunedal^1,2, Valentin Kindesjö¹, Federica Viola^2,3, Karin Rådholm³, Carl-Johan Carlhäll^2,3,4, Gunnar Cedersund^1,2, Tino Ebbers^2,3

¹Department of Biomedical Engineering, Linköping University, Linköping, Sweden; ²Center for Medical Image Science and Visualization (CMIV), Linköping University, Linköping, Sweden; ³Department of Health, Medicine and Caring Sciences, Linköping University, Linköping, Sweden; ⁴Department of Clinical Physiology in Linköping, and Department of Health, Medicine and Caring Sciences, Linköping University, Linköping, Sweden