Deep-Learning to predict outcome of CRT based on pulsed-wave Doppler, clinical biomarkers and pacemaker settings

Paulo Tostes; Ahmed S. Beela; Somayeh Akbari; Helena Williams; Joost Lumens; Jan D'Hooge

doi:10.1109/IUS62464.2025.11201532

Deep-Learning to predict outcome of CRT based on pulsed-wave Doppler, clinical biomarkers and pacemaker settings

Paulo Tostes^*
, Ahmed S. Beela
, Somayeh Akbari
, Helena Williams
, Joost Lumens
, Jan D'Hooge

^*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceeding › Conference article in proceeding › Academic › peer-review

Abstract

Cardiac Resynchronization Therapy uses a biventricular pacemaker and is the recommended treatment for Heart Failure patients with Left Bundle Branch Block. The pacemaker settings are determined during the implantation procedure based on the patient's acute response and can be altered during follow-up exams months after implantation. Despite the careful follow-up, only 65-70% of eligible patients respond to this (expensive) therapy and better selection of candidates for CRT as well as optimization of the pacemaker settings for an elected patient are required. Therefore, we developed a deep learning (DL) algorithm on commonly acquired echocardiographic recordings during the standard care path to predict how a patient will likely respond to certain pacemaker settings after 6 months.

Original language	English
Title of host publication	2025 IEEE International Ultrasonics Symposium, IUS 2025
Publisher	IEEE Computer Society
ISBN (Electronic)	9798331523329
DOIs	https://doi.org/10.1109/IUS62464.2025.11201532
Publication status	Published - 1 Jan 2025
Event	2025 IEEE International Ultrasonics Symposium - Jaarbeurs Utrecht, Utrecht, Netherlands Duration: 15 Sept 2025 → 18 Sept 2025 Conference number: 62 https://2025.ieee-ius.org/

Publication series

Series	IEEE International Ultrasonics Symposium, IUS
ISSN	1948-5719

Symposium

Symposium	2025 IEEE International Ultrasonics Symposium
Abbreviated title	IUS 2025
Country/Territory	Netherlands
City	Utrecht
Period	15/09/25 → 18/09/25
Internet address	https://2025.ieee-ius.org/

Keywords

Cardiac Resynchronization Therapy
Cardiac Ultrasound
Convolutional Neural Networks
Deep Learning

Access to Document

10.1109/IUS62464.2025.11201532

Cite this

@inproceedings{8fbc206797774676a2556bc21f11f68b,

title = "Deep-Learning to predict outcome of CRT based on pulsed-wave Doppler, clinical biomarkers and pacemaker settings",

abstract = "Cardiac Resynchronization Therapy uses a biventricular pacemaker and is the recommended treatment for Heart Failure patients with Left Bundle Branch Block. The pacemaker settings are determined during the implantation procedure based on the patient's acute response and can be altered during follow-up exams months after implantation. Despite the careful follow-up, only 65-70\% of eligible patients respond to this (expensive) therapy and better selection of candidates for CRT as well as optimization of the pacemaker settings for an elected patient are required. Therefore, we developed a deep learning (DL) algorithm on commonly acquired echocardiographic recordings during the standard care path to predict how a patient will likely respond to certain pacemaker settings after 6 months.",

keywords = "Cardiac Resynchronization Therapy, Cardiac Ultrasound, Convolutional Neural Networks, Deep Learning",

author = "Paulo Tostes and Beela, \{Ahmed S.\} and Somayeh Akbari and Helena Williams and Joost Lumens and Jan D'Hooge",

note = "Funding Information: This work was part of a larger International Training Network project called \textbackslash{}{"}MArie Curie Intelligent UltraSound (MARCIUS)\textbackslash{}{"}. The MARCIUS project was funded by the European Union's Horizon 2020 research and innovation programme under the Marie Sk\textbackslash{}u0142odowska-Curie grant agreement No 860745. Publisher Copyright: {\textcopyright} 2025 IEEE.; 2025 IEEE International Ultrasonics Symposium, IUS 2025 ; Conference date: 15-09-2025 Through 18-09-2025",

year = "2025",

month = jan,

day = "1",

doi = "10.1109/IUS62464.2025.11201532",

language = "English",

series = "IEEE International Ultrasonics Symposium, IUS",

publisher = "IEEE Computer Society",

booktitle = "2025 IEEE International Ultrasonics Symposium, IUS 2025",

address = "United States",

url = "https://2025.ieee-ius.org/",

}

Tostes, P, Beela, AS, Akbari, S, Williams, H, Lumens, J & D'Hooge, J 2025, Deep-Learning to predict outcome of CRT based on pulsed-wave Doppler, clinical biomarkers and pacemaker settings. in 2025 IEEE International Ultrasonics Symposium, IUS 2025. IEEE Computer Society, IEEE International Ultrasonics Symposium, IUS, 2025 IEEE International Ultrasonics Symposium, Utrecht, Netherlands, 15/09/25. https://doi.org/10.1109/IUS62464.2025.11201532

Deep-Learning to predict outcome of CRT based on pulsed-wave Doppler, clinical biomarkers and pacemaker settings. / Tostes, Paulo; Beela, Ahmed S.; Akbari, Somayeh et al.
2025 IEEE International Ultrasonics Symposium, IUS 2025. IEEE Computer Society, 2025. (IEEE International Ultrasonics Symposium, IUS).

Research output: Chapter in Book/Report/Conference proceeding › Conference article in proceeding › Academic › peer-review

TY - GEN

T1 - Deep-Learning to predict outcome of CRT based on pulsed-wave Doppler, clinical biomarkers and pacemaker settings

AU - Tostes, Paulo

AU - Beela, Ahmed S.

AU - Akbari, Somayeh

AU - Williams, Helena

AU - Lumens, Joost

AU - D'Hooge, Jan

N1 - Conference code: 62

PY - 2025/1/1

Y1 - 2025/1/1

N2 - Cardiac Resynchronization Therapy uses a biventricular pacemaker and is the recommended treatment for Heart Failure patients with Left Bundle Branch Block. The pacemaker settings are determined during the implantation procedure based on the patient's acute response and can be altered during follow-up exams months after implantation. Despite the careful follow-up, only 65-70% of eligible patients respond to this (expensive) therapy and better selection of candidates for CRT as well as optimization of the pacemaker settings for an elected patient are required. Therefore, we developed a deep learning (DL) algorithm on commonly acquired echocardiographic recordings during the standard care path to predict how a patient will likely respond to certain pacemaker settings after 6 months.

AB - Cardiac Resynchronization Therapy uses a biventricular pacemaker and is the recommended treatment for Heart Failure patients with Left Bundle Branch Block. The pacemaker settings are determined during the implantation procedure based on the patient's acute response and can be altered during follow-up exams months after implantation. Despite the careful follow-up, only 65-70% of eligible patients respond to this (expensive) therapy and better selection of candidates for CRT as well as optimization of the pacemaker settings for an elected patient are required. Therefore, we developed a deep learning (DL) algorithm on commonly acquired echocardiographic recordings during the standard care path to predict how a patient will likely respond to certain pacemaker settings after 6 months.

KW - Cardiac Resynchronization Therapy

KW - Cardiac Ultrasound

KW - Convolutional Neural Networks

KW - Deep Learning

U2 - 10.1109/IUS62464.2025.11201532

DO - 10.1109/IUS62464.2025.11201532

M3 - Conference article in proceeding

T3 - IEEE International Ultrasonics Symposium, IUS

BT - 2025 IEEE International Ultrasonics Symposium, IUS 2025

PB - IEEE Computer Society

T2 - 2025 IEEE International Ultrasonics Symposium

Y2 - 15 September 2025 through 18 September 2025

ER -

Deep-Learning to predict outcome of CRT based on pulsed-wave Doppler, clinical biomarkers and pacemaker settings

Abstract

Publication series

Symposium

Keywords

Access to Document

Fingerprint

Cite this