PacECG-Net: A Multi-modal Approach Integrating LLMs and ECG for LVSD Classification in Pacemaker Patients

Wonkyeong Shim, Namjun Park, Donggeun Ko, San Kim, Hye Bin Gwag, Young Jun Park, Seung-Jung Park, Jaekwang Kim

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

This study presents an AI-based model using ECG signals to predict left ventricular systolic dysfunction (LVSD) in pacemaker patients. A 1D convolutional neural network (CNN) combined with large language models processed both sequential ECG data and nonsequential clinical metadata. The model achieved an AUROC of 0.97 on both general and pacemaker-specific datasets, demonstrating its high accuracy. This approach offers a fast, cost-effective alternative to traditional echocardiography, improving LVSD detection in patients with pacemakers.

Original languageEnglish
Title of host publication40th Annual ACM Symposium on Applied Computing, SAC 2025
PublisherAssociation for Computing Machinery
Pages1303-1305
Number of pages3
ISBN (Electronic)9798400706295
DOIs
StatePublished - 14 May 2025
Event40th Annual ACM Symposium on Applied Computing, SAC 2025 - Catania, Italy
Duration: 31 Mar 20254 Apr 2025

Publication series

NameProceedings of the ACM Symposium on Applied Computing

Conference

Conference40th Annual ACM Symposium on Applied Computing, SAC 2025
Country/TerritoryItaly
CityCatania
Period31/03/254/04/25

Keywords

  • classification
  • CNN
  • ECG
  • echocardiography
  • imbalanced data
  • LLMs
  • LVEF
  • LVSD
  • multi-modal
  • pacemaker
  • PPM

Fingerprint

Dive into the research topics of 'PacECG-Net: A Multi-modal Approach Integrating LLMs and ECG for LVSD Classification in Pacemaker Patients'. Together they form a unique fingerprint.

Cite this