Automated Detection and Removal of Pacing Artifacts from ECG Signal: CRIC and Cleveland Clinic Cohorts.

Authors

Rajkumar Dhar, Hassaan A Bukhari, Shivangi Kewalramani, Claudia Wong, Luke Witzigreuter, Hernan Rincon-Choles, Mayank Kansal, L Lee Hamm, Jiang He, Panduranga Rao, Zeenat Bhat, Crystal Gadegbeku, Bernard Jaar, Larisa G Tereshchenko, Amanda H Anderson, Lawrence J Appel, Jing Chen, Debbie L Cohen, Laura M Dember, Alan S Go, James P Lash, Mahboob Rahman

Published in

IEEE transactions on bio-medical engineering. Volume PP. Jul 24, 2026. Epub Jul 24, 2026.

Abstract

Pacing artifacts in electrocardiogram (ECG) signals can interfere with waveform analysis and downstream quantitative interpretation. This study presents an algorithm for detecting and removing pacing artifacts from routine ECG recordings.
The algorithm applies high pass filtering and Shannon energy computation to suppress cardiac components and enhance pacing artifacts. Principal component analysis (PCA) is then applied to the 12-lead ECGs to identify artifact start and end points from the first principal component. At each candidate location, slopes are calculated across leads, and artifacts are removed by linear interpolation only when the slope magnitude exceeds a predefined threshold. The algorithm was developed using 493 12-lead ECGs from the Chronic Renal Insufficiency Cohort and validated using 203 Cleveland Clinic 12-lead ECGs, 80 Cardiac Memory with ICD 12 lead ECGs, and 200 10-second two-lead Holter ECG epochs from the MIT-BIH Arrhythmia Database. A graphical user interface was developed for review and refinement.
The algorithm automatically detected and removed pacing artifacts in 84% of validation ECG files; the remaining files required user-guided refinement. Overall sensitivity and specificity for pacing artifact detection were 98.4% and 76.2%, respectively.
The proposed algorithm detects and removes pacing artifacts with substantial automation while allowing guided refinement in challenging recordings.
The framework combines multilead PCA-based localization, lead-specific slope confirmation, and adaptive artifact-width removal directly on routine ECG, enabling morphology-preserving preprocessing for quantitative and AI-enabled ECG analysis.

PMID:
42497052
Bibliographic data and abstract were imported from PubMed on 25 Jul 2026.

Read full publication at:
Please sign in to see all details.

Stats

1-terrible, 9-excellent. How would you rate this publication? Sign in in to submit your rating.

Post a comment

You need to be signed in to post comments. You can sign in here.

Comments

There are no comments yet.