Related Experiment Video
Updated: May 16, 2026
Analysis of SAMHD1 Restriction by Flow Cytometry in Human Myeloid U937 Cells
Published on: June 14, 2021
Automated detection of non-physiological artifacts on ECG signal: UK Biobank and CRIC
Hassaan A Bukhari1, Shivangi Kewalramani1, Luke Witzigreuter1
1Quantitative Health Sciences, Lerner Research Institute, Cleveland Clinic, Cleveland, OH, USA.
Insights
An automated algorithm accurately detects electrocardiogram (ECG) artifacts and lead misplacement, improving ECG quality control. This tool enhances the reliability of clinical interpretations by identifying poor data quality before analysis.
Area of Science:
- Cardiology
- Biomedical Engineering
- Data Science
Background:
- Electrocardiograms (ECGs) are crucial in clinical practice.
- Poor data quality, artifacts, and electrode misplacement can compromise ECG interpretation.
- Automated identification of these issues is needed for reliable analysis.
Purpose of the Study:
- To develop a fully automated algorithm for detecting ECG artifacts and lead misplacement.
- To ensure the quality and accuracy of ECG data used in clinical settings.
Main Methods:
- Utilized large datasets (UK Biobank and CRIC cohort) for algorithm development and validation.
- Developed an algorithm to detect non-physiological ECG artifacts (amplitude, frequency outliers) and misplaced electrodes.
- Assessed algorithm performance using sensitivity, specificity, ROC AUC, and Kappa statistics.
Main Results:
- The algorithm demonstrated high accuracy in detecting artifacts and misplacements in both datasets.
- UK Biobank: 84.9% sensitivity, 100% specificity, 0.924 ROC AUC, 0.91 Kappa.
- CRIC cohort: 94.90% agreement, 16.8% sensitivity, 99.3% specificity, 0.580 ROC AUC.
Conclusions:
- The developed automated algorithm accurately identifies ECG artifacts and lead misplacement.
- This enables automated quality control for ECG analysis, enhancing clinical interpretation.
- The algorithm's code is publicly available for further research and application.
Introduction:
An electrocardiogram (ECG) is commonly used in clinical practice. Poor data quality, artifacts, and misplacement of electrodes have to be identified before the clinical interpretation of ECG. We aimed to develop an algorithm to automatically identify ECG artifacts and lead misplacement.
Methods And Results:
We utilized 42,743 ECGs from UK Biobank (UKB; n = 42,743 participants; age 55±8 y; cardiovascular disease 1.2 %; diabetes 0.9 %; chronic kidney disease 0.5 %; ventricular pacing 0 %) for the algorithm development and 41,495 ECGs from the Chronic Renal Insufficiency Cohort (CRIC; n = 3912 participants; age 63 ± 11 y; cardiovascular disease 78 %; diabetes 56 %; chronic kidney disease 100 %; ventricular pacing 3.5 %) for external validation. We developed a fully automated algorithm to detect non-physiological ECG artifacts, such as high or low peak-to-peak amplitude, frequency-based outliers, and misplaced electrodes. In UKB, the algorithm demonstrated a sensitivity of 84.9 %, a specificity of 100 %, an ROC AUC of 0.924, and a Kappa statistic of 0.91. We observed 98.81 % agreement between ground truth and algorithm-identified non-physiological ECG artifacts, significantly (p < 0.00001) larger than the random agreement of 86.91 % expected at the observed 7.6 % prevalence. The misplacement of limb lead electrodes in UKB affected the Wilson Central Terminal. In CRIC, we observed an agreement of 94.90 %, which was significantly (p < 0.00001) better than by chance (93.27 % at the observed 5.3 % prevalence, including pacing artifacts), 16.8 % sensitivity, 99.3 % specificity, and an ROC AUC of 0.580.
Conclusion:
The fully automated algorithm can accurately detect ECG artifacts and potential lead misplacement, thus permitting automated quality control of ECG analysis. The code is provided at https://github.com/Tereshchenkolab/ECG-quality-control.
