PulseExploreJournal ClubDebatesTrendingResearchersJournals
Instagram
HomeExploreJournal ClubTrending
Synapse
⌘+K
Synapse
May 9, 2026Physiological Measurement0 citationsOpen Access

Machine learning-based information flow analysis of ECG signals for long QT syndrome

View Full Paper
MOMateusz OzimekWarsaw University of TechnologyMAMałgorzata Andrzejewska-OzimekWarsaw University of TechnologyMPMonika PetelczycWarsaw University of Technology

Key Result

Machine learning models using entropy-based ECG features successfully discriminated congenital long QT syndrome patients from healthy controls, with Random Forest achieving a mean accuracy of 95.9%.

Key Points

  • This research aims to explore ECG signal information flow to identify biomarkers of long QT syndrome.
  • ECG recordings were analyzed using entropy-based measures to evaluate information transfer.
  • Supervised machine learning models classified congenital long QT syndrome patients versus healthy controls.
  • Model performance was assessed through repeated stratified train-test splits and various performance metrics.
  • Random Forest classifier achieved accuracy of 95.9%, sensitivity of 95.9%, and specificity of 92.9%.
  • Support Vector Machine classifier achieved accuracy of 93.1%, sensitivity of 93.1%, and specificity of 92.0%.
  • Explainability analysis showed the importance of multivariate information flow features over single-source measures.

Study Design

Type

Cross-Sectional

Structured PICO

Does machine learning-based information flow analysis of ECG signals accurately discriminate patients with congenital long QT syndrome from healthy controls?

P
Population
Patients with congenital long QT syndrome and healthy controls
I
Intervention
Machine learning models (Random Forest and Support Vector Machine) using entropy-based measures of information transfer derived from beat-to-beat ECG time series
C
Comparator
Healthy controls
O
Outcome
Discrimination between long QT syndrome patients and healthy controls (accuracy, sensitivity, specificity, AUC)surrogate

Machine learning models using entropy-based information flow from ECG signals can accurately discriminate patients with congenital long QT syndrome from healthy controls.

Abstract

OBJECTIVE: Cardiovascular diseases remain the leading cause of death worldwide, highlighting the need for non-invasive and cost-effective risk assessment tools. Biological systems, including the heart, exhibit complex nonlinear dynamics arising from interactions between their subsystems. Information-theoretic measures, particularly entropy-based methods, provide a framework to quantify these interactions. Using ECG recordings, we investigate information flow between heart rhythm and ventricular repolarization to identify potential markers of pathological alterations in cardiac electrical activity. Approach: Entropy-based measures of information transfer were derived from beat-to-beat ECG time series using a window-based approach and subsequently averaged at the subject level. These features were used as inputs to supervised machine learning models to discriminate patients with congenital long QT syndrome from healthy controls. Model performance was evaluated using repeated stratified train-test splits, and classification robustness was assessed across multiple runs using standard performance metrics, including the area under the receiver operating characteristic curve. The explainable artificial intelligence techniques were applied. SHapley Additive exPlanations (SHAP) were used to quantify the contribution of entropy-based features to the model predictions. This post-hoc explainability analysis enabled systematic assessment of feature importance while preserving the predictive performance of the models. Results: The proposed approach achieved high and stable classification performance across repeated validation runs. Both Random Forest (RF) and Support Vector Machine (SVM) classifiers demonstrated high discrimination between long QT syndrome patients and healthy controls, with consistently high AUC. For RF a mean accuracy of 95.9%, mean sensitivity of 95.9%, and mean specificity of 92.9% were achieved across repeated runs. For SVM the corresponding mean values were 93.1%, 93.1%, and 92.0%, respectively. Conclusions: Explainability analysis revealed a dominant contribution of multivariate and conditional information flow features compared with single-source entropy measures, highlighting the relevance of joint and conditional interactions in the classification patterns.

Ask AI
Helpful
Bookmark
Share
View Full Paper

Cite This Study

Ozimek et al. (2026) conducted a cross-sectional in Congenital long QT syndrome. Machine learning models (Random Forest and Support Vector Machine) using entropy-based ECG features was evaluated on Discrimination between long QT syndrome patients and healthy controls (accuracy). Machine learning models using entropy-based ECG features successfully discriminated congenital long QT syndrome patients from healthy controls, with Random Forest achieving a mean accuracy of 95.9%.

synapsesocial.com/papers/69fecf16b9154b0b8287638bhttps://doi.org/10.1088/1361-6579/ae6969
Ask AI
Helpful
Bookmark
Share
View Full Paper