EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Machine Learning-Based Risk Stratification for Sudden Cardiac Death Using Clinical and Device-Derived Data

Hana Ivandic iD, Branimir Pervan iD, Mislav Puljevic iD, Vedran Velagic iD, Alan Jovic iD

Sensors · 2025

DOI: 10.3390/s26010086 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, 2025. Verfasst von Hana Ivandic und 4 weiteren Autor:innen. Beteiligte Einrichtung: University of Zagreb Faculty of Electrical Engineering and Computing, Unska 3, HR-10000 Zagreb, Croatia. Hauptthemen laut MEDLINE: Death, Sudden, Cardiac, Machine Learning. Die Arbeit nennt 35 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Sudden cardiac death (SCD) remains a major clinical challenge, with implantable cardioverter-defibrillators (ICDs) serving as the primary preventive intervention. Current patient selection guidelines rely on limited and imperfect risk markers. This study explores the potential of machine learning (ML) models to improve SCD risk prediction using tabular clinical data that include features derived from medical sensing devices such as electrocardiograms (ECGs) and ICDs. Several ML models, including tree-based models, Naive Bayes (NB), logistic regression (LR), and voting classifiers (VC), were trained on demographic, clinical, laboratory, and device-derived variables from patients who underwent ICD implantation at a Croatian tertiary center. The target variable was the activation of the ICD device (appropriate or inappropriate/missed), serving as a surrogate for high-risk SCD detection. Models were optimized for the F2-score to prioritize high-risk patient detection, and interpretability was achieved with post hoc SHAP value analysis, which confirmed known and revealed additional potential SCD predictors. The random forest (RF) model achieved the highest F2-score (F2-score 0.74, AUC-ROC 0.73), demonstrating a recall of 97.30% and meeting the primary objective of high true positive detection, while the VC classifier achieved the highest overall discrimination (F2-score 0.71, AUC-ROC 0.76). The predictive performance of multiple ML models, particularly the high recall they achieved, demonstrates the promising potential of ML to refine ICD patient selection.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Death, Sudden, CardiacMachine LearningHumansDefibrillators, ImplantableRandom ForestRisk AssessmentBayes TheoremFemaleElectrocardiographyClassification AlgorithmsMalePredictive Learning ModelsMiddle AgedPrediction AlgorithmsRisk FactorsLogistic ModelsROC CurveAged

Stichwörter der Autor:innen

SHAP analysisimplantable cardioverter defibrillatormachine learningsudden cardiac death

Autor:innen und Institutionen

  • University of Zagreb Faculty of Electrical Engineering and Computing, Unska 3, HR-10000 Zagreb, Croatia.
  • University Hospital Centre Zagreb, Ulica Mije Kišpatića 12, HR-10000 Zagreb, Croatia.
  • University of Zagreb School of Medicine, Šalata 2, HR-10000 Zagreb, Croatia.

ORCID-Profile: Hana Ivandic, Branimir Pervan, Mislav Puljevic, Vedran Velagic, Alan Jovic

Zitieren

APA

Ivandic, H., Pervan, B., Puljevic, M., Velagic, V., & Jovic, A. (2025). Machine Learning-Based Risk Stratification for Sudden Cardiac Death Using Clinical and Device-Derived Data. Sensors. https://doi.org/10.3390/s26010086

Vancouver

Ivandic H, Pervan B, Puljevic M, Velagic V, Jovic A. Machine Learning-Based Risk Stratification for Sudden Cardiac Death Using Clinical and Device-Derived Data. Sensors. 2025. doi:10.3390/s26010086

BibTeX
@article{Ivandic2025,
  author = {Ivandic, Hana and Pervan, Branimir and Puljevic, Mislav and Velagic, Vedran and Jovic, Alan},
  title = {Machine Learning-Based Risk Stratification for Sudden Cardiac Death Using Clinical and Device-Derived Data},
  journal = {Sensors},
  year = {2025},
  doi = {10.3390/s26010086}
}
Kostenlos starten →