Background: Implantable cardioverter defibrillators (ICDs) have significantly reduced the incidence of sudden cardiac death in patients with heart failure, particularly those with ischemic heart disease. However, the impact on overall mortality remains controversial, especially in non-ischemic heart failure patients. The Danish Study to Assess the Efficacy of ICDs in Patients with Non-Ischemic Systolic Heart Failure (DANISH) trial and subsequent studies have questioned the efficacy of ICDs in this population, particularly among older patients. The present study aimed to evaluate survival outcomes and predictors in a Croatian cohort of patients with an ICD or cardiac resynchronization therapy defibrillator (CRT-D) device. Methods: This retrospective cohort study analyzed data from 614 patients who received an ICD or CRT-D device at KBC Zagreb between 2009 and 2018. Patient data, including demographic information, device indication, and clinical parameters, were collected at the time of implantation. Follow-up data were systematically recorded to assess device activation and survival outcomes. Statistical analyses included a detailed descriptive analysis, Kaplan–Meier survival estimates, and Cox regression models. Results: The cohort consisted predominantly of males (83.4%), with a mean age of 58.7 years. Most had reduced left ventricular ejection fraction (mean 31.4%) and were classified as New York Heart Association (NYHA) class II or III. Over a median follow-up of 48.4 months, 36.6% of patients died. Device activation occurred in 30.3% of patients, with appropriate activation observed in 88.2% of these cases. Cox regression identified age, non-sustained ventricular tachycardia (NSVT), and decompensation history as significant survival predictors. Conclusions: This study confirmed that appropriate device activation improved survival in patients with an ICD/CRT-D. Age, NSVT, and history of decompensation were key predictors of device activation and survival outcomes. These findings underscore the need for individualized patient assessment when considering inserting ICDs, particularly in non-ischemic heart failure patients. Further research is needed to refine clinical guidelines and optimize patient selection for ICD therapy.

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.

Background: Sudden cardiac death (SCD) remains a major cause of cardiovascular mortality. Implantable cardioverter-defibrillators (ICDs) reduce arrhythmic mortality, but current selection based largely on left ventricular ejection fraction (LVEF) lacks precision. Many patients undergo device implantation without ever receiving therapy, while others at risk remain unprotected. Interpretable machine learning (ML) can integrate diverse clinical variables and refine patient selection while maintaining transparency in clinical reasoning. Methods: We retrospectively analyzed 607 patients who underwent ICD or CRT-D implantation at a Croatian tertiary care center. Baseline demographic, clinical, echocardiographic, laboratory, and device-related variables were collected. Patients were followed through routine device interrogations, with appropriate ICD activation serving as a surrogate for SCD prevention. A logistic regression (LR) model was trained to predict appropriate device activation. Results: LR model demonstrated strong predictive ability (AUC-ROC 0.74, sensitivity 86.50%). Significant predictors included ventricular tachycardia (VT) burden, sustained VT, longer follow-up, and secondary prevention. The combination of furosemide and spironolactone therapy was linked to lower predicted SCD risk. Conclusions: ML applied to routinely collected data can support risk stratification in SCD and complement existing guideline criteria by reinforcing known predictors and uncovering novel associations.