Implantable cardioverter defibrillators (ICDs) protect patients from sudden cardiac death (SCD). Landmark trials demonstrating their efficacy for primary prevention in patients with heart failure (HF) used reduced left ventricular ejection fraction (LVEF) as a major inclusion criterion and current recommendations for ICDs rely on this variable in patient selection. Contemporary medical management has reduced the risk of SCD from 10-15% annually in patients in the control arm of early pivotal ICD trials to approximately 3% in patients enrolled in recent trials of guideline directed medical therapy. Although SCD is the major cause of cardiovascular mortality in HF patients with LVEF >35%, ICDs are not recommended for primary prevention in this subset of the population. Consequently, an increasingly large proportion of patients receiving an ICD for primary prevention never require the protection offered by the device while patients who fail to meet LVEF criteria for a device experience SCD. The availability of novel diagnostic tests and use of artificial intelligence (AI) approaches to access and standardize test results offer the opportunity to improve risk prediction of SCD. This review summarizes reasons for the widening gap between risk of SCD and current recommendations for ICD use in the HF population. It discusses limitations in the current approach for predicting risk of SCD, including gaps in our knowledge base due to differences between patients enrolled in clinical trials and those seen in real world settings. The review provides an overview of variables associated with SCD that could be used to generate novel risk prediction models that have greater predictive accuracy than LVEF alone. The application of AI for extracting and standardizing diagnostic test results and machine learning algorithms for developing risk prediction models are also discussed. The potential impact of ongoing clinical trials on recommendations for ICD use for primary prevention is summarized. The review concludes by describing a dynamic approach for generating novel risk prediction models to better align risk of SCD with recommendations for ICD implantation in patients with HF for both the present and in the future as additional treatment strategies that alter risk of SCD become available.
EditorsEditor-in-ChiefHarlan M. Krumholz, MD, SM, FACC CME EditorRagavendra R. Baliga, MDAuthorBhaskar Arora, MD
Important DatesDate of Release: July 28, 2025Term of Approval/Date of CME/MOC Expiration: July 27, 2026