CinE caRdiac magneTic resonAnce to predIct veNTricular arrhYthmia (CERTAINTY)

Abstract

Better models to identify individuals at low risk of ventricular arrhythmia (VA) are needed for implantable cardioverter-defibrillator (ICD) candidates to mitigate the risk of ICD-related complications. We designed the CERTAINTY study (CinE caRdiac magneTic resonAnce to predIct veNTricular arrhYthmia) with deep learning for VA risk prediction from cine cardiac magnetic resonance (CMR). Using a training cohort of primary prevention ICD recipients (n = 350, 97 women, median age 59 years, 178 ischemic cardiomyopathy) who underwent CMR immediately prior to ICD implantation, we developed two neural networks: Cine Fingerprint Extractor and Risk Predictor. The former extracts cardiac structure and function features from cine CMR in a form of cine fingerprint in a fully unsupervised fashion, and the latter takes in the cine fingerprint and outputs disease outcomes as a cine risk score. Patients with VA (n = 96) had a significantly higher cine risk score than those without VA. Multivariate analysis showed that the cine risk score was significantly associated with VA after adjusting for clinical characteristics, cardiac structure and function including CMR-derived scar extent. These findings indicate that non-contrast, cine CMR inherently contains features to improve VA risk prediction in primary prevention ICD candidates. We solicit participation from multiple centers for external validation.

Artificial Intelligence Applications in Cardiovascular Magnetic Resonance Imaging: Are We on the Path to Avoiding the Administration of Contrast Media?

“…The proposed score remained significantly associated with ventricular arrhythmia after adjustment in the multivariable regression analysis (Model I: adjusting for sex, type of cardiomyopathy, use of diuretics, and hsCRP; HR 3.24, p = 0.005. Model II: further adjusting for LVEDI, LV ejection fraction, LV LGE gray zone, LA maximum volume index, and LA total emptying fraction; HR 2.67, p = 0.027) [ 75 ]. Although it delivered promising prognostic results, the CERTAINTY study has intrinsic limitations, including the lack of an external validation cohort and the small sample size obtained from a single institution for the training cohort.…”

Artificial Intelligence in Ventricular Arrhythmias and Sudden Death

“…33 Somewhat similarly, another study used a DL-derived cine risk score from cardiac MRI images that achieved an AUC of 0.69 for predicting appropriate ICD therapy in 7.1 years in 350 ICD recipients (96 events). 34…”

Advanced imaging for risk stratification for ventricular arrhythmias and sudden cardiac death

“…ML was also used for dimensionality reduction in this study, which interestingly resulted in all LGE-derived features being discarded. Along these lines, a recent study used an unsupervised, deep learning approach on cine CMR among ICM patients to derive cardiac features that were then used as inputs in a separate deep neural network that successfully predicted VA risk ( 138 ). The inverse approach, using ML to generate pre-defined features, is also appreciable in recent literature.…”