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.
Subject(s)
Arrhythmias, Cardiac/etiology , Arrhythmias, Cardiac/prevention & control , Cardiomyopathies/diagnostic imaging , Cardiomyopathies/therapy , Defibrillators, Implantable/adverse effects , Magnetic Resonance Imaging, Cine/methods , Myocardial Ischemia/diagnostic imaging , Myocardial Ischemia/therapy , Primary Prevention/methods , Aged , Cicatrix/diagnostic imaging , Clinical Decision-Making/methods , Deep Learning , Female , Follow-Up Studies , Humans , Male , Middle Aged , Prognosis , Retrospective Studies , Risk Factors , Ventricular Dysfunction, Left/diagnostic imaging , Ventricular Function, LeftABSTRACT
Chronic inhibition of nitric oxide (NO) synthesis with N(omega)-nitro-L-arginine methyl ester (L-NAME) has become a model of hypertension. The purpose of this study was to evaluate the morphological changes of cerebral arteries in rats with genetic hypertension and hypertension induced by chronic NO deprivation. Spontaneously hypertensive rats (SHR) and normotensive Wistar-Kyoto strain (WKY) were given L-NAME (1 mg.ml(-1)) from age 5 to 7 or 9 weeks. We assessed vascular remodelling and arteriolar injury score (AIS) in various cerebral arteries using different immunohistochemical staining techniques. In WKY and SHR, L-NAME caused an elevation in tail cuff pressure (TCP). The increase in TCP was larger in SHR than in WKY. L-NAME decreased body weight, but increased heart weight in SHR. The lumen diameter and media cross-section area of internal carotid artery (ICA) in SHR were smaller than those in WKY, and further reduced in SHR and WKY after L-NAME treatment. These findings indicate that cerebral vascular remodelling occurs following chronic hypertension either from genetic origin or NO deprivation. L-NAME increased the media thickness in SHR, but not in WKY. This agent also caused an increase in cell volume density, AIS, and inflammatory cells infiltration in perivascular space with a negative growth index in ICA. The media/lumen ratio was higher in SHR than WKY, and further increased following L-NAME treatment. Diversified vascular remodelling occurred in hypertensive rats, but not in untreated WKY. In summary, these results suggest that NO deprivation and genetic hypertension cause vascular changes in various cerebral arteries.
