P6485Biventricular imaging markers to predict outcome in non-compaction cardiomyopathy: a machine learning study

Abstract

Aims: Left ventricular non-compaction cardiomyopathy (LVNC) is a genetic heart disease, which main clinical manifestations are heart failure, arrhythmias and em-bolic events. Its prevalence is increasing due to improvements in cardiac imaging methods, such as echocardiography (echo) and cardiac magnetic resonance imaging (CMRI). However, imaging parameters related to prognosis are poorly known. The goal of this study was to analyze a large set of echo and CMR parameters using machine learning techniques, in order to find an association between these imaging markers and clinical outcome in a long-term follow-up of LVNC patients. Methods: One hundred and eight LVNC patients (38.3 +15.5 years, 48% male) diagnosed by echo and CMRI criteria were recruited for this study and were followed for 5.83 + 3.9 years, during which combined "hard events" (death, cardiac transplantation, heart failure hospitalization, aborted sudden cardiac death, complex ventricular arrhythmias, and embolisms) were registered. CMRI and echo parameters were extracted by expert users and subsequently analyzed via a su-pervised machine learning methodology using "cross-validation". Results: Forty-seven (43,5%) patients presented at least one hard event. The best combination of imaging markers was left ventricular ejection fraction (by CMRI), right ventricular end-systolic volume (by CMRI), right ventricular systolic dysfunction (by echo) and right ventricular lower diameter (by CMRI) with accu-racy, sensitivity and specificity rates of 75.5%, 77%, 75%, respectively. Figure shows the results of ROC analyses on the classification outcomes obtained with using only echo or CMRI markers as well as combination of echo and CMRI markers. For the latter case, the selected echo and CMRI markers are written in blue and red, respectively. "»r Echo CMRI Echo & CMRI Results of ROC analyses on outcomes Conclusion: The combination of echo and CMRI indices improved the stratifi-cation of the risk in LVNC patients. Also, ourfindings showed the importance of biventricular assessment to detect the severity of this cardiomyopathy.