The role of precision phenotyping in dilated cardiomyopathy: Defining novel disease subtypes using multidimensional data

Background: Dilated cardiomyopathy (DCM) is a final common manifestation of heterogenous etiologies. Adverse outcomes highlight the need for disease stratification beyond ejection fraction. Objectives: To identify novel, reproducible sub-phenotypes of DCM using multi-parametric data for improved patient-stratification. Methods: Longitudinal, observational UK-derivation (n=426, median age 54y, 67% men) and Dutch-validation (n=239, median age 56y, 64% men) cohorts of DCM patients (enrolled 2009-16) with clinical, genetic, cardiovascular magnetic resonance, and proteomic assessments. Machine learning with profile regression identified novel disease subtypes. Penalized multinomial logistic regression was used for validation. Nested Cox models compared novel groupings to conventional risk measures. Primary composite outcome was cardiovascular death, heart failure or arrhythmia events (median follow-up 4y). Results: Three novel DCM subtypes were identified: profibrotic metabolic; mild non-fibrotic; and biventricular impairment. Prognosis differed between subtypes in both derivation (p