Phenotypic clustering of dilated cardiomyopathy patients highlights important pathophysiological differences

Abstract

Aims The dilated cardiomyopathy (DCM) phenotype is the result of combined genetic and acquired triggers. Until now, clinical decision-making in DCM has mainly been based on ejection fraction (EF) and NYHA classification, not considering the DCM heterogenicity. The present study aimed to identify patient subgroups by phenotypic clustering integrating aetiologies, comorbidities, and cardiac function along cardiac transcript levels, to unveil pathophysiological differences between DCM subgroups. Methods and results We included 795 consecutive DCM patients from the Maastricht Cardiomyopathy Registry who underwent in-depth phenotyping, comprising extensive clinical data on aetiology and comorbodities, imaging and endomyocardial biopsies. Four mutually exclusive and clinically distinct phenogroups (PG) were identified based upon unsupervised hierarchical clustering of principal components: [PG1] mild systolic dysfunction, [PG2] auto-immune, [PG3] genetic and arrhythmias, and [PG4] severe systolic dysfunction. RNA-sequencing of cardiac samples (n = 91) revealed a distinct underlying molecular profile per PG: pro-inflammatory (PG2, auto-immune), pro-fibrotic (PG3; arrhythmia), and metabolic (PG4, low EF) gene expression. Furthermore, event-free survival differed among the four phenogroups, also when corrected for well-known clinical predictors. Decision tree modelling identified four clinical parameters (auto-immune disease, EF, atrial fibrillation, and kidney function) by which every DCM patient from two independent DCM cohorts could be placed in one of the four phenogroups with corresponding outcome (n = 789; Spain, n = 352 and Italy, n = 437), showing a feasible applicability of the phenogrouping. Conclusion The present study identified four different DCM phenogroups associated with significant differences in clinical presentation, underlying molecular profiles and outcome, paving the way for a more personalized treatment approach.

Machine-learning–based exploration to identify remodeling patterns associated with death or heart-transplant in pediatric-dilated cardiomyopathy

“…The use of artificial intelligence is evolving, predominantly in adult studies, using 'bigdata' and unsupervised ML approaches to classify phenotypes who may be treated similarly, with a predictable response. 25 Unbiased or unsupervised hierarchical clustering has been used to identify new phenotypes in cohorts of adults with heart failure. 26,27 Our approach could foreseeably be utilized in the same way in the phenotypically heterogenous paediatric population.…”

Cardiovascular adverse events in pregnancy: A global perspective

“…68 Contributing factors to PPCM include genetic predisposition 69 as well as auto-immune responses. [70][71][72] Using such factors, all be it indirectly, to define phenoclusters 73 -it could be possible to identify novel therapeutic targets to guide personalized medicine in PPCM.…”

Diagnosis and Risk Prediction of Dilated Cardiomyopathy in the Era of Big Data and Genomics

“…Unsupervised clustering algorithms may also be able to help our understanding of phenotypic heterogeneity in DCM, as they can identify pathophysiologically similar individuals who may respond in a uniform and predictable way to treatment [ 100 ]. Indeed, a recent study identified four different DCM phenotype subgroups (“phenogroups”) using an unsupervised hierarchical clustering algorithm, which was validated in two external registries: the Italian Trieste Registry and a cohort from Madrid [ 4 , 101 , 102 ]. The four identified phenogroups were summarised as (i) mild systolic dysfunction, (ii) auto-immune disease, (iii) arrhythmic, and (iv) severe systolic dysfunction.…”

“…The four identified phenogroups were summarised as (i) mild systolic dysfunction, (ii) auto-immune disease, (iii) arrhythmic, and (iv) severe systolic dysfunction. The latter three groups had comparable and relatively unfavourable outcome compared to the first phenogroup [ 101 ]. Whether these subgroups can be used to guide clinical decision-making remains to be investigated [ 5 ].…”