Clustering of patients with inconclusive non-invasive stress testing referred for vasodilator stress cardiovascular magnetic resonance

Background: Inconclusive non-invasive stress testing is associated with impaired outcome. This population is very heterogeneous, and its characteristics are not well depicted by conventional methods.

Aims: To identify patient subgroups by phenotypic unsupervised clustering, integrating clinical and cardiovascular magnetic resonance data to unveil pathophysiological differences between subgroups of patients with inconclusive stress tests.

Methods: Between 2008 and 2020, consecutive patients with a first inconclusive non-invasive stress test referred for stress cardiovascular magnetic resonance were followed for the occurrence of major adverse cardiovascular events (defined as cardiovascular death or myocardial infarction). A cluster analysis was performed on clinical and cardiovascular magnetic resonance variables.

Results: Of 1402 patients (67% male; mean age 70±11years) who completed the follow-up (median 6.5years, interquartile range 5.6-7.5years), 197 experienced major adverse cardiovascular events (14.1%). Three distinct phenogroups were identified based upon unsupervised hierarchical clustering of principal components: phenogroup 1=history of percutaneous coronary intervention with viable myocardial infarction and preserved left ventricular ejection fraction; phenogroup 2=atrial fibrillation with preserved left ventricular ejection fraction; and phenogroup 3=coronary artery bypass graft with non-viable myocardial scar and reduced left ventricular ejection fraction. Using survival analysis, the occurrence of major adverse cardiovascular events (P=0.007), cardiovascular mortality (P=0.002) and all-cause mortality (P<0.001) differed among the three phenogroups. Phenogroup 3 presented the worse prognosis. In each phenogroup, ischaemia was associated with major adverse cardiovascular events (phenogroup 1: hazard ratio 2.79, 95% confidence interval 1.61-4.84; phenogroup 2: hazard ratio 2.59, 95% confidence interval 1.69-3.97; phenogroup 3: hazard ratio 3.16, 95% confidence interval 1.82-5.49; all P<0.001).

Conclusions: Cluster analysis of clinical and cardiovascular magnetic resonance variables identified three phenogroups of patients with inconclusive stress testing, with distinct prognostic profiles.