Subgrouping multimorbid patients with ischemic heart disease by means of unsupervised clustering: A cohort study of 72,249 patients defined comprehensively by diagnoses prior to presentation

Background There are no methods for classifying patients with ischemic heart disease (IHD) based on the entire spectrum of pre-existing diseases. Such methods might be clinically useful due to the marked differences in presentation and course of disease. Methods A population-based cohort study from a Danish secondary care setting of patients with IHD (2004-2016) and subjected to a coronary angiography (CAG) or coronary computed tomography angiography (CCTA). Data sources were The Danish National Patient Registry, in-hospital laboratory data, and genetic data from Copenhagen Hospital Biobank. Comorbidities included diagnoses assigned prior to presentation of IHD. Patients were clustered by means of the Markov Clustering Algorithm using the entire spectrum of registered multimorbidity. The two prespecified outcomes were: New ischemic events (including death from IHD causes) and death from non-IHD causes. Patients were followed from date of CAG/CCTA until one of the two outcomes occurred or end of follow-up, whichever came first. Biological and clinical appropriateness of clusters was assessed by comparing risks (estimated from Cox proportional hazard models) in clusters and by phenotypic and genetic enrichment analyses, respectively. Findings In a cohort of 72,249 patients with IHD (mean age 63.9 years, 63.1% males), 31 distinct clusters (C1-31, 67,136 patients) were identified. Comparing each cluster to the 30 others, seven clusters (9,590 patients) had statistically significantly higher or lower risk of new ischemic events (five and two clusters, respectively). 18 clusters (35,982 patients) had a higher or lower risk of death from non-IHD causes (12 and six clusters, respectively). All clusters at increased risk of new ischemic events, associated with risk of death from non-IHD causes as well. Cardiovascular or inflammatory diseases were commonly enriched in clusters (13), and distributions for 24 laboratory test results differed significantly across clusters. Clusters enriched for cerebrovascular diseases were generally not at increased risk of the two outcomes. Polygenic risk scores were increased in a total of 15 clusters (48.4%). Conclusions Clustering of patients with IHD based on pre-existing comorbidities identified subgroups of patients with significantly different clinical outcomes and presented a tool to rank pre-existing comorbidities based on their association with clinical outcomes. This novel method may support better classification of patients and thereby differentiation of treatment intensity depending on expected outcomes in subgroups.