Related Experiment Video
Updated: Mar 27, 2026
Interventional Diagnostic Procedure: A Practical Guide for the Assessment of Coronary Vascular Function
Published on: March 15, 2022
Identifying clinical phenotype clusters in patients with coronary artery disease
Joris Holtrop1, Carl-Emil Lim2, Alicia Uijl3,4
1Department of Vascular Medicine, Utrecht University, Utrecht, The Netherlands.
Insights
Four distinct patient phenotypes were identified in coronary artery disease (CAD), revealing varying risks for recurrent cardiovascular (CV) events. These findings suggest personalized approaches may improve patient outcomes in CAD management.
Area of Science:
- Cardiology
- Data Science
- Public Health
Background:
- Current cardiovascular (CV) event prevention guidelines for coronary artery disease (CAD) lack personalization.
- Distinct patient subgroups within CAD may benefit from tailored management strategies.
- Identifying these phenotypes is crucial for optimizing secondary prevention in CAD patients.
Purpose of the Study:
- To identify distinct clinical phenotypic clusters in patients with coronary artery disease (CAD).
- To assess the association between these identified phenotypes and the risk of recurrent CV events.
Main Methods:
- Unsupervised machine learning (latent class analysis) was applied to large CAD cohorts (SWEDEHEART and UCC-SMART).
- Patient characteristics were used for clustering, with analysis performed in SWEDEHEART and validated in UCC-SMART.
- Cox proportional hazard models assessed the risk of myocardial infarction, stroke, or CV death across clusters.
Main Results:
- Four reproducible CAD phenotypes were identified: younger males with metabolic risk factors (38%), smokers with few risk factors (21%), older patients with few comorbidities (30%), and patients with multimorbidity (11%).
- The multimorbidity phenotype (cluster 4) exhibited the highest risk of recurrent CV events (HR 4.38), followed by the older patients phenotype (cluster 3, HR 1.78).
- The smoker phenotype (cluster 2) showed a similar risk to the reference group (HR 0.97), with validation confirming these findings.
Conclusions:
- Four distinct and reproducible phenotypes exist in CAD patients, each associated with varying risks of recurrent CV events.
- These identified phenotypes may hold clinical relevance, suggesting a need for personalized treatment strategies.
- Further research into the specific pathophysiology and differential treatment effects for each phenotype is warranted.
Background:
Guideline recommendations for the prevention of cardiovascular (CV) events in patients with coronary artery disease (CAD) are predominantly one-size-fits-all. Clinically identifiable phenotypes needing specific considerations might exist. The purpose of this study is to identify such clinical phenotypic clusters in patients with CAD and assess their relationship with the risk of recurrent CV events.
Methods:
Unsupervised machine learning through latent class analysis was performed in patients with CAD from the Swedish Web-System for Enhancement and Development of Evidence-Based Care in Heart Disease Evaluated According to Recommended Therapies (SWEDEHEART) registry (n=88 894) and Utrecht Cardiovascular Cohort-Second Manifestations of Arterial Disease (UCC-SMART) cohort (n=5506). Characteristics for clustering were based on availability, missingness and clinical relevance. Clustering was performed in SWEDEHEART and validated in UCC-SMART. Association between clusters and the composite of myocardial infarction, stroke or CV death was assessed using Cox proportional hazard models.
Results:
Four phenotypes could be distinguished: cluster 1 (38%, n=33 777) of predominantly younger males with increased body mass index, blood pressure and C-reactive protein, cluster 2 (21%, n=18 775) of smokers with few traditional risk factors, cluster 3 (30%, n=26 501) of older patients with few comorbidities and cluster 4 (11%, n=9841) of patients with multimorbidity. Compared with cluster 1, cluster 4 was at the highest risk (HR 4.38 95% CI (4.01 to 4.78)), followed by cluster 3 (HR 1.78 (1.70 to 1.85)), and cluster 2 (HR 0.97 (0.88 to 1.07)). Validation in UCC-SMART yielded similar results.
Conclusion:
Four distinct and reproducible phenotypes, with differences in the risk of recurrent CV events, were identified among patients with CAD. These may be relevant in practice and warrant research into specific pathophysiology and differences in treatment effects.
Related Concept Videos
01:30Coronary Artery Disease III: Clinical Manifestations
01:30Coronary Artery Disease I: Introduction
01:19Acute Coronary Syndrome II: Pathophysiology and Clinical Manifestations
01:26Coronary Artery Disease II: Pathophysiology
01:27Atherosclerosis II: Clinical Manifestations and Diagnostic Tests
01:30Acute Coronary Syndrome III: Diagnostic Studies