Cluster Analysis of Cardiovascular Phenotypes in Patients With Type 2 Diabetes and Established Atherosclerotic Cardiovascular Disease: A Potential Approach to Precision Medicine

Abhinav Sharma, Yinggan Zheng, Justin A. Ezekowitz, Cynthia M. Westerhout, Jacob A. Udell, Shaun G. Goodman, Paul W. Armstrong, John B. Buse, Jennifer B. Green, Robert G. Josse, Keith D. Kaufman, Darren K. McGuire, Giuseppe Ambrosio, Lee Ming Chuang, Renato D. Lopes, Eric D. Peterson, Rury R. Holman

Research output: Contribution to journalArticlepeer-review

17 Scopus citations

Abstract

OBJECTIVE Phenotypic heterogeneity among patients with type 2 diabetes mellitus (T2DM) and atherosclerotic cardiovascular disease (ASCVD) is ill defined. We used cluster analysis machine-learning algorithms to identify phenotypes among trial participants with T2DM and ASCVD. RESEARCH DESIGN AND METHODS We used data from the Trial Evaluating Cardiovascular Outcomes with Sitagliptin (TECOS) study (n = 14,671), a cardiovascular outcome safety trial comparing sitagliptin with placebo in patients with T2DM and ASCVD (median follow-up 3.0 years). Cluster analysis using 40 baseline variables was conducted, with associations between clusters and the primary composite outcome (cardiovascular death, nonfatal myocardial infarction, nonfatal stroke, or hospitalization for unstable angina) assessed by Cox proportional hazards models. We replicated the results using the Exenatide Study of Cardiovascular Event Lowering (EXSCEL) trial. RESULTS Four distinct phenotypes were identified: Cluster I included Caucasian men with a high prevalence of coronary artery disease; cluster II included Asian patients with a low BMI; cluster III included women with noncoronary ASCVD disease; and cluster IV included patients with heart failure and kidney dysfunction. The primary outcome occurred, respectively, in 11.6%, 8.6%, 10.3%, and 16.8% of patients in clusters I to IV. The crude difference in cardiovascular risk for the highest versus lowest risk cluster (cluster IV vs. II) was statistically significant (hazard ratio 2.74 [95% CI 2.29–3.29]). Similar phenotypes and outcomes were identified in EXSCEL. CONCLUSIONS In patients with T2DM and ASCVD, cluster analysis identified four clinically distinct groups. Further cardiovascular phenotyping is warranted to inform patient care and optimize clinical trial designs.

Original languageEnglish (US)
Pages (from-to)204-212
Number of pages9
JournalDiabetes care
Volume45
Issue number1
DOIs
StatePublished - Jan 2022

ASJC Scopus subject areas

  • Internal Medicine
  • Endocrinology, Diabetes and Metabolism
  • Advanced and Specialized Nursing

Fingerprint

Dive into the research topics of 'Cluster Analysis of Cardiovascular Phenotypes in Patients With Type 2 Diabetes and Established Atherosclerotic Cardiovascular Disease: A Potential Approach to Precision Medicine'. Together they form a unique fingerprint.

Cite this