4348Cluster analysis of cardiovascular risk phenotypes in patients with type 2 diabetes and established atherosclerotic cardiovascular disease: a potential approach to precision medicine
Bibliographic record
Abstract
Introduction: Phenotypic heterogeneity among patients with type 2 diabetes (T2D) and atherosclerotic cardiovascular disease (ASCVD) is ill defined although likely there are multiple subtypes. Purpose: We aimed to use a data agnostic machine learning algorithm to identify potentially different phenotypes among patients with T2DM and ASCVD. Methods: We used data from the 14,671 patients with T2DM and ASCVD enrolled in TECOS, a cardiovascular (CV) safety outcome trial comparing sitagliptin vs placebo with median 3.0 years follow-up. Hierarchical clustering of 40 potentially prognostic baseline variables was conducted. The primary composite outcome (CV death, nonfatal MI/stroke or unstable angina hospitalization) across these clusters was then assessed using Cox proportional models. We also examined whether a differential treatment effect of sitagliptin across the clusters affected clinical outcomes. Results: Five distinct patient clusters were identified. Cluster I included older men with a high prevalence of prior coronary artery disease. Cluster II primarily included women with non-coronary ASCVD. Cluster III comprised Asian patients with a low BMI. Cluster IV included younger males with a high BMI. Cluster V consisted of patients with heart failure. The primary composite outcome occurred in 11.9%, 10.6%, 8.7%, 11.0%, and 16.7% of patients in clusters I to V respectively. The CV risk for the highest vs lowest risk clusters (cluster V vs III) was statistically significant (HR 2.65; p≤0.001; Figure). No heterogeneity of sitagliptin vs. placebo on CV risk across the clusters was evident (interaction P value = 0.54).
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.006 | 0.014 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.002 | 0.002 |
| Bibliometrics | 0.003 | 0.002 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.002 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.002 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".