Abstract Body (Do not enter title and authors here): Introduction: Young patients with acute coronary syndrome (ACS) exhibit diverse demographic, clinical and angiographic characteristics.

Hypothesis: We hypothesized that unsupervised machine learning (ML) can identify phenotypic clusters and predict the prognosis among young patients with ACS who undergo percutaneous coronary intervention (PCI).

Methods: We used the Houston Methodist Young-ACS PCI registry (2010-2022) and performed agglomerative clustering to analyze demographic, clinical and angiographic variables among young patients (≤50 years) treated with PCI for ACS.

Results: Among 633 patients, cluster analysis identified three distinct phenotypes. Low risk (n=273) exhibited lowest proportions of heart failure (HF: 10.3%) and peripheral arterial disease (PAD): 5.9%), normal left ventricular ejection fraction (LVEF) (median =0.60) and shorter median culprit vessel stent length (16 mm). Moderate risk (n=101) was characterized by moderate rates of diabetes (36.6%), hypertension (77.2%), prior myocardial infarction (16.8%) and prior PCI (18.8%). High risk (n=78) had highest proportion of diabetes (67.9%), hypertension (93.6%), HF (65.4%), PAD (17.9%), prior MI (41.0%), prior PCI (46.2%), the lowest median LVEF (0.3) and the most frequent use of mechanical circulatory device (5.1%). All-cause mortality differed significantly (Figure), with high-risk cluster showing a four-fold increase in all-cause mortality (HR: 4.50 [1.68-12.1]). There was no significant difference in mortality between moderate and low-risk clusters (HR: 1.52 [0.44-5.19]).

Conclusions: Through unsupervised ML, we identified three distinct phenotypic clusters among young patients with ACS treated with PCI, each exhibiting varying degrees of comorbidity burden and allowing identification of patients with high mortality risk, thus underscoring the potential for phenotype-guided therapeutic approaches.