331 A Machine Learning-based Pharmacogenomic Association Study of Major Adverse Cardiovascular Events (MACEs) in Caribbean Hispanic Patients on Clopidogrel

Abstract

OBJECTIVES/GOALS: To summarize baseline characteristics and risk factors for major adverse cardiovascular events (MACEs) and develop a prediction model by testing the association between genetic variants and MACEs in Caribbean Hispanic patients on clopidogrel using machine-learning (ML) techniques. METHODS/STUDY POPULATION: This is a secondary analysis of available clinical and genomic data from an existing database of 600 Caribbean Hispanic cardiovascular (CV) patients on clopidogrel. MACEs is defined as the composite of all-cause death, myocardial infarction, stroke and stent thrombosis over 6 months. Dataset is divided into training (60%) and testing (40%) sets, respectively. Two different supervised ML approaches (i.e. multiclass classification and regression algorithms) are applied to the study dataset using Python v3.5 and WEKA, and tested by receiver operating curve (ROC) analysis. A case-control association analysis between MACEs at 6 months and genotypes is performed by using chi-squared test. RESULTS/ANTICIPATED RESULTS: Average age of participants was 68 years-old, 55% males, with high prevalence of risk factors (i.e., overweight: 28.4 kg/m2; hypertension: 83.8%; hypercholesterolemia: 71.9% and diabetes: 54.8%). MACEs rate is 13.8%, with 33.5% resistant to clopidogrel. Logistic regression, KNN and gradient boosting showed the best performance, as suggested by ROC analysis and AUC CV scores of 0.6-0.7. A significant association between MACE occurrence and ≥3 risk alleles was found (OR=8.17; p=0.041). We anticipate that these genetic variants (CYP2C19*2, rs12777823, PON1-rs662, ABCB1-rs2032582, PEAR1-rs12041331) will uniquely contribute to clopidogrel resistance and MACEs in Caribbean Hispanics. DISCUSSION/SIGNIFICANCE: Our findings help address in part the long-standing problem of excluding minorities from research, which entails a gap of knowledge about clopidogrel pharmacogenomics in Puerto Ricans. This study provides a possible ML model that integrates clinical and pharmacogenomics for MACE risk estimation.