Baseline and on-statin treatment lipoprotein(a) levels for prediction of cardiovascular events: individual patient-data meta-analysis of statin outcome trials

Abstract

Background: Elevated lipoprotein(a) is a genetic risk factor for cardiovascular disease in general population studies. However, its contribution to risk for cardiovascular events in patients with established cardiovascular disease or on statin therapy is uncertain.

Methods: Patient-level data from seven randomised, placebo-controlled, statin outcomes trials were collated and harmonised to calculate hazard ratios (HRs) for cardiovascular events, defined as fatal or non-fatal coronary heart disease, stroke, or revascularisation procedures. HRs for cardiovascular events were estimated within each trial across predefined lipoprotein(a) groups (15 to <30 mg/dL, 30 to <50 mg/dL, and ≥50 mg/dL, vs <15 mg/dL), before pooling estimates using multivariate random-effects meta-analysis.

Findings: Analyses included data for 29 069 patients with repeat lipoprotein(a) measurements (mean age 62 years [SD 8]; 8064 [28%] women; 5751 events during 95 576 person-years at risk). Initiation of statin therapy reduced LDL cholesterol (mean change -39% [95% CI -43 to -35]) without a significant change in lipoprotein(a). Associations of baseline and on-statin treatment lipoprotein(a) with cardiovascular disease risk were approximately linear, with increased risk at lipoprotein(a) values of 30 mg/dL or greater for baseline lipoprotein(a) and 50 mg/dL or greater for on-statin lipoprotein(a). For baseline lipoprotein(a), HRs adjusted for age and sex (vs <15 mg/dL) were 1·04 (95% CI 0·91-1·18) for 15 mg/dL to less than 30 mg/dL, 1·11 (1·00-1·22) for 30 mg/dL to less than 50 mg/dL, and 1·31 (1·08-1·58) for 50 mg/dL or higher; respective HRs for on-statin lipoprotein(a) were 0·94 (0·81-1·10), 1·06 (0·94-1·21), and 1·43 (1·15-1·76). HRs were almost identical after further adjustment for previous cardiovascular disease, diabetes, smoking, systolic blood pressure, LDL cholesterol, and HDL cholesterol. The association of on-statin lipoprotein(a) with cardiovascular disease risk was stronger than for on-placebo lipoprotein(a) (interaction p=0·010) and was more pronounced at younger ages (interaction p=0·008) without effect-modification by any other patient-level or study-level characteristics.

Interpretation: In this individual-patient data meta-analysis of statin-treated patients, elevated baseline and on-statin lipoprotein(a) showed an independent approximately linear relation with cardiovascular disease risk. This study provides a rationale for testing the lipoprotein(a) lowering hypothesis in cardiovascular disease outcomes trials.

Funding: Novartis Pharma AG.