Epidemiology
A random survival forest model beats traditional risk scores at predicting cardiovascular events in 4,369 patients with measured Lp(a) (Circ Genom Precis Med 2025)
Original title: Random Survival Forest Machine Learning for the Prediction of Cardiovascular Events Among Patients With a Measured Lipoprotein(a) Level: A Model Development Study
Using the Nashville Biosciences Lp(a) data set from Vanderbilt University Health System, the authors developed a random survival forest model to predict time to first myocardial infarction, stroke/TIA or coronary revascularisation in 4,369 patients with a measured Lp(a) level (49.5% female, mean age 51 years, mean Lp(a) 33.6 mg/dL, 23.7% with a prior cardiovascular event). The random survival forest model outperformed traditional risk factor models in the test set (C-index 0.82) compared with the Pooled Cohort Equations-based primary prevention model (C-index 0.69) and the secondary prevention SMART/TIMI-based model (C-index 0.80); a Cox model built from the top 25 machine-learning-selected variables reached a C-index of 0.80. Results held across primary-prevention-only and competing-risk sensitivity analyses. Standard risk equations underperform in patients who already have a measured Lp(a) level, and machine-learning models built for this population do better.
Original abstract
Background: Established risk models may not be applicable to patients at higher cardiovascular risk with a measured Lp(a) (lipoprotein[a]) level, a causal risk factor for atherosclerotic cardiovascular disease.
Methods: This was a model development study. The data source was the Nashville Biosciences Lp(a) data set, which includes clinical data from the Vanderbilt University Health System. We included patients with an Lp(a) measured between 1989 and 2022 and who had at least 1 year of electronic health record data before measurement of an Lp(a) level. The end point of interest was time to first myocardial infarction, stroke/TIA, or coronary revascularization. A random survival forest model was derived and compared with a Cox proportional hazards model derived from traditional cardiovascular risk factors (ie, the variables used to estimate the Pooled Cohort Equations for the primary prevention population and the variables used to estimate the Second Manifestations of Arterial Disease and Thrombolysis in Myocardial Infarction Risk Score for Secondary Prevention scores for the secondary prevention population). Model discrimination was evaluated using Harrell's C-index.
Results: A total of 4369 patients were included in the study (49.5% were female, mean age was 51 [SD 18] years, and mean Lp(a) level was 33.6 [38.6] mg/dL, of whom 23.7% had a prior cardiovascular event). The random survival forest model outperformed the traditional risk factor models in the test set (c-index, 0.82 [random forest model] versus 0.69 [primary prevention model] versus 0.80 [secondary prevention model]). These results were similar when restricted to a primary prevention population and under various strategies to handle competing risk. A Cox proportional hazard model based on the top 25 variables from the random forest model had a c-index of 0.80.
Conclusions: A random survival forest model outperformed a model using traditional risk factors for predicting cardiovascular events in patients with a measured Lp(a) level.
Summary written by lp-a.org from the published abstract; figures as published. Page updated 18 August 2026. Methods.